Geological relic evaluation method and system based on grey correlation and entropy weight method coupling

Abstract

The invention provides a geological relic evaluation method and system based on gray correlation and entropy weight method coupling, and relates to the technical field of data processing, and the method comprises the steps: constructing a geological relic comprehensive evaluation system; obtaining score values of the geological relics under the comprehensive evaluation system, and constructing a score matrix; standardizing the scoring matrix to determine a standard matrix; determining the entropy weight of each evaluation index through an entropy weight method according to the standard matrix; according to the entropy weight of each evaluation index, the grey correlation degree between each geological trace and the ideal sample is determined through a grey correlation method; sorting the geological relics according to a sequence of grey relational degrees between the geological relics and the ideal samples from high to low; dividing the geological relics into different protection grades according to the sorting result; and taking corresponding protection measures for each geological trace according to the protection level. The objectivity and accuracy of the comprehensive evaluation result can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a geological heritage evaluation method and system based on the coupling of grey correlation and entropy weight method. Background Art

[0002] Geological heritage is the real record and heritage formed and preserved by the combined action of internal and external geological agents during the development and evolution of the earth. It is not only very important but also extremely necessary to formulate a scientific and reasonable geological heritage evaluation plan and propose a geological heritage protection plan including stratotype sections.

[0003] At present, the research on geological heritage investigation is relatively common and in-depth, but there are not many studies on the scientific evaluation of geological heritage, especially the quantitative evaluation methods. Most of them adopt the analytic hierarchy process and expert scoring method. The method and index system for quantitatively studying geological heritage evaluation have not been fully established. At the same time, the evaluation of geological heritage mostly focuses on aesthetic value and protectability, and the scientific value system has not been fully established.

[0004] Currently, the grey correlation method is often used for investigation and evaluation. The grey correlation method is a mathematical method for analyzing the correlation degree between various factors in a system, mainly applicable to complex problems with incomplete information or less data. Its core idea is to determine the relative influence degree of each factor on the system target by calculating the correlation coefficient between different factor sequences and the reference sequence. The grey correlation method quantifies the correlation degree between indicators into grey correlation degree through data differentiation and normalization processing. The higher the correlation degree, the stronger the similarity or correlation between the two sequences.

[0005] However, the traditional grey correlation method usually assumes that the importance of each evaluation index is the same, without considering the difference in the importance degree between indicators. This equal-weight processing method lacks scientific basis, easily leads to deviation of the evaluation result, and affects the accuracy of the evaluation result. Summary of the Invention

[0006] In order to solve the technical problem that the traditional grey correlation method usually assumes that the importance of each evaluation index is the same, without considering the difference in the importance degree between indicators, this equal-weight processing method lacks scientific basis, easily leads to deviation of the evaluation result, and affects the accuracy of the evaluation result, the present invention provides a geological heritage evaluation method and system based on the coupling of grey correlation and entropy weight method.

[0007] The technical solutions provided by the embodiments of the present invention are as follows:

[0008] First aspect:

[0009] A geological heritage evaluation method based on the coupling of grey correlation and entropy weight method provided by the embodiments of the present invention includes:

[0010] S1: Construct a comprehensive evaluation system for geological heritage;

[0011] S2: Obtain the scoring values of geological heritage under the comprehensive evaluation system and construct a scoring matrix;

[0012] S3: Standardize the scoring matrix to determine the standard matrix;

[0013] S4: According to the standard matrix, determine the entropy weight values of each evaluation index by the entropy weight method;

[0014] S5: According to the entropy weight values of each evaluation index, determine the grey correlation degrees between each geological heritage and the ideal sample by the grey correlation method;

[0015] S6: Sort each geological heritage in descending order of the grey correlation degrees between each geological heritage and the ideal sample;

[0016] S7: According to the sorting results, divide each geological heritage into different protection levels;

[0017] S8: According to the protection levels, take corresponding protection measures for each geological heritage.

[0018] Second aspect:

[0019] A geological heritage evaluation system based on the coupling of grey correlation and entropy weight method provided by an embodiment of the present invention includes:

[0020] A processor;

[0021] A memory, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor, the geological heritage evaluation method based on the coupling of grey correlation and entropy weight method as described in the first aspect is implemented.

