Ecological assessment method and system based on analytic hierarchy process and entropy weight method

Abstract

The invention discloses an ecological assessment method and system based on an analytic hierarchy process and an entropy weight method, and belongs to the technical field of ecological environment assessment, and the method comprises the steps: data collection and preprocessing: collecting evaluation index data related to ecological environment influence, and carrying out cleaning and processing; determining objective weights by an entropy weight method; calculating the objective weights of the indexes according to the data variation degree; determining a subjective weight by an analytic hierarchy process: constructing a judgment matrix in combination with expert opinions, calculating the subjective weight of each index, and performing consistency check; an analytic hierarchy process and an entropy weight method are combined, optimized and weighted; the objective weight and the subjective weight are combined and optimized, and a comprehensive weight is determined; tOPSIS comprehensive evaluation: the original indexes are subjected to forward processing and standardization processing, the distance between each evaluation object and the optimal solution and the distance between each evaluation object and the worst solution are calculated, and a normalized score is obtained. According to the invention, the accuracy and reliability of an ecological assessment result can be improved, and a more scientific and comprehensive solution is provided for ecological assessment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of ecological environment assessment, in particular to an ecological assessment method and system based on analytic hierarchy process and entropy weight method. BACKGROUND

[0002] In the field of ecological assessment, there are currently a variety of methods widely used, mainly including single subjective weighting evaluation method and single objective weighting evaluation method.

[0003] The subjective weighting method is to decompose complex problems into multiple levels, and determine the weights of each index by constructing a judgment matrix through expert scoring. This method can fully consider the knowledge and experience of experts, and combines qualitative analysis with quantitative analysis. However, its shortcomings are also obvious. Since the weight determination mainly depends on the subjective judgment of experts, there are differences in experience and cognition among different experts, which may lead to lack of objectivity and consistency in weight assignment, and the evaluation results are easily affected by subjective factors, reducing the accuracy and reliability of the evaluation.

[0004] The objective weighting method determines the weight according to the variation degree of each index data, and the greater the data variation degree, the higher the weight. This method fully utilizes the information of the data itself, and avoids the interference of subjective factors. However, it also has some shortcomings. The entropy weight method completely calculates the weight based on data, ignoring the actual importance of the index and the experience of experts. When the data is abnormal or missing, the calculated weight may not truly reflect the actual significance of the index in ecological assessment, leading to deviation of the evaluation results from the actual situation.

[0005] Therefore, how to consider the subjective experience and knowledge of experts, fully utilize the objective information of data, and efficiently combine the two is a problem to be solved at present. SUMMARY

[0006] The technical task of the present application is to solve the above problems, and provide an ecological assessment method and system based on analytic hierarchy process and entropy weight method, which determines the weight of each index by combining weighting method, can effectively avoid the subjective or objective defects of single method, improve the accuracy and reliability of ecological assessment results, and provide a more scientific and comprehensive solution for ecological assessment.

[0007] The technical solution adopted by the present application to solve its technical problems is:

[0008] An ecological assessment method based on analytic hierarchy process and entropy weight method, the implementation of the method includes the following steps:

[0009] Data collection and preprocessing: collect evaluation index data related to ecological environment impact, and clean and process;

[0010] The entropy weight method determines the objective weight: according to the data variation degree, the objective weight of each index is calculated;

[0011] The analytic hierarchy process determines the subjective weight: a judgment matrix is constructed combining expert opinions, the subjective weight of each index is calculated, and consistency test is performed;

[0012] The analytic hierarchy process and the entropy weight method are combined to optimize the weight: the objective weight and the subjective weight are combined and optimized to determine the comprehensive weight;

[0013] TOPSIS comprehensive evaluation: the original index is normalized and standardized, the distance between each evaluation object and the optimal solution and the worst solution is calculated, and the normalized score is obtained.

[0014] The method combines the advantages of the analytic hierarchy process and the entropy weight method, considers the subjective experience and knowledge of experts, fully utilizes the objective information of data, determines the weight of each index through combined weight, effectively avoids the subjective or objective defects of a single method, and improves the accuracy and reliability of the ecological evaluation result.

[0015] Further, the step of determining the objective weight by the entropy weight method comprises:

[0016] The index data is imported, an original matrix is established, and standardized processing is performed;

[0017] Quantitative processing and calculation of the entropy value and information utility value of each index;

[0018] According to the information utility value, the objective weight of each index is calculated.

[0019] Further, the step of determining the subjective weight by the analytic hierarchy process comprises:

[0020] The importance of each level index is compared and valued by using the 9-scale method, and a judgment matrix is constructed;

[0021] The judgment matrix is normalized to obtain the approximate weight;

[0022] Consistency test is performed to ensure that the consistency of the judgment matrix is acceptable.

