New prawn culture optimization method and system based on water quality characteristic analysis

Abstract

The invention discloses a new prawn culture optimization method and system based on water quality characteristic analysis. The method comprises the following steps: firstly, acquiring water environment data and new prawn growth condition data of each sub-region of a target new prawn culture water area, and performing difference analysis to obtain new prawn culture difference data of each sub-region; then, key factors influencing the growth of the new prawns are determined, and the optimal culture parameter range of the factors is analyzed to serve as culture reference parameters; secondly, acquiring actual water environment data of a water area to be cultured, comparing the actual water environment data with the reference parameters, and calculating deviation degree data; and according to the deviation degree data, evaluating the cultivation suitability, if the suitability is lower than a preset value, performing water environment regulation and control on the to-be-cultivated water area by optimizing the ecological conditions of the protists, and formulating a cultivation optimization scheme. According to the method, by accurately analyzing and adjusting the water quality and the growth conditions, the new prawn culture environment is optimized, and the culture efficiency and the prawn growth quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of Litopenaeus vannamei aquaculture, and particularly relates to an optimization method and system for Litopenaeus vannamei aquaculture based on water quality characteristic analysis. Background Art

[0002] With the development of the aquaculture industry, Litopenaeus vannamei aquaculture has gradually become an important part of global aquaculture. However, there are many challenges in the process of Litopenaeus vannamei aquaculture, and the most prominent one is the water quality management problem. The quality of water directly affects the growth rate, health status and final yield of Litopenaeus vannamei. Therefore, how to optimize the Litopenaeus vannamei aquaculture effect through scientific and effective water quality management means has become the focus of research.

[0003] At present, the water quality management in Litopenaeus vannamei aquaculture mainly relies on experience and regular detection, lacking systematic and scientific guiding methods. There are many drawbacks in this traditional management method, such as insufficient detection frequency, inability to grasp water quality fluctuations in real time, and difficulty in analyzing the interaction between environmental factors. These problems may lead to the instability of the growth environment of Litopenaeus vannamei, thus affecting the growth and yield of Litopenaeus vannamei.

[0004] In recent years, with the development of big data technology and machine learning algorithms, the water quality management method has been significantly improved. By systematically analyzing water quality data, the changing trend of water quality and key influencing factors can be grasped more accurately. However, most of the existing methods are limited to the analysis of single factors, lacking comprehensive consideration of the comprehensive effects of multiple factors, resulting in poor optimization effect of aquaculture parameters. In addition, the existing water quality optimization methods also rarely consider the water environment characteristics of the actual aquaculture area, resulting in limitations in the applicability and effect of the optimization scheme.

[0005] In view of the above problems, the present invention proposes an optimization method for Litopenaeus vannamei aquaculture based on water quality characteristic analysis. By performing differential analysis on the water environment data of the aquaculture water area and the data of the growth situation of Litopenaeus vannamei, the key factors affecting the growth of Litopenaeus vannamei are identified, and the decision tree algorithm is used to determine the optimal aquaculture parameter range, so as to provide a scientific guiding scheme for Litopenaeus vannamei aquaculture. At the same time, the present invention also combines the method of optimizing water quality by protists to further improve the suitability of the aquaculture environment and maximize the Litopenaeus vannamei aquaculture effect. Summary of the Invention

[0006] In order to solve at least one of the above technical problems, the present invention proposes an optimization method and system for Litopenaeus vannamei aquaculture based on water quality characteristic analysis.

[0007] The first aspect of the present invention provides an optimization method for Litopenaeus vannamei aquaculture based on water quality characteristic analysis, including:

[0008] Obtain the water environment data and the new shrimp growth data for each sub-region in the target new shrimp aquaculture water area, perform a difference analysis on the water environment data and the new shrimp growth data of the sub-regions, and obtain the new shrimp aquaculture difference data for each sub-region;

[0009] Determine the influencing factors that affect the growth of new shrimp in the target new shrimp aquaculture water area according to the new shrimp aquaculture difference data;

[0010] Based on the decision tree algorithm, analyze the influencing factors, determine the optimal aquaculture parameter range of the influencing factors, and use the optimal aquaculture parameter range as the benchmark parameter range for new shrimp aquaculture;

[0011] Obtain the actual water environment data of the water area to be cultured, compare the actual water environment data with the benchmark parameter range, and calculate the deviation degree data between the actual water environment data and the benchmark parameter range;

[0012] Judge the suitability of new shrimp aquaculture in the water area to be cultured according to the deviation degree data. If the aquaculture suitability is less than the preset value, optimize the water environment of the water area to be cultured through the native organisms in the water area to be cultured to obtain an aquaculture optimization plan.

[0013] In this solution, the obtaining of the water environment data and the new shrimp growth data for each sub-region in the target new shrimp aquaculture water area, the performance of a difference analysis on the water environment data and the new shrimp growth data of the sub-regions, and the obtaining of the new shrimp aquaculture difference data for each sub-region are specifically as follows:

[0014] Obtain the geographical environment data of the target new shrimp aquaculture water area, construct a two-dimensional plane map of the target new shrimp aquaculture water area according to the geographical environment data, and divide the target new shrimp aquaculture water area into N sub-regions based on the two-dimensional plane map;

[0015] Obtain the water environment data and the new shrimp growth data for each sub-region. The water environment data includes water temperature, pH value, dissolved oxygen, pollutant concentration, and organic matter concentration. The new shrimp growth data includes body weight, body length, survival rate, disease condition, and activity;

[0016] Construct data tables for the water environment data and the new shrimp growth data of each sub-region to obtain the water environment data table and the new shrimp growth data table for each sub-region;

[0017] Calculate the Euclidean distance of the corresponding data items between the water environment data tables and the new shrimp growth data tables of each sub-region, and evaluate the water environment data difference and the new shrimp growth situation difference between each sub-region according to the Euclidean distance of the data items to obtain the new shrimp aquaculture difference data for each sub-region.

[0018] In this solution, the impact factors that affect the growth of new penaeid shrimp in the target new penaeid shrimp aquaculture water area determined according to the new penaeid shrimp aquaculture difference data are specifically as follows:

[0019] Evaluate the new penaeid shrimp aquaculture quality of each sub-region in the target new penaeid shrimp aquaculture water area according to the new penaeid shrimp aquaculture difference data to obtain the aquaculture quality evaluation results of the sub-regions;

[0020] Divide the sub-regions into high-quality aquaculture areas and non-high-quality aquaculture areas according to the aquaculture quality evaluation results;

[0021] Obtain the first aquaculture water environment difference data between high-quality aquaculture areas and non-high-quality aquaculture areas, the second aquaculture water environment difference data between high-quality aquaculture areas and high-quality aquaculture areas, and the third aquaculture water environment difference data between non-high-quality aquaculture areas and non-high-quality aquaculture areas according to the new penaeid shrimp aquaculture difference data;

[0022] Based on the grey relational analysis method, conduct a correlation analysis on the first aquaculture water environment difference data, the second aquaculture water environment difference data, the third aquaculture water environment difference data and the new penaeid shrimp growth situation data in the corresponding aquaculture areas, identify the water environment factors that affect the new penaeid shrimp in the target new penaeid shrimp aquaculture water area, and obtain the impact factors.