[0022] The beneficial effects brought by the technical solution provided by the embodiment of the present invention at least include:

[0023] In the present invention, on the basis of the grey correlation method, the entropy weight method is combined. The entropy weight values of each evaluation index are determined by the entropy weight method, and then according to the entropy weight values of each evaluation index, the grey correlation degrees between each geological heritage and the ideal sample are determined by the grey correlation method, which can more comprehensively consider the importance of each evaluation index and improve the objectivity and accuracy of the comprehensive evaluation results. Description of the Drawings

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0025] Figure 1 FIG.

[0026] Figure 2 is a schematic flow chart of a geological heritage evaluation method based on the coupling of grey correlation and entropy weight method provided by an embodiment of the present invention;

[0027] Figure 3 is a schematic structural diagram of a comprehensive geological heritage evaluation system provided by an embodiment of the present invention;

[0028] Figure 4 is a schematic structural diagram of a geological heritage evaluation system based on the coupling of grey correlation and entropy weight method provided by an embodiment of the present invention. Specific Embodiments

[0029] The following will describe the technical solutions in the present invention in conjunction with the accompanying drawings.

[0030] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0031] To make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will be described in detail in conjunction with the accompanying drawings and specific embodiments.

[0032] Referring to the attached Figure 1 illustrates a schematic flow chart of a geological heritage evaluation method based on the coupling of grey correlation and entropy weight method provided by an embodiment of the present invention.

[0033] Referring to the attached Figure 2 illustrates a schematic structural diagram of a geological heritage evaluation method based on the coupling of grey correlation and entropy weight method provided by an embodiment of the present invention.

[0034] The embodiments of the present invention provide a geological heritage evaluation method based on the coupling of grey correlation and entropy weight method, which may include the following steps:

[0035] S1: Construct a comprehensive evaluation system for geological heritage.

[0036] Refer to the appendix of the specification Figure 3 , which shows a schematic diagram of a comprehensive evaluation system for geological heritage provided by an embodiment of the present invention.

[0037] In a possible implementation, the comprehensive evaluation system for geological heritage specifically includes:

[0038] First-level indicators: resource attributes and value attributes.

[0039] Under the first-level indicator of resource attributes, there are second-level indicators: natural attributes and scientific attributes.

[0040] Under the second-level indicator of natural attributes, there are third-level indicators: typicality, rarity, integrity, naturalness, and landscape richness.

[0041] Under the second-level indicator of scientific attributes, there are third-level indicators: representativeness of earth evolution and geological diversity.

[0042] Under the first-level indicator of value attributes, there are second-level indicators: functional value and development value.

[0043] Under the second-level indicator of functional value, there are third-level indicators: popular science education, aesthetic property, social economy, history and culture, and ecological environment.

[0044] Under the second-level indicator of development value, there are third-level indicators: overall level of regional development, regional environmental capacity, basic service facilities, protectability, traffic conditions, awareness of openness, population quality level, and relationship with neighboring tourist destinations.

[0045] In the present invention, the comprehensive evaluation system for geological heritage starts from the natural attributes, scientific attributes, and their functional and development values of resources, covering the ecological, scientific, social, economic and other multi-dimensional characteristics of geological heritage, ensuring the integrity and systematicness of the evaluation content.

[0046] S2: Obtain the scoring values of geological heritage under the comprehensive evaluation system and construct a scoring matrix.

[0047] Optionally, the scoring matrix is specifically:

[0048]

[0049] Among them, A represents the scoring matrix, and a ij represents the scoring value of the jth geological heritage under the ith evaluation indicator, m represents the total number of evaluation indicators, and n represents the total number of geological heritages.

[0050] S3: Standardize the scoring matrix to determine the standard matrix.