[0023] Further, the step of combining and optimizing the weight by the analytic hierarchy process and the entropy weight method comprises:

[0024] The objective weight obtained by the entropy weight method and the subjective weight obtained by the analytic hierarchy process are combined and optimized;

[0025] The comprehensive weight is determined by minimizing the deviation sum of squares.

[0026] Further, the step of TOPSIS comprehensive evaluation comprises:

[0027] The original index is normalized and converted into a maximum index;

[0028] The normalized matrix is standardized to remove the influence of dimension;

[0029] The distance between each evaluation object and the optimal solution and the worst solution is calculated to obtain the normalized score.

[0030] Further, the specific implementation of the entropy weight method for determining the objective weight is as follows:

[0031] S1.1, import the index data and establish the original matrix:

[0032]

[0033] S1.2, standardize the original matrix:

[0034]

[0035] Where, i = 1, 2, ···, m; j = 1, 2, ···, n;

[0036] S1.3, quantization processing:

[0037]

[0038] S1.4, calculate the entropy value e and the information utility value d of the index, the information entropy value of the jth index is:

[0039]

[0040] The information utility value is d j = 1-e j ;

[0041] S1.5, calculate the weight of the index, according to the utility value to infer the importance of the index, the weight of the jth index is:

[0042]

[0043] The specific implementation of the analytic hierarchy process for determining the subjective weight is as follows:

[0044] S2.1: Construct the judgment matrix:

[0045] According to the characteristics of the analytic hierarchy process and the ecological impact evaluation index system, the importance of each level index is compared and valued by using the 9-scale method:

[0046] Scale a ij = 1, index i and index j are equally important,

[0047] Scale a ij= 3, indicator i is slightly more important than indicator j,

[0048] Scale a ij = 5, indicator i is significantly more important than indicator j,

[0049] Scale a ij = 7, indicator i is strongly more important than indicator j,

[0050] Scale a ij = 9, indicator i is extremely more important than indicator j;

[0051] Scale a ij = 2, 4, 6 or 8, the importance of indicator i and indicator j is between the median of two adjacent judgments above;

[0052] S2.2: Approximate weight:

[0053] The n column vectors of the judgment matrix are normalized to obtain the approximate weight, that is:

[0054]

[0055] S2.3: Consistency check:

[0056] Consistency index:

[0057] Consistency ratio index:

[0058] According to the definition of the analytic hierarchy process, when CR < 0.10, the consistency of the judgment matrix is considered acceptable;

[0059] The specific implementation of the combination optimization of weights according to the analytic hierarchy process and the entropy weight method is as follows:

[0060] The objective weight obtained by the entropy weight method and the subjective weight obtained by the analytic hierarchy process are combined and optimized to determine the comprehensive weight:

[0061] W = αw i + (1-α)w j (9),

[0062] When the deviation sum of squares is the smallest, the optimal combination α = 0.5.

[0063] Further, the specific implementation of the TOPSIS comprehensive evaluation is as follows:

[0064] S1: Normalize the original indicators:

[0065] That is, the original matrix is normalized, and all indicator types are uniformly converted into maximum type indicators, including:

[0066] Convert the minimum type indicator into a maximum type indicator:

[0067] max-x(10);

[0068] Transforming intermediate indicators into extremely large indicators:

[0069] Let {x} i} is a set of intermediate indicator sequences, and the optimal value is x. best The formula for forwarding is as follows:

[0070]

[0071] The simplified result should be within the range of [0,1] as much as possible, and the closer it is to the optimal value, the closer it is to 1;

[0072] Converting a range-type indicator to an extremely large indicator:

[0073] Let {x} i If} is a set of interval-type indicator sequences, and the optimal interval is [a, b], then the formula for positive transformation is as follows:

[0074]

[0075] S2: Standardize the matrix:

[0076] Suppose there are n objects to be evaluated, and the positive matrix consists of m evaluation indicators (already positiveized) as follows:

[0077]

[0078] Let Z be the normalized matrix, and each element of Z be:

[0079]

[0080] There are many methods for standardization, the main purpose of which is to remove the influence of dimensions. This method uses the proportion method (normalization method) to achieve standardization. After transformation, this method reflects the relationship between indicators more objectively and takes into account the differences between indicators; however, in order to distinguish between positive and negative indicators, x is required to... ij It only applies to values ​​≥0, and the formula is as follows:

[0081]

[0082] S3: Calculate the score and normalize it:

[0083] Suppose there are n objects to be evaluated, and a standardized matrix of m evaluation metrics:

[0084]

[0085] Define the maximum value:

[0086]

[0087] Define the minimum value:

[0088]

[0089] Define the distance between the i-th (i = 1, 2, ..., n) evaluation object and the maximum value:

[0090]

[0091] Define the distance between the i-th (i = 1, 2, ..., n) evaluation object and the minimum value.

