Ecological aquaculture optimization method and system based on bacterial and algal communities in seawater ponds

By obtaining and analyzing aquaculture information and seawater pond monitoring information, a knowledge map of bacterial and algae ecological functions was constructed and the structure of bacterial and algae community was optimized using the SAPSO algorithm, which solved the problem of traditional aquaculture methods neglecting bacterial and algae communities, and achieved ecological optimization of seawater pond aquaculture , improves production and quality, reduces costs and pollution.

CN118428566BActive Publication Date: 2024-11-05SOUTH CHINA SEA FISHERIES RES INST CHINESE ACAD OF FISHERY SCI +1
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202410897175.0
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-05
Publication Date
2024-11-05
Estimated Expiration
2044-07-05

AI Technical Summary

Technical Problem

Traditional seawater pond aquaculture methods ignore the role of bacterial and algae communities, leading to deterioration of the ecological environment. How to scientifically utilize and manage bacterial and algae communities to improve farming output and product quality, reduce costs and environmental pollution is an urgent problem.

Method used

By obtaining aquaculture information and seawater pond monitoring information, performing adaptive environment analysis and water quality abnormality detection, constructing a knowledge map of bacteria and algae ecological functions, combining SAPSO algorithm to build a breeding optimization model, optimizing bacteria and algae community structure, and analyzing the optimization cost of candidate solutions and cycle, select the final plan.

Benefits of technology

It effectively improves the breeding output and product quality, reduces the breeding costs and environmental pollution, and achieves the goal of ecological breeding.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118428566B_ABST
    Figure CN118428566B_ABST
Patent Text Reader

Abstract

The present invention discloses an ecological aquaculture optimization method and system based on bacteria and algae communities in seawater ponds, including: obtaining information on cultivated objects, analyzing the suitable living environment of cultivated objects according to the cultivated object information, and obtaining suitable living environment analysis information; performing water quality anomaly detection according to the monitoring information of seawater ponds, evaluating the water quality status according to the abnormal detection results, and obtaining water quality status evaluation information; constructing a knowledge map of bacteria and algae ecological functions, analyzing the bacteria and algae ecological structure in the target seawater pond, and analyzing the causes of abnormal water quality according to the analysis results; constructing an aquaculture optimization model based on the SAPSO algorithm, optimizing the bacteria and algae communities of the target seawater pond, and obtaining candidate aquaculture optimization schemes; analyzing the optimization cost and optimization cycle of each candidate aquaculture optimization scheme, sorting and selecting the final aquaculture optimization scheme. By optimizing the bacteria and algae communities, the aquaculture output and product quality can be improved, and the aquaculture cost and environmental pollution can be effectively reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of ecological aquaculture, and in particular to an ecological aquaculture optimization method and system based on bacteria and algae communities in seawater ponds. Background Art

[0002] Bacteria and algae communities are an important part of the aquatic ecosystem, and they play an irreplaceable role in water purification, ecological balance regulation and nutrient cycling. Bacteria and algae can convert organic matter in water into inorganic matter through processes such as photosynthesis and biodegradation, thereby purifying water quality; at the same time, they provide oxygen and necessary nutrients for other organisms in the water to maintain the stability of the ecosystem. However, traditional aquaculture methods often ignore the role of bacteria and algae communities, and even destroy the balance of bacteria and algae communities due to excessive feeding and the use of chemical drugs, further exacerbating the deterioration of the ecological environment.

[0003] In recent years, with the introduction of ecological aquaculture concepts and the enhancement of environmental awareness, how to scientifically utilize and manage bacterial and algal communities in seawater ponds has become a hot topic in the industry. Therefore, how to optimize bacterial and algal communities, improve aquaculture output and product quality, effectively reduce aquaculture costs and environmental pollution, and achieve the purpose of ecological aquaculture is an issue that needs to be solved urgently. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and provides an ecological aquaculture optimization method and system based on bacteria and algae communities in seawater ponds, the important purpose of which is to increase aquaculture output and product quality and reduce aquaculture costs and environmental pollution.

[0005] To achieve the above-mentioned purpose, the present invention provides a first aspect of an ecological aquaculture optimization method based on bacterial and algal communities in seawater ponds, comprising:

[0006] Acquire information about cultivated plants, and perform suitable environment analysis on the cultivated plants according to the information about the cultivated plants to obtain suitable environment analysis information;

[0007] Perform water quality anomaly detection based on seawater pond monitoring information, and evaluate water quality status based on the anomaly detection results to obtain water quality status evaluation information;

[0008] Construct a knowledge map of bacterial and algal ecological functions, analyze the bacterial and algal ecological structure in the target seawater pond, and analyze the causes of abnormal water quality based on the analysis results;

[0009] Based on the SAPSO algorithm, an aquaculture optimization model was constructed to optimize the bacterial and algal communities in the target seawater ponds and obtain candidate aquaculture optimization plans.

[0010] Analyze the optimization cost and optimization cycle of each candidate breeding optimization plan, sort them and select the final breeding optimization plan.

[0011] In this solution, the step of obtaining the information of the cultivated objects and analyzing the suitable living environment of the cultivated objects based on the information of the cultivated objects to obtain the suitable living environment analysis information specifically includes:

[0012] Acquire information about cultivated objects, obtain cultivation examples of target cultivated objects based on big data retrieval, form an example data set, extract the cultivation environment characteristics and bacterial and algal community characteristics of each cultivation example, and obtain characteristic information of the cultivation example;

[0013] Setting the breeding index category, calculating the Euclidean distance between the breeding instance feature information and each breeding index category, and classifying each breeding instance feature into the corresponding breeding index category by combining the clustering algorithm to obtain the category classification information;

[0014] Extract the breeding benefits of each breeding instance as the subsidiary attribute of each breeding instance feature, and rank the breeding instance features under each breeding indicator category;

[0015] According to the sorting results, the optimal breeding instance characteristics under each breeding indicator category are selected to obtain the suitable environment analysis information of the target breeding object.