[0051] Optionally, the normalization matrix is specifically:

[0052]

[0053] where R represents the normalization matrix, and r ij represents the normalized score value of the jth geological heritage site under the ith evaluation index, and a ij represents the score value of the jth geological heritage site under the ith evaluation index, and a i,max represents the highest score value under the ith evaluation index, and a i,min represents the lowest score value under the ith evaluation index, m represents the total number of evaluation indices, and n represents the total number of geological heritage sites.

[0054] In the present invention, since the units and dimensions of different indices may be different, direct comparison may lead to unreasonable evaluation results. The normalization process converts all indices to the same scale (between 0 and 1), which helps to objectively compare different geological heritage sites under the same evaluation framework.

[0055] S4: According to the standard matrix, determine the entropy weight values of each evaluation index by the entropy weight method.

[0056] Among them, the entropy weight method is an objective weighting method that determines the importance of each evaluation index based on the principle of information entropy. Its core idea is: the information entropy of an index reflects the uncertainty or dispersion degree of the data. If the data of a certain index has a greater difference, it provides more information and its weight is higher; on the contrary, if the data difference is small or tends to be stable, the importance of this index is relatively low. The entropy weight method determines the weights of each index by calculating the proportion, information entropy, and information utility value of the index, avoiding the deviation caused by subjective weighting by humans, making the evaluation results more scientific and objective, and is especially suitable for the problem of determining weights in multi-index comprehensive evaluation.

[0057] In a possible implementation manner, S4 specifically includes sub-steps S401 to S403:

[0058] S401: Calculate the proportion of the score values of each geological heritage site under each evaluation index:

[0059]

[0060] where p ij represents the proportion of the score value of the jth geological heritage site under the ith evaluation index, and r ij represents the normalized score value of the jth geological heritage site under the ith evaluation index, and n represents the total number of geological heritage sites.

[0061] S402: Calculate the entropy value of each evaluation index:

[0062]

[0063] Among them, e i represents the entropy value of the i-th evaluation index, and m represents the total number of evaluation indexes.

[0064] It should be noted that through entropy value calculation, indicators with less information and low discrimination can be identified, reducing the interference of redundant data on the evaluation results and improving the accuracy and effectiveness of the evaluation.

[0065] S403: Calculate the entropy weight values of each evaluation index:

[0066]

[0067] Among them, w i represents the entropy weight value of the i-th evaluation index.

[0068] It should be noted that when the data of a certain index has a large difference, it indicates that its contribution and discrimination to the system are relatively high, and the weight increases accordingly; on the contrary, the weight of the index with smaller data changes decreases, thus highlighting the index with larger information volume.

[0069] In the present invention, the entropy weight method measures the degree of dispersion and uncertainty of data by calculating the information entropy of the indicators, avoiding the influence of human subjective factors on weight assignment and making the weight assignment more scientific and objective.

[0070] S5: According to the entropy weight values of each evaluation index, determine the grey correlation degrees between each geological heritage and the ideal sample through the grey correlation method.

[0071] Among them, the grey correlation method is a mathematical method used to analyze the similarity or proximity between various factors in a system and the reference sequence. Its core idea is to measure the correlation degree between each evaluation object and the ideal sample by calculating the difference sequence and grey correlation coefficient. The larger the correlation degree, the higher the similarity between the two. The grey correlation method is especially suitable for situations with small data volume, strong uncertainty or incomplete information, and can effectively handle multi-index comprehensive evaluation problems. Its advantages lie in simple calculation, strong adaptability, and the ability to objectively reflect the influence degree of each factor in the system, and it is widely used in fields such as resource evaluation, decision analysis and ranking.

[0072] In a possible implementation manner, S5 specifically includes sub-steps S501 to S503:

[0073] S501: Use the ideal sample composed of the maximum values under each evaluation index as the reference sequence, calculate the difference between each geological heritage and the ideal sample, and construct a difference matrix:

[0074]

[0075] bij = r i,max -r ij

[0076] Among them, B represents the difference matrix, and b ij represents the difference between the score value of the j-th geological heritage under the i-th evaluation index and the maximum value, and r j,max represents the maximum value of the i-th evaluation index.

