A method and system for evaluating the effect of building ecological seawall oyster reefs

Abstract

The present invention discloses a method and system for evaluating the construction effect of ecological seawall oyster reefs, comprising the following steps: obtaining oyster reef monitoring information, performing survival status analysis based on the oyster reef monitoring information to obtain survival status analysis information; obtaining construction effect evaluation factors based on big data retrieval, classifying the factors, and determining construction effect evaluation indicators to obtain evaluation indicator information; assigning weights to each evaluation indicator based on the evaluation indicator information to obtain evaluation indicator weight information; constructing a construction effect evaluation model based on a CNN combined with the evaluation indicator weight information; obtaining target area monitoring information, performing construction effect evaluation based on the survival status analysis information, determining whether the construction effect meets the expected effect, and formulating an adjustment plan. The method improves the accuracy and reliability of the evaluation of the construction effect of ecological seawall oyster reefs.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological seawall construction, and in particular to a construction effect evaluation method and system for ecological seawall oyster reefs. Background Art

[0002] With global climate change and increasing human activities, the ecological environment faces increasingly severe challenges. To protect coastlines and ecosystems, the construction of ecological seawall oyster reefs has become increasingly important. The construction of ecological seawall oyster reefs is a beneficial ecological project aimed at enhancing the stability and biodiversity of marine ecosystems. They not only provide food and habitat, but also improve water quality, reduce coastal erosion, and enhance coastline stability.

[0003] With the continuous advancement of science and technology, the application of modern monitoring technologies has enabled us to more comprehensively understand the impact of oyster reefs on the marine environment. For example, with the help of advanced sensor network technology, changes in ecological parameters such as water quality, temperature, and salinity can be monitored in real time, thereby gaining a deeper understanding of the ecological effects of oyster reefs. Traditional assessment methods mainly rely on expert experience and subjective judgment, lacking objectivity and scientificity. For specific ecological engineering projects, such as the assessment of ecological seawall oyster reefs, a more sophisticated and comprehensive approach is required. Therefore, in order to ensure the effective construction and maintenance of oyster reefs, it is necessary to establish a scientific and reasonable assessment method to monitor and evaluate their actual effects in the marine environment, thereby improving the accuracy and reliability of the assessment of the effectiveness of ecological seawall oyster reef construction. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and provides a method and system for evaluating the effect of building an ecological seawall oyster reef. The important purpose of the present invention is to improve the accuracy and reliability of the evaluation of the effect of building an ecological seawall oyster reef.

[0005] To achieve the above objectives, the present invention provides a first aspect of a method for evaluating the effect of establishing an ecological seawall oyster reef, comprising:

[0006] Acquiring oyster reef monitoring information, performing survival status analysis based on the oyster reef monitoring information, and obtaining survival status analysis information;

[0007] Based on big data retrieval, we can obtain construction effect evaluation factors, classify the factors, determine construction effect evaluation indicators, and obtain evaluation indicator information;

[0008] Assigning weights to the evaluation indicators according to the evaluation indicator information to obtain evaluation indicator weight information;

[0009] Constructing a construction effect evaluation model based on CNN and combining the evaluation index weight information;

[0010] Obtain monitoring information of the target area, combine it with the survival status analysis information to evaluate the construction effect, determine whether it meets the expected effect, and formulate an adjustment plan.

[0011] In this solution, the acquisition of oyster reef monitoring information and the analysis of the survival status based on the oyster reef monitoring information are specifically as follows:

[0012] Acquiring oyster reef monitoring information, and performing denoising, filtering, and enhancement preprocessing on the oyster reef monitoring information;

[0013] A target detection model was constructed based on the YOLOv3 algorithm and the attention mechanism, including a feature extraction layer and a target detection layer. The oyster reef monitoring information was input for target detection.

[0014] Extract features of the oyster reef monitoring information according to the feature extraction layer to generate a first feature map, calculate the attention score of each feature in combination with the attention mechanism and generate an attention feature map;

[0015] Based on the YOLOv3 algorithm, a feature pyramid is built to fuse the attention feature map and the first feature map to obtain the second feature map. Target detection is performed based on the second feature map to generate candidate detection frames. The generated candidate detection frames are screened using the non-maximum suppression method to obtain target detection information.

[0016] Based on the image segmentation algorithm and the target detection information, the corresponding detection object image is segmented to obtain image segmentation information;

[0017] A survival status analysis model is constructed, and the image segmentation information and the oyster reef monitoring information are input into the survival status analysis model for analysis to obtain survival status analysis information.