[0023] In this solution, the analysis of the impact factors based on the decision tree algorithm to determine the optimal aquaculture parameter range of the impact factors and use the optimal aquaculture parameter range as the benchmark parameter range for new penaeid shrimp aquaculture is specifically as follows:

[0024] Extract the parameter data of the impact factors in each sub-region, divide the new penaeid shrimp growth indicators into three grades: excellent, medium, and poor according to the aquaculture quality evaluation results of the sub-regions, and obtain the new penaeid shrimp aquaculture indicator grade data of each sub-region;

[0025] Build a decision tree model based on the decision tree algorithm, use the impact factors as the features of the decision tree model, use the parameter data as the input variables of the features, and use the new penaeid shrimp aquaculture indicator grade data as the target variables of the decision tree model;

[0026] Use information gain as the splitting criterion of the decision tree model, calculate the information gain of each feature in the decision tree model, use the feature with the largest information gain as the splitting feature of the current node, split the corresponding parameter data into multiple subsets according to the selected splitting feature, and create a new node for each subset. Iteratively calculate the information gain and splitting operations for the new nodes until the decision tree reaches the preset depth, and obtain the relationship decision tree between the parameter data of the impact factors and the new penaeid shrimp growth indicators;

[0027] Perform path analysis on the relationship decision tree, mark the decision paths with excellent growth indicators for the new shrimp, extract the range of influence factor parameters for the decision paths, and obtain the optimal breeding parameter range for each influence factor in the new shrimp breeding;

[0028] Use the optimal breeding parameter range as the benchmark parameter range for the new shrimp breeding.

[0029] In this solution, obtain the actual water environment data of the water area to be cultured, compare the actual water environment data with the benchmark parameter range, and calculate the deviation data between the actual water environment data and the benchmark parameter range, specifically:

[0030] Divide the water area to be cultured for the new shrimp, and obtain the actual water environment data of each divided water area;

[0031] Compare the actual water environment data of each divided water area with the benchmark parameter range, and calculate the deviation degree between the actual water environment data of each divided water area and the benchmark parameter range based on the percentage deviation to obtain the deviation data.

[0032] In this solution, determine the breeding suitability of the new shrimp in the water area to be cultured according to the deviation data. If the breeding suitability is less than the preset value, optimize the water environment of the water area to be cultured through the native organisms in the water area to be cultured to obtain a breeding optimization plan, specifically:

[0033] Determine the influence weight of each influence factor on the breeding quality of the new shrimp based on the information entropy weight method to obtain the influence weight information;

[0034] Evaluate the breeding suitability of the new shrimp in each divided water area of the water area to be cultured based on the deviation data and the influence weight information;

[0035] Construct a native organism database for the water area to be cultured, and obtain the native organism species information in the water area to be cultured. The native organism species information includes the species information of protozoa, native plants, and native microorganisms in the water area to be cultured;

[0036] Obtain the biological purification function data of each native species from the Internet according to the native organism species information, and import the native organism species information and the biological purification function data into the native organism database for storage;

[0037] Mark the divided water areas with breeding suitability less than the preset value according to the breeding suitability of the new shrimp in each divided water area to obtain the water areas to be optimized;

[0038] Determine the influence factors and the degree of deviation severity corresponding to the deviation data items of the water areas to be optimized according to the deviation data;

[0039] Perform data matching based on the impact factors corresponding to the protist database and the deviation data items, identify the protists that have the ability to repair the impact factors corresponding to the deviation data items and have the strongest repair performance, and obtain the organisms to be released;

[0040] Determine the release quantity of the organisms to be released in each water area to be optimized according to the repair performance data of the organisms to be released and the degree of deviation;

[0041] Optimize the water environment of the aquaculture water area according to the organisms to be released and the release quantity, and obtain an aquaculture optimization plan.

[0042] The second aspect of the present invention also provides a new penaeid shrimp aquaculture optimization system based on water quality characteristic analysis. The system includes: a memory and a processor. The memory includes a program for the new penaeid shrimp aquaculture optimization method based on water quality characteristic analysis. When the program for the new penaeid shrimp aquaculture optimization method based on water quality characteristic analysis is executed by the processor, the following steps are implemented:

[0043] Obtain the water environment data and the growth data of new penaeid shrimp in each sub-region of the target new penaeid shrimp aquaculture water area, perform a difference analysis on the water environment data and the growth data of new penaeid shrimp in the sub-regions, and obtain the new penaeid shrimp aquaculture difference data for each sub-region;

[0044] Determine the impact factors that affect the growth of new penaeid shrimp in the target new penaeid shrimp aquaculture water area according to the new penaeid shrimp aquaculture difference data;

[0045] Analyze the impact factors based on the decision tree algorithm, determine the optimal aquaculture parameter range of the impact factors, and use the optimal aquaculture parameter range as the benchmark parameter range for new penaeid shrimp aquaculture;

[0046] Obtain the actual water environment data of the aquaculture water area to be cultured, compare the actual water environment data with the benchmark parameter range, and calculate the deviation degree data between the actual water environment data and the benchmark parameter range;

[0047] Judge the aquaculture suitability of new penaeid shrimp in the aquaculture water area to be cultured according to the deviation degree data. If the aquaculture suitability is less than the preset value, optimize the water environment of the aquaculture water area to be cultured through the protists in the aquaculture water area to be cultured, and obtain an aquaculture optimization plan.

[0048] In this solution, the analysis of the impact factors based on the decision tree algorithm to determine the optimal aquaculture parameter range of the impact factors and use the optimal aquaculture parameter range as the benchmark parameter range for new penaeid shrimp aquaculture is specifically as follows:

[0049] Extract the parameter data of the influencing factors in each sub-region, and divide the new shrimp growth indicators into three grades: excellent, medium, and poor according to the aquaculture quality evaluation results of the sub-regions, so as to obtain the new shrimp aquaculture index grade data for each sub-region;

[0050] Construct a decision tree model based on the decision tree algorithm, use the influencing factors as the features of the decision tree model, use the parameter data as the input variables of the features, and use the new shrimp aquaculture index grade data as the target variables of the decision tree model;

[0051] Use information gain as the splitting criterion of the decision tree model, calculate the information gain of each feature in the decision tree model, take the feature with the largest information gain as the splitting feature of the current node, split the corresponding parameter data into multiple subsets according to the selected splitting feature, and create a new node for each subset, and iteratively calculate the information gain and splitting operation for the new node until the decision tree reaches the preset depth, so as to obtain the relationship decision tree between the parameter data of the influencing factors and the new shrimp growth indicators;

[0052] Conduct path analysis on the relationship decision tree, mark the decision paths with excellent new shrimp growth indicators, extract the parameter ranges of the influencing factors of the decision paths, and obtain the optimal aquaculture parameter ranges of each influencing factor for new shrimp aquaculture;

[0053] Take the optimal aquaculture parameter range as the benchmark parameter range for new shrimp aquaculture.

