A method and system for intelligently regulating the aquaculture ecology of bacterial and algal communities in seawater ponds

Through pond partitioning and long-term memory network prediction model evaluation, combined with pollution source traceability and microbial treatment, the problem of water quality deterioration caused by excessive concentration of bacteria and algae communities in seawater ponds is solved, and the ecological environment restoration of seawater ponds and the optimization of breeding environment is achieved. .

CN118364977BActive Publication Date: 2024-11-08SOUTH CHINA SEA FISHERIES RES INST CHINESE ACAD OF FISHERY SCI +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410798114.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-06-20
Publication Date
2024-11-08
Estimated Expiration
2044-06-20

AI Technical Summary

Technical Problem

Excessive concentration of bacterial and algae communities in seawater ponds leads to deterioration of water quality, affecting aquaculture yield and ecological balance, and it is difficult for the existing technology to effectively regulate.

Method used

Through pond partitioning, water quality detection and fungal algae community species assessment, a long-term and short-term memory network prediction model is constructed, and breeding ecological assessment and intelligent regulation are carried out, including traceability isolation at the source of pollution, microbial delivery and chemical agent use to maintain water quality and fungal algae concentration in the standard Within the threshold.

Benefits of technology

The ecological environment restoration of seawater ponds has been achieved, ensuring good water quality, suitable for the growth of aquaculture marine organisms, reducing management costs, and reducing economic losses.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118364977B_ABST
    Figure CN118364977B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of ecological regulation, and discloses a method and system for intelligent regulation of aquaculture ecology of bacterial and algal communities in seawater ponds, comprising the following steps: partitioning the seawater pond, performing water quality sampling and testing and bacterial and algal community species assessment after the pond partitioning, and obtaining the concentrations of different types of bacterial and algal communities after the bacterial and algal community species assessment; combining water quality data and the concentrations of different types of bacterial and algal communities, constructing a long-short-term memory network prediction model, and based on the long-short-term memory network prediction model, performing aquaculture ecology assessment and aquaculture ecology regulation on the seawater pond. The present invention can analyze the water quality data and bacterial and algal communities of the seawater pond, and realize intelligent regulation of aquaculture ecology on the seawater pond based on the analysis results, which is helpful to the restoration of the ecological environment of the seawater pond, ensuring that the seawater pond is suitable for aquaculture and growth of marine organisms, and is helpful to the environment.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of ecological regulation, and in particular to an intelligent regulation method and system for the aquaculture ecology of bacteria and algae communities in seawater ponds. Background Art

[0002] Seawater ponds are artificial or naturally formed water bodies specially designed and constructed for breeding marine life, studying marine ecology, and processing seawater resources. Unlike freshwater ponds, seawater ponds use seawater, which is usually high in salinity and suitable for breeding and growing marine life. The water quality in seawater ponds may be affected by high-density breeding, excess nutrients, and external sewage infection, resulting in abnormal water quality in seawater ponds. The high concentration of bacterial and algal communities in seawater ponds may be caused by suitable water temperature, appropriate light intensity, and poor water fluidity. Since bacterial and algal communities may lead to water quality deterioration, such as excessive oxygen consumption and accumulation of toxic organic matter, they may also destroy the ecological balance, such as interruption of the food chain and deterioration of the benthic environment, resulting in reduced aquaculture production, increased management costs, etc., causing serious economic losses. Therefore, it is necessary to regulate the bacterial and algal communities in seawater ponds, that is, to regulate the aquaculture ecology, to ensure good water quality in seawater ponds, and to ensure that the concentration of bacterial and algal communities in seawater ponds remains at an appropriate level. Summary of the invention

[0003] The present invention overcomes the shortcomings of the prior art and provides a method and system for intelligently regulating the aquaculture ecology of bacteria and algae communities in seawater ponds.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides a method for intelligently regulating the aquaculture ecology of bacterial and algal communities in seawater ponds, comprising the following steps:

[0006] Divide the ponds into different zones and conduct water quality sampling and assessment of bacterial and algal community species in the ponds in different zones;

[0007] Determine the concentration of different bacterial and algal community species in all target seawater pond sub-areas, and build a long-short-term memory network prediction model based on the water quality data of different target seawater pond sub-areas;

[0008] The aquaculture ecology of the target seawater pond is evaluated and classified through the long short-term memory network prediction model, and the aquaculture ecology of the target seawater pond is intelligently adjusted based on the aquaculture ecology evaluation and classification results.

[0009] Furthermore, in a preferred embodiment of the present invention, the pond is divided into zones in the seawater pond, and water quality sampling and testing and bacterial and algal community species assessment are performed in the seawater ponds in different zones, specifically:

[0010] Marking the seawater pond that needs to be regulated for aquaculture ecology as the target seawater pond, and obtaining the area and shape of the target seawater pond;

[0011] A device for intelligently regulating the aquaculture ecology of a target seawater pond is obtained and calibrated as a target regulating device, wherein a camera for image acquisition is inherited in the target regulating device and calibrated as a target camera;

[0012] Acquire specification parameters of a target camera, wherein the specification parameters of the target camera include an image acquisition range of the target camera;

[0013] Analyze the area and shape of the target seawater pond to obtain all partitioning schemes of the target seawater pond, analyze all the partitioning schemes of the target seawater pond, select a partitioning scheme in which all sub-areas of the target seawater pond after partitioning are smaller than the image acquisition range of the target camera, and mark it as the target partitioning scheme;

[0014] Based on the target partitioning scheme, the target seawater pond is partitioned to obtain target seawater pond sub-areas, a water quality testing device is obtained, water samples are extracted from all target seawater pond sub-areas, and the water samples extracted from different target seawater pond sub-areas are introduced into the water quality testing device for water quality testing to obtain water quality data of different target seawater pond sub-areas;