[0077] S502: Determine the maximum and minimum numbers in the difference matrix, and calculate the grey correlation coefficient matrix:

[0078]

[0079] Among them, C represents the grey correlation coefficient matrix, and c ij represents the grey correlation coefficient of the score value of the j-th geological heritage under the i-th evaluation index, b min represents the minimum number in the difference matrix, b max represents the maximum number in the difference matrix, ρ i represents the discrimination coefficient of the i-th evaluation index.

[0080] S503: According to the grey correlation coefficient matrix, calculate the grey correlation degree between each geological heritage and the ideal sample:

[0081]

[0082] Among them, γ j represents the grey correlation degree between the j-th geological heritage and the ideal sample.

[0083] In the present invention, when calculating the grey correlation degree, the weight determined by the entropy weight method is introduced, which objectively reflects the importance of each evaluation index, making the index with a higher weight have a greater impact on the final result and improving the scientificity and rationality of the evaluation.

[0084] In a possible implementation manner, the discrimination coefficient is specifically:

[0085]

[0086] Among them, ρ i represents the discrimination coefficient of the i-th evaluation index, and δ i represents the proportionality factor of the i-th evaluation index.

[0087] It should be noted that when the proportionality factor is large, it indicates a high degree of difference in this index, and the discrimination coefficient increases accordingly, thereby improving the ability to distinguish differences between indexes and enhancing the distinguishability of the evaluation results.

[0088] In the present invention, the discrimination coefficient is set in segments according to the value of the scale factor, which can adapt to the numerical distribution characteristics of different evaluation indicators, making the sensitivity of the grey relational analysis method to the differences between indicators more flexible and accurate. At the same time, the dynamic discrimination coefficient can better reflect the contributions of various indicators in the actual data, ensuring that the calculation of the grey relational coefficient is more reasonable, and thus improving the accuracy and reliability of the grey relational degree evaluation result.

[0089] Optionally, the scale factor is specifically:

[0090]

[0091] where b ij represents the difference between the score value of the jth geological heritage under the ith evaluation indicator and the maximum value, and b max represents the maximum number in the difference matrix, and n represents the total number of geological heritages.

[0092] It should be noted that the scale factor is a parameter that measures the degree of difference between each geological heritage and the ideal sample under a certain evaluation indicator. The larger the scale factor, the higher the discreteness of the indicator, the more significant the difference, and the stronger the discrimination ability; conversely, if the scale factor is smaller, it indicates that the difference of the indicator is lower and its contribution to the overall evaluation is relatively small. Therefore, the scale factor provides a quantitative basis for the adaptive discrimination coefficient, enabling the evaluation model to more sensitively adapt to the distribution characteristics of different indicator data, and enhancing the distinguishability and accuracy of the results.

[0093] In a possible implementation manner, the determination method of the discrimination coefficient is specifically: aiming at maximizing the discrimination ability of the grey relational degree, the discrimination coefficients of each evaluation indicator are determined through the bat optimization algorithm.

[0094] Among them, the bat optimization algorithm (Bat Algorithm, BA) is an intelligent optimization algorithm inspired by the echolocation behavior of bats, mainly used to solve complex global optimization problems. The algorithm simulates the mechanism of bats emitting ultrasonic waves and receiving echoes to locate targets during the predation process, and dynamically adjusts the search direction using parameters such as position, speed, and frequency. Bats evaluate the quality of the current position through the fitness function, continuously update the speed and position, and at the same time perform local search combined with random perturbations to ensure a balance between global and local search efficiency.

[0095] Optionally, the fitness function of the bat optimization algorithm is specifically:

[0096]

[0097] where σ represents the fitness function, P represents the set of discrimination coefficients, P = (ρ 1 , ρ 2 , …, ρm), m represents the total number of evaluation indicators, γj represents the grey relational grade between the j-th geological heritage site and the ideal sample, represents the average value of the grey relational grades, and n represents the total number of geological heritage sites.

[0098] In the present invention, the fitness function measures the dispersion degree of the results by calculating the absolute difference between the grey relational grade of each geological heritage site and the average value, so as to find the discrimination coefficient that can maximize the relational grade difference and enhance the discrimination ability of the evaluation results.