[0054] In this solution, obtain the actual water environment data of the water area to be cultured, compare the actual water environment data with the benchmark parameter range, and calculate the deviation degree data between the actual water environment data and the benchmark parameter range, specifically:

[0055] Divide the water area to be cultured with new shrimps, and obtain the actual water environment data of each divided water area;

[0056] Compare the actual water environment data of each divided water area with the benchmark parameter range, and calculate the deviation degree between the actual water environment data of each divided water area and the benchmark parameter range based on the percentage deviation to obtain the deviation degree data.

[0057] In this solution, judge the aquaculture suitability of the water area to be cultured with new shrimps according to the deviation degree data. If the aquaculture suitability is less than the preset value, optimize the water environment of the water area to be cultured through the native organisms in the water area to be cultured to obtain an aquaculture optimization plan, specifically:

[0058] Determine the influence weight of each influencing factor on the aquaculture quality of new shrimps based on the information entropy weight method to obtain the influence weight information;

[0059] Evaluate the new shrimp farming suitability of each divided water area in the water area to be farmed based on the deviation data and influence weight information;

[0060] Construct a protist database for the water area to be farmed, and obtain the protist species information in the water area to be farmed. The protist species information includes the species information of protozoa, protophyta, and protomicroorganisms in the water area to be farmed;

[0061] Obtain the biological purification function data of each protist species from the Internet according to the protist species information, and import the protist species information and the biological purification function data into the protist database for storage;

[0062] Mark the divided water areas with a new shrimp farming suitability less than a preset value according to the new shrimp farming suitability of each divided water area to obtain the water areas to be optimized;

[0063] Determine the influencing factors and deviation severity corresponding to the deviation data items of the water areas to be optimized according to the deviation data;

[0064] Match the data according to the influencing factors corresponding to the deviation data items in the protist database, and identify the protist with the ability to repair the influencing factors corresponding to the deviation data items and the strongest repair performance to obtain the organisms to be released;

[0065] Determine the release quantity of the organisms to be released in each water area to be optimized according to the repair performance data of the organisms to be released and the deviation degree;

[0066] Optimize the water environment of the water area to be farmed according to the organisms to be released and the release quantity to obtain a farming optimization plan.

[0067] The present invention discloses a new shrimp farming optimization method and system based on water quality characteristic analysis. First, obtain the water environment data and new shrimp growth data of each sub-region of the target new shrimp farming water area, and conduct a difference analysis to obtain the new shrimp farming difference data of each sub-region. Subsequently, determine the key factors affecting the growth of new shrimp, and analyze the optimal farming parameter ranges of these factors as the farming benchmark parameters. Then, obtain the actual water environment data of the water area to be farmed, compare it with the benchmark parameters, and calculate the deviation data. Evaluate the farming suitability according to the deviation data. If the suitability is lower than the preset value, adjust the water environment of the water area to be farmed by optimizing the protist ecological conditions, and formulate a farming optimization plan. This method optimizes the new shrimp farming environment, improves the farming efficiency and the growth quality of shrimp through precise analysis and adjustment of water quality and growth conditions. Description of the Drawings

[0068] Figure 1Shows the flowchart of a new optimization method for penaeid shrimp farming based on water quality characteristic analysis of the present invention;

[0069] Figure 2 Shows the flowchart of determining influencing factors of the present invention;

[0070] Figure 3 Shows the flowchart of calculating deviation degree data of the present invention;

[0071] Figure 4 Shows the block diagram of a new optimization system for penaeid shrimp farming based on water quality characteristic analysis of the present invention. Detailed implementation manners

[0072] In order to be able to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the drawings and specific implementation manners. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0073] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0074] Figure 1 Shows the flowchart of a new optimization method for penaeid shrimp farming based on water quality characteristic analysis of the present invention.

[0075] As Figure 1 shown, the first aspect of the present invention provides a new optimization method for penaeid shrimp farming based on water quality characteristic analysis, including:

[0076] S102, obtaining the water environment data and the penaeid shrimp growth situation data of each sub-region in the target penaeid shrimp farming water area, performing a difference analysis on the water environment data and the penaeid shrimp growth situation data of the sub-regions, and obtaining the penaeid shrimp farming difference data of each sub-region;

[0077] S104, determining the influencing factors that affect the growth of penaeid shrimp in the target penaeid shrimp farming water area according to the penaeid shrimp farming difference data;

[0078] S106, analyzing the influencing factors based on the decision tree algorithm, determining the optimal farming parameter range of the influencing factors, and taking the optimal farming parameter range as the benchmark parameter range for penaeid shrimp farming;

[0079] S108, obtaining the actual water environment data of the water area to be farmed, comparing the actual water environment data with the benchmark parameter range, and calculating the deviation degree data of the actual water environment data from the benchmark parameter range;

[0080] S110. Determine the suitability of the new penaeid shrimp farming in the water area to be farmed according to the deviation data. If the farming suitability is less than the preset value, optimize the water environment of the water area to be farmed through the native organisms in the water area to be farmed to obtain a farming optimization plan.

[0081] It should be noted that by obtaining the water environment data and the growth data of the new penaeid shrimp in the target new penaeid shrimp farming water area, analyzing the water environment data of different sub-areas, finding out the specific factors causing the growth differences of the new penaeid shrimp, such as the water temperature being too high or the dissolved oxygen being insufficient in a certain area, and determining which environmental conditions are most suitable for the growth of the new penaeid shrimp through the decision tree algorithm, and determining the optimal farming parameter range for each environmental condition, taking the optimal farming parameter range as the benchmark parameter range for the new penaeid shrimp farming, judging whether the water area to be farmed is suitable for the new penaeid shrimp farming by comparing the deviation degree between the actual water environment data of the water area to be farmed and the benchmark parameter range. If not, carry out native organism restoration on the water area to be farmed. By introducing native organisms, promoting their proliferation in the water body and the restoration of ecological functions. For example, introducing specific algae can effectively reduce the ammonia nitrogen and nitrite concentrations in the water, improve the water transparency and redox potential. Introducing native organisms for water environment optimization can not only optimize the farming water environment, but also avoid introducing non-native organisms to cause negative impacts on the original ecosystem and maintain the stability and health of the ecological environment; the new penaeid shrimp belongs to the genus Penaeus, including Metapenaeus joyneri, Metapenaeus monoceros, Metapenaeus intermedius, Metapenaeus ensis, Metapenaeus vannamei.