[0016] In this scheme, the water quality anomaly detection is performed based on the seawater pond monitoring information, and the water quality status is evaluated based on the anomaly detection result to obtain the water quality status evaluation information, which specifically includes:

[0017] Monitoring the target seawater pond to obtain seawater pond monitoring information, wherein the seawater pond monitoring information includes water quality monitoring information and bacterial and algal community monitoring information;

[0018] Acquiring water quality monitoring information according to the seawater pond monitoring information, performing data preprocessing on the water quality monitoring information, and performing time series processing on the preprocessed data;

[0019] A water quality anomaly detection model is constructed based on a generative adversarial network, an instance data set is obtained, aquaculture water quality characteristics of each aquaculture instance are extracted according to the instance data set, and an aquaculture water quality change curve of each aquaculture instance is constructed according to the time attribute of each aquaculture water quality characteristic;

[0020] The normal fluctuation range of water quality indicators is set, random water quality indicator changes are added to the aquaculture water quality change curve of each aquaculture instance, sample enhancement is performed, and a training data set is formed to train the water quality anomaly detection model;

[0021] The water quality monitoring information is input into a water quality anomaly detection model to perform water quality anomaly detection, and anomaly detection is performed by calculating the reconstruction error between the generated sequence and the original sequence to obtain water quality anomaly detection information;

[0022] Abnormal water quality index data is extracted according to the abnormal water quality detection information, the deviation from the normal fluctuation range of the water quality index is calculated, and the water quality status is evaluated according to the calculated deviation to obtain water quality status evaluation information.

[0023] In this scheme, the construction of the knowledge map of bacterial and algal ecological functions and the analysis of the bacterial and algal ecological structure in the target seawater pond are carried out, and the cause of abnormal water quality is analyzed according to the analysis results, which specifically includes:

[0024] Based on big data retrieval, the ecological function characteristics and efficacy quantification characteristics of various bacteria and algae are obtained, the efficacy quantification standards are set, the efficacy standards of each ecological function are quantified, and the replacement relationship between the ecological function characteristics of different types of bacteria and algae is obtained to obtain ecological function analysis information;

[0025] Entity triples are constructed based on the species of bacteria and algae, the ecological function characteristics of bacteria and algae, and the ecological function analysis information; a knowledge graph of the ecological function of bacteria and algae is constructed based on the entity triples, and the functional replacement relationship between various types of bacteria and algae is used as an auxiliary feature;

[0026] Acquire seawater pond monitoring information, acquire bacterial and algal community monitoring information according to the seawater pond monitoring information, analyze the bacterial and algal ecological structure of the target seawater pond through the bacterial and algal community monitoring information, and obtain bacterial and algal ecological structure analysis information;

[0027] According to the bacterial-algae ecological structure analysis information and the bacterial-algae ecological function knowledge map, an ecological benefit evaluation is performed on the bacterial-algae community of the target seawater pond, and it is determined whether the bacterial-algae community of the target seawater pond is in a bacterial-algae balance, thereby obtaining ecological benefit evaluation information;

[0028] Acquire water quality status assessment information, calculate the Mahalanobis distance between the ecological benefit assessment information and the water quality status assessment information, analyze the correlation between abnormal water quality and various bacterial and algal communities, and obtain abnormal water quality cause analysis information.

[0029] In this scheme, the aquaculture optimization model is constructed based on the SAPSO algorithm, and the bacterial and algal communities of the target seawater pond are optimized to obtain candidate aquaculture optimization schemes, which specifically include:

[0030] Acquire abnormal water quality cause analysis information and suitable environment analysis information, analyze aquaculture optimization targets according to the abnormal water quality cause analysis information and suitable environment analysis information, and obtain aquaculture optimization target information;

[0031] Based on the SAPSO algorithm, an aquaculture optimization model is constructed, a knowledge map of bacterial and algal ecological functions is obtained, and a training data set is constructed to train the aquaculture optimization model to obtain an aquaculture optimization model that meets expectations;

[0032] Acquire the bacterial and algae ecological structure analysis information, set the objective function and constraint conditions according to the aquaculture optimization target information, set the penalty conditions according to the bacterial and algae balance, and input the bacterial and algae ecological structure analysis information into the aquaculture optimization model for analysis;

[0033] Based on the bacterial and algae ecological structure analysis information, the bacterial and algae ecological function knowledge map is searched to obtain the replaceable bacterial and algae species and replacement relationships of the ecological functions corresponding to the bacterial and algae structure in the current seawater pond, and the replacement bacterial and algae analysis information is obtained;

[0034] Initializing the population according to the bacterial and algae ecological structure analysis information to generate an initial particle group, generating an optimized particle group according to the replacement bacterial and algae analysis information, replacing, adding and deleting the initial particle group through the optimized particle group, calculating the fitness of each particle in the initial particle group, and judging it with a preset threshold to obtain the current optimal solution;

[0035] Preset the initial receiving probability and the drop rate, use the current optimal solution as the initial solution of the SA algorithm, determine whether to accept it according to the initial receiving probability, and make a penalty determination according to the set penalty condition;

[0036] The acceptance probability is adjusted based on the decline rate and penalty judgment results, and iterative optimization is performed until the model converges to obtain the final solution, and the candidate breeding optimization plan is generated through the final solution.

[0037] In this scheme, the optimization cost and optimization cycle of each candidate breeding optimization scheme are analyzed, sorted and the final breeding optimization scheme is selected, which specifically includes:

[0038] Obtain candidate aquaculture optimization plans, perform feature extraction on each candidate aquaculture optimization plan, extract the optimized bacterial and algal community structure characteristics and the corresponding bacterial and algal community change characteristics, and obtain the characteristic information of the candidate aquaculture optimization plan;

[0039] Calculating the optimization cost and optimization period of each candidate breeding optimization scheme according to the characteristic information of the candidate breeding optimization scheme, taking the optimization cost and optimization period as weights, and performing weighted calculation on each candidate breeding optimization scheme;

[0040] The candidate breeding optimization schemes are ranked according to the weighted calculation results, and the optimization cost ranking and optimization cycle ranking of each candidate breeding optimization scheme are extracted to obtain the average ranking of each candidate breeding optimization scheme;

[0041] The final breeding optimization plan is selected and recommended based on the average ranking of each candidate breeding optimization plan.

[0042] The second aspect of the present invention provides an ecological aquaculture optimization system based on bacteria and algae communities in seawater ponds, the system comprising: a memory, a processor, the memory containing an ecological aquaculture optimization method program based on bacteria and algae communities in seawater ponds, the ecological aquaculture optimization method program based on bacteria and algae communities in seawater ponds when executed by the processor implements the following steps:

[0043] Acquire information about cultivated plants, and perform suitable environment analysis on the cultivated plants according to the information about the cultivated plants to obtain suitable environment analysis information;

[0044] Perform water quality anomaly detection based on seawater pond monitoring information, and evaluate water quality status based on the anomaly detection results to obtain water quality status evaluation information;

[0045] Construct a knowledge map of bacterial and algal ecological functions, analyze the bacterial and algal ecological structure in the target seawater pond, and analyze the causes of abnormal water quality based on the analysis results;

[0046] Based on the SAPSO algorithm, an aquaculture optimization model was constructed to optimize the bacterial and algal communities in the target seawater ponds and obtain candidate aquaculture optimization plans.