[0015] Using a target camera to perform bacterial and algal community image recognition in different target seawater pond sub-areas to obtain bacterial and algal community images, performing image preprocessing and image feature extraction processing on the bacterial and algal community images to obtain bacterial and algal community feature data of different target seawater pond sub-areas;

[0016] Acquire a big data network, and retrieve a bacterial and algal community knowledge graph in the big data network, wherein the bacterial and algal community knowledge graph stores characteristic data of different types of bacterial and algal communities;

[0017] The characteristic data of bacterial and algal communities in different target seawater pond sub-areas were imported into the bacterial and algal community knowledge graph for characteristic data matching analysis. Based on the characteristic data matching analysis results, the types of bacterial and algal communities existing in different target seawater pond sub-areas were determined respectively.

[0018] Furthermore, in a preferred embodiment of the present invention, the concentrations of different species of bacterial and algal communities in all target seawater pond sub-areas are determined, and the long short-term memory network prediction model is constructed in combination with the water quality data of different target seawater pond sub-areas, specifically:

[0019] Sampling bacterial and algal communities in all target seawater pond sub-areas to obtain bacterial and algal community samples, and obtaining fluorescent dyes, and using the fluorescent dyes to dye the bacterial and algal community samples to obtain bacterial and algal community fluorescent samples;

[0020] Obtaining the sampling volume of the bacterial and algal community fluorescence sample and obtaining a flow cytometer, introducing the bacterial and algal community fluorescence sample into the flow cytometer, and combining the sampling volume of the bacterial and algal community fluorescence sample and the bacterial and algal community species existing in different target seawater pond sub-areas to obtain the fluorescence intensity of different types of bacterial and algal communities;

[0021] In the bacterial and algal community fluorescence sample, the concentrations of the different types of bacterial and algal communities are obtained based on the fluorescence intensities of the different types of bacterial and algal communities, and the concentrations of the different types of bacterial and algal communities in the different target seawater pond sub-areas are determined based on the concentrations of the different types of bacterial and algal communities;

[0022] A time step for predicting water quality in a seawater pond is preset and calibrated as a type of time step. Based on the type of time step, the model layer number and the number of single-layer neurons with the highest frequency of use of the long short-term memory network model under the type of time step are retrieved in a big data network and calibrated as the target model layer number and the target single-layer neuron number;

[0023] Based on the target number of model layers and the target number of single-layer neurons, a long short-term memory network basic model is constructed, and the concentrations of different types of bacterial and algal communities in different target seawater pond sub-areas and water quality data of different target seawater pond sub-areas are imported into the long short-term memory network basic model for model training to obtain a long short-term memory network prediction model, which is a data model that can predict the water quality data of different target seawater pond sub-areas and the concentrations of different types of bacterial and algal communities within a class of time steps.

[0024] Furthermore, in a preferred embodiment of the present invention, the aquaculture ecology of the target seawater pond is evaluated and classified by the long short-term memory network prediction model, and the aquaculture ecology of the target seawater pond is intelligently adjusted based on the aquaculture ecology evaluation and classification results, specifically:

[0025] Based on the long short-term memory network prediction model, the water quality data of different target seawater pond sub-areas within a time step and the concentration of different types of bacterial and algal communities are predicted and obtained, and the standard water quality data thresholds of different target seawater pond sub-areas within a time step and the standard concentration thresholds of different types of bacterial and algal communities are preset;

[0026] If, within a time step, the water quality data of all sub-areas of the target seawater pond remain within the standard water quality data threshold, and the concentrations of all types of bacterial and algal communities remain within the standard concentration threshold, the target seawater pond will be evaluated as a qualified seawater pond for aquaculture ecology;

[0027] If, within a time step, the water quality data of the sub-area of ​​the target seawater pond does not remain within the standard water quality data threshold, or the concentration of any type of bacterial and algal community does not remain within the standard concentration threshold, the target seawater pond will be evaluated as a seawater pond for aquaculture ecology to be optimized, and an aquaculture ecology early warning signal will be generated in the target regulation device;

[0028] When an aquaculture ecology early warning signal is generated in the target regulating device, the pollution source of the seawater pond for aquaculture ecology to be optimized is traced and isolated, and after the pollution source is traced and isolated, the water quality of the seawater pond for aquaculture ecology to be optimized is regulated through the target regulating device.

[0029] Furthermore, in a preferred embodiment of the present invention, the pollution source of the seawater pond to be optimized for aquaculture ecology is traced back and isolated, and after the pollution source is traced back and isolated, the water quality of the seawater pond to be optimized for aquaculture ecology is regulated by a target regulating device, specifically:

[0030] In the seawater pond where the aquaculture ecology is to be optimized, all water sources connected to the seawater pond where the aquaculture ecology is to be optimized are obtained and marked as water sources to be analyzed;

[0031] Sampling and testing all water sources to be analyzed, and determining whether there are water quality data of the water sources to be analyzed that are not within the preset threshold. If so, the corresponding water sources to be analyzed are marked as polluted water sources, and an isolation barrier is set at the connection between the polluted water source and the seawater pond to be optimized for aquaculture ecology, so that the seawater pond to be optimized for aquaculture ecology is not connected to the polluted water source;

[0032] In the seawater pond to be optimized for aquaculture ecology, a target seawater pond sub-region whose water quality data is not maintained within the standard water quality data threshold is marked as a seawater pond sub-region with abnormal water quality, and based on the water quality data of the seawater pond sub-region with abnormal water quality, the types of restoration microorganisms that can act on the seawater pond sub-region with abnormal water quality and can maintain the water quality data of the seawater pond sub-region with abnormal water quality within the standard water quality data threshold are retrieved in the big data network and marked as a type of restoration microorganisms;