[0082] According to an embodiment of the present invention, obtain the water environment data and the growth data of the new penaeid shrimp in each sub-area of the target new penaeid shrimp farming water area, and perform a difference analysis on the water environment data and the growth data of the new penaeid shrimp in the sub-areas to obtain the new penaeid shrimp farming difference data of each sub-area, specifically:

[0083] Obtain the geographical environment data of the target new penaeid shrimp farming water area, construct a two-dimensional plane map of the target new penaeid shrimp farming water area according to the geographical environment data, and divide the target new penaeid shrimp farming water area into N sub-areas based on the two-dimensional plane map;

[0084] Obtain the water environment data and the growth data of the new penaeid shrimp in each sub-area. The water environment data includes water temperature, pH value, dissolved oxygen, pollutant concentration, and organic matter concentration. The growth data of the new penaeid shrimp includes body weight, body length, survival rate, disease condition, and activity;

[0085] Construct data tables for the water environment data and the growth data of the new penaeid shrimp in each sub-area to obtain the water environment data tables and the growth data tables of the new penaeid shrimp in each sub-area;

[0086] Calculate the Euclidean distance of corresponding data items between the water environment data tables of each sub-region and between the new shrimp growth situation data tables. Evaluate the water environment data differences and new shrimp growth situation differences between each sub-region according to the Euclidean distance of the data items, and obtain the new shrimp farming difference data of each sub-region.

[0087] It should be noted that by obtaining the water environment data and new shrimp growth situation data of each sub-region and performing a difference analysis, it can help the farm accurately understand the environmental conditions and shrimp growth effects in different regions; by constructing the water environment data table and the new shrimp growth situation data table, and calculating the Euclidean distance between data items, the differences between each sub-region can be objectively evaluated.

[0088] Figure 2 The flowchart of determining the influencing factors of the present invention is shown.

[0089] According to an embodiment of the present invention, the influencing factors that affect the growth of new shrimp in the target new shrimp farming water area are determined according to the new shrimp farming difference data, specifically:

[0090] S202, evaluate the new shrimp farming quality of each sub-region in the target new shrimp farming water area according to the new shrimp farming difference data, and obtain the farming quality evaluation result of the sub-region;

[0091] S204, divide the sub-regions into high-quality farming areas and non-high-quality farming areas according to the farming quality evaluation result;

[0092] S206, obtain the first aquaculture water environment difference data between the high-quality farming area and the non-high-quality farming area, the second aquaculture water environment difference data between the high-quality farming areas, and the third aquaculture water environment difference data between the non-high-quality farming areas according to the new shrimp farming difference data;

[0093] S208, perform a correlation analysis on the first aquaculture water environment difference data, the second aquaculture water environment difference data, and the third aquaculture water environment difference data and the new shrimp growth situation data of the corresponding aquaculture areas based on the grey relational analysis method, identify the water environment factors that affect the new shrimp in the target new shrimp farming water area, and obtain the influencing factors.

[0094] It should be noted that by dividing each sub-region of the target new shrimp aquaculture water area into high-quality aquaculture areas and non-high-quality aquaculture areas, and determining the first aquaculture water environment difference data, the second aquaculture water environment difference data, and the third aquaculture water environment difference data between each area, these water environment difference data well reflect the data differences between high-quality aquaculture areas and non-high-quality aquaculture areas, as well as between high-quality aquaculture areas and between non-high-quality aquaculture areas. Then, analysis is carried out through the grey relational analysis method. Grey relational analysis is a method that can handle the influence of multiple factors. When analyzing aquaculture water environment data, multiple factors such as water temperature, pH value, dissolved oxygen, pollutant concentration, etc. are considered. These factors have important impacts on the growth, survival, and health status of new shrimp. Different from traditional correlation analysis, grey relational analysis can handle non-linear relationships. Because in actual farms, the relationship between water environment factors and the growth of shrimp is often complex and non-linear. Grey relational analysis reduces the non-linear influence between data by transforming the data into grey sequences, and more accurately reflects the correlation degree between factors, and finally accurately identifies the water environment factors that will affect new shrimp aquaculture.

[0095] According to an embodiment of the present invention, the impact factors are analyzed based on the decision tree algorithm to determine the optimal aquaculture parameter range of the impact factors, and the optimal aquaculture parameter range is used as the benchmark parameter range for new shrimp aquaculture, specifically:

[0096] Extract the parameter data of the impact factors in each sub-region, and divide the new shrimp growth indicators into three grades: excellent, medium, and poor according to the aquaculture quality evaluation results of the sub-region, so as to obtain the new shrimp aquaculture index grade data of each sub-region;

[0097] Based on the decision tree algorithm, a decision tree model is constructed. The impact factors are used as the features of the decision tree model, the parameter data is used as the input variable of the feature, and the new shrimp aquaculture index grade data is used as the target variable of the decision tree model;

[0098] Use information gain as the splitting criterion of the decision tree model, calculate the information gain of each feature in the decision tree model, take the feature with the largest information gain as the splitting feature of the current node, split the corresponding parameter data into multiple subsets according to the selected splitting feature, and create a new node for each subset. Iteratively calculate the information gain and splitting operation for the new node until the decision tree reaches the preset depth, and obtain the relationship decision tree between the parameter data of the impact factors and the new shrimp growth indicators;

[0099] Conduct path analysis on the relationship decision tree, mark the decision path with excellent new shrimp growth indicators, extract the parameter range of the impact factors of the decision path, and obtain the optimal aquaculture parameter range of each impact factor for new shrimp aquaculture;

[0100] Take the optimal aquaculture parameter range as the benchmark parameter range for the new shrimp aquaculture.