[0047] Analyze the optimization cost and optimization cycle of each candidate breeding optimization plan, sort them and select the final breeding optimization plan.

[0048] The present invention discloses an ecological aquaculture optimization method and system based on bacteria and algae communities in seawater ponds, including: obtaining information on cultivated objects, analyzing the suitable living environment of cultivated objects according to the information on cultivated objects, and obtaining suitable living environment analysis information; performing water quality anomaly detection according to the monitoring information of seawater ponds, evaluating the water quality status according to the abnormal detection results, and obtaining water quality status evaluation information; constructing a knowledge map of bacteria and algae ecological functions, analyzing the bacteria and algae ecological structure in the target seawater pond, and analyzing the causes of abnormal water quality according to the analysis results; constructing an aquaculture optimization model based on the SAPSO algorithm, optimizing the bacteria and algae communities in the target seawater pond, and obtaining candidate aquaculture optimization schemes; analyzing the optimization cost and optimization cycle of each candidate aquaculture optimization scheme, sorting and selecting the final aquaculture optimization scheme. By optimizing the bacteria and algae communities, the aquaculture output and product quality can be improved, and the aquaculture cost and environmental pollution can be effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. 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 the drawings without paying creative work.

[0050] Figure 1A flow chart of an ecological aquaculture optimization method based on bacterial and algal communities in seawater ponds provided in one embodiment of the present invention;

[0051] Figure 2 A flow chart of abnormal water quality detection provided by an embodiment of the present invention;

[0052] Figure 3 A block diagram of an ecological aquaculture optimization system based on bacterial and algal communities in seawater ponds provided by one embodiment of the present invention;

[0053] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] In order to more clearly understand the above-mentioned purpose, 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 the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0055] 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 protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0056] Figure 1 A flow chart of an ecological aquaculture optimization method based on bacterial and algal communities in seawater ponds provided in one embodiment of the present invention;

[0057] like Figure 1 As shown, the present invention provides a flow chart of an ecological aquaculture optimization method based on bacterial and algal communities in seawater ponds, comprising:

[0058] S102, acquiring information of cultivated plants, and performing suitable environment analysis on the cultivated plants according to the information of the cultivated plants to obtain suitable environment analysis information;

[0059] S104, performing water quality anomaly detection based on the seawater pond monitoring information, and evaluating the water quality status based on the anomaly detection result to obtain water quality status evaluation information;

[0060] S106, constructing a knowledge map of bacterial and algal ecological functions, analyzing the bacterial and algal ecological structure in the target seawater pond, and analyzing the causes of abnormal water quality based on the analysis results;

[0061] S108, constructing an aquaculture optimization model based on the SAPSO algorithm, optimizing the bacterial and algal communities of the target seawater pond, and obtaining a candidate aquaculture optimization plan;

[0062] S110, analyzing the optimization cost and optimization period of each candidate breeding optimization plan, sorting them and selecting the final breeding optimization plan.

[0063] It should be noted that the present invention provides an ecological aquaculture optimization method and system based on the bacterial and algal community in seawater ponds. First, the specific information of the cultured objects, such as species, growth habits, etc., is obtained to obtain the environmental conditions under which the cultured objects grow best, that is, the suitable environment analysis information. Next, the seawater pond is monitored to obtain monitoring information including water quality parameters, bacterial and algal community structure, etc., and water quality abnormality detection is performed to determine whether there are problems such as pollution or overnutrition, and the water quality status is evaluated based on this to obtain water quality status evaluation information. Subsequently, a knowledge map of bacterial and algal ecological functions is constructed to describe different bacterial and algal species and their ecological functions. By analyzing the bacterial and algal ecological structure in the target seawater pond, the key causes of abnormal water quality are found. The SAPSO algorithm is used to construct an aquaculture optimization model, and the aquaculture of the target seawater pond is optimized by optimizing the bacterial and algal community structure to achieve the purpose of ecological aquaculture.

[0064] Further, in a preferred embodiment of the present invention, the acquiring of the culture information and the analysis of the suitable living environment of the culture according to the culture information to obtain the suitable living environment analysis information specifically include:

[0065] Acquire information about cultivated objects, obtain cultivation examples of target cultivated objects based on big data retrieval, form an example data set, extract the cultivation environment characteristics and bacterial and algal community characteristics of each cultivation example, and obtain characteristic information of the cultivation example;

[0066] Set the breeding indicator category, calculate the Euclidean distance between the breeding instance feature information and each breeding indicator category, and classify each breeding instance feature into the corresponding breeding indicator category by combining the clustering algorithm to obtain the category classification information;

[0067] Extract the breeding benefits of each breeding instance as the subsidiary attributes of each breeding instance feature, and rank the breeding instance features under each breeding indicator category;

[0068] According to the sorting results, the optimal breeding instance characteristics under each breeding indicator category are selected to obtain the suitable environment analysis information of the target breeding object.

[0069] It should be noted that, in order to analyze the aquaculture in the target seawater pond and determine its suitable living environment, first, the relevant aquaculture examples of the target aquaculture are obtained through big data retrieval to form an example data set. These example data include detailed aquaculture environment characteristics and bacterial and algal community characteristics, such as water temperature, salinity, pH value, bacterial and algal species and density, etc. Next, the aquaculture indicator category is set. By calculating the Euclidean distance between the characteristic information of each aquaculture instance and these aquaculture indicator categories, combined with the clustering algorithm, the aquaculture instances with similar characteristics are divided into the corresponding aquaculture indicator categories, and the category division information is obtained, thereby obtaining different aquaculture instance characteristics under each aquaculture indicator category. The aquaculture benefits of each aquaculture instance are extracted as subsidiary attributes, and the instance characteristics under each aquaculture indicator category are sorted, so as to obtain the ranking results of the aquaculture instance characteristics under each aquaculture indicator category. According to these sorting results, the optimal aquaculture instance characteristics under each aquaculture indicator category are selected to obtain the suitable living environment analysis information of the target aquaculture.