[0099] Specifically, bat individuals are initialized. Each bat individual represents a set of feasible discrimination coefficients. Each bat individual consists of multiple dimensional components, and each component represents the discrimination coefficient of an evaluation index.

[0100] In the global search stage, update the flying speed and position of the bat individuals:

[0101]

[0102] where f i represents the pulse emission frequency of the i-th bat individual, f min represents the minimum value of the pulse emission frequency, f max represents the maximum value of the pulse emission frequency, β t represents the non-linear inverse cosine acceleration factor at the t-th iteration, represents the speed of the i-th bat individual at the (t + 1)-th iteration, r 1 、r 2 represent random numbers between 0 and 1, ω t represents the inertia weight factor at the t-th iteration, represents the speed of the i-th bat individual at the t-th iteration, x′ represents the individual optimal solution, c i represents the learning factor, x * represents the global optimal solution, represents the position of the i-th bat individual at the t-th iteration, represents the position of the i-th bat individual at the (t + 1)-th iteration, Levy represents the Levy flight step size.

[0103] In the present invention, through the dynamic combination of global search and local search, random perturbation and jump mechanism, the search efficiency, global optimal solution search ability and convergence accuracy of the algorithm are effectively improved, enabling it to quickly find high-quality solutions in complex problems.

[0104] Optionally, the inertia weight factor is specifically:

[0105]

[0106] where ω tRepresents the inertia weight factor at the t-th iteration, ω min Represents the minimum inertia weight factor, ω max Represents the maximum inertia weight factor, t represents the current iteration number, and T represents the maximum number of iterations.

[0107] It should be noted that the inertia weight factor is dynamically adjusted with the number of iterations. The weight is larger in the initial stage and gradually decreases as the number of iterations increases. This design enables the algorithm to conduct a wide-range global search in the initial stage, quickly exploring the solution space, and gradually shrinking the step size in the later stage, focusing on the local area of the optimal solution to improve the convergence accuracy. The dynamic inertia weight can effectively balance global search and local search, accelerate the algorithm convergence, and avoid the premature convergence problem.

[0108] Optionally, the non-linear arccosine acceleration factor is specifically:

[0109]

[0110] Where arccos represents the arccosine function, t represents the current iteration number, and T represents the maximum number of iterations.

[0111] It should be noted that the non-linear arccosine acceleration factor makes the search process gradually accelerate through non-linear changes. As the number of iterations increases, the value of the non-linear arccosine acceleration factor gradually decreases, controlling the accuracy of the search direction. This non-linear change helps the algorithm to conduct a global exploration with a larger step size in the initial stage and gradually accelerate towards the optimal solution in the later stage. Compared with linear acceleration, the arccosine non-linear factor can better smooth the search path and improve the search efficiency and accuracy of the algorithm.

[0112] Optionally, the learning factor is specifically:

[0113] c i = c max -(c max - c min )β t

[0114] Where c i Represents the learning factor of the i-th bat individual, c max Represents the maximum learning factor, c min Represents the minimum learning factor.

[0115] It should be noted that the learning factor is dynamically adjusted by combining with the non-linear acceleration factor and gradually changes from the maximum value to the minimum value during the search process. This design enables the bat individual to have a larger learning ability in the early stage, widely exploring the solution space, and converging to the local area in the later stage to enhance the search accuracy. The dynamic learning factor can effectively guide the individual towards the local optimal solution and the global optimal solution, improving the directionality and efficiency of the search process.

[0116] Optionally, the Levy flight step size is specifically:

[0117]

[0118] where Γ represents the standard Gamma function, λ represents the exponential parameter, and s represents the size parameter.

[0119] It should be noted that the Levy flight step size simulates the random search of bat individuals with large step sizes by introducing a long jump mechanism. Its distribution characteristics combine the standard Gamma function and the exponential parameter to ensure that the search step size has the ability to explore a wide range and can also perform fine search in local areas. The non-uniform jump characteristics of Levy flight help the algorithm jump out of local optimal traps, broaden the search range, increase the search probability of the global optimal solution, and improve the robustness and search efficiency of the algorithm.