[0101] It should be noted that by using the decision tree algorithm to construct a decision tree model, the influencing factors are used as the features (input variables) of the decision tree model, the corresponding parameter data are used as the values of these features (input data), and the new shrimp aquaculture index levels (excellent, medium, poor) are used as the target variables. The best splitting feature is selected according to the information gain of each feature. Information gain measures the degree of reduction in classification uncertainty brought by a certain feature after splitting the node. The feature with the largest information gain is selected as the splitting feature of the current node. According to the selected splitting feature, the corresponding parameter data are split into multiple subsets, and a new node is created for each subset. These nodes represent different ranges of influencing factor parameters; analyze the paths of the decision tree, especially those paths that lead to excellent growth indicators of the new shrimp. Each path corresponds to a specific range of influencing factor parameter values; the path from the root node to each leaf node represents the aquaculture results under different combinations of conditions. Find the path corresponding to the best aquaculture results (such as the highest growth rate or survival rate), and determine the water quality parameter range on this path. For example, assume that a certain best path shows that the temperature is between 24°C and 28°C, the pH value is between 7.5 and 8.0, and the dissolved oxygen is above 5 mg / L, and the growth rate of the new shrimp is the best. Then these parameter ranges are the optimal aquaculture parameter ranges of the influencing factors; by analyzing the decision tree paths, the optimal range of each influencing factor on the shrimp growth can be accurately determined.

[0102] Figure 3 The flowchart of calculating the deviation data according to the present invention is shown.

[0103] According to an embodiment of the present invention, the actual water environment data of the water area to be cultured are obtained, and the actual water environment data are compared with the benchmark parameter range, and the deviation data of the actual water environment data from the benchmark parameter range are calculated. Specifically:

[0104] S302, divide the water area to be cultured with new shrimps into water area partitions, and obtain the actual water environment data of each partitioned water area;

[0105] S304, compare the actual water environment data of each partitioned water area with the benchmark parameter range, and calculate the deviation degree of the actual water environment data of each partitioned water area from the benchmark parameter range based on the percentage deviation to obtain the deviation data.

[0106] According to an embodiment of the present invention, the suitability of the new shrimp aquaculture in the water area to be cultured is judged according to the deviation data. If the aquaculture suitability is less than a preset value, the water environment of the water area to be cultured is optimized by the native organisms in the water area to be cultured to obtain an aquaculture optimization plan. Specifically:

[0107] Determine the influence weight of each influencing factor on the quality of new shrimp farming based on the information entropy weight method to obtain influence weight information;

[0108] Evaluate the suitability of new shrimp farming in each divided water area in the water area to be farmed based on the deviation data and influence weight information;

[0109] Construct a protist database for the water area to be farmed, and obtain protist species information in the water area to be farmed. The protist species information includes the species information of protozoa, protophyta, and protomicroorganisms in the water area to be farmed;

[0110] Obtain the biological purification function data of each of the above-mentioned protist species from the Internet according to the protist species information, and import the protist species information and the biological purification function data into the protist database for storage;

[0111] Mark the divided water areas with a new shrimp farming suitability less than the preset value according to the new shrimp farming suitability of each divided water area to obtain the water areas to be optimized;

[0112] Determine the influencing factors and deviation severity corresponding to the deviation data items of the water areas to be optimized according to the deviation data;

[0113] Match the data according to the influencing factors corresponding to the deviation data items in the protist database, and identify the protist with the ability to repair the influencing factors corresponding to the deviation data items and the strongest repair performance to obtain the organisms to be released;

[0114] Determine the release quantity of the organisms to be released in each water area to be optimized according to the repair performance data of the organisms to be released and the deviation degree;

[0115] Optimize the water environment of the water area to be farmed according to the organisms to be released and the release quantity to obtain a farming optimization plan.

[0116] It should be noted that constructing a protist database and utilizing the bioremediation function of protists can effectively enhance the ecological system stability and biodiversity of the water area to be cultured. Releasing suitable protists helps restore the ecological balance in the water area, reduce the risk of alien invasion, and protect the local ecological environment. Combining the deviation data of influencing factors and the remediation ability of protists can accurately determine the bioremediation strategies and release amounts required for each divided water area, minimizing resource waste to the greatest extent and ensuring the effectiveness and efficiency of the released organisms. Optimizing the aquaculture water area using the biological resources in the natural ecological system can reduce economic costs and, at the same time, reduce the environmental risks that may be brought about by the use of chemical substances. Optimizing the water area to be cultured according to protists can not only improve the aquaculture environment for new shrimp but also support the sustainable development of the aquaculture industry and environmental protection, providing dual benefits in science and economy for aquaculturists.

[0117] According to an embodiment of the present invention, it further includes:

[0118] Real-time obtain the real-time water environment change data of the water area to be cultured according to the aquaculture optimization plan during a preset time period;

[0119] Convert the real-time water environment change data into time series data, construct a water environment prediction model based on the ARIMA algorithm, import the time series data into the water environment prediction model, and judge the stationarity of the time series data through moving average and variance;

[0120] When the stationarity is lower than the preset value, perform a first-order difference operation on the time series data to obtain stationary time series data;

[0121] Import the stationary time series data into the water environment prediction model for learning and training, import the water environment change data of the current time period into the water environment prediction model, and predict the water environment change of the water area to be cultured in a future preset time period to obtain a water environment change prediction result;

[0122] Evaluate according to the water environment change prediction result, judge the suitability of the water environment for new shrimp culture at each time point in the water environment change prediction result, and determine the time nodes with a culture suitability greater than the preset value;

[0123] Carry out new shrimp culture in the water area to be cultured according to the time nodes.

[0124] It should be noted that since it takes a certain amount of time to optimize the water environment through the aquaculture optimization plan, real-time water environment change data of the water area to be cultured in a preset time period is obtained, and a water environment prediction model is constructed based on the ARIMA time series prediction model to predict the water environment change of the water area to be cultured in the future preset time period. When the water environment changes to be suitable for the new shrimp culture, the time node is marked, and new shrimp culture is carried out in the water area to be cultured according to the time node. By predicting the time node suitable for culture, it is possible to reduce the manual detection of the water environment of the water area to be cultured, save human resources, and by predicting the time node suitable for culture, the culture time point of the new shrimp can be known in advance, enabling the culturists to prepare for the new shrimp culture in advance, providing sufficient time for preparation to make the new shrimp culture proceed in an orderly manner and improving the culture quality.

[0125] Figure 4 The block diagram of a new shrimp culture optimization system based on water quality characteristic analysis according to the present invention is shown.

[0126] In a second aspect of the present invention, a new shrimp culture optimization system 4 based on water quality characteristic analysis is further provided. The system includes: a memory 41 and a processor 42. The memory includes a program for the new shrimp culture optimization method based on water quality characteristic analysis. When the program for the new shrimp culture optimization method based on water quality characteristic analysis is executed by the processor, the following steps are implemented:

[0127] Obtain the water environment data and the new shrimp growth situation data of each sub-region in the target new shrimp culture water area, perform a difference analysis on the water environment data and the new shrimp growth situation data of the sub-regions, and obtain the new shrimp culture difference data of each sub-region;

[0128] Determine the influencing factors that affect the growth of new shrimp in the target new shrimp culture water area according to the new shrimp culture difference data;

[0129] Analyze the influencing factors based on the decision tree algorithm, determine the optimal culture parameter range of the influencing factors, and use the optimal culture parameter range as the benchmark parameter range for new shrimp culture;

[0130] Obtain the actual water environment data of the water area to be cultured, compare the actual water environment data with the benchmark parameter range, and calculate the deviation degree data of the actual water environment data from the benchmark parameter range;

[0131] Judge the new shrimp culture suitability of the water area to be cultured according to the deviation degree data. If the culture suitability is less than the preset value, optimize the water environment of the water area to be cultured through the native organisms in the water area to be cultured to obtain a culture optimization plan.