[0070] Further, in a preferred embodiment of the present invention, the water quality anomaly detection is performed based on the seawater pond monitoring information, and the water quality status is evaluated based on the anomaly detection result to obtain the water quality status evaluation information, which specifically includes:

[0071] Monitoring the target seawater pond to obtain seawater pond monitoring information, wherein the seawater pond monitoring information includes water quality monitoring information and bacterial and algal community monitoring information;

[0072] Acquiring water quality monitoring information according to the seawater pond monitoring information, performing data preprocessing on the water quality monitoring information, and performing time series processing on the preprocessed data;

[0073] A water quality anomaly detection model is constructed based on a generative adversarial network, an instance data set is obtained, aquaculture water quality characteristics of each aquaculture instance are extracted according to the instance data set, and an aquaculture water quality change curve of each aquaculture instance is constructed according to the time attribute of each aquaculture water quality characteristic;

[0074] The normal fluctuation range of water quality indicators is set, random water quality indicator changes are added to the aquaculture water quality change curve of each aquaculture instance, sample enhancement is performed, and a training data set is formed to train the water quality anomaly detection model;

[0075] The water quality monitoring information is input into a water quality anomaly detection model to perform water quality anomaly detection, and anomaly detection is performed by calculating the reconstruction error between the generated sequence and the original sequence to obtain water quality anomaly detection information;

[0076] Abnormal water quality index data is extracted according to the abnormal water quality detection information, the deviation from the normal fluctuation range of the water quality index is calculated, and the water quality status is evaluated according to the calculated deviation to obtain water quality status evaluation information.

[0077] It should be noted that, first, the monitoring information of the seawater pond is obtained, and the water quality monitoring information is preprocessed, including data cleaning, denoising, missing value filling, etc., to ensure the accuracy and consistency of the data. The preprocessed data will be processed in time series to generate time series data to reflect the changes in water quality parameters at different time points. Then, a water quality anomaly detection model is constructed based on the generative adversarial network (GAN), and the aquaculture water quality characteristics of each aquaculture instance are extracted using the instance data set, and the aquaculture water quality change curve is generated according to the time attributes of these characteristics. These change curves can show the dynamic changes of water quality parameters over time and provide a basis for anomaly detection. The normal fluctuation range of water quality indicators is set, and the aquaculture water quality change curve of each aquaculture instance is sample enhanced. By adding random changes in water quality indicators, possible water quality anomalies are simulated, the training data is expanded, and a training data set is constructed for model training. Among them, the water quality anomaly detection model is trained by using normal water quality change data. When the real-time monitoring data is input, the model will generate abnormal data as normal data to obtain the generation sequence of the model. At this time, according to the reconstruction error between the generation sequence and the original sequence, the abnormal data can be detected, including abnormal time points and abnormal indicators, to help timely discover potential problems. Finally, according to the water quality anomaly detection information, the abnormal water quality indicator data is extracted, and the deviation between these data and the normal fluctuation range is calculated. By analyzing the size and trend of the deviation, the water quality status is evaluated, and the water quality status evaluation information is obtained, so as to understand the current health status of the water quality and ensure the stability and health of the aquaculture environment.

[0078] Furthermore, in a preferred embodiment of the present invention, the construction of the knowledge map of bacterial and algal ecological functions and the analysis of the bacterial and algal ecological structure in the target seawater pond are carried out, and the cause of abnormal water quality is analyzed according to the analysis results, specifically including:

[0079] Based on big data retrieval, the ecological function characteristics and efficacy quantification characteristics of various bacteria and algae are obtained, the efficacy quantification standards are set, the efficacy standards of each ecological function are quantified, and the replacement relationship between the ecological function characteristics of different types of bacteria and algae is obtained to obtain ecological function analysis information;

[0080] Entity triples are constructed based on the species of bacteria and algae, the ecological function characteristics of bacteria and algae, and the ecological function analysis information; a knowledge graph of the ecological function of bacteria and algae is constructed based on the entity triples, and the functional replacement relationship between various types of bacteria and algae is used as an auxiliary feature;

[0081] Acquire seawater pond monitoring information, acquire bacterial and algal community monitoring information according to the seawater pond monitoring information, analyze the bacterial and algal ecological structure of the target seawater pond through the bacterial and algal community monitoring information, and obtain bacterial and algal ecological structure analysis information;

[0082] According to the bacterial-algae ecological structure analysis information and the bacterial-algae ecological function knowledge map, an ecological benefit evaluation is performed on the bacterial-algae community of the target seawater pond, and it is determined whether the bacterial-algae community of the target seawater pond is in a bacterial-algae balance, thereby obtaining ecological benefit evaluation information;

[0083] Acquire water quality status assessment information, calculate the Mahalanobis distance between the ecological benefit assessment information and the water quality status assessment information, analyze the correlation between abnormal water quality and various bacterial and algal communities, and obtain abnormal water quality cause analysis information.

[0084] It should be noted that first, the ecological function characteristics and efficacy quantitative characteristics of various bacteria and algae are obtained based on big data retrieval, including the specific role of bacteria and algae in water purification, nutrient cycle and ecological balance. After setting the efficacy quantification standard, the ecological function of each bacteria and algae is quantitatively evaluated, and the functional substitution relationship between different types of bacteria and algae is analyzed, that is, the degree to which each bacteria and algae species can provide a certain ecological function under a unit volume and the substitution relationship between bacteria and algae species, such as how many Class A bacteria and algae corresponding to a certain ecological function under a unit volume are equal to Class B bacteria, so as to obtain ecological function analysis information. Next, based on the bacteria and algae species, the ecological function characteristics of bacteria and algae and the ecological function analysis information, the entity triple is constructed. The entity triple contains the bacteria and algae species, its corresponding ecological function and specific quantitative characteristics. Using these triples, the knowledge graph of bacteria and algae ecological functions is constructed, and the functional substitution relationship between different bacteria and algae species is used as an auxiliary feature. The monitoring information of seawater ponds is obtained, the monitoring information of bacteria and algae communities is analyzed, the ecological structure of bacteria and algae in the target seawater pond is understood, and the analysis information of the ecological structure of bacteria and algae is obtained. This information includes the species distribution, quantity and functional performance of bacteria and algae, providing a detailed view of the pond ecosystem. Based on the analysis information of the ecological structure of bacteria and algae, combined with the knowledge map of the ecological functions of bacteria and algae, the ecological benefit evaluation of the bacteria and algae community in the target seawater pond is carried out to determine whether the bacteria and algae community is in a balanced state, whether it can effectively play its ecological function, and whether there is a problem of excessive abundance of certain types of bacteria and algae. Finally, the water quality status assessment information is obtained, the Mahalanobis distance between the ecological benefit assessment information and the water quality status assessment information is calculated, the correlation between abnormal water quality and each bacteria and algae community is analyzed, the bacteria and algae factors that may cause abnormal water quality are identified, and the cause analysis information of abnormal water quality is obtained.