[0018] In this plan, the classification of elements and the determination of construction effect evaluation indicators are as follows:

[0019] Based on big data retrieval, we retrieve the construction effect evaluation factors, calculate the Pearson correlation coefficient between each evaluation factor and the construction effect, use it as a correlation analysis indicator, and compare it with the preset threshold to screen out the evaluation factors with the greatest correlation with the construction effect to form the initial set of evaluation factors;

[0020] Obtaining influence information of each evaluation factor in the initial set of evaluation factors based on an expert analysis method, constructing an influence matrix based on the influence information, and calculating the similarity between each evaluation factor to form a similarity matrix;

[0021] Construct a Laplace matrix based on the similarity matrix, perform eigenvalue decomposition on the Laplace matrix, obtain eigenvalues ​​and corresponding eigenvectors, preset the number of clusters K, select K eigenvalues ​​and corresponding vectors to form an eigenvector space;

[0022] The K-means algorithm is used to cluster the eigenvectors in the eigenvector space multiple times, and the corresponding evaluation factors are classified into categories to obtain the factor classification information;

[0023] The influence of each evaluation factor is extracted, and the evaluation index analysis is performed in combination with the factor category classification information. Each evaluation factor is graded according to its influence, and the evaluation factor is selected as the construction effect evaluation index based on the classification result to obtain the evaluation index information.

[0024] In this solution, the weights of the evaluation indicators are assigned according to the evaluation indicator information, specifically:

[0025] Obtain evaluation index information, extract the influence of each evaluation index, introduce the intuitive fuzzy analysis method to assign subjective weights to each evaluation index, and construct the intuitive fuzzy evaluation matrix based on the influence;

[0026] Calculating the intuitionistic fuzzy entropy of each evaluation indicator according to the intuitionistic fuzzy evaluation matrix, and assigning subjective weights to each evaluation indicator using the calculated intuitionistic fuzzy entropy to obtain subjective weight information;

[0027] Based on the CRITIC method and the influence of each evaluation indicator, an objective weight is assigned to each evaluation indicator, and a matrix to be evaluated is constructed according to the influence of each evaluation indicator, and the matrix to be evaluated is standardized;

[0028] Calculate the variability and conflict of each evaluation indicator according to the matrix to be evaluated, wherein the variability is the standard deviation of the corresponding indicator, and the conflict is the correlation coefficient of the corresponding indicator, and obtain variability information and conflict information;

[0029] According to the conflict information, the evaluation indicators are sorted in ascending order, and an ordered vector is constructed based on the sorting results. The difference coefficient of each indicator in the ordered vector is calculated, and the objective weight of each evaluation indicator is calculated in combination with the variability information to obtain the objective weight information.

[0030] Based on the game theory method, the subjective weight information and objective weight information are combined to make the final weight distribution of each indicator and obtain the evaluation indicator weight information.

[0031] In this solution, the construction effect evaluation model is constructed based on CNN combined with the evaluation index weight information, specifically:

[0032] Obtain evaluation index information and evaluation index weight information, obtain ecological seawall oyster reef examples based on big data retrieval, extract indicator characteristics corresponding to the ecological seawall oyster reef examples based on the evaluation index information, perform time series processing, and obtain indicator characteristic information;

[0033] Combining the evaluation index weight information and the index characteristic information, the creation effect of each ecological seawall oyster reef example is evaluated, and a training data set and a validation data set are formed;

[0034] Constructing a construction effect evaluation model based on CNN, including an input layer, a hidden layer, and an output layer, presetting a loss function, and performing deep learning and training on the construction effect evaluation model by combining the training data set with a back propagation algorithm;

[0035] The validation data set is used to evaluate the trained construction effect evaluation model, and the construction effect evaluation model is adjusted according to the evaluation results to obtain a construction effect evaluation model that meets the expectations.

[0036] In this plan, the construction effect evaluation is carried out to determine whether it meets the expected effect and formulate an adjustment plan, specifically:

[0037] Acquiring target area monitoring information and survival status analysis information, wherein the target area monitoring information includes target area water body monitoring information and target area oyster reef image monitoring information;

[0038] Inputting the target area monitoring information and the survival status analysis information into a construction effect evaluation model for evaluation to obtain construction effect evaluation information;

[0039] Preset a construction effect judgment threshold, compare the construction effect evaluation information with the construction effect judgment threshold, analyze whether the construction effect meets expectations, and formulate an adjustment plan if it fails to meet expectations;

[0040] Based on big data retrieval, ecological seawall oyster reef adjustment plans in different environmental states are obtained to form a comparative data set, and similarity calculation is performed between the target area monitoring information and survival status analysis information and the comparative data set to obtain a similarity value;

[0041] The similarity value is compared with the preset threshold, and candidate adjustment plans are selected based on the judgment result. The adjustment cost of each candidate adjustment is calculated as the weight, and the candidate adjustment plans are weighted and ranked according to the weighted calculation result;

[0042] According to the sorting results, the optimal adjustment plan is selected for construction adjustment.

[0043] A second aspect of the present invention provides an ecological seawall oyster reef construction effect evaluation system, the system comprising: a memory and a processor, the memory containing an ecological seawall oyster reef construction effect evaluation method program, the ecological seawall oyster reef construction effect evaluation method program when executed by the processor to implement the following steps:

[0044] Acquiring oyster reef monitoring information, performing survival status analysis based on the oyster reef monitoring information, and obtaining survival status analysis information;

[0045] Based on big data retrieval, we can obtain construction effect evaluation factors, classify the factors, determine construction effect evaluation indicators, and obtain evaluation indicator information;

[0046] Assigning weights to the evaluation indicators according to the evaluation indicator information to obtain evaluation indicator weight information;

[0047] Constructing a construction effect evaluation model based on CNN and combining the evaluation index weight information;

[0048] Obtain monitoring information of the target area, combine it with the survival status analysis information to evaluate the construction effect, determine whether it meets the expected effect, and formulate an adjustment plan.