[0132] According to an embodiment of the present invention, obtaining the water environment data and the new shrimp growth data of each sub-region in the target new shrimp aquaculture water area, and performing a difference analysis on the water environment data and the new shrimp growth data of the sub-regions to obtain the new shrimp aquaculture difference data of each sub-region, specifically:

[0133] Obtain the geographical environment data of the target new shrimp aquaculture water area, construct a two-dimensional plane map of the target new shrimp aquaculture water area according to the geographical environment data, and divide the target new shrimp aquaculture water area into N sub-regions based on the two-dimensional plane map;

[0134] Obtain the water environment data and the new shrimp growth data of each sub-region. The water environment data includes water temperature, pH value, dissolved oxygen, pollutant concentration, and organic matter concentration. The new shrimp growth data includes body weight, body length, survival rate, disease condition, and activity;

[0135] Construct data tables for the water environment data and the new shrimp growth data of each sub-region to obtain the water environment data tables and the new shrimp growth data tables of each sub-region;

[0136] Calculate the Euclidean distances of the corresponding data items between the water environment data tables and between the new shrimp growth data tables of each sub-region, and evaluate the water environment data differences and the new shrimp growth situation differences between each sub-region according to the Euclidean distances of the data items to obtain the new shrimp aquaculture difference data of each sub-region.

[0137] According to an embodiment of the present invention, determining the influencing factors that affect the growth of new shrimp in the target new shrimp aquaculture water area according to the new shrimp aquaculture difference data, specifically:

[0138] Evaluate the new shrimp aquaculture quality of each sub-region in the target new shrimp aquaculture water area according to the new shrimp aquaculture difference data to obtain the aquaculture quality evaluation results of the sub-regions;

[0139] Divide the sub-regions into high-quality aquaculture regions and non-high-quality aquaculture regions according to the aquaculture quality evaluation results;

[0140] Obtain the first aquaculture water environment difference data between the high-quality aquaculture region and the non-high-quality aquaculture region, the second aquaculture water environment difference data between the high-quality aquaculture regions, and the third aquaculture water environment difference data between the non-high-quality aquaculture regions according to the new shrimp aquaculture difference data;

[0141] Perform a correlation analysis on the first aquaculture water environment difference data, the second aquaculture water environment difference data, the third aquaculture water environment difference data and the corresponding new shrimp growth data in the aquaculture area based on the grey relational analysis method, identify the water environment factors that affect the new shrimp in the target new shrimp aquaculture water area, and obtain the influencing factors.

[0142] According to the embodiment of the present invention, analyze the influencing factors based on the decision tree algorithm, determine the optimal aquaculture parameter range of the influencing factors, and use the optimal aquaculture parameter range as the benchmark parameter range for new shrimp aquaculture, specifically:

[0143] Extract the parameter data of the influencing factors in each sub-region, divide the new shrimp growth indicators into three grades: excellent, medium and poor according to the aquaculture quality evaluation results of the sub-region, and obtain the new shrimp aquaculture indicator grade data of each sub-region;

[0144] Construct a decision tree model based on the decision tree algorithm, use the influencing factors as the features of the decision tree model, use the parameter data as the input variables of the features, and use the new shrimp aquaculture indicator grade data as the target variables of the decision tree model;

[0145] Use information gain as the splitting criterion of the decision tree model, calculate the information gain of each feature in the decision tree model, use the feature with the largest information gain as the splitting feature of the current node, split the corresponding parameter data into multiple subsets according to the selected splitting feature, and create a new node for each subset, and iteratively calculate the information gain and splitting operation for the new node until the decision tree reaches the preset depth, and obtain the relationship decision tree between the parameter data of the influencing factors and the new shrimp growth indicators;

[0146] Perform path analysis on the relationship decision tree, mark the decision path with excellent new shrimp growth indicators, extract the parameter range of the influencing factors of the decision path, and obtain the optimal aquaculture parameter range of each influencing factor for new shrimp aquaculture;

[0147] Use the optimal aquaculture parameter range as the benchmark parameter range for new shrimp aquaculture.

[0148] According to the embodiment of the present invention, obtain the actual water environment data of the water area to be cultured, compare the actual water environment data with the benchmark parameter range, and calculate the deviation degree data between the actual water environment data and the benchmark parameter range, specifically:

[0149] Divide the water area to be cultured with new shrimp, and obtain the actual water environment data of each divided water area;

[0150] Compare the actual water environment data of each divided water area with the reference parameter range, calculate the degree of deviation between the actual water environment data of each divided water area and the reference parameter range based on the percentage deviation, and obtain the deviation degree data.

[0151] According to an embodiment of the present invention, the new shrimp farming suitability of the water area to be cultured is judged according to the deviation degree data. If the farming suitability is less than a preset value, the water environment of the water area to be cultured is optimized by the native organisms in the water area to be cultured to obtain a farming optimization plan. Specifically:

[0152] Determine the influence weight of each influencing factor on the new shrimp farming quality based on the information entropy weight method to obtain the influence weight information;

[0153] Evaluate the new shrimp farming suitability of each divided water area in the water area to be cultured based on the deviation degree data and the influence weight information;

[0154] Construct a native organism database for the water area to be cultured, and obtain the native organism species information in the water area to be cultured. The native organism species information includes the species information of protozoa, protophyta, and native microorganisms in the water area to be cultured;

[0155] Obtain the biological purification function data of each of the above-mentioned native species from the Internet according to the native organism species information, and import the native organism species information and the biological purification function data into the native organism database for storage;

[0156] Mark the divided water areas with a farming suitability less than the preset value according to the new shrimp farming suitability of each divided water area to obtain the water areas to be optimized;

[0157] Determine the influencing factors and the degree of deviation severity corresponding to the deviation data items of the water areas to be optimized according to the deviation degree data;

[0158] Match the data of the native organism database with the influencing factors corresponding to the deviation data items, and identify the native organisms with the ability to repair the influencing factors corresponding to the deviation data items and the strongest repair performance to obtain the organisms to be put in;

[0159] Determine the release quantity of the organisms to be released in each water area to be optimized according to the repair performance data of the organisms to be released and the degree of deviation;

[0160] Optimize the water environment of the water area to be cultured according to the organisms to be released and the release quantity to obtain a farming optimization plan.