[0033] Combine and analyze the water quality data of the abnormal water quality seawater pond sub-area and the first type of remediation microorganism to determine the release concentration of the first type of remediation microorganism, and release the first type of remediation microorganism in the abnormal water quality seawater pond sub-area with a concentration equal to the release concentration of the first type of remediation microorganism through the target adjustment device;

[0034] After a type of repair microorganism is released, a repair time is preset, and the repair rate of the type of repair microorganism is measured within the repair time. If the repair rate of the type of repair microorganism is less than the preset value, a chemical agent that improves the repair rate of the type of repair microorganism is searched in the big data network and marked as a target chemical agent;

[0035] Control the microorganism delivery device to deliver the target chemical agent during the process of the first type of repair microorganisms repairing the sub-area of ​​the seawater pond with abnormal water quality, so that the repair rate of the first type of repair microorganisms is greater than a preset value, and the water quality data of the sub-area of ​​the seawater pond with abnormal water quality is maintained within the standard water quality data threshold, so as to obtain a seawater pond with qualified water quality;

[0036] The bacterial and algal community species analysis is conducted on seawater ponds with qualified water quality, and the bacterial and algal community in the seawater ponds with qualified water quality is adjusted based on the results of the bacterial and algal community analysis.

[0037] Furthermore, in a preferred embodiment of the present invention, the bacterial and algal community species analysis is performed on the seawater pond with qualified water quality, and the bacterial and algal community is adjusted in the seawater pond with qualified water quality based on the bacterial and algal community species analysis result, specifically:

[0038] After obtaining a seawater pond with qualified water quality, determine whether there are still any types of bacterial and algal communities in the seawater pond with qualified water quality whose concentration is not maintained within the standard concentration threshold;

[0039] If not, the seawater pond with qualified water quality shall be calibrated as a seawater pond with qualified aquaculture ecology;

[0040] If so, the species of bacterial and algal communities whose concentrations in the seawater ponds with qualified water quality do not maintain the standard concentration threshold are marked as abnormal bacterial and algal community species, and all bacterial and algal community species that may cause damage to the aquaculture ecology of the seawater ponds are retrieved from the big data network;

[0041] Determine whether all the species of algae and bacteria that may damage the aquaculture ecology of the seawater pond include abnormal algae and bacteria. If so, mark the seawater pond with qualified water quality as a type of seawater pond to be optimized, and mark the target seawater pond sub-area where the algae and bacteria of the abnormal algae and bacteria exist in the type of seawater pond to be optimized as an abnormal algae and bacteria sub-area, and at the same time, enclose the abnormal algae and bacteria sub-area;

[0042] Retrieving an inhibitor that can inhibit bacterial and algal communities of abnormal bacterial and algal community types in a big data network, marking the inhibitor as an abnormal bacterial and algal community inhibitor, and using the abnormal bacterial and algal community inhibitor to perform bacterial and algal community inhibition treatment in a sub-area of ​​the bacterial and algal community abnormal seawater pond until there is no abnormal bacterial and algal community type in a type of seawater pond to be optimized;

[0043] When there is no abnormal bacterial and algal community species in the first type of seawater pond to be optimized, the enclosure of the sub-area of ​​the seawater pond with abnormal bacterial and algal community is released, and the first type of seawater pond to be optimized is marked as the second type of seawater pond to be optimized;

[0044] A filtering device and an air flotation device are introduced into the second type of seawater pond to be optimized. The air flotation device is used to perform pressurized dissolved air treatment in the second type of seawater pond to be optimized, so that all bacterial and algal communities in the second type of seawater pond to be optimized float to the water surface. The bacterial and algal communities floating to the water surface are filtered by the filtering device, so that the concentrations of all types of bacterial and algal communities in the second type of seawater pond to be optimized are maintained within the standard concentration threshold, thereby obtaining a seawater pond with qualified aquaculture ecology.

[0045] The second aspect of the present invention also provides an aquaculture ecological intelligent regulation system for bacterial and algal communities in seawater ponds, the aquaculture ecological intelligent regulation system comprising a memory and a processor, the memory storing an aquaculture ecological intelligent regulation method, and when the aquaculture ecological intelligent regulation method is executed by the processor, the following steps are implemented:

[0046] Divide the ponds into different zones and conduct water quality sampling and assessment of bacterial and algal community species in the ponds in different zones;

[0047] Determine the concentration of different bacterial and algal community species in all target seawater pond sub-areas, and build a long-short-term memory network prediction model based on the water quality data of different target seawater pond sub-areas;

[0048] The aquaculture ecology of the target seawater pond is evaluated and classified through the long short-term memory network prediction model, and the aquaculture ecology of the target seawater pond is intelligently adjusted based on the aquaculture ecology evaluation and classification results.