[0092]

[0093] The normalized score for the i-th (i = 1, 2, ..., n) evaluation object is calculated as follows:

[0094]

[0095] 0≤S i ≤1, and S i The bigger The smaller it is, the closer it is to the maximum value.

[0096] This invention also claims protection for an ecological assessment system based on the analytic hierarchy process (AHP) and entropy weight method, comprising:

[0097] The data collection and preprocessing module is used to collect evaluation index data related to ecological and environmental impacts, and to clean and process them.

[0098] The entropy weight algorithm module is used to calculate the objective weight of each indicator based on the degree of data variation.

[0099] The hierarchical analysis algorithm module is used to construct a judgment matrix by combining expert opinions, calculate the subjective weight of each indicator, and perform consistency checks.

[0100] The combined optimization weighting module is used to combine and optimize the objective weights and the subjective weights to determine the comprehensive weights;

[0101] The TOPSIS comprehensive evaluation module is used to positively transform and standardize the original indicators, calculate the distance between each evaluation object and the optimal and worst solutions, and obtain a normalized score.

[0102] The system can perform ecological assessments using the methods described above.

[0103] The present invention also claims an ecological assessment device based on the analytic hierarchy process and the entropy weight method, comprising: at least one memory and at least one processor;

[0104] The at least one memory is used to store a machine-readable program;

[0105] The at least one processor is used to call the machine-readable program to implement the above method.

[0106] The present invention also claims a computer-readable medium storing computer instructions that, when executed by a processor, enable the implementation of the above-described method.

[0107] Compared with existing technologies, the ecological assessment method and system based on the analytic hierarchy process and entropy weight method of this invention have the following advantages:

[0108] This invention considers both the subjective experience and knowledge of experts and makes full use of the objective information of data. By determining the weight of each indicator through a combination of weighting methods, it effectively avoids the subjective or objective defects of a single method and improves the accuracy and reliability of ecological assessment results. By organically combining the two methods and integrating subjective and objective factors, the weight of each ecological assessment indicator is determined more rationally, thereby constructing a scientific, comprehensive, and accurate ecological assessment system that provides more reliable technical support and decision-making basis for the monitoring, protection, restoration, and sustainable development of the ecological environment. Attached Figure Description

[0109] Figure 1 This is a flowchart illustrating the ecological assessment method based on the analytic hierarchy process and the entropy weight method provided in this embodiment of the invention.

[0110] Figure 2 This is a chart showing the overall score trend from 1962 to 2021 provided in an embodiment of the present invention. Detailed Implementation

[0111] This invention provides an ecological assessment method based on the analytic hierarchy process (AHP) and the entropy weight method. The implementation of this method includes the following steps:

[0112] Data collection and preprocessing: Collect data on evaluation indicators related to ecological and environmental impacts, and clean and process them.

[0113] The entropy weight method determines objective weights: the objective weights of each indicator are calculated based on the degree of data variation.

[0114] The Analytic Hierarchy Process (AHP) is used to determine subjective weights: a judgment matrix is ​​constructed by combining expert opinions, the subjective weights of each indicator are calculated, and a consistency test is performed.

[0115] Combining the Analytic Hierarchy Process (AHP) and the Entropy Weight Method for Optimized Weight Assignment: Combining and optimizing the objective weights and the subjective weights to determine the comprehensive weights.

[0116] TOPSIS comprehensive evaluation: The original indicators are positiveized and standardized, and the distance between each evaluation object and the optimal and worst solutions is calculated to obtain a normalized score.

[0117] The steps for determining objective weights using the entropy weight method include:

[0118] Import the indicator data, build the original matrix, and perform standardization processing;

[0119] The entropy and information utility values ​​of each indicator are quantified and calculated.

[0120] The objective weights of each indicator are calculated based on the information utility value.

[0121] The steps for determining subjective weights using the analytic hierarchy process include:

[0122] The importance of each level of indicator was compared and assigned values ​​using the 9-scale method, and a judgment matrix was constructed.

[0123] The judgment matrix is ​​normalized to obtain approximate weights;

[0124] Perform a consistency check to ensure that the consistency of the judgment matrix is ​​acceptable.

[0125] The steps for optimizing weighting using the combined analytic hierarchy process and entropy weighting method include:

[0126] The objective weights obtained by the entropy weight method and the subjective weights obtained by the analytic hierarchy process are combined and optimized.

[0127] The overall weights are determined by minimizing the sum of squared deviations.

[0128] The steps of the TOPSIS comprehensive evaluation include:

[0129] The original indicators are positiveized and uniformly transformed into extremely large indicators;

[0130] The normalized matrix is ​​standardized to remove the influence of dimensions.