[0161] The present invention discloses a new penaeid shrimp farming optimization method and system based on water quality characteristic analysis. First, obtain the water environment data and penaeid shrimp growth data of each sub-region in the target penaeid shrimp farming water area, and conduct a difference analysis to obtain the penaeid shrimp farming difference data of each sub-region. Subsequently, determine the key factors affecting the growth of penaeid shrimp, and analyze the optimal farming parameter ranges of these factors as the farming benchmark parameters. Then, obtain the actual water environment data of the water area to be farmed, compare it with the benchmark parameters, and calculate the deviation degree data. Evaluate the farming suitability according to the deviation degree data. If the suitability is lower than the preset value, regulate the water environment of the water area to be farmed by optimizing the protist ecological conditions, and formulate a farming optimization plan. This method optimizes the penaeid shrimp farming environment by accurately analyzing and adjusting the water quality and growth conditions, improving the farming efficiency and the growth quality of penaeid shrimp.

[0162] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 various components shown or discussed can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0163] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] In addition, in each embodiment of the present invention, the various functional units can all be integrated in one processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit; the above integrated units can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0165] Those of ordinary skill in the art will understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including those of the above method embodiments. The aforementioned storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0166] Alternatively, if the above-integrated unit is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0167] The above are only specific embodiments 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 all be covered by 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.

Claims

1. A new shrimp farming optimization method based on water quality characteristics analysis, characterized in that: The following steps are involved: Obtain water environment data and new shrimp growth data of each sub-area in the target new shrimp breeding waters, perform difference analysis on the water environment data and new shrimp growth data of the sub-areas, and obtain new shrimp breeding difference data of each sub-area; Determine the influencing factors affecting the growth of new shrimp in the target new shrimp farming waters according to the new shrimp farming difference data; Analyze the influencing factors based on a decision tree algorithm to determine the optimal breeding parameter range of the influencing factors, and use the optimal breeding parameter range as the benchmark parameter range for new shrimp breeding; Acquire actual water environment data of the aquaculture water area, compare the actual water environment data with the reference parameter range, and calculate the deviation data between the actual water environment data and the reference parameter range; The suitability of the new shrimps for breeding in the breeding waters is determined according to the deviation data. If the breeding suitability is less than a preset value, the water environment of the breeding waters is optimized by the protozoa in the breeding waters to obtain a breeding optimization plan.

2. A new shrimp farming optimization method based on water quality characteristic analysis according to claim 1, characterized in that: The water environment data and new shrimp growth data of each sub-area in the target new shrimp breeding waters are obtained, and the water environment data and new shrimp growth data of each sub-area are analyzed for differences to obtain the new shrimp breeding difference data of each sub-area, specifically: Acquire geographical environment data of the target new shrimp farming waters, construct a two-dimensional plane map of the target new shrimp farming waters according to the geographical environment data, and divide the target new shrimp farming waters into N sub-areas based on the two-dimensional plane map; Obtain water environment data and new shrimp growth data of each sub-area, wherein the water environment data includes water temperature, pH value, dissolved oxygen, pollutant concentration, and organic matter concentration, and the new shrimp growth data includes weight, body length, survival rate, disease status, and activity; The water environment data and the new shrimp growth data of each sub-region are used to construct a data table to obtain a water environment data table and a new shrimp growth data table of each sub-region; The Euclidean distances of the corresponding data items between the water environment data tables and the new shrimp growth data tables of each sub-region are calculated, and the differences in water environment data and new shrimp growth conditions between each sub-region are evaluated according to the Euclidean distances of the data items to obtain the new shrimp farming difference data of each sub-region.

3. A new shrimp farming optimization method based on water quality characteristic analysis according to claim 1, characterized in that: The influencing factors affecting the growth of new shrimp in the target new shrimp farming waters are determined according to the new shrimp farming difference data, specifically: According to the new shrimp farming difference data, the new shrimp farming quality of each sub-area in the target new shrimp farming waters is evaluated to obtain a farming quality evaluation result of the sub-area; Dividing the sub-areas into high-quality breeding areas and non-high-quality breeding areas according to the breeding quality assessment results; According to the new shrimp farming difference data, first farming water environment difference data between high-quality farming areas and non-high-quality farming areas, second farming water environment difference data between high-quality farming areas and high-quality farming areas, and third farming water environment difference data between non-high-quality farming areas and non-high-quality farming areas are obtained; Based on the grey correlation analysis method, a correlation analysis is performed on the first aquaculture water environment difference data, the second aquaculture water environment difference data, the third aquaculture water environment difference data and the new shrimp growth data in the corresponding aquaculture areas to identify the water environment factors that affect the new shrimp in the target new shrimp aquaculture waters and obtain the influencing factors.

4. A new shrimp farming optimization method based on water quality characteristic analysis according to claim 3, characterized in that: The decision tree algorithm is used to analyze the influencing factors, determine the optimal breeding parameter range of the influencing factors, and use the optimal breeding parameter range as the benchmark parameter range for new shrimp breeding, specifically: Extracting parameter data of the influencing factors in each sub-region, dividing the growth index of the new shrimp into three levels: excellent, medium and poor according to the aquaculture quality assessment results of the sub-region, and obtaining the new shrimp aquaculture index level data of each sub-region; A decision tree model is constructed based on a decision tree algorithm, the influencing factors are used as features of the decision tree model, the parameter data are used as input variables of the features, and the new shrimp farming indicator level data are used as target variables of the decision tree model; Using information gain as the splitting criterion of the decision tree model, calculating the information gain of each feature in the decision tree model, using the feature with the largest information gain as the splitting feature of the current node, splitting the corresponding parameter data into multiple subsets according to the selected splitting feature, and creating a new node for each subset, iteratively calculating the information gain and splitting operation on the new node until the decision tree reaches a preset depth, and obtaining a decision tree of the relationship between the parameter data of the influencing factor and the new shrimp growth index; Performing path analysis on the relationship decision tree, marking the decision path with the best growth index of the new shrimp, extracting the parameter range of the influencing factors of the decision path, and obtaining the optimal breeding parameter range of each influencing factor for the breeding of the new shrimp; The optimal breeding parameter range is used as the benchmark parameter range for new shrimp breeding.

5. A new shrimp farming optimization method based on water quality characteristic analysis according to claim 1, characterized in that: The actual water environment data of the aquaculture water area is obtained, the actual water environment data is compared with the reference parameter range, and the deviation data between the actual water environment data and the reference parameter range is calculated, specifically: Divide the water area where new shrimps are to be cultured into different areas and obtain the actual water environment data of each divided area; The actual water environment data of each divided water area is compared with the reference parameter range, and the degree of deviation of the actual water environment data of each divided water area from the reference parameter range is calculated based on the percentage deviation to obtain the deviation data.