[0049] The present invention discloses a method and system for evaluating the construction effect of ecological seawall oyster reefs, comprising the following steps: obtaining oyster reef monitoring information, performing survival status analysis based on the oyster reef monitoring information to obtain survival status analysis information; obtaining construction effect evaluation factors based on big data retrieval, classifying the factors, and determining construction effect evaluation indicators to obtain evaluation indicator information; assigning weights to each evaluation indicator based on the evaluation indicator information to obtain evaluation indicator weight information; constructing a construction effect evaluation model based on a CNN combined with the evaluation indicator weight information; obtaining target area monitoring information, performing construction effect evaluation based on the survival status analysis information, determining whether the construction effect meets the expected effect, and formulating an adjustment plan. The method improves the accuracy and reliability of the evaluation of the construction effect of ecological seawall oyster reefs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or exemplary descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to these drawings without paying any creative work.

[0051] Figure 1 A flow chart of a method for evaluating the effectiveness of establishing an ecological seawall oyster reef provided by one embodiment of the present invention;

[0052] Figure 2 A flowchart of setting evaluation index weights provided by one embodiment of the present invention;

[0053] Figure 3 A block diagram of an ecological seawall oyster reef construction effect evaluation system provided by one embodiment of the present invention;

[0054] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0055] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0056] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0057] Figure 1 A flow chart of a method for evaluating the effectiveness of establishing an ecological seawall oyster reef provided by one embodiment of the present invention;

[0058] like Figure 1 As shown, the present invention provides a flow chart of a method for evaluating the effect of building an ecological seawall oyster reef, including:

[0059] S102, obtaining oyster reef monitoring information, performing survival status analysis based on the oyster reef monitoring information, and obtaining survival status analysis information;

[0060] Acquiring oyster reef monitoring information, and performing denoising, filtering, and enhancement preprocessing on the oyster reef monitoring information;

[0061] A target detection model was constructed based on the YOLOv3 algorithm and the attention mechanism, including a feature extraction layer and a target detection layer. The oyster reef monitoring information was input for target detection.

[0062] Extract features of the oyster reef monitoring information according to the feature extraction layer to generate a first feature map, calculate the attention score of each feature in combination with the attention mechanism and generate an attention feature map;

[0063] Based on the YOLOv3 algorithm, a feature pyramid is built to fuse the attention feature map and the first feature map to obtain the second feature map. Target detection is performed based on the second feature map to generate candidate detection frames. The generated candidate detection frames are screened using the non-maximum suppression method to obtain target detection information.

[0064] Based on the image segmentation algorithm and the target detection information, the corresponding detection object image is segmented to obtain image segmentation information;

[0065] A survival status analysis model is constructed, and the image segmentation information and the oyster reef monitoring information are input into the survival status analysis model for analysis to obtain survival status analysis information.

[0066] It should be noted that, first, oyster reef monitoring information is obtained, and the oyster reefs deployed in the target area are monitored by high-resolution cameras and other equipment. The acquired image information is denoised, filtered and enhanced to improve the image information quality; then, target detection is performed on the acquired oyster reef monitoring information to detect the oysters that need to be analyzed. The target detection model is constructed by the YOLOv3 algorithm and the attention mechanism, which includes a feature extraction layer and a target detection layer. The preprocessed oyster reef monitoring information is input into the model for target detection. The oyster reef monitoring information is subjected to feature extraction by the feature extraction layer. This step extracts the features of the entire image, and the first feature map is generated by this feature. Subsequently, it is input into the target detection layer for target detection. The attention score of each attention is calculated by the attention mechanism to generate an attention feature map, which is fused with the first feature map to enhance the model's attention to the features and avoid ignoring key features. Target detection is performed based on the fused second feature map to obtain target detection information; the detected object image is segmented by the image segmentation algorithm to further extract detailed image information. To construct a survival status analysis model, CNN, BP or support vector machine techniques can be used to construct it. Image segmentation information and oyster reef monitoring information can be input into the model for analysis. The growth status of oysters can be analyzed in detail through image segmentation information. At the same time, the degree of change of oyster reefs can be analyzed through oyster reef monitoring information. Combined with the growth status of oysters, the survival status of oyster reefs can be judged, thereby reflecting the construction effect of oyster reefs and providing a basis for subsequent analysis.