[0131] Calculate the distance between each evaluation object and the optimal and worst solutions to obtain a normalized score.

[0132] Entropy weight method is an objective comprehensive evaluation method used for multiple objects and multiple indicators. It calculates the entropy weight of each indicator based on the degree of variation among the indicators using information entropy, and then adjusts the weights of each indicator using entropy weight to obtain a more objective indicator weight.

[0133] The Analytic Hierarchy Process (AHP) is a systematic and hierarchical analytical method that combines qualitative and quantitative approaches. Its key feature is that, based on in-depth research into the nature, influencing factors, and internal relationships of complex decision-making problems, it uses relatively little quantitative information to mathematize the decision-making process, thus providing a convenient decision-making method for complex problems with multiple objectives, multiple criteria, or unstructured characteristics.

[0134] TOPSIS Comprehensive Evaluation: TOPSIS is a common and widely used comprehensive evaluation method. It can make full use of the information in the original data to evaluate the comprehensive distance of any scheme in the scheme system from the ideal optimal solution and the worst solution. The results can accurately reflect the gap between the evaluated schemes, obtain the similarity between each scheme and the optimal solution, and give a ranking of the many schemes.

[0135] The specific implementation method of this method is as follows:

[0136] 1. Model establishment.

[0137] (1) Determining objective weights using the entropy weight method:

[0138] S1.1 Import the indicator data and establish the original matrix:

[0139]

[0140] S1.2, Standardize the original matrix:

[0141]

[0142] Where i = 1, 2, ..., m; j = 1, 2, ..., n;

[0143] S1.3 Quantification Processing:

[0144]

[0145] S1.4 Calculate the entropy value e and information utility value d of the index. The information entropy value of the j-th index is:

[0146]

[0147] The information utility value is d j =1-e j ;

[0148] S1.5 Calculate the weights of the indicators. Infer the importance of the indicators based on their utility values. The weight of the j-th indicator is:

[0149]

[0150] (2) Analytic Hierarchy Process (AHP) for determining subjective weights:

[0151] S2.1: Construct the judgment matrix:

[0152] Combining the characteristics of the analytic hierarchy process (AHP) and the ecological impact assessment index system, the importance of each level of index was compared and assigned values ​​using the 9-scale method, as shown in Table 1.

[0153] Table 1. 9-Scale Assignment

[0154]

[0155] Scale a ij =1, Indicator i and Indicator j are equally important.

[0156] Scale a ij =3, Indicator i is slightly more important than indicator j.

[0157] Scale a ij =5, Indicator i is significantly more important than indicator j.

[0158] Scale a ij =7, Indicator i is significantly more important than indicator j.

[0159] Scale a ij =9, indicator i is extremely important than indicator j;

[0160] Scale a ij =2, 4, 6 or 8, the importance of indicator i and indicator j is between the median of the above two adjacent judgments;

[0161] S2.2: Find the approximate weights:

[0162] Normalize the n column vectors of the judgment matrix to obtain the approximate weights, i.e.:

[0163]

[0164] S2.3: Consistency check:

[0165] Consistency Indicators:

[0166] Consistency ratio:

[0167] According to the definition of the Analytic Hierarchy Process (AHP), when CR < 0.10, the consistency of the judgment matrix is ​​considered acceptable.

[0168] (3) Combination optimization of weighting using the analytic hierarchy process and the entropy weighting method:

[0169] The objective weights obtained by the entropy weight method and the subjective weights obtained by the analytic hierarchy process are combined and optimized to determine the comprehensive weight:

[0170] W = αw i +(1-α)w j (9),

[0171] The optimal combination α = 0.5 is achieved when the sum of squared deviations is minimized.

[0172] (4) The specific implementation of the TOPSIS comprehensive evaluation is as follows:

[0173] S4.1: Positively transform the original indicators:

[0174] The process of forward-orienting the original matrix involves transforming all indicator types into extremely large indicators. The four most common indicators are shown in Table 2:

[0175] Table 2 Common Indicators and Their Characteristics

[0176]

[0177] Converting very small indicators to very large indicators:

[0178] max-x(10);

[0179] Transforming intermediate indicators into extremely large indicators:

[0180] Let {x} i} is a set of intermediate indicator sequences, and the optimal value is x. best The formula for forwarding is as follows:

[0181]

[0182] The simplified result should be within the range of [0,1] as much as possible, and the closer it is to the optimal value, the closer it is to 1;

[0183] Converting a range-type indicator to an extremely large indicator:

[0184] Let {x} i If} is a set of interval-type indicator sequences, and the optimal interval is [a, b], then the formula for positive transformation is as follows:

[0185]

[0186] S4.2: Standardize the matrix:

[0187] Suppose there are n objects to be evaluated, and the positive matrix consists of m evaluation indicators (already positiveized) as follows:

[0188]

[0189] Let Z be the normalized matrix, and each element of Z be:

[0190]

[0191] There are many methods for standardization, the main purpose of which is to remove the influence of dimensions. This embodiment uses the proportion method (normalization method) to achieve standardization. This method, after transformation, reflects the relationship between indicators more objectively and takes into account the differences between indicators; however, in order to distinguish between positive and negative indicators, x is required to... ij It only applies to values ​​≥0. The formula is as follows:

[0192]

[0193] S3: Calculate the score and normalize it:

[0194] Suppose there are n objects to be evaluated, and a standardized matrix of m evaluation metrics:

[0195]

[0196] Define the maximum value:

[0197]

[0198] Define the minimum value:

[0199]

[0200] Define the distance between the i-th (i = 1, 2, ..., n) evaluation object and the maximum value:

[0201]

[0202] Define the distance between the i-th (i = 1, 2, ..., n) evaluation object and the minimum value:

[0203]

[0204] Therefore, the normalized score of the i-th (i = 1, 2, ..., n) evaluation object can be calculated:

[0205]

[0206] 0≤S i ≤1, and S i The bigger The smaller it is, the closer it is to the maximum value.

[0207] This embodiment selects Saihanba as the research object. The establishment of Saihanba has had a positive impact on the harsh local ecological environment. This paper first determines appropriate evaluation indicators for ecological and environmental impact, then collects indicator data, and conducts quantitative analysis on Saihanba before and after restoration based on the data. By observing the changes in each indicator and the overall trend of the data, an ecological and environmental impact assessment model for Saihanba is finally established.

[0208] The implementation method is as follows:

[0209] 1. Data collection and preprocessing:

[0210] To assess the ecological and environmental impacts of Saihanba, relevant evaluation indicators and data will be collected, including but not limited to forest coverage rate, coverage area, timber volume, water conservation capacity, carbon dioxide absorption, and oxygen release.

[0211] The collected raw data is cleaned, and missing and outlier values ​​are removed to ensure the accuracy and integrity of the data.

[0212] 2. Determining objective weights using the entropy weight method:

[0213] Import the processed data, build the original matrix, and perform standardization.

[0214] The entropy and information utility values ​​of each indicator are quantified and calculated.

[0215] The objective weights of each indicator are calculated based on the information utility value.

[0216] 3. Determining subjective weights using the Analytic Hierarchy Process (AHP):

[0217] Based on the characteristics of the ecological impact assessment index system, the 9-scale method is used to compare and assign values ​​to the importance of each level of indicators, and a judgment matrix is ​​constructed.

[0218] The judgment matrix is ​​normalized to obtain approximate weights.

[0219] Perform a consistency check to ensure that the consistency of the judgment matrix is ​​acceptable.

[0220] 4. Combining the Analytic Hierarchy Process (AHP) and the Entropy Weighting Method for Optimization of Weight Assignment:

[0221] The objective weights obtained by the entropy weight method and the subjective weights obtained by the analytic hierarchy process are combined and optimized, and the comprehensive weights are determined by minimizing the sum of squared deviations.

[0222] 5. TOPSIS Overall Evaluation:

[0223] The original indicators are positiveized and uniformly transformed into extremely large indicators.

[0224] The normalized matrix is ​​standardized to remove the influence of dimensions.

[0225] Calculate the distance between each evaluation object and the optimal and worst solutions to obtain a normalized score.

[0226] Results Analysis and Visualization: Based on the results of the TOPSIS comprehensive evaluation, the scores of each ecological assessment indicator are analyzed.

[0227] Generate an overall score trend chart to visually demonstrate the changes in the Saihanba ecological environment before and after restoration.

[0228] The specific implementation process is as follows:

[0229] 1. Obtaining weights using the entropy weight method

[0230] The solution was obtained using Matlab software. Table 3 shows the index weights obtained after correcting each index using the entropy weight method.

[0231] Table 3. Weight coefficients of each index in the entropy weight method.

[0232]

[0233] According to the principle of entropy weight method, the greater the degree of variation of an indicator, the more information it reflects, and therefore the higher its corresponding weight. Thus, it can be concluded that among all indicators, forest stock, water conservation capacity, carbon dioxide absorption, and oxygen release have a relatively large weight.

[0234] 2. Obtaining weights using the Analytic Hierarchy Process (AHP)

[0235] Matrix A is the constructed judgment matrix. By solving for the eigenvalues ​​and eigenvectors of the matrix, it is found that the consistency test is passed, and the weights of each indicator are generated, as shown in Table 5.