6. A new shrimp farming optimization method based on water quality characteristic analysis according to claim 1, characterized in that: The breeding suitability of the new shrimp in the breeding waters is determined according to the deviation data. If the breeding suitability is less than a preset value, the water environment of the breeding waters is optimized by the protozoa in the breeding waters to obtain a breeding optimization plan, which is specifically: Based on the information entropy weight method, the influence weight of each influencing factor on the quality of new shrimp farming is determined to obtain the influence weight information; Evaluate the suitability of new shrimp farming in each divided water area in the water area to be farmed based on the deviation data and the impact weight information; Constructing a protist database of the waters to be cultured, and obtaining species information of the protists in the waters to be cultured, wherein the protists species information includes species information of protozoa, protophytes and protomicroorganisms in the waters to be cultured; Acquire biological purification function data of each protist species from the Internet according to the protist species information, and import the protist species information and the biological purification function data into the protist database for storage; According to the new shrimp farming suitability of each divided water area, the divided water areas with farming suitability less than a preset value are marked to obtain the water areas to be optimized; Determine the impact factor and the deviation severity corresponding to the deviation data item of the water area to be optimized according to the deviation data; Performing data matching according to the protist database and the impact factors corresponding to the deviated data items, identifying the protist that has the ability to repair the impact factors corresponding to the deviated data items and has the strongest repair performance, and obtaining the organism to be released; Determining the quantity of the organisms to be released in each water area to be optimized according to the restoration performance data of the organisms to be released and the degree of deviation; The water environment of the aquaculture waters is optimized according to the organisms to be released and the release quantity, so as to obtain an aquaculture optimization plan.

7. A new shrimp farming optimization system based on water quality characteristics analysis, characterized in that: The new shrimp farming optimization system based on water quality characteristic analysis includes a storage device and a processor. The storage device includes a new shrimp farming optimization method program based on water quality characteristic analysis. When the new shrimp farming optimization method program based on water quality characteristic analysis is executed by the processor, the following steps are implemented: Obtain water environment data and new shrimp growth data of each sub-area in the target new shrimp breeding waters, perform difference analysis on the water environment data and new shrimp growth data of the sub-areas, and obtain new shrimp breeding difference data of each sub-area; Determine the influencing factors affecting the growth of new shrimp in the target new shrimp farming waters according to the new shrimp farming difference data; Analyze the influencing factors based on a decision tree algorithm to determine the optimal breeding parameter range of the influencing factors, and use the optimal breeding parameter range as the benchmark parameter range for new shrimp breeding; Acquire actual water environment data of the aquaculture water area, compare the actual water environment data with the reference parameter range, and calculate the deviation data between the actual water environment data and the reference parameter range; The suitability of the new shrimps for breeding in the breeding waters is determined according to the deviation data. If the breeding suitability is less than a preset value, the water environment of the breeding waters is optimized by the protozoa in the breeding waters to obtain a breeding optimization plan.

8. A new shrimp farming optimization system based on water quality characteristic analysis according to claim 7, characterized in that: The decision tree algorithm is used to analyze the influencing factors, determine the optimal breeding parameter range of the influencing factors, and use the optimal breeding parameter range as the benchmark parameter range for new shrimp breeding, specifically: Extracting parameter data of the influencing factors in each sub-region, dividing the growth index of the new shrimp into three levels: excellent, medium and poor according to the aquaculture quality assessment results of the sub-region, and obtaining the new shrimp aquaculture index level data of each sub-region; A decision tree model is constructed based on a decision tree algorithm, the influencing factors are used as features of the decision tree model, the parameter data are used as input variables of the features, and the new shrimp farming indicator level data are used as target variables of the decision tree model; Using information gain as the splitting criterion of the decision tree model, calculating the information gain of each feature in the decision tree model, using the feature with the largest information gain as the splitting feature of the current node, splitting the corresponding parameter data into multiple subsets according to the selected splitting feature, and creating a new node for each subset, iteratively calculating the information gain and splitting operation on the new node until the decision tree reaches a preset depth, and obtaining a decision tree of the relationship between the parameter data of the influencing factor and the new shrimp growth index; Performing path analysis on the relationship decision tree, marking the decision path with the best growth index of the new shrimp, extracting the parameter range of the influencing factors of the decision path, and obtaining the optimal breeding parameter range of each influencing factor for the breeding of the new shrimp; The optimal breeding parameter range is used as the benchmark parameter range for new shrimp breeding.

9. A new shrimp farming optimization system based on water quality characteristic analysis according to claim 7, characterized in that: The actual water environment data of the aquaculture water area is obtained, the actual water environment data is compared with the reference parameter range, and the deviation data between the actual water environment data and the reference parameter range is calculated, specifically: Divide the water area where new shrimps are to be cultured into different areas and obtain the actual water environment data of each divided area; The actual water environment data of each divided water area is compared with the reference parameter range, and the degree of deviation of the actual water environment data of each divided water area from the reference parameter range is calculated based on the percentage deviation to obtain the deviation data.

10. A new shrimp farming optimization system based on water quality characteristic analysis according to claim 7, characterized in that: The breeding suitability of the new shrimp in the breeding waters is determined according to the deviation data. If the breeding suitability is less than a preset value, the water environment of the breeding waters is optimized by the protozoa in the breeding waters to obtain a breeding optimization plan, which is specifically: Based on the information entropy weight method, the influence weight of each influencing factor on the quality of new shrimp farming is determined to obtain the influence weight information; Evaluate the suitability of new shrimp farming in each divided water area in the water area to be farmed based on the deviation data and the impact weight information; Constructing a protist database of the waters to be cultured, and obtaining species information of the protists in the waters to be cultured, wherein the protists species information includes species information of protozoa, protophytes and protomicroorganisms in the waters to be cultured; Acquire biological purification function data of each protist species from the Internet according to the protist species information, and import the protist species information and the biological purification function data into the protist database for storage; According to the new shrimp farming suitability of each divided water area, the divided water areas with farming suitability less than a preset value are marked to obtain the water areas to be optimized; Determine the impact factor and the deviation severity corresponding to the deviation data item of the water area to be optimized according to the deviation data; Performing data matching according to the protist database and the impact factors corresponding to the deviated data items, identifying the protist that has the ability to repair the impact factors corresponding to the deviated data items and has the strongest repair performance, and obtaining the organism to be released; Determining the quantity of the organisms to be released in each water area to be optimized according to the restoration performance data of the organisms to be released and the degree of deviation; The water environment of the aquaculture waters is optimized according to the organisms to be released and the release quantity, so as to obtain an aquaculture optimization plan.

Images