[0049] The present invention solves the technical defects existing in the background technology, and the present invention has the following beneficial effects: pond zoning is performed on seawater ponds, and water quality sampling and detection and bacterial and algal community species assessment are performed after pond zoning, and the concentrations of different types of bacterial and algal communities are obtained after the bacterial and algal community species assessment; a long-short-term memory network prediction model is constructed in combination with water quality data and the concentrations of different types of bacterial and algal communities, and a breeding ecology assessment and breeding ecology regulation are performed on seawater ponds based on the long-short-term memory network prediction model. The present invention can analyze the water quality data and bacterial and algal communities of seawater ponds, and realize intelligent breeding ecology regulation of seawater ponds based on the analysis results, which is helpful to the restoration of the ecological environment of seawater ponds, ensure that seawater ponds are suitable for breeding and growing marine life, and help the environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0051] Figure 1 A flow chart showing an intelligent regulation method for the aquaculture ecology of bacterial and algal communities in seawater ponds;

[0052] Figure 2 A flow chart of a method for evaluating and classifying aquaculture ecology and intelligently regulating aquaculture ecology of a target seawater pond is shown;

[0053] Figure 3 The program view of an aquaculture ecological intelligent regulation system for bacterial and algal communities in seawater ponds is shown. 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 a method for intelligently regulating the aquaculture ecology of bacterial and algal communities in seawater ponds is shown, comprising the following steps:

[0057] S102: Divide the ponds into different zones and conduct water quality sampling and testing and bacterial and algal community species assessment in the ponds in different zones;

[0058] S104: determining the concentrations of different bacterial and algal community species in all target seawater pond sub-areas, and constructing a long short-term memory network prediction model based on water quality data of different target seawater pond sub-areas;

[0059] S106: Perform aquaculture ecology assessment and classification of the target seawater pond through the long short-term memory network prediction model, and perform aquaculture ecology intelligent adjustment of the target seawater pond based on the aquaculture ecology assessment and classification results.

[0060] Furthermore, in a preferred embodiment of the present invention, the pond is divided into zones in the seawater pond, and water quality sampling and testing and bacterial and algal community species assessment are performed in the seawater ponds in different zones, specifically:

[0061] Marking the seawater pond that needs to be regulated for aquaculture ecology as the target seawater pond, and obtaining the area and shape of the target seawater pond;

[0062] A device for intelligently regulating the aquaculture ecology of a target seawater pond is obtained and calibrated as a target regulating device, wherein a camera for image acquisition is inherited in the target regulating device and calibrated as a target camera;

[0063] Acquire specification parameters of a target camera, wherein the specification parameters of the target camera include an image acquisition range of the target camera;

[0064] Analyze the area and shape of the target seawater pond to obtain all partitioning schemes of the target seawater pond, analyze all the partitioning schemes of the target seawater pond, select a partitioning scheme in which all sub-areas of the target seawater pond after partitioning are smaller than the image acquisition range of the target camera, and mark it as the target partitioning scheme;

[0065] Based on the target partitioning scheme, the target seawater pond is partitioned to obtain target seawater pond sub-areas, a water quality testing device is obtained, water samples are extracted from all target seawater pond sub-areas, and the water samples extracted from different target seawater pond sub-areas are introduced into the water quality testing device for water quality testing to obtain water quality data of different target seawater pond sub-areas;

[0066] Using a target camera to perform bacterial and algal community image recognition in different target seawater pond sub-areas to obtain bacterial and algal community images, performing image preprocessing and image feature extraction processing on the bacterial and algal community images to obtain bacterial and algal community feature data of different target seawater pond sub-areas;

[0067] Acquire a big data network, and retrieve a bacterial and algal community knowledge graph in the big data network, wherein the bacterial and algal community knowledge graph stores characteristic data of different types of bacterial and algal communities;

[0068] The characteristic data of bacterial and algal communities in different target seawater pond sub-areas were imported into the bacterial and algal community knowledge graph for characteristic data matching analysis. Based on the characteristic data matching analysis results, the types of bacterial and algal communities existing in different target seawater pond sub-areas were determined respectively.

[0069] It should be noted that seawater ponds are artificial ponds used to cultivate marine life and study marine ecology. Due to the wide variety of marine life and complex marine ecology, the area of ​​seawater ponds is large. When analyzing the bacterial and algal communities in seawater ponds, it is necessary to perform zoning analysis to improve the accuracy. To zonate seawater ponds, it is necessary to first obtain the area and shape of the seawater ponds to confirm the zoning scheme. Since the analysis of seawater ponds includes water quality analysis and bacterial and algal community species analysis, and the method for analyzing bacterial and algal community species is image analysis, images are obtained through cameras to analyze bacterial and algal community species. Since the camera shooting range is limited, the target zoning scheme is that the range of the seawater pond sub-area after the partition needs to meet the camera's full shooting. Among them, the camera is integrated in the target adjustment device, which can improve the shooting efficiency. The target adjustment device is an integrated device for taking pictures and adjusting the aquaculture ecology. After zoning, water quality testing of seawater ponds requires water samples to be extracted in different sub-areas for testing. Because the area of ​​seawater ponds is large, the water quality in different areas may be different. The water quality data in some areas, that is, the parameters such as salinity, pH, and ammonia nitrogen content, may be high. Similarly, the types of algae communities in different sub-areas may be different, because the light intensity in different sub-areas may be different, so the analysis of algae community types requires partition sampling analysis. The analysis of algae community types is to extract the feature data of the sub-area image for analysis, because the color, shape, etc. of different algae community types may be different. The method to determine the type of algae community is to match the feature data with the algae community type knowledge graph. The algae community type knowledge graph stores the feature data of all types of algae communities. The feature data matching is to calculate the Euclidean distance between the feature data. If the feature data of the algae community obtained by image analysis has the smallest Euclidean distance with the feature data in the algae community type knowledge graph, the type of algae community can be determined.