[0067] S104, based on the big data search, obtaining construction effect evaluation factors, classifying the factors, and determining construction effect evaluation indicators to obtain evaluation indicator information;

[0068] Based on big data retrieval, we retrieve the construction effect evaluation factors, calculate the Pearson correlation coefficient between each evaluation factor and the construction effect, use it as a correlation analysis indicator, and compare it with the preset threshold to screen out the evaluation factors with the greatest correlation with the construction effect to form the initial set of evaluation factors;

[0069] Obtaining influence information of each evaluation factor in the initial set of evaluation factors based on an expert analysis method, constructing an influence matrix based on the influence information, and calculating the similarity between each evaluation factor to form a similarity matrix;

[0070] Construct a Laplace matrix based on the similarity matrix, perform eigenvalue decomposition on the Laplace matrix, obtain eigenvalues ​​and corresponding eigenvectors, preset the number of clusters K, select K eigenvalues ​​and corresponding vectors to form an eigenvector space;

[0071] The K-means algorithm is used to cluster the eigenvectors in the eigenvector space multiple times, and the corresponding evaluation factors are classified into categories to obtain the factor classification information;

[0072] The influence of each evaluation factor is extracted, and the evaluation index analysis is performed in combination with the factor category classification information. Each evaluation factor is graded according to its influence, and the evaluation factor is selected as the construction effect evaluation index based on the classification result to obtain the evaluation index information.

[0073] It should be noted that, first, various evaluation factors for the creation effect of oyster reefs, including water quality, oyster reef changes, ecological diversity, etc., are obtained through big data retrieval, and the Pearson correlation coefficient between each evaluation factor and the creation effect is calculated. The Pearson correlation coefficient is used to measure the strength of the linear relationship between two variables. It is used here as a measure of the correlation between the evaluation factor and the creation effect. According to the calculated Pearson correlation coefficient, the obtained indicators are initially screened, and the evaluation factors with high correlation with the creation effect are selected to form the initial set of evaluation factors; then, the influence information of each evaluation factor in the initial set of evaluation factors is obtained through expert analysis, and an influence matrix is ​​constructed; the similarity between each element is calculated based on the influence matrix.

[0074] Based on the similarities between the evaluation factors, a similarity matrix is ​​constructed. Various similarity metrics can be used, such as Euclidean distance and cosine similarity. A vertex matrix is ​​calculated from the similarity matrix, where the sum of the rows of the similarity matrix is ​​the diagonal elements of the vertex matrix. Next, a Laplacian matrix is ​​calculated. The Laplacian matrix is ​​obtained by subtracting the vertex matrix from the similarity matrix. The Laplacian matrix is ​​then subjected to eigenvalue decomposition to obtain the eigenvalues ​​and corresponding eigenvectors. Subsequently, k eigenvalues ​​and eigenvectors are selected. Based on the number of clusters k required, the top k largest eigenvalues ​​and corresponding eigenvectors are selected. These selected eigenvectors are combined into a matrix, with each row representing the projection of a sample onto each eigenvector. A feature space is then constructed. K-means or other clustering algorithms are used to cluster the eigenvectors in the feature vector space, thereby partitioning the evaluation factors. Finally, the final evaluation index is determined based on the influence of each evaluation factor. This information is then used to more accurately select representative evaluation indicators and thus more accurately evaluate the construction effect.

[0075] S106, assigning weights to the evaluation indicators according to the evaluation indicator information to obtain evaluation indicator weight information;

[0076] Obtain evaluation index information, extract the influence of each evaluation index, introduce the intuitive fuzzy analysis method to assign subjective weights to each evaluation index, and construct the intuitive fuzzy evaluation matrix based on the influence;

[0077] Calculating the intuitionistic fuzzy entropy of each evaluation indicator according to the intuitionistic fuzzy evaluation matrix, and assigning subjective weights to each evaluation indicator using the calculated intuitionistic fuzzy entropy to obtain subjective weight information;

[0078] Based on the CRITIC method and the influence of each evaluation indicator, an objective weight is assigned to each evaluation indicator, and a matrix to be evaluated is constructed according to the influence of each evaluation indicator, and the matrix to be evaluated is standardized;

[0079] Calculate the variability and conflict of each evaluation indicator according to the matrix to be evaluated, wherein the variability is the standard deviation of the corresponding indicator, and the conflict is the correlation coefficient of the corresponding indicator, and obtain variability information and conflict information;

[0080] According to the conflict information, the evaluation indicators are sorted in ascending order, and an ordered vector is constructed based on the sorting results. The difference coefficient of each indicator in the ordered vector is calculated, and the objective weight of each evaluation indicator is calculated in combination with the variability information to obtain the objective weight information.

[0081] Based on the game theory method, the subjective weight information and objective weight information are combined to make the final weight distribution of each indicator and obtain the evaluation indicator weight information.