[0120] Randomly generate a random number r between 0 and 1 3 , and judge whether the random number r 3 is greater than the pulse rate. If so, enter the local search phase. Otherwise, enter the phase of updating the pulse rate and the average pulse loudness.

[0121] In the local search phase, select a solution from the optimal solution set to generate a new local solution:

[0122]

[0123] where represents the average pulse loudness emitted by the i-th bat individual at the t-th iteration, ε represents a random number between 0 and 1, represents the average pulse loudness emitted by the i-th bat individual at the t-th iteration, and α represents the pulse loudness attenuation coefficient.

[0124] It should be noted that by selecting solutions from the optimal solution set, the local search focuses around the current optimal solution, focuses on the vicinity of potential high-quality solutions, and conducts detailed searches to improve the accuracy of local solutions.

[0125] Calculate the fitness value of the new local solution, and generate a random number r between 0 and 1 4 , and judge whether it satisfies and If so, accept the new local solution. Otherwise, do not accept the new local solution.

[0126] It should be noted that the combination of fitness conditions and random perturbations makes the search process have a certain degree of fault tolerance. Even if the current optimal solution does not have significant improvement, potential solutions can be retained, increasing the possibility of finding the global optimal solution and improving the stability and robustness of the algorithm.

[0127] Update the pulse rate and the average pulse loudness:

[0128]

[0129] where, represents the pulse rate emitted by the i-th bat individual at the (t + 1)-th iteration, represents the initial pulse rate emitted by the i-th bat individual, e represents the natural constant, and γ represents the pulse rate enhancement coefficient, represents the average pulse loudness emitted by the i-th bat individual at the t-th iteration, and α represents the pulse loudness attenuation coefficient.

[0130] It should be noted that the average pulse loudness gradually decays with the number of iterations. Through the attenuation coefficient, the bat individuals have a larger exploration step size at the initial stage of the search, and gradually reduce the search range in the later stage, focusing on fine-grained local search near the optimal solution.

[0131] Furthermore, the pulse rate gradually increases with the number of iterations. Through the exponential enhancement coefficient, the search frequency of individuals gradually focuses near high-quality solutions. This mechanism enables the algorithm to have a strong global search ability in the early stage, and is more inclined to local search in the later stage, improving the convergence accuracy.

[0132] Judge whether the current number of iterations has reached the maximum number of iterations; if so, output the set of discrimination coefficients represented by the bat individual with the highest current fitness; otherwise, return to continue the iteration.

[0133] In the present invention, using the bat optimization algorithm to optimize the discrimination coefficients helps to improve the evaluation accuracy and discrimination ability of the grey relational method, and provides more scientific and objective results for the evaluation of geological relics.

[0134] S6: Sort each geological relic in descending order of the grey relational degree between each geological relic and the ideal sample.

[0135] S7: Divide each geological relic into different protection levels according to the sorting result.

[0136] In the present invention, classifying each geological heritage into different protection levels according to the sorting results can achieve the optimal allocation of resources and targeted protection. By scientifically evaluating the importance and vulnerability of each heritage, and accordingly allocating limited financial, human, and technical resources, it ensures that the most representative and scientifically valuable geological heritages are given priority protection, while also effectively preventing and controlling the possible damage to the heritages. In addition, this hierarchical management method helps to formulate more specific and effective protection strategies, promoting the long-term preservation of geological heritages and the maximization of the display of their natural beauty and scientific value. This method not only improves the efficiency of the protection work, but also enhances the public's awareness and attention to geological heritages at different levels, promoting a good atmosphere of the whole society's joint participation in protection.

[0137] S8: According to the protection level, take corresponding protection measures for each geological heritage.

[0138] In the present invention, taking corresponding protection measures for each geological heritage according to the protection level can ensure the combination of the effective utilization and precise protection of resources, maximizing the protection effect. Doing so not only helps to concentrate efforts on giving priority to protecting those sites with the most scientific value and vulnerability, preventing irreversible damage to key geological heritages, but also through customized management strategies, can more efficiently address the specific challenges of different heritages, such as natural erosion, human activity impacts, etc. In addition, the reasonable allocation of protection resources also helps to raise the protection awareness of the public and stakeholders, promoting the development of sustainable tourism and education, thus while protecting natural heritage, also supporting the economic and social development of local communities. This method achieves a win-win situation between environmental protection and social development.