[0070] Furthermore, in a preferred embodiment of the present invention, the concentrations of different species of bacterial and algal communities in all target seawater pond sub-areas are determined, and the long short-term memory network prediction model is constructed in combination with the water quality data of different target seawater pond sub-areas, specifically:

[0071] Sampling bacterial and algal communities in all target seawater pond sub-areas to obtain bacterial and algal community samples, and obtaining fluorescent dyes, and using the fluorescent dyes to dye the bacterial and algal community samples to obtain bacterial and algal community fluorescent samples;

[0072] Obtaining the sampling volume of the bacterial and algal community fluorescence sample and obtaining a flow cytometer, introducing the bacterial and algal community fluorescence sample into the flow cytometer, and combining the sampling volume of the bacterial and algal community fluorescence sample and the bacterial and algal community species existing in different target seawater pond sub-areas to obtain the fluorescence intensity of different types of bacterial and algal communities;

[0073] In the bacterial and algal community fluorescence sample, the concentrations of the different types of bacterial and algal communities are obtained based on the fluorescence intensities of the different types of bacterial and algal communities, and the concentrations of the different types of bacterial and algal communities in the different target seawater pond sub-areas are determined based on the concentrations of the different types of bacterial and algal communities;

[0074] A time step for predicting water quality in a seawater pond is preset and calibrated as a type of time step. Based on the type of time step, the model layer number and the number of single-layer neurons with the highest frequency of use of the long short-term memory network model under the type of time step are retrieved in a big data network and calibrated as the target model layer number and the target single-layer neuron number;

[0075] Based on the target number of model layers and the target number of single-layer neurons, a long short-term memory network basic model is constructed, and the concentrations of different types of bacterial and algal communities in different target seawater pond sub-areas and water quality data of different target seawater pond sub-areas are imported into the long short-term memory network basic model for model training to obtain a long short-term memory network prediction model, which is a data model that can predict the water quality data of different target seawater pond sub-areas and the concentrations of different types of bacterial and algal communities within a class of time steps.

[0076] It should be noted that the long short-term memory network prediction model is a special recursive neural network that is specially designed to process and predict long-term dependency problems in sequence data. In this paper, the long short-term memory network prediction model is used to predict the water quality data and the growth of bacterial and algal communities in seawater ponds. After obtaining the types of bacterial and algal communities in different sub-areas, it is necessary to determine the concentrations of different types of bacterial and algal communities in different sub-areas. This can be determined by flow cytometry analysis. Before using flow cytometry for analysis, the bacterial and algal community samples need to be stained in order to distinguish different types of bacterial and algal communities based on fluorescence intensity. Flow cytometry is an instrument that can quickly detect and count cells of bacterial and algal community samples. Using flow cytometry, combined with the sampling volume of bacterial and algal community fluorescence samples and the types of bacterial and algal communities in different target seawater pond sub-areas, the fluorescence intensity of different bacterial and algal community fluorescence samples can be generated, and the concentration of different types of bacterial and algal communities can be determined by the intensity. The purpose of determining the time step is to determine the time period for prediction. The number of model layers and single-layer neurons required for water quality data prediction by the long short-term memory network prediction model at different time steps are different, so the target number of model layers and target number of single-layer neurons are determined according to the time step. A big data network is a network that stores various solutions. By entering conditions in the big data network, the required solution can be obtained. Based on the target number of model layers and target number of single-layer neurons, combined with the concentration of different bacterial and algal community species in different target seawater pond sub-areas, a long short-term memory network prediction model can be trained.

[0077] Figure 2 A flow chart of a method for evaluating and classifying aquaculture ecology and intelligently regulating aquaculture ecology of a target seawater pond is shown, comprising the following steps:

[0078] S202: analyzing the target seawater pond by using a long short-term memory network prediction model, and classifying the target seawater pond based on the analysis result;

[0079] S204: Tracing and isolating the pollution source of the seawater pond whose aquaculture ecology is to be optimized, and regulating the water quality of the seawater pond whose aquaculture ecology is to be optimized through target regulating equipment after tracing and isolating the pollution source;

[0080] S206: Analyze the species of bacterial and algal communities in the seawater pond with qualified water quality, and adjust the bacterial and algal communities in the seawater pond with qualified water quality based on the results of the bacterial and algal community analysis.

[0081] Furthermore, in a preferred embodiment of the present invention, the target seawater pond is analyzed by the long short-term memory network prediction model, and the target seawater pond is classified based on the analysis result, specifically:

[0082] Based on the long short-term memory network prediction model, the water quality data of different target seawater pond sub-areas within a time step and the concentration of different types of bacterial and algal communities are predicted and obtained, and the standard water quality data thresholds of different target seawater pond sub-areas within a time step and the standard concentration thresholds of different types of bacterial and algal communities are preset;

[0083] If, within a time step, the water quality data of all sub-areas of the target seawater pond remain within the standard water quality data threshold, and the concentrations of all types of bacterial and algal communities remain within the standard concentration threshold, the target seawater pond will be evaluated as a qualified seawater pond for aquaculture ecology;

[0084] If, within a certain time step, the water quality data of a sub-area of ​​the target seawater pond does not remain within the standard water quality data threshold, or the concentration of any type of bacterial and algal community does not remain within the standard concentration threshold, the target seawater pond will be evaluated as a seawater pond whose aquaculture ecology needs to be optimized, and an aquaculture ecology early warning signal will be generated in the target regulation equipment.

[0085] It should be noted that after the water quality data and the concentration of different types of algae communities in different target seawater pond sub-areas within a time step are predicted by the long short-term memory network prediction model, the water quality data and the concentration of different types of algae communities are analyzed. If the water quality data and the concentration of different types of algae communities are within the preset threshold, it proves that the seawater pond under the current aquaculture ecology will not aggravate the pollution, such as not making the pH of the water worse, and will not increase the concentration of algae communities, so the seawater pond is a qualified seawater pond for aquaculture ecology. If any of the water quality data and the concentration of different types of algae communities is not maintained within the preset threshold, it proves that the current water quality data and the concentration of algae communities will seriously affect the aquaculture ecology of the seawater pond, and adjustments need to be made to prevent the aquaculture ecology of the seawater pond from further deteriorating in the future. The target adjustment device will issue an aquaculture ecology warning signal when it detects abnormal water quality data and the concentration of different types of algae communities. When an aquaculture ecology warning signal is generated, water quality adjustment and algae community adjustment are required.