[0085] Further, in a preferred embodiment of the present invention, the aquaculture optimization model is constructed based on the SAPSO algorithm, and the bacterial and algal communities of the target seawater pond are optimized to obtain a candidate aquaculture optimization plan, which specifically includes:

[0086] Acquire abnormal water quality cause analysis information and suitable environment analysis information, analyze aquaculture optimization targets according to the abnormal water quality cause analysis information and suitable environment analysis information, and obtain aquaculture optimization target information;

[0087] Based on the SAPSO algorithm, an aquaculture optimization model is constructed, a knowledge map of bacterial and algal ecological functions is obtained, and a training data set is constructed to train the aquaculture optimization model to obtain an aquaculture optimization model that meets expectations;

[0088] Acquire the bacterial and algae ecological structure analysis information, set the objective function and constraint conditions according to the aquaculture optimization target information, set the penalty conditions according to the bacterial and algae balance, and input the bacterial and algae ecological structure analysis information into the aquaculture optimization model for analysis;

[0089] Based on the bacterial and algae ecological structure analysis information, the bacterial and algae ecological function knowledge map is searched to obtain the replaceable bacterial and algae species and replacement relationships of the ecological functions corresponding to the bacterial and algae structure in the current seawater pond, and the replacement bacterial and algae analysis information is obtained;

[0090] Initializing the population according to the bacterial and algae ecological structure analysis information to generate an initial particle group, generating an optimized particle group according to the replacement bacterial and algae analysis information, replacing, adding and deleting the initial particle group through the optimized particle group, calculating the fitness of each particle in the initial particle group, and judging it with a preset threshold to obtain the current optimal solution;

[0091] Preset the initial receiving probability and the drop rate, use the current optimal solution as the initial solution of the SA algorithm, determine whether to accept it according to the initial receiving probability, and make a penalty determination according to the set penalty condition;

[0092] The acceptance probability is adjusted based on the decline rate and penalty judgment results, and iterative optimization is performed until the model converges to obtain the final solution, and the candidate breeding optimization plan is generated through the final solution.

[0093] It should be noted that, first, based on the abnormal water quality cause analysis information and the suitable environment analysis information, the goal of aquaculture optimization is analyzed, such as improving water quality, optimizing the structure of bacteria and algae communities, etc., so as to obtain the target information of aquaculture optimization. Next, the SAPSO algorithm is used to construct an aquaculture optimization model, and a training data set is constructed based on the knowledge map of bacteria and algae ecological functions to train the model. The aquaculture optimization model that meets the expectations is obtained through training. Then, the analysis information of the ecological structure of bacteria and algae is obtained and input into the aquaculture optimization model. The objective function and constraint conditions are set according to the target information of aquaculture optimization. At the same time, in ecological aquaculture, the balance of bacteria and algae in seawater ponds is particularly critical. If the balance of bacteria and algae in seawater ponds is unbalanced, it may affect the environment of seawater ponds, thereby reducing the aquaculture benefits. In order to maintain the balance of the bacteria and algae community, it is necessary to set corresponding penalty conditions, that is, the harmful products of a certain fungus or algae need to be balanced with the processing capacity of the corresponding bacteria and algae that absorb and process such harmful products, so as to avoid ecological imbalance caused by over-optimization. In the process of model analysis, the knowledge map of the ecological function of bacteria and algae is retrieved based on the analysis information of the ecological structure of bacteria and algae. After finding out the replaceable algae species and their replacement relationships corresponding to the ecological functions of the algae structure in the current seawater pond, the replacement algae analysis information is obtained, and suggestions for the replacement of algae species that may be needed during the optimization process are provided. Next, the population is initialized based on the algae ecological structure analysis information to generate an initial particle group, and an optimized particle group is generated based on the replacement algae analysis information to optimize the initial particle group. Subsequently, the initial particle group is replaced, added, and deleted by the optimized particle group to find a better solution. In each iteration, the fitness of each particle in the initial particle group is calculated and compared with the preset threshold to determine the current optimal solution. The initial acceptance probability and the decline rate are preset. In each iteration, the current optimal solution is used as the initial solution of the SA algorithm, and the initial acceptance probability is used to determine whether to accept this solution. If accepted, a penalty judgment is made according to the set penalty conditions to avoid the solution violating the constraint conditions or causing ecological imbalance. Then, the acceptance probability is adjusted in combination with the decline rate and the penalty judgment results to balance the ability to explore new solutions and utilize the current optimal solution. Finally, the optimization process is iterated until the model converges and the final solution is obtained. The candidate aquaculture optimization schemes are obtained through the final solution, such as adjusting the species or proportion of bacteria and algae, so as to optimize the aquaculture environment and improve the aquaculture efficiency.

[0094] Further, in a preferred embodiment of the present invention, the analysis of the optimization cost and optimization period of each candidate breeding optimization scheme, sorting and selecting the final breeding optimization scheme specifically includes:

[0095] Obtain candidate aquaculture optimization plans, perform feature extraction on each candidate aquaculture optimization plan, extract the optimized bacterial and algal community structure characteristics and the corresponding bacterial and algal community change characteristics, and obtain the characteristic information of the candidate aquaculture optimization plan;

[0096] Calculating the optimization cost and optimization period of each candidate breeding optimization scheme according to the characteristic information of the candidate breeding optimization scheme, taking the optimization cost and optimization period as weights, and performing weighted calculation on each candidate breeding optimization scheme;

[0097] The candidate breeding optimization schemes are ranked according to the weighted calculation results, and the optimization cost ranking and optimization cycle ranking of each candidate breeding optimization scheme are extracted to obtain the average ranking of each candidate breeding optimization scheme;

[0098] The final breeding optimization plan is selected and recommended based on the average ranking of each candidate breeding optimization plan.