[0139] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0140] In the present invention, based on the grey relational analysis method and combined with the entropy weight method, the entropy weight values of each evaluation index are determined by the entropy weight method, and then according to the entropy weight values of each evaluation index, the grey relational degree between each geological heritage and the ideal sample is determined by the grey relational analysis method, which can more comprehensively consider the importance of each evaluation index and improve the objectivity and accuracy of the comprehensive evaluation results.

[0141] Refer to the attached Figure 4 illustrates a schematic structural diagram of a geological heritage evaluation system provided by the present invention based on the coupling of grey relational analysis and entropy weight method.

[0142] The present invention also provides a geological heritage evaluation system 20 based on the coupling of grey relational analysis and entropy weight method, including:

[0143] Processor 201;

[0144] A memory 202, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor 201, the geological heritage evaluation method based on the coupling of the grey correlation method and the entropy weight method as described in the method embodiment is implemented.

[0145] The geological heritage evaluation system 20 provided by the present invention based on the coupling of the grey correlation method and the entropy weight method can execute the above-mentioned geological heritage evaluation method based on the coupling of the grey correlation method and the entropy weight method and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate further.

[0146] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0147] In the present invention, on the basis of the grey correlation method, the entropy weight method is combined. The entropy weight values of each evaluation index are determined by the entropy weight method, and then according to the entropy weight values of each evaluation index, the grey correlation degrees between each geological heritage and the ideal sample are determined by the grey correlation method, which can more comprehensively consider the importance of each evaluation index and improve the objectivity and accuracy of the comprehensive evaluation results.

[0148] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0149] The following points need to be explained:

[0150] (1) The attached drawings of the embodiments of the present invention only relate to the structures involved in the embodiments of the present invention, and other structures can refer to the general design.

[0151] (2) For clarity, in the attached drawings used to describe the embodiments of the present invention, the thickness of the film, region or substrate is enlarged or reduced, that is, these drawings are not drawn according to the actual ratio. It can be understood that when an element such as a film, region or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element or there can be an intermediate element.

[0152] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0153] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A geological relic evaluation method based on the coupling of grey correlation and entropy weight method, characterized in that: include: S1: Construct a comprehensive evaluation system for geological relics; S2: Obtain the scoring values ​​of geological relics under the comprehensive evaluation system and construct a scoring matrix; S3: Standardizing the scoring matrix to determine a standard matrix; S4: Determine the entropy weight of each evaluation index by entropy weight method according to the standard matrix; S5: According to the entropy weight of each evaluation index, the grey correlation degree between each geological relic and the ideal sample is determined by the grey correlation method; S6: Sort each geological relic according to the grey correlation between each geological relic and the ideal sample from high to low; S7: According to the ranking results, each geological heritage site is divided into different protection levels; S8: Take corresponding protection measures for each geological relic based on the protection level.

2. The geological relic evaluation method based on the coupling of grey correlation and entropy weight method according to claim 1 is characterized in that: The comprehensive evaluation system of geological relics specifically includes: First-level indicators: resource attributes and value attributes; The first-level indicator resource attributes has two secondary indicators: natural attributes and scientific attributes; The second-level indicator, natural attributes, has three levels of indicators: typicality, rarity, integrity, naturalness, and landscape richness; The second-level indicator scientific attributes are divided into three levels of indicators: representativeness of earth evolution and geological diversity; The first-level indicator value attribute has two secondary indicators: functional value and development value; The functional value of the secondary indicator consists of three levels of indicators: popular science education, aesthetics, social economy, historical culture, and ecological environment; The secondary indicator development value consists of three levels of indicators: overall level of regional development, regional environmental capacity, basic service facilities, protectability, transportation conditions, openness awareness, population quality level and relationship with neighboring tourist destinations.