[0086] Furthermore, in a preferred embodiment of the present invention, the pollution source of the seawater pond to be optimized for aquaculture ecology is traced back and isolated, and after the pollution source is traced back and isolated, the water quality of the seawater pond to be optimized for aquaculture ecology is regulated by a target regulating device, specifically:

[0087] In the seawater pond where the aquaculture ecology is to be optimized, all water sources connected to the seawater pond where the aquaculture ecology is to be optimized are obtained and marked as water sources to be analyzed;

[0088] Sampling and testing all water sources to be analyzed, and determining whether there are water quality data of the water sources to be analyzed that are not within the preset threshold. If so, the corresponding water sources to be analyzed are marked as polluted water sources, and an isolation barrier is set at the connection between the polluted water source and the seawater pond to be optimized for aquaculture ecology, so that the seawater pond to be optimized for aquaculture ecology is not connected to the polluted water source;

[0089] In the seawater pond to be optimized for aquaculture ecology, a target seawater pond sub-region whose water quality data is not maintained within the standard water quality data threshold is marked as a seawater pond sub-region with abnormal water quality, and based on the water quality data of the seawater pond sub-region with abnormal water quality, the types of restoration microorganisms that can act on the seawater pond sub-region with abnormal water quality and can maintain the water quality data of the seawater pond sub-region with abnormal water quality within the standard water quality data threshold are retrieved in the big data network and marked as a type of restoration microorganisms;

[0090] Combine and analyze the water quality data of the abnormal water quality seawater pond sub-area and the first type of remediation microorganism to determine the release concentration of the first type of remediation microorganism, and release the first type of remediation microorganism in the abnormal water quality seawater pond sub-area with a concentration equal to the release concentration of the first type of remediation microorganism through the target adjustment device;

[0091] After a type of repair microorganism is released, a repair time is preset, and the repair rate of the type of repair microorganism is measured within the repair time. If the repair rate of the type of repair microorganism is less than the preset value, a chemical agent that improves the repair rate of the type of repair microorganism is searched in the big data network and marked as a target chemical agent;

[0092] The microorganism delivery device is controlled to deliver target chemical agents during the process of a type of repair microorganisms repairing a sub-area of ​​a seawater pond with abnormal water quality, so that the repair rate of the type of repair microorganisms is greater than a preset value, and the water quality data of the sub-area of ​​the seawater pond with abnormal water quality is maintained within the standard water quality data threshold, thereby obtaining a seawater pond with qualified water quality.

[0093] It should be noted that water quality regulation is required first for aquaculture ecological regulation of seawater ponds to be optimized. Water is the basis for the life of bacterial and algal communities. If the water quality data is poor, such as abnormal pH and high microbial content in the water, it will promote the growth of bacterial and algal communities and pollute the seawater pond environment. Before water quality regulation is performed on seawater ponds to be optimized, the pollution source needs to be isolated. Pollution sources include but are not limited to sewage treatment plants, chemical plants, etc. All water sources connected to seawater ponds may be pollution sources, so it is necessary to sample and test the water sources to be analyzed to determine whether their water quality data is within the predetermined range. If not, it is determined to be a pollution source. The method for isolating the pollution source from the seawater pond is to set up an isolation barrier. In the seawater pond, not all sub-areas have abnormal water quality data. There may be only some sub-areas with abnormal water quality data. Therefore, the sub-areas with abnormal water quality data are marked as sub-areas of seawater ponds with abnormal water quality, and according to the water quality data in the sub-areas of seawater ponds with abnormal water quality, microorganisms that can repair the sub-areas of seawater ponds with abnormal water quality are retrieved in the big data network, that is, a class of repair microorganisms. The first type of repair microorganisms can repair water quality. The principle is to degrade and adsorb organic pollutants and heavy metals to achieve water quality repair. A type of repair microorganism is released through a target regulating device. During the operation of the microorganism, the repair rate of the microorganism may be reduced due to environmental influences, such as water temperature. At this time, a catalyst is needed to increase the microbial repair rate, so that the water quality in the seawater pond is purified, and the water quality data of the seawater pond sub-area with abnormal water quality is maintained within the standard water quality data threshold. The water quality data of all the seawater pond sub-areas with abnormal water quality are normal, that is, a seawater pond with qualified water quality data is obtained, that is, a seawater pond with qualified water quality data.

[0094] Furthermore, in a preferred embodiment of the present invention, the bacterial and algal community species analysis is performed on the seawater pond with qualified water quality, and the bacterial and algal community is adjusted in the seawater pond with qualified water quality based on the bacterial and algal community species analysis result, specifically:

[0095] After obtaining a seawater pond with qualified water quality, determine whether there are still any types of bacterial and algal communities in the seawater pond with qualified water quality whose concentration is not maintained within the standard concentration threshold;

[0096] If not, the seawater pond with qualified water quality shall be calibrated as a seawater pond with qualified aquaculture ecology;

[0097] If so, the species of bacterial and algal communities whose concentrations in the seawater ponds with qualified water quality do not maintain the standard concentration threshold are marked as abnormal bacterial and algal community species, and all bacterial and algal community species that may cause damage to the aquaculture ecology of the seawater ponds are retrieved from the big data network;