[0236]

[0237] The eigenvalues ​​and eigenvectors of the matrix were solved using Matlab software. The largest eigenvalue of matrix A was t = 6.2197. The consistency of the matrix was checked using the Saaty consistency index: CI = (λ-n) / (n-1). The results are shown in Table 4.

[0238] Table 4 shows the random consistency table based on Saaty.

[0239]

[0240] Consistency ratio: CR = CI / R = 0.03488 < 0.10, passing the consistency test.

[0241] Table 5. Weight coefficients of each indicator in the Analytic Hierarchy Process (AHP)

[0242]

[0243] By combining the judgment matrix and analyzing it using the analytic hierarchy process, we can determine the weight of each indicator. As shown in Table 5, forest coverage rate and coverage area have relatively high weights among the indicators.

[0244] 3. Combining the Analytic Hierarchy Process (AHP) with the Entropy Weight Method to Optimize Weight Assignment

[0245] By comparing the indicator weight coefficients obtained from the above two methods, it is not difficult to find that neither the entropy weight method, which combines objective data analysis, nor the hierarchical analysis method, which is based on the judgment matrix constructed by expert opinions, can comprehensively analyze the actual weight of each indicator. Therefore, this method adopts the combination of hierarchical analysis method and entropy weight method to optimize the weighting and obtain W. It explores from both subjective and objective perspectives to obtain the final weight of each indicator, as shown in Table 6.

[0246] W = αw i +(1-α)w j (9).

[0247] Table 6. Weighting Coefficients for Optimization Using the Analytic Hierarchy Process (AHP) – Entropy Weight Method

[0248]

[0249] 4. TOPSIS Comprehensive Evaluation Method

[0250] Step 1: Following the calculation steps of the TOPSIS model, the normalized decision matrix Z is obtained by normalizing the original data matrix of the evaluation index. Due to the large amount of data, the decision matrix Z is simplified here by compressing the year intervals and data and taking the average value to generate a simplified decision matrix z. The original decision matrix Z can be observed in Matlab.

[0251]

[0252] Step 2: After normalizing the numerical values, combine the weights obtained from the combination of the analytic hierarchy process and the entropy weight method, and obtain the optimal solution Z from equations (17) and (18). + And worst-case scenario Z - .

[0253]

[0254] Step 3: Finally, combine Equation 19 to obtain the normalized score:

[0255] S i =(0 0.0006 0.0012 0.0018 0.0023 0.0029 0.0034 0.0039 0.0043 0.0048 0.0053) 0.0057 0.0061 0.0066 0.007 0.0074 0.0078 0.0082 0.0085 0.0089 0.0092 0.0096 0.01 0.0104 0.011 0.0116 0.0121 0.0125 0.0128 0.0134 0.014 0.0146 0.0153 0.016 0.0167 0.0175 0.0183 0.0192 0.0202 0.0216 0.0229 0.0238 0.0246 0.0253 0.026 0.0266 0.0272 0.0279 0.0284 0.029 0.0297 0.0303 0.031 0.0317 0.0324 0.0331 0.035 0.0389 0.044 0.0494)

[0261] Step 4: Generate an overall score trend chart from 1962 to 2021, as shown below. Figure 2 As shown:

[0262] Data on ecological impact indicators of Saihanba were collected from 1962 to 2021 (60 years). Quantitative analysis was conducted using this data, and the analytic hierarchy process (AHP) – entropy weight method was used for optimized weighting. This revealed that forest coverage rate and coverage area have relatively high weights among the numerous indicators. Furthermore, TOPSIA analysis showed that the local ecological environment score has been consistently rising since the establishment of Saihanba.

[0263] This invention also provides an ecological assessment system based on the analytic hierarchy process (AHP) and entropy weight method, comprising:

[0264] 1. Data collection and preprocessing module, used to collect evaluation index data related to ecological and environmental impacts, and to clean and process them.

[0265] 2. The entropy weight algorithm module is used to calculate the objective weights of each indicator based on the degree of data variation. The steps for determining the objective weights using the entropy weight method include:

[0266] Import the indicator data, build the original matrix, and perform standardization processing;

[0267] The entropy and information utility values ​​of each indicator are quantified and calculated.

[0268] The objective weights of each indicator are calculated based on the information utility value.

[0269] 3. The Analytic Hierarchy Process (AHP) module is used to construct a judgment matrix by combining expert opinions, calculate the subjective weights of each indicator, and perform consistency checks. The steps of determining subjective weights using the AHP include:

[0270] The importance of each level of indicator was compared and assigned values ​​using the 9-scale method, and a judgment matrix was constructed.

[0271] The judgment matrix is ​​normalized to obtain approximate weights;

[0272] Perform a consistency check to ensure that the consistency of the judgment matrix is ​​acceptable.