[0082] It should be noted that, first, evaluation indicator information is obtained and its corresponding influence information is extracted. Subjective weights are determined using intuitionistic fuzzy analysis. Using intuitionistic fuzzy theory, an intuitionistic fuzzy evaluation matrix is ​​constructed based on the influence of each indicator. Assuming there are m evaluation experts and n evaluation indicators, an m×n intuitionistic fuzzy evaluation matrix can be constructed, where each element represents an expert's evaluation of a particular indicator. For example, suppose there is an evaluation indicator A, and an expert rates A as "very good." This evaluation can be represented as an intuitionistic fuzzy number, such as (0.8, 0.2), where 0.8 represents the probability of A being rated "very good" and 0.2 represents the hesitation to rate A as "very good." The intuitionistic fuzzy evaluation matrix is ​​used to calculate the intuitionistic fuzzy entropy for each evaluation indicator. The calculated intuitionistic fuzzy entropy is used to assign subjective weights to each evaluation indicator. This step aims to weight indicators based on the fuzziness and uncertainty reflected by the entropy value, thereby obtaining subjective weight information. Next, the CRITIC method is used to objectively assign weights based on the influence of each evaluation indicator. We construct an evaluation matrix and standardize it to eliminate the influence of different dimensions. Based on the evaluation matrix, we calculate the variability (i.e., standard deviation) and conflict (i.e., correlation coefficient) of each evaluation metric. These represent the degree of fluctuation in the metric data and the interrelationships between the metrics, respectively. We then use this conflict information to sort the evaluation metrics in ascending order and construct an ordered vector. Within this ordered vector, we calculate the coefficient of variation for each metric and, combined with the previously obtained variability information, calculate the objective weight for each metric. Finally, we use game theory to integrate the subjective and objective weight information to assign the final weights to each metric. This ensures that the weights of the evaluation metrics take into account both the subjective judgment of the experts and the objective nature of the data. This ultimately results in a more reasonable and comprehensive set of evaluation metric weights, thereby improving the accuracy and scientific nature of the evaluation.

[0083] It should be noted that the CRITIC method is an evaluation method for objective weighting. Its core concept is to comprehensively assess the objective weighting of indicators by utilizing their comparative strength (also known as volatility) and conflict (also known as correlation). Comparative strength is measured by the difference in indicator values ​​between different evaluation schemes, typically expressed as a standard deviation. A larger standard deviation indicates greater indicator volatility and, therefore, a higher weight. Conversely, if two indicators have a large correlation coefficient, they exhibit a strong positive or negative correlation, indicating less conflict and, therefore, a relatively lower weight. The CRITIC method is particularly suitable for indicators or factors that exhibit interrelated relationships between the analyzed objects, and the data exhibits a certain degree of stability and predictability. This method helps reduce unnecessary double counting caused by strong correlations between certain indicators. It considers both indicator variability and correlation, rather than relying solely on the magnitude of the indicator values ​​to determine weighting, thereby improving the accuracy of evaluation results.

[0084] It should be noted that the correlation coefficient is a statistic used to measure the strength and direction of the linear relationship between two variables. Its value range is between -1 and 1, where "1" indicates a perfect positive correlation, meaning that when one variable increases, the other variable also increases synchronously; "0" indicates no correlation, meaning there is no linear relationship between the two variables; -1 indicates a perfect negative correlation, meaning that when one variable increases, the other variable decreases. The closer the absolute value of the correlation coefficient r is to 1, the stronger the linear relationship between the two variables; the closer it is to 0, the weaker the linear relationship between the two variables. In practical applications, the correlation coefficient is often used to assess the degree of dependence between variables, study the potential relationship between variables, and measure data quality.

[0085] S108, constructing a construction effect evaluation model based on CNN and the evaluation index weight information;

[0086] Obtain evaluation index information and evaluation index weight information, obtain ecological seawall oyster reef examples based on big data retrieval, extract indicator characteristics corresponding to the ecological seawall oyster reef examples based on the evaluation index information, perform time series processing, and obtain indicator characteristic information;

[0087] Combining the evaluation index weight information and the index characteristic information, the creation effect of each ecological seawall oyster reef example is evaluated, and a training data set and a validation data set are formed;

[0088] Constructing a construction effect evaluation model based on CNN, including an input layer, a hidden layer, and an output layer, presetting a loss function, and performing deep learning and training on the construction effect evaluation model by combining the training data set with a back propagation algorithm;

[0089] The validation data set is used to evaluate the trained construction effect evaluation model, and the construction effect evaluation model is adjusted according to the evaluation results to obtain a construction effect evaluation model that meets the expectations.

[0090] It's important to note that after determining the evaluation indicators and weights, a construction effectiveness evaluation model was constructed based on this information. This model was constructed using a CNN. CNNs have strong feature learning capabilities, automatically extracting useful features from large amounts of data. They also have strong analytical capabilities for image information. By processing indicator features in a temporal manner, CNNs can capture temporal trends in these indicators, enabling a better assessment of the effectiveness of ecological seawall oyster reefs. CNNs have a deep structure, enabling them to capture complex nonlinear relationships in the data. In the effectiveness evaluation, CNNs can learn the interactions and influences between evaluation indicators, further improving the accuracy of the assessment. Examples of ecological seawall oyster reefs were obtained through big data retrieval, and then evaluated. The effectiveness of each example was analyzed, and training and validation sets were constructed to train the model, ultimately achieving a model that met the expectations.