[0098] Determine whether all the species of algae and bacteria that may damage the aquaculture ecology of the seawater pond include abnormal algae and bacteria. If so, mark the seawater pond with qualified water quality as a type of seawater pond to be optimized, and mark the target seawater pond sub-area where the algae and bacteria of the abnormal algae and bacteria exist in the type of seawater pond to be optimized as an abnormal algae and bacteria sub-area, and at the same time, enclose the abnormal algae and bacteria sub-area;

[0099] Retrieving an inhibitor that can inhibit bacterial and algal communities of abnormal bacterial and algal community types in a big data network, marking the inhibitor as an abnormal bacterial and algal community inhibitor, and using the abnormal bacterial and algal community inhibitor to perform bacterial and algal community inhibition treatment in a sub-area of ​​the bacterial and algal community abnormal seawater pond until there is no abnormal bacterial and algal community type in a type of seawater pond to be optimized;

[0100] When there is no abnormal bacterial and algal community species in the first type of seawater pond to be optimized, the enclosure of the sub-area of ​​the seawater pond with abnormal bacterial and algal community is released, and the first type of seawater pond to be optimized is marked as the second type of seawater pond to be optimized;

[0101] A filtering device and an air flotation device are introduced into the second type of seawater pond to be optimized. The air flotation device is used to perform pressurized dissolved air treatment in the second type of seawater pond to be optimized, so that all bacterial and algal communities in the second type of seawater pond to be optimized float to the water surface. The bacterial and algal communities floating to the water surface are filtered by the filtering device, so that the concentrations of all types of bacterial and algal communities in the second type of seawater pond to be optimized are maintained within the standard concentration threshold, thereby obtaining a seawater pond with qualified aquaculture ecology.

[0102] It should be noted that after the water quality of the seawater pond is adjusted, the concentration of the algae community in the seawater pond may decrease. If the decrease is within the preset value, there is no need to treat the algae community temporarily, and it can be adjusted by the self-repair ability of the seawater pond. If the concentration of the algae community is still greater than the preset value, the seawater pond needs to be treated with algae communities. Different types of algae communities in seawater ponds require different adjustment methods. If the algae community in the seawater pond is a species that should not appear in the seawater pond, that is, an alien species, the algae community may seriously affect the ecological environment of the seawater pond. Therefore, when there are algae communities of abnormal algae community types in the seawater pond, it is necessary to first treat the algae communities of abnormal algae community types. The treatment method is to first enclose the area containing the algae community of abnormal algae community types to ensure that the algae community does not affect other areas, and to treat the algae community of abnormal algae community types with inhibitors to ensure that they do not grow all the time. After inhibiting the growth, since the bacterial and algal communities in the seawater pond may float on the water surface or be located deeper in the water, it is necessary to pressurize the dissolved air in the water through flotation equipment to bring the bacterial and algal communities to the surface, and then filter them through filtration equipment to ensure that the concentrations of all types of bacterial and algal communities are maintained within the standard concentration threshold, thereby obtaining a seawater pond with qualified aquaculture ecology.

[0103] In addition, the method for intelligently regulating the aquaculture ecology of bacterial and algal communities in seawater ponds further comprises the following steps:

[0104] If the seawater pond with qualified water quality is calibrated as a type of seawater pond to be optimized, a fish finder is introduced into the seawater pond sub-region with abnormal bacterial and algal communities of the type of seawater pond to be optimized, and a sonar signal is emitted to the seawater pond sub-region with abnormal bacterial and algal communities through the fish finder;

[0105] Controlling the fish finder to receive the sonar signal reflected by the abnormal seawater pond sub-region of the bacterial and algal community, calibrating it as a reflected sonar signal, and performing signal preprocessing on the reflected sonar signal to obtain the reflected sonar signal after signal preprocessing;

[0106] Based on the reflected sonar signal after the signal preprocessing, a sonar image of the abnormal seawater pond sub-area of ​​the bacterial and algal community is generated in the image generation software and marked as a target sonar image;

[0107] Determine all biological species existing in a type of seawater pond to be optimized, obtain image features of all biological species existing in a type of seawater pond to be optimized, and construct a biological species knowledge graph based on the image features of all biological species existing in the type of seawater pond to be optimized;

[0108] Importing the target sonar image into the biological species knowledge graph for comparison, determining the biological species in the sub-area of ​​the abnormal seawater pond with bacterial and algal communities, and marking them as target biological species;

[0109] In the big data network, based on the target biological species, a scheme for inducing the flow of the target biological species is retrieved and marked as an luring scheme. Before using the abnormal bacterial and algal community inhibitor to perform bacterial and algal community inhibition treatment in the bacterial and algal community abnormal seawater pond sub-area, the luring scheme is executed to make the organisms in the bacterial and algal community abnormal seawater pond sub-area leave the bacterial and algal community abnormal seawater pond sub-area.

[0110] It should be noted that before using the abnormal algae community inhibitor to perform algae community inhibition treatment in the algae community abnormal seawater pond sub-area, it is necessary to perform biological expulsion, such as fish expulsion, in the algae community abnormal seawater pond sub-area, because the inhibitor may cause damage to the organisms, causing the organisms to become ill, thereby affecting economic benefits, and may even affect the organisms in other sub-areas. Different organisms have different luring schemes, so it is necessary to determine the species of the organisms and then determine the luring scheme. The method for determining the species of organisms can use a fish finder to perform sonar identification in the sub-area and construct a sonar image. After the sonar signal is reflected back, there may be excessive noise, so signal preprocessing is required. The signal preprocessing includes but is not limited to wavelet decomposition and graying of the signal. After obtaining the sonar image, there is image feature data of the organism in the sonar image, and then the type of the organism can be determined by comparing it with the biological species knowledge map, thereby determining the luring scheme.