[0099] It should be noted that, first, feature extraction is performed on the candidate aquaculture optimization schemes, and the structural characteristics of the optimized bacterial and algal communities and the corresponding community change characteristics are analyzed. Next, the optimization cost and optimization cycle of each scheme are calculated based on the extracted feature information of the candidate aquaculture optimization schemes. The optimization cost may include the introduction of strains, equipment investment, labor costs, etc., while the optimization cycle reflects the time required for the scheme to take effect from implementation. Then, the optimization cost and optimization cycle are used as weights to perform weighted calculations on the candidate aquaculture optimization schemes, and the two factors of cost and cycle are comprehensively considered to obtain a comprehensive evaluation result. A scheme with a higher optimization cost may bring better results, but it will also increase economic pressure; while a scheme with a longer optimization cycle may mean that the breeder needs a longer time to see the effect. Therefore, through weighted calculation, a balance point can be found to ensure that the selected scheme is both economical and efficient. The candidate aquaculture optimization schemes are ranked according to the weighted calculation results, and the optimization cost ranking and optimization cycle ranking of each scheme are further extracted, and their average ranking is calculated. The average ranking can more comprehensively reflect the performance of the scheme in terms of cost and cycle. Finally, according to the average ranking of each candidate breeding optimization plan, the final breeding optimization plan is selected for recommendation, and a breeding optimization plan with high feasibility and practicality is obtained to maximize the breeding benefits.

[0100] Figure 2 A flow chart of abnormal water quality detection provided by an embodiment of the present invention;

[0101] like Figure 2 As shown, the present invention provides a water quality anomaly detection flow chart, including:

[0102] S202, obtaining water quality monitoring information according to the seawater pond monitoring information and performing data preprocessing and time series processing;

[0103] S204, inputting the processed water quality monitoring information into a water quality anomaly detection model for analysis, and constructing an original sequence based on the input data;

[0104] S206, the generator obtains a generated sequence according to the original sequence, inputs it into the discriminator to calculate the reconstruction error between the generated sequence and the original sequence, and judges it with a preset threshold, and outputs water quality anomaly detection information;

[0105] S208, extracting abnormal water quality index data according to the abnormal water quality detection information, and calculating the deviation from the normal fluctuation range of the water quality index;

[0106] S210, presetting water quality assessment rules, performing water quality assessment according to the calculated deviation, and obtaining water quality assessment information.

[0107] It should be noted that the water quality anomaly detection model constructed based on the generative adversarial network is trained based on normal water quality data. After the model training is completed, the data to be detected is input, and the generator of the model will generate corresponding generated data based on the input data. Because the generator has only learned the distribution of normal data, the corresponding abnormal data will be generated into normal data when generating according to the input data. Therefore, the abnormal data points in the input data can be found through the reconstruction error of the generated sequence and the original sequence, thereby achieving the purpose of anomaly detection and improving the detection efficiency and accuracy of water quality anomalies.

[0108] In addition, the ecological aquaculture optimization method based on the bacterial and algal community in the seawater pond provided by the present invention also includes the following steps:

[0109] Based on big data retrieval, we obtain growth examples of various bacteria and algae in different living environments, and use the living environment as a category to combine clustering algorithms to divide each growth example to obtain growth example division information;

[0110] Extracting climate characteristics of different bacterial and algal growth instances under each environmental category according to the growth instance classification information, setting climate categories based on the extracted climate characteristics, and subdividing the growth instances under each environmental category to obtain first analysis information;

[0111] Based on the Markov algorithm, a state space is constructed according to the first analysis information to define the growth states of various bacteria and algae in different living environments and climates;

[0112] According to the constructed state space, the state transition probability of the growth state of bacteria and algae transferring to the next state under different climates in each environmental category is calculated, and the state transition matrix is ​​generated. The initial state probability distribution is set, and the growth prediction model of bacteria and algae is constructed by combining the state space and the transition probability matrix.

[0113] Constructing a training data set through the first analysis information to train the bacteria and algae growth prediction model, so as to obtain a bacteria and algae growth prediction model that meets expectations;

[0114] Acquire real-time meteorological information, water quality monitoring information and bacterial and algal ecological structure information of the target seawater pond, input them into the bacterial and algal growth prediction model for analysis, and obtain bacterial and algal growth prediction information;

[0115] Based on the bacterial and algae growth prediction information, the bacterial and algae growth change degree analysis is performed to obtain growth change degree analysis information, an abnormal growth judgment threshold is preset, and the growth change degree analysis information is judged with the abnormal growth judgment threshold to obtain abnormal growth judgment result information;

[0116] An abnormal growth warning of bacteria and algae is issued based on the abnormal growth judgment result information.

[0117] It should be noted that the bacterial and algal communities in seawater ponds will continue to grow while ecological aquaculture is being carried out. However, climate change may cause the growth of certain types of bacteria and algae in seawater ponds that originally had a balance between bacteria and algae to change too much, thereby destroying the balance of bacteria and algae and affecting the environment in seawater ponds and the survival of aquaculture. By predicting the growth of bacteria and algae in seawater ponds, taking into account real-time meteorological changes, and predicting the growth of bacteria and algae in future time periods, we can avoid abnormal reproduction of bacteria and algae, which will limit the living environment of aquaculture and reduce the efficiency of aquaculture production.

[0118] Figure 3 An ecological aquaculture optimization system 3 based on bacteria and algae communities in seawater ponds is provided in one embodiment of the present invention. The system includes: a memory 31 and a processor 32. The memory 31 contains an ecological aquaculture optimization method program based on bacteria and algae communities in seawater ponds. When the ecological aquaculture optimization method program based on bacteria and algae communities in seawater ponds is executed by the processor 32, the following steps are implemented:

[0119] Acquire information about cultivated plants, and perform suitable environment analysis on the cultivated plants according to the information about the cultivated plants to obtain suitable environment analysis information;

[0120] Perform water quality anomaly detection based on seawater pond monitoring information, and evaluate water quality status based on the anomaly detection results to obtain water quality status evaluation information;

[0121] Construct a knowledge map of bacterial and algal ecological functions, analyze the bacterial and algal ecological structure in the target seawater pond, and analyze the causes of abnormal water quality based on the analysis results;

[0122] Based on the SAPSO algorithm, an aquaculture optimization model was constructed to optimize the bacterial and algal communities in the target seawater ponds and obtain candidate aquaculture optimization plans.

[0123] Analyze the optimization cost and optimization cycle of each candidate breeding optimization plan, sort them and select the final breeding optimization plan.

[0124] In the 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 schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, 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.

[0125] 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 on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0126] 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.