[0091] S110, obtaining monitoring information of the target area, combining it with the living condition analysis information to evaluate the construction effect, determine whether it meets the expected effect, and formulate an adjustment plan;

[0092] Acquiring target area monitoring information and survival status analysis information, wherein the target area monitoring information includes target area water body monitoring information and target area oyster reef image monitoring information;

[0093] Inputting the target area monitoring information and the survival status analysis information into a construction effect evaluation model for evaluation to obtain construction effect evaluation information;

[0094] Preset a construction effect judgment threshold, compare the construction effect evaluation information with the construction effect judgment threshold, analyze whether the construction effect meets expectations, and formulate an adjustment plan if it fails to meet expectations;

[0095] Based on big data retrieval, ecological seawall oyster reef adjustment plans in different environmental states are obtained to form a comparative data set, and similarity calculation is performed between the target area monitoring information and survival status analysis information and the comparative data set to obtain a similarity value;

[0096] The similarity value is compared with the preset threshold, and candidate adjustment plans are selected based on the judgment result. The adjustment cost of each candidate adjustment is calculated as the weight, and the candidate adjustment plans are weighted and ranked according to the weighted calculation result;

[0097] According to the sorting results, the optimal adjustment plan is selected for construction adjustment.

[0098] It should be noted that, first, monitoring information for the target area is obtained, including water monitoring information and oyster reef image monitoring data. The oyster reef image monitoring information obtained in this step covers the entire reef area and is primarily used to compare before and after reef construction and analyze changes in the reefs. Next, an evaluation is conducted using a pre-established reef effectiveness evaluation model. The acquired information is input into the model for analysis. The model evaluates the corresponding indicators in the input information based on preset evaluation weights, generating reef effectiveness evaluation information. Pre-set reef effectiveness judgment thresholds are used to compare the evaluation information with the reef effectiveness information. If the evaluation results indicate that the expected results have not been achieved, appropriate adjustment plans are developed. At this point, through big data retrieval, adjustment plans for ecological seawall oyster reefs in different environmental conditions are obtained, and a comparative dataset is constructed. Similarity calculations are performed between the monitoring information and survival analysis data for the target area and the comparative dataset to identify historical cases that most closely resemble the current situation. The calculated similarity values ​​are compared with preset thresholds, and potential adjustment plans are selected based on the comparison results. For each candidate adjustment plan, the adjustment cost is calculated and used as a weight in the weighted calculation. The candidate options are ranked using weighted calculations. Ultimately, the optimal adjustment plan is selected based on the ranking results and implemented. This ensures that the adjustment plan is based on scientific assessments and considers cost-effectiveness to achieve optimal ecological seawall oyster reef management.

[0099] Furthermore, the construction effect evaluation information is obtained, and abnormal analysis is performed based on the construction effect evaluation information, abnormal indicators are analyzed, and abnormal indicator analysis information is obtained; based on the big data retrieval, the inducement information corresponding to various abnormal indicators is obtained to form an inducement data set, and the inducement information of the abnormal indicators is analyzed in combination with the abnormal indicator analysis information to obtain abnormal indicator inducement information; according to the abnormal indicator inducement information, whether each inducement is analyzed

[0100] Furthermore, construction effect evaluation information is obtained, and abnormal index analysis is performed based on the construction effect evaluation information to obtain abnormal index analysis information; based on the abnormal index analysis information, it is determined whether abnormal coastline erosion occurs in the target area to obtain judgment result information; if the judgment result information indicates that coastline erosion occurs, an early warning is issued and a remedial plan is formulated; monitoring information of the target area is obtained, the deviation between the coastline at time t and the coastline at time t-1 is analyzed, and the coastline change rate is calculated to obtain coastline erosion analysis information; a number of change rate level judgment thresholds are preset, and the coastline erosion analysis information is compared with the change rate level judgment thresholds to analyze the coastline erosion degree and obtain coastline erosion degree analysis information; response plans for coastline erosion under various different environments are obtained based on big data retrieval to form a response plan data set; similarity is calculated between the coastline request degree information and the target area monitoring information and the response plan data set, and response plans under the same environment are extracted based on the calculated similarity to obtain candidate response plan information; the prevention and control timeliness and effect of each candidate response plan are extracted as weights and weighted calculation is performed on each candidate plan; the candidate plans are sorted according to the weighted calculation results, and the optimal response plan is selected to prevent coastline erosion from causing seawall hazards.

[0101] Figure 2 A flowchart of setting evaluation index weights provided by one embodiment of the present invention;

[0102] like Figure 2 As shown, the present invention provides a flow chart for setting evaluation index weights, including:

[0103] S202, obtaining construction effect evaluation factors based on big data retrieval, and calculating the Pearson correlation coefficient between each evaluation factor and the construction effect;

[0104] S204, judging against a preset threshold, screening out evaluation factors that are highly correlated with the construction effect, and forming an initial set of evaluation factors;

[0105] S206, obtaining influence information of each evaluation factor in the initial set of evaluation factors based on an expert analysis method, and classifying each evaluation factor into a factor category using a clustering algorithm;

[0106] S208, classifying each evaluation factor according to its influence, and selecting the evaluation factor as a construction effect evaluation index based on the classification result to obtain evaluation index information;

[0107] S210, introducing an intuitive fuzzy analysis method to assign subjective weights to each evaluation indicator, constructing an intuitive fuzzy evaluation matrix, calculating the intuitive fuzzy entropy of each evaluation indicator, and assigning subjective weights to each evaluation indicator;

[0108] S212, constructing a matrix to be evaluated, assigning objective weights to each evaluation indicator based on the CRITIC method, calculating the variability and conflict of each evaluation indicator, assigning objective weights, and obtaining objective weight information;

[0109] S214, introducing the game theory method to combine the subjective weight information and the objective weight information to perform the final weight distribution on each indicator, and obtain the evaluation indicator weight information.