3. The geological relic evaluation method based on the coupling of grey correlation and entropy weight method according to claim 1 is characterized in that: The scoring matrix is ​​specifically: Among them, A represents the scoring matrix, a ij It represents the score value of the jth geological relic under the ith evaluation index, m represents the total number of evaluation indicators, and n represents the total number of geological relics.

4. The geological relic evaluation method based on the coupling of grey correlation and entropy weight method according to claim 3 is characterized in that: The standardized matrix is ​​specifically: Among them, R represents the standardized matrix, r ij represents the standardized score value of the jth geological heritage under the i-th evaluation index, a ij represents the score of the jth geological heritage under the i-th evaluation index, a i,max represents the highest score under the i-th evaluation index, a i,min It represents the lowest score under the i-th evaluation index, m represents the total number of evaluation indicators, and n represents the total number of geological relics.

5. The geological relic evaluation method based on the coupling of grey correlation and entropy weight method according to claim 4 is characterized in that: The S4 specifically includes: S401: Calculate the weight of the score of each geological relic under each evaluation index: Among them, p ij represents the weight of the score of the jth geological relic under the i-th evaluation index, r ij represents the standardized score value of the jth geological heritage under the i-th evaluation index, and n represents the total number of geological heritage sites; S402: Calculate the entropy value of each evaluation index: Among them, e i represents the entropy value of the i-th evaluation index, and m represents the total number of evaluation indicators; S403: Calculate the entropy weight of each evaluation index: Among them, w i Represents the entropy weight of the i-th evaluation index.

6. The geological relic evaluation method based on the coupling of grey correlation and entropy weight method according to claim 5 is characterized in that: The S5 specifically includes: S501: Taking the ideal sample composed of the maximum values ​​under each evaluation index as the reference sequence, calculating the difference between each geological relic and the ideal sample, and constructing a difference matrix: b ij ＝r i,max -r ij Among them, B represents the difference matrix, b ij represents the difference between the score of the jth geological relic under the i-th evaluation index and the maximum value, r j,max Represents the maximum value of the i-th evaluation index; S502: Determine the maximum number and the minimum number in the difference matrix, and calculate the grey correlation coefficient matrix: Among them, C represents the grey correlation coefficient matrix, c ij The grey correlation coefficient of the score of the jth geological heritage under the i-th evaluation index, b min represents the minimum number in the difference matrix, b max represents the maximum number in the difference matrix, ρ i represents the resolution coefficient of the i-th evaluation index; S503: Calculate the grey correlation degree between each geological relic and the ideal sample according to the grey correlation coefficient matrix: Among them, γ j Represents the grey correlation between the jth geological relic and the ideal sample.

7. The geological relic evaluation method based on the coupling of grey correlation and entropy weight method according to claim 6 is characterized in that: The resolution coefficient is specifically: Among them, ρ i represents the resolution coefficient of the i-th evaluation index, δ i represents the scaling factor of the i-th evaluation index; The scale factor is specifically: Among them, b ij represents the difference between the score of the jth geological relic under the i-th evaluation index and the maximum value, b max represents the maximum number in the difference matrix, and n represents the total number of geological relics.

8. The geological relic evaluation method based on the coupling of grey correlation and entropy weight method according to claim 6 is characterized in that: The determination method of the resolution coefficient is specifically as follows: With the goal of maximizing the discrimination ability of grey relational degree, the resolution coefficients of various evaluation indicators are determined through bat optimization algorithm.

9. The geological relic evaluation method based on the coupling of grey correlation and entropy weight method according to claim 6 is characterized in that: The fitness function of the bat optimization algorithm is specifically: Among them, σ represents the fitness function, P represents the set of resolution coefficients, P = (ρ1, ρ2, ..., ρ m ), m represents the total number of evaluation indicators, γ j represents the grey correlation between the jth geological relic and the ideal sample, represents the average value of grey correlation, and n represents the total number of geological relics.

10. A geological heritage evaluation system based on the coupling of grey correlation and entropy weight method, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the geological relic evaluation method based on the coupling of grey correlation and entropy weight method as described in any one of claims 1 to 7 is implemented.

Images