[0273] 4. The combined optimization weighting module is used to combine and optimize the objective weights and the subjective weights to determine the comprehensive weight. The steps of the combined optimization weighting of the analytic hierarchy process and the entropy weight method include:

[0274] The objective weights obtained by the entropy weight method and the subjective weights obtained by the analytic hierarchy process are combined and optimized.

[0275] The overall weights are determined by minimizing the sum of squared deviations.

[0276] 5. The TOPSIS comprehensive evaluation module is used to positively transform and standardize the original indicators, calculate the distance between each evaluation object and the optimal and worst solutions, and obtain a normalized score. The steps of the TOPSIS comprehensive evaluation include:

[0277] The original indicators are positiveized and uniformly transformed into extremely large indicators;

[0278] The normalized matrix is ​​standardized to remove the influence of dimensions.

[0279] Calculate the distance between each evaluation object and the optimal and worst solutions to obtain a normalized score.

[0280] This system can perform ecological assessments using the ecological assessment methods based on the analytic hierarchy process and entropy weight method described in the above embodiments.

[0281] This invention also provides an ecological assessment device based on the analytic hierarchy process (AHP) and the entropy weight method, comprising: at least one memory and at least one processor;

[0282] The at least one memory is used to store a machine-readable program;

[0283] The at least one processor is used to call the machine-readable program to implement the ecological assessment method based on the analytic hierarchy process and the entropy weight method described in the above embodiments.

[0284] This invention also provides a computer-readable medium storing computer instructions. When executed by a processor, the computer instructions cause the processor to perform the ecological assessment method based on the analytic hierarchy process and entropy weight method described in the above embodiments. Specifically, a system or apparatus equipped with a storage medium storing software program code that implements the functions of any of the embodiments described above, and enabling the computer (or CPU or MPU) of the system or apparatus to read and execute the program code stored in the storage medium.

[0285] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0286] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0287] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0288] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion unit connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion unit execute some and all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0289] The present invention has been shown and described in detail above with reference to the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above embodiments, those skilled in the art will know that more embodiments of the present invention can be obtained by combining the code review methods in the different embodiments. These embodiments are also within the protection scope of the present invention.

Claims

1. An ecological assessment method based on the analytic hierarchy process (AHP) and entropy weight method, characterized in that, The implementation of this method includes the following steps: Data collection and preprocessing: Collect data on evaluation indicators related to ecological and environmental impacts, and clean and process them; Entropy weight method for determining objective weights: Calculate the objective weights of each indicator based on the degree of data variation; The Analytic Hierarchy Process (AHP) is used to determine subjective weights: a judgment matrix is ​​constructed by combining expert opinions, the subjective weights of each indicator are calculated, and a consistency test is performed. Combining the Analytic Hierarchy Process (AHP) and the Entropy Weight Method for Optimized Weight Assignment: Combining and optimizing the objective weights and the subjective weights to determine the comprehensive weights; TOPSIS comprehensive evaluation: The original indicators are positiveized and standardized, and the distance between each evaluation object and the optimal and worst solutions is calculated to obtain a normalized score.

2. The ecological assessment method based on the analytic hierarchy process and entropy weight method according to claim 1, characterized in that, The steps for determining objective weights using the entropy weight method include: Import the indicator data, build the original matrix, and perform standardization processing; The entropy and information utility values ​​of each indicator are quantified and calculated. The objective weights of each indicator are calculated based on the information utility value.

3. The ecological assessment method based on the analytic hierarchy process and entropy weight method according to claim 1, characterized in that, The steps for determining subjective weights using the analytic hierarchy process include: The importance of each level of indicator was compared and assigned values ​​using the 9-scale method, and a judgment matrix was constructed. The judgment matrix is ​​normalized to obtain approximate weights; Perform a consistency check to ensure that the consistency of the judgment matrix is ​​acceptable.

4. The ecological assessment method based on the analytic hierarchy process and entropy weight method according to claim 1, characterized in that, The steps for optimizing weighting using the combined analytic hierarchy process and entropy weighting method include: The objective weights obtained by the entropy weight method and the subjective weights obtained by the analytic hierarchy process are combined and optimized. The overall weights are determined by minimizing the sum of squared deviations.

5. The ecological assessment method based on the analytic hierarchy process and entropy weight method according to claim 1, characterized in that, The steps of the TOPSIS comprehensive evaluation include: The original indicators are positiveized and uniformly transformed into extremely large indicators; The normalized matrix is ​​standardized to remove the influence of dimensions. Calculate the distance between each evaluation object and the optimal and worst solutions to obtain a normalized score.