[0110] It should be noted that after analysis, subjective and objective weights were obtained. Game theory was introduced to determine the comprehensive weights, thereby balancing subjectivity and objectivity, and thus obtaining more reasonable and comprehensive evaluation weights. The subjective and objective weights were analyzed as the two sides of the game to obtain the combined weights when the two sides reached equilibrium. In other words, a solution was found that minimized the sum of the deviations between the subjective and objective weights and the combined weights. For example, a game model was constructed, and the subjective and objective weights were combined using a linear combination to obtain the combined weights. Then, the objective function and constraints were constructed, and the linear combination coefficients were optimized to obtain the optimal solution. The linear combination coefficients were then standardized. Finally, the obtained linear combination coefficients were used to obtain the combined weights, that is, the final evaluation weights of each indicator, thereby accurately measuring the impact of each evaluation factor on the construction effect.

[0111] Figure 3 An embodiment of the present invention provides an ecological seawall oyster reef construction effect evaluation system 3, which includes: a memory 31 and a processor 32. The memory 31 contains an ecological seawall oyster reef construction effect evaluation method program. When the ecological seawall oyster reef construction effect evaluation method program is executed by the processor 32, the following steps are implemented:

[0112] Acquiring oyster reef monitoring information, performing survival status analysis based on the oyster reef monitoring information, and obtaining survival status analysis information;

[0113] Based on big data retrieval, we can obtain construction effect evaluation factors, classify the factors, determine construction effect evaluation indicators, and obtain evaluation indicator information;

[0114] Assigning weights to the evaluation indicators according to the evaluation indicator information to obtain evaluation indicator weight information;

[0115] Constructing a construction effect evaluation model based on CNN and combining the evaluation index weight information;

[0116] Obtain monitoring information of the target area, combine it with the survival status analysis information to evaluate the construction effect, determine whether it meets the expected effect, and formulate an adjustment plan.

[0117] It should be noted that the present invention provides a method and system for evaluating the construction effect of an ecological seawall oyster reef, which evaluates the construction effect by selecting reasonable evaluation indicators and formulating scientific evaluation weights. Through the indicator determination method provided by the present invention, it is possible to find evaluation indicators with a high correlation with the construction effect, thereby selecting representative indicators to evaluate the construction effect, eliminating indicators with small correlation, and being able to perform a more comprehensive evaluation during the evaluation. At the same time, the intuitive fuzzy analysis method and the CRITIC method are introduced to determine the weights of each indicator, the subjective weight is determined by the intuitive fuzzy analysis method, the objective weight is determined by the CRITIC method, and then the subjective weight and the objective weight are combined according to game theory to obtain the evaluation weights of each evaluation indicator, ensuring that the weights of the evaluation indicators take into account both the subjective judgment of the experts and the objective nature of the data themselves, thereby improving the accuracy and reliability of the construction effect evaluation.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0119] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0120] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0121] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0122] Alternatively, if the integrated units described above are implemented as software modules and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0123] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for evaluating the effect of building an ecological seawall oyster reef, characterized in that: include: Acquiring oyster reef monitoring information, performing survival status analysis based on the oyster reef monitoring information, and obtaining survival status analysis information; Based on big data retrieval, we retrieve the construction effect evaluation factors, calculate the Pearson correlation coefficient between each evaluation factor and the construction effect, use it as a correlation analysis indicator, and compare it with the preset threshold to screen out the evaluation factors with the greatest correlation with the construction effect to form the initial set of evaluation factors; Obtaining influence information of each evaluation factor in the initial set of evaluation factors based on an expert analysis method, constructing an influence matrix based on the influence information, and calculating the similarity between each evaluation factor to form a similarity matrix; Construct a Laplace matrix based on the similarity matrix, perform eigenvalue decomposition on the Laplace matrix, obtain eigenvalues ​​and corresponding eigenvectors, preset the number of clusters K, select K eigenvalues ​​and corresponding vectors to form an eigenvector space; The K-means algorithm is used to cluster the eigenvectors in the eigenvector space multiple times, and the corresponding evaluation factors are classified into categories to obtain the factor classification information; Extract the influence of each evaluation factor, combine the factor classification information to perform evaluation index analysis, classify each evaluation factor according to its influence, and select the evaluation factor as the construction effect evaluation index based on the classification results to obtain evaluation index information; Obtain evaluation index information, extract the influence of each evaluation index, introduce the intuitive fuzzy analysis method to assign subjective weights to each evaluation index, and construct the intuitive fuzzy evaluation matrix based on the influence; Calculating the intuitionistic fuzzy entropy of each evaluation indicator according to the intuitionistic fuzzy evaluation matrix, and assigning subjective weights to each evaluation indicator using the calculated intuitionistic fuzzy entropy to obtain subjective weight information; Based on the CRITIC method and the influence of each evaluation indicator, an objective weight is assigned to each evaluation indicator, and a matrix to be evaluated is constructed according to the influence of each evaluation indicator, and the matrix to be evaluated is standardized; Calculate the variability and conflict of each evaluation indicator according to the matrix to be evaluated, wherein the variability is the standard deviation of the corresponding indicator, and the conflict is the correlation coefficient of the corresponding indicator, and obtain variability information and conflict information; According to the conflict information, the evaluation indicators are sorted in ascending order, and an ordered vector is constructed based on the sorting results. The difference coefficient of each indicator in the ordered vector is calculated, and the objective weight of each evaluation indicator is calculated in combination with the variability information to obtain the objective weight information. Based on the game theory method, the subjective weight information and objective weight information are combined to make the final weight distribution of each indicator, and the evaluation indicator weight information is obtained; Constructing a construction effect evaluation model based on CNN and combining the evaluation index weight information; Obtain monitoring information of the target area, combine it with the survival status analysis information to evaluate the construction effect, determine whether it meets the expected effect, and formulate an adjustment plan.