[0127] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0128] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function 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 embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0129] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An ecological aquaculture optimization method based on bacterial and algal communities in seawater ponds, characterized in that: include: Acquire information about cultivated plants, and perform suitable environment analysis on the cultivated plants according to the information about the cultivated plants to obtain suitable environment analysis information; Perform water quality anomaly detection based on seawater pond monitoring information, and evaluate water quality status based on the anomaly detection results to obtain water quality status evaluation information; Construct a knowledge map of bacterial and algal ecological functions, analyze the bacterial and algal ecological structure in the target seawater pond, and analyze the causes of abnormal water quality based on the analysis results; Based on the SAPSO algorithm, an aquaculture optimization model was constructed to optimize the bacterial and algal communities in the target seawater ponds and obtain candidate aquaculture optimization plans. Analyze the optimization cost and optimization cycle of each candidate breeding optimization plan, sort them and select the final breeding optimization plan; The acquiring of the cultured plant information and performing a suitable living environment analysis on the cultured plant according to the cultured plant information to obtain suitable living environment analysis information specifically includes: Acquire information about cultivated objects, obtain cultivation examples of target cultivated objects based on big data retrieval, form an example data set, extract the cultivation environment characteristics and bacterial and algal community characteristics of each cultivation example, and obtain characteristic information of the cultivation example; Set the breeding indicator category, calculate the Euclidean distance between the breeding instance feature information and each breeding indicator category, and classify each breeding instance feature into the corresponding breeding indicator category by combining the clustering algorithm to obtain the category classification information; Extract the breeding benefits of each breeding instance as the subsidiary attributes of each breeding instance feature, and rank the breeding instance features under each breeding indicator category; According to the sorting results, the optimal breeding instance characteristics under each breeding index category are selected to obtain the suitable environment analysis information of the target breeding object; The water quality anomaly detection is performed according to the seawater pond monitoring information, and the water quality status is evaluated according to the anomaly detection result to obtain the water quality status evaluation information, specifically including: Monitoring the target seawater pond to obtain seawater pond monitoring information, wherein the seawater pond monitoring information includes water quality monitoring information and bacterial and algal community monitoring information; Acquiring water quality monitoring information according to the seawater pond monitoring information, performing data preprocessing on the water quality monitoring information, and performing time series processing on the preprocessed data; A water quality anomaly detection model is constructed based on a generative adversarial network, an instance data set is obtained, aquaculture water quality characteristics of each aquaculture instance are extracted according to the instance data set, and an aquaculture water quality change curve of each aquaculture instance is constructed according to the time attribute of each aquaculture water quality characteristic; The normal fluctuation range of water quality indicators is set, random water quality indicator changes are added to the aquaculture water quality change curve of each aquaculture instance, sample enhancement is performed, and a training data set is formed to train the water quality anomaly detection model; The water quality monitoring information is input into a water quality anomaly detection model to perform water quality anomaly detection, and anomaly detection is performed by calculating the reconstruction error between the generated sequence and the original sequence to obtain water quality anomaly detection information; Extracting abnormal water quality index data according to the abnormal water quality detection information, calculating the deviation from the normal fluctuation range of the water quality index, and evaluating the water quality status according to the calculated deviation to obtain water quality status evaluation information; The construction of the knowledge map of bacterial and algal ecological functions and the analysis of the bacterial and algal ecological structure in the target seawater pond are carried out, and the cause of abnormal water quality is analyzed according to the analysis results, specifically including: Based on big data retrieval, the ecological function characteristics and efficacy quantification characteristics of various bacteria and algae are obtained, the efficacy quantification standards are set, the efficacy standards of each ecological function are quantified, and the replacement relationship between the ecological function characteristics of different types of bacteria and algae is obtained to obtain ecological function analysis information; Entity triples are constructed based on the species of bacteria and algae, the ecological function characteristics of bacteria and algae, and the ecological function analysis information; a knowledge graph of the ecological function of bacteria and algae is constructed based on the entity triples, and the functional replacement relationship between various types of bacteria and algae is used as an auxiliary feature; Acquire seawater pond monitoring information, acquire bacterial and algal community monitoring information according to the seawater pond monitoring information, analyze the bacterial and algal ecological structure of the target seawater pond through the bacterial and algal community monitoring information, and obtain bacterial and algal ecological structure analysis information; According to the bacterial-algae ecological structure analysis information and the bacterial-algae ecological function knowledge map, an ecological benefit evaluation is performed on the bacterial-algae community of the target seawater pond, and it is determined whether the bacterial-algae community of the target seawater pond is in a bacterial-algae balance, thereby obtaining ecological benefit evaluation information; Acquire water quality status assessment information, calculate the Mahalanobis distance between the ecological benefit assessment information and the water quality status assessment information, analyze the correlation between abnormal water quality and various bacterial and algal communities, and obtain abnormal water quality cause analysis information.

2. The ecological aquaculture optimization method based on bacteria and algae communities in seawater ponds according to claim 1, characterized in that: The aquaculture optimization model is constructed based on the SAPSO algorithm, and the bacterial and algal communities of the target seawater pond are optimized to obtain candidate aquaculture optimization schemes, which specifically include: Acquire abnormal water quality cause analysis information and suitable environment analysis information, analyze aquaculture optimization targets according to the abnormal water quality cause analysis information and suitable environment analysis information, and obtain aquaculture optimization target information; Based on the SAPSO algorithm, an aquaculture optimization model is constructed, a knowledge map of bacterial and algal ecological functions is obtained, and a training data set is constructed to train the aquaculture optimization model to obtain an aquaculture optimization model that meets expectations; Acquire the bacterial and algae ecological structure analysis information, set the objective function and constraint conditions according to the aquaculture optimization target information, set the penalty conditions according to the bacterial and algae balance, and input the bacterial and algae ecological structure analysis information into the aquaculture optimization model for analysis; Based on the bacterial and algae ecological structure analysis information, the bacterial and algae ecological function knowledge map is searched to obtain the replaceable bacterial and algae species and replacement relationships of the ecological functions corresponding to the bacterial and algae structure in the current seawater pond, and the replacement bacterial and algae analysis information is obtained; Initializing the population according to the bacterial and algae ecological structure analysis information to generate an initial particle group, generating an optimized particle group according to the replacement bacterial and algae analysis information, replacing, adding and deleting the initial particle group through the optimized particle group, calculating the fitness of each particle in the initial particle group, and judging it with a preset threshold to obtain the current optimal solution; Preset the initial receiving probability and the drop rate, use the current optimal solution as the initial solution of the SA algorithm, determine whether to accept it according to the initial receiving probability, and make a penalty determination according to the set penalty condition; The acceptance probability is adjusted based on the decline rate and penalty judgment results, and iterative optimization is performed until the model converges to obtain the final solution, and the candidate breeding optimization plan is generated through the final solution.