6. The ecological assessment method based on the analytic hierarchy process and entropy weight method according to claim 1, characterized in that, The specific implementation of the entropy weight method for determining objective weights is as follows: S1.1 Import the indicator data and establish the original matrix: S1.2, Standardize the original matrix: Where i = 1, 2, ..., m; j = 1, 2, ..., n; S1.3 Quantification Processing: S1.4 Calculate the entropy value e and information utility value d of the index. The information entropy value of the j-th index is: The information utility value is d j =1-e j ; S1.5 Calculate the weights of the indicators. Infer the importance of the indicators based on their utility values. The weight of the j-th indicator is: The specific implementation of the analytic hierarchy process (AHP) for determining subjective weights is as follows: S2.1: Construct the judgment matrix: Combining the characteristics of the analytic hierarchy process (AHP) and the ecological impact assessment index system, the 9-scale method is used to compare and assign values ​​to the importance of indicators at each level: Scale a ij =1, Indicator i and Indicator j are equally important. Scale a ij =3, Indicator i is slightly more important than indicator j. Scale a ij =5, Indicator i is significantly more important than indicator j. Scale a ij =7, Indicator i is significantly more important than indicator j. Scale a ij =9, indicator i is extremely important than indicator j; Scale a ij =2, 4, 6 or 8, the importance of indicator i and indicator j is between the median of the above two adjacent judgments; S2.2: Find the approximate weights: Normalize the n column vectors of the judgment matrix to obtain the approximate weights, i.e.: S2.3: Consistency check: Consistency Indicators: Consistency ratio: According to the definition of the Analytic Hierarchy Process (AHP), when CR < 0.10, the consistency of the judgment matrix is ​​considered acceptable. The specific implementation of the combined optimization of weighting using the analytic hierarchy process and the entropy weight method is as follows: The objective weights obtained by the entropy weight method and the subjective weights obtained by the analytic hierarchy process are combined and optimized to determine the comprehensive weight: W=αw i +(1-a)w j (9), The optimal combination α = 0.5 is achieved when the sum of squared deviations is minimized.

7. The ecological assessment method based on the analytic hierarchy process and entropy weight method according to claim 1, characterized in that, The specific implementation of the TOPSIS comprehensive evaluation is as follows: S1: Positively transform the original indicator: This involves forward-oriented transformation of the original matrix, unifying all indicator types into extremely large indicators, including: Converting very small indicators to very large indicators: max-x(10); Transforming intermediate indicators into extremely large indicators: Let {x} i } is a set of intermediate indicator sequences, and the optimal value is x. best The formula for forwarding is as follows: The simplified result is between [0,1], and the closer it is to the optimal value, the closer it is to 1; Converting a range-type indicator to an extremely large indicator: Let {x} i If} is a set of interval-type indicator sequences, and the optimal interval is [a, b], then the formula for positive transformation is as follows: S2: Standardize the matrix: Suppose there are n objects to be evaluated, and the positive matrix composed of m evaluation indicators is as follows: Let Z be the normalized matrix of Z, then each element of Z is: Standardization is achieved using the proportion method; to distinguish between positive and negative indicators, x is required to... ij Applicable when ≥0, the formula is as follows: S3: Calculate the score and normalize it: Suppose there are n objects to be evaluated, and a standardized matrix of m evaluation metrics: Define the maximum value: Define the minimum value: Define the distance between the i-th (i = 1, 2, ..., n) evaluation object and the maximum value: Define the distance between the i-th (i = 1, 2, ..., n) evaluation object and the minimum value: The normalized score for the i-th (i = 1, 2, ..., n) evaluation object is calculated as follows: 0≤S i ≤1, and S i The bigger The smaller it is, the closer it is to the maximum value.

8. An ecological assessment system based on the analytic hierarchy process (AHP) and entropy weight method, characterized in that, include: The data collection and preprocessing module is used to collect evaluation index data related to ecological and environmental impacts, and to clean and process them. The entropy weight algorithm module is used to calculate the objective weight of each indicator based on the degree of data variation. The hierarchical analysis algorithm module is used to construct a judgment matrix by combining expert opinions, calculate the subjective weight of each indicator, and perform consistency checks. The combined optimization weighting module is used to combine and optimize the objective weights and the subjective weights to determine the comprehensive weights; The TOPSIS comprehensive evaluation module is used to positively transform and standardize the original indicators, calculate the distance between each evaluation object and the optimal and worst solutions, and obtain a normalized score. The system is capable of performing ecological assessments using the method described in any one of claims 1 to 7.

9. An ecological assessment device based on the analytic hierarchy process (AHP) and entropy weight method, characterized in that, include: At least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is configured to invoke the machine-readable program to implement the method according to any one of claims 1 to 7.

10. A computer-readable medium, characterized in that, The computer-readable medium stores computer instructions that, when executed by a processor, enable the implementation of the method described in any one of claims 1 to 7.

Images