2. The method for evaluating the effect of building an ecological seawall oyster reef according to claim 1, wherein: The obtaining of oyster reef monitoring information and performing survival status analysis based on the oyster reef monitoring information specifically includes: Acquiring oyster reef monitoring information, and performing denoising, filtering, and enhancement preprocessing on the oyster reef monitoring information; A target detection model was constructed based on the YOLOv3 algorithm and the attention mechanism, including a feature extraction layer and a target detection layer. The oyster reef monitoring information was input for target detection. Extract features of the oyster reef monitoring information according to the feature extraction layer to generate a first feature map, calculate the attention score of each feature in combination with the attention mechanism and generate an attention feature map; Based on the YOLOv3 algorithm, a feature pyramid is built to fuse the attention feature map and the first feature map to obtain the second feature map. Target detection is performed based on the second feature map to generate candidate detection frames. The generated candidate detection frames are screened using the non-maximum suppression method to obtain target detection information. Based on the image segmentation algorithm and the target detection information, the corresponding detection object image is segmented to obtain image segmentation information; A survival status analysis model is constructed, and the image segmentation information and the oyster reef monitoring information are input into the survival status analysis model for analysis to obtain survival status analysis information.

3. The method for evaluating the effect of building an ecological seawall oyster reef according to claim 1, wherein: The construction effect evaluation model is constructed based on CNN and combined with the evaluation index weight information, specifically including: Obtain evaluation index information and evaluation index weight information, obtain ecological seawall oyster reef examples based on big data retrieval, extract indicator characteristics corresponding to the ecological seawall oyster reef examples based on the evaluation index information, perform time series processing, and obtain indicator characteristic information; Combining the evaluation index weight information and the index characteristic information, the creation effect of each ecological seawall oyster reef example is evaluated, and a training data set and a validation data set are formed; Constructing a construction effect evaluation model based on CNN, including an input layer, a hidden layer, and an output layer, presetting a loss function, and performing deep learning and training on the construction effect evaluation model by combining the training data set with a back propagation algorithm; The validation data set is used to evaluate the trained construction effect evaluation model, and the construction effect evaluation model is adjusted according to the evaluation results to obtain a construction effect evaluation model that meets the expectations.

4. The method for evaluating the effect of building an ecological seawall oyster reef according to claim 1, wherein: The above mentioned evaluation of construction effect is carried out to determine whether it meets the expected effect and formulate adjustment plans, including: Acquiring target area monitoring information and survival status analysis information, wherein the target area monitoring information includes target area water body monitoring information and target area oyster reef image monitoring information; Inputting the target area monitoring information and the survival status analysis information into a construction effect evaluation model for evaluation to obtain construction effect evaluation information; Preset a construction effect judgment threshold, compare the construction effect evaluation information with the construction effect judgment threshold, analyze whether the construction effect meets expectations, and formulate an adjustment plan if it fails to meet expectations; Based on big data retrieval, ecological seawall oyster reef adjustment plans in different environmental states are obtained to form a comparative data set, and similarity calculation is performed between the target area monitoring information and survival status analysis information and the comparative data set to obtain a similarity value; The similarity value is compared with the preset threshold, and candidate adjustment plans are selected based on the judgment result. The adjustment cost of each candidate adjustment is calculated as the weight, and the candidate adjustment plans are weighted and ranked according to the weighted calculation result; According to the sorting results, the optimal adjustment plan is selected for construction adjustment.

5. A system for evaluating the effect of building an ecological seawall oyster reef, characterized in that: The system includes: a memory and a processor, wherein the memory contains a method program for evaluating the effect of creating an ecological seawall oyster reef. When the method program for evaluating the effect of creating an ecological seawall oyster reef is executed by the processor, the method steps for evaluating the effect of creating an ecological seawall oyster reef as described in any one of claims 1 to 4 are implemented.

Images