3. The ecological aquaculture optimization method based on bacteria and algae communities in seawater ponds according to claim 1 is characterized in that: The analysis of the optimization cost and optimization cycle of each candidate breeding optimization scheme, sorting and selecting the final breeding optimization scheme specifically includes: Obtain candidate aquaculture optimization plans, perform feature extraction on each candidate aquaculture optimization plan, extract the optimized bacterial and algal community structure characteristics and the corresponding bacterial and algal community change characteristics, and obtain the characteristic information of the candidate aquaculture optimization plan; Calculating the optimization cost and optimization period of each candidate breeding optimization scheme according to the characteristic information of the candidate breeding optimization scheme, taking the optimization cost and optimization period as weights, and performing weighted calculation on each candidate breeding optimization scheme; The candidate breeding optimization schemes are ranked according to the weighted calculation results, and the optimization cost ranking and optimization cycle ranking of each candidate breeding optimization scheme are extracted to obtain the average ranking of each candidate breeding optimization scheme; The final breeding optimization plan is selected and recommended based on the average ranking of each candidate breeding optimization plan.

4. An ecological aquaculture optimization system based on bacterial and algal communities in seawater ponds, characterized in that: The system includes: a memory and a processor, wherein the memory contains an ecological aquaculture optimization method program based on bacteria and algae communities in seawater ponds, and when the ecological aquaculture optimization method program based on bacteria and algae communities in seawater ponds is executed by the processor, the following steps are implemented: Acquire information about cultivated plants, and perform suitable environment analysis on the cultivated plants according to the information about the cultivated plants to obtain suitable environment analysis information; Perform water quality anomaly detection based on seawater pond monitoring information, and evaluate water quality status based on the anomaly detection results to obtain water quality status evaluation information; Construct a knowledge map of bacterial and algal ecological functions, analyze the bacterial and algal ecological structure in the target seawater pond, and analyze the causes of abnormal water quality based on the analysis results; Based on the SAPSO algorithm, an aquaculture optimization model was constructed to optimize the bacterial and algal communities in the target seawater ponds and obtain candidate aquaculture optimization plans. Analyze the optimization cost and optimization cycle of each candidate breeding optimization plan, sort them and select the final breeding optimization plan; The acquiring of the cultured plant information and performing a suitable living environment analysis on the cultured plant according to the cultured plant information to obtain suitable living environment analysis information specifically includes: Acquire information about cultivated objects, obtain cultivation examples of target cultivated objects based on big data retrieval, form an example data set, extract the cultivation environment characteristics and bacterial and algal community characteristics of each cultivation example, and obtain characteristic information of the cultivation example; Set the breeding indicator category, calculate the Euclidean distance between the breeding instance feature information and each breeding indicator category, and classify each breeding instance feature into the corresponding breeding indicator category by combining the clustering algorithm to obtain the category classification information; Extract the breeding benefits of each breeding instance as the subsidiary attributes of each breeding instance feature, and rank the breeding instance features under each breeding indicator category; According to the sorting results, the optimal breeding instance characteristics under each breeding index category are selected to obtain the suitable environment analysis information of the target breeding object; The water quality anomaly detection is performed according to the seawater pond monitoring information, and the water quality status is evaluated according to the anomaly detection result to obtain the water quality status evaluation information, specifically including: Monitoring the target seawater pond to obtain seawater pond monitoring information, wherein the seawater pond monitoring information includes water quality monitoring information and bacterial and algal community monitoring information; Acquiring water quality monitoring information according to the seawater pond monitoring information, performing data preprocessing on the water quality monitoring information, and performing time series processing on the preprocessed data; A water quality anomaly detection model is constructed based on a generative adversarial network, an instance data set is obtained, aquaculture water quality characteristics of each aquaculture instance are extracted according to the instance data set, and an aquaculture water quality change curve of each aquaculture instance is constructed according to the time attribute of each aquaculture water quality characteristic; The normal fluctuation range of water quality indicators is set, random water quality indicator changes are added to the aquaculture water quality change curve of each aquaculture instance, sample enhancement is performed, and a training data set is formed to train the water quality anomaly detection model; The water quality monitoring information is input into a water quality anomaly detection model to perform water quality anomaly detection, and anomaly detection is performed by calculating the reconstruction error between the generated sequence and the original sequence to obtain water quality anomaly detection information; Extracting abnormal water quality index data according to the abnormal water quality detection information, calculating the deviation from the normal fluctuation range of the water quality index, and evaluating the water quality status according to the calculated deviation to obtain water quality status evaluation information; The construction of the knowledge map of bacterial and algal ecological functions and the analysis of the bacterial and algal ecological structure in the target seawater pond are carried out, and the cause of abnormal water quality is analyzed according to the analysis results, specifically including: Based on big data retrieval, the ecological function characteristics and efficacy quantification characteristics of various bacteria and algae are obtained, the efficacy quantification standards are set, the efficacy standards of each ecological function are quantified, and the replacement relationship between the ecological function characteristics of different types of bacteria and algae is obtained to obtain ecological function analysis information; Entity triples are constructed based on the species of bacteria and algae, the ecological function characteristics of bacteria and algae, and the ecological function analysis information; a knowledge graph of the ecological function of bacteria and algae is constructed based on the entity triples, and the functional replacement relationship between various types of bacteria and algae is used as an auxiliary feature; Acquire seawater pond monitoring information, acquire bacterial and algal community monitoring information according to the seawater pond monitoring information, analyze the bacterial and algal ecological structure of the target seawater pond through the bacterial and algal community monitoring information, and obtain bacterial and algal ecological structure analysis information; According to the bacterial-algae ecological structure analysis information and the bacterial-algae ecological function knowledge map, an ecological benefit evaluation is performed on the bacterial-algae community of the target seawater pond, and it is determined whether the bacterial-algae community of the target seawater pond is in a bacterial-algae balance, thereby obtaining ecological benefit evaluation information; Acquire water quality status assessment information, calculate the Mahalanobis distance between the ecological benefit assessment information and the water quality status assessment information, analyze the correlation between abnormal water quality and various bacterial and algal communities, and obtain abnormal water quality cause analysis information.

Citation Information

Patent Citations

  • Underwater robot device and underwater regulation and control management optimization system and method

    CN111897350A

  • Algae culture method and system based on data analysis and medium

    CN115100414A

  • Aquaculture water quality regulation and control method and system based on prawns and medium

    CN115793585A

  • Aquaculture information intelligent supervision system and method based on big data

    CN116502016A

  • Prawn culture water quality regulation and control method and system based on Internet of Things

    CN116941562A