[0111] like Figure 3 As shown, the second aspect of the present invention also provides an aquaculture ecological intelligent regulation system for bacterial and algal communities in seawater ponds, the aquaculture ecological intelligent regulation system comprising a memory 31 and a processor 32, the memory 31 stores an aquaculture ecological intelligent regulation method, and when the aquaculture ecological intelligent regulation method is executed by the processor 32, the following steps are implemented:

[0112] Divide the ponds into different zones and conduct water quality sampling and assessment of bacterial and algal community species in the ponds in different zones;

[0113] Determine the concentration of different bacterial and algal community species in all target seawater pond sub-areas, and build a long-short-term memory network prediction model based on the water quality data of different target seawater pond sub-areas;

[0114] The aquaculture ecology of the target seawater pond is evaluated and classified through the long short-term memory network prediction model, and the aquaculture ecology of the target seawater pond is intelligently adjusted based on the aquaculture ecology evaluation and classification results.

[0115] 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 who is familiar with the technical field 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. A method for intelligently regulating the aquaculture ecology of bacterial and algal communities in seawater ponds, characterized in that: The following steps are involved: Divide the ponds into different zones and conduct water quality sampling and assessment of bacterial and algal community species in the ponds in different zones; Determine the concentration of different bacterial and algal community species in all target seawater pond sub-areas, and build a long-short-term memory network prediction model based on the water quality data of different target seawater pond sub-areas; The aquaculture ecology of the target seawater ponds is evaluated and classified through the long short-term memory network prediction model, and the aquaculture ecology of the target seawater ponds is intelligently adjusted based on the aquaculture ecology evaluation and classification results; The aquaculture ecology of the target seawater pond is evaluated and classified by the long short-term memory network prediction model, and the aquaculture ecology of the target seawater pond is intelligently adjusted based on the aquaculture ecology evaluation and classification results, specifically: Based on the long short-term memory network prediction model, the water quality data of different target seawater pond sub-areas within a time step and the concentration of different types of bacterial and algal communities are predicted and obtained, and the standard water quality data thresholds of different target seawater pond sub-areas within a time step and the standard concentration thresholds of different types of bacterial and algal communities are preset; If, within a time step, the water quality data of all sub-areas of the target seawater pond remain within the standard water quality data threshold, and the concentrations of all types of bacterial and algal communities remain within the standard concentration threshold, the target seawater pond will be evaluated as a qualified seawater pond for aquaculture ecology; If, within a time step, the water quality data of the sub-area of ​​the target seawater pond does not remain within the standard water quality data threshold, or the concentration of any type of bacterial and algal community does not remain within the standard concentration threshold, the target seawater pond will be evaluated as a seawater pond for aquaculture ecology to be optimized, and an aquaculture ecology early warning signal will be generated in the target regulation device; When an aquaculture ecology early warning signal is generated in the target regulating device, the pollution source of the seawater pond to be optimized for aquaculture ecology is traced and isolated, and after the pollution source is traced and isolated, the water quality of the seawater pond to be optimized for aquaculture ecology is regulated through the target regulating device; The method of isolating the pollution source of the seawater pond whose aquaculture ecology is to be optimized and regulating the water quality of the seawater pond whose aquaculture ecology is to be optimized through target regulating equipment after tracing and isolating the pollution source is specifically as follows: In the seawater pond where the aquaculture ecology is to be optimized, all water sources connected to the seawater pond where the aquaculture ecology is to be optimized are obtained and marked as water sources to be analyzed; Sampling and testing all water sources to be analyzed, and determining whether there are water quality data of the water sources to be analyzed that are not within the preset threshold. If so, the corresponding water sources to be analyzed are marked as polluted water sources, and an isolation barrier is set at the connection between the polluted water source and the seawater pond to be optimized for aquaculture ecology, so that the seawater pond to be optimized for aquaculture ecology is not connected to the polluted water source; In the seawater pond to be optimized for aquaculture ecology, a target seawater pond sub-region whose water quality data is not maintained within the standard water quality data threshold is marked as a seawater pond sub-region with abnormal water quality, and based on the water quality data of the seawater pond sub-region with abnormal water quality, the types of restoration microorganisms that can act on the seawater pond sub-region with abnormal water quality and can maintain the water quality data of the seawater pond sub-region with abnormal water quality within the standard water quality data threshold are retrieved in the big data network and marked as a type of restoration microorganisms; Combine and analyze the water quality data of the abnormal water quality seawater pond sub-area and the first type of remediation microorganism to determine the release concentration of the first type of remediation microorganism, and release the first type of remediation microorganism in the abnormal water quality seawater pond sub-area with a concentration equal to the release concentration of the first type of remediation microorganism through the target adjustment device; After a type of repair microorganism is released, a repair time is preset, and the repair rate of the type of repair microorganism is measured within the repair time. If the repair rate of the type of repair microorganism is less than the preset value, a chemical agent that improves the repair rate of the type of repair microorganism is searched in the big data network and marked as a target chemical agent; Control the microorganism delivery device to deliver the target chemical agent during the process of the first type of repair microorganisms repairing the sub-area of ​​the seawater pond with abnormal water quality, so that the repair rate of the first type of repair microorganisms is greater than a preset value, and the water quality data of the sub-area of ​​the seawater pond with abnormal water quality is maintained within the standard water quality data threshold, so as to obtain a seawater pond with qualified water quality; Conduct bacterial and algal community species analysis on seawater ponds with qualified water quality, and adjust bacterial and algal community in seawater ponds with qualified water quality based on the results of bacterial and algal community species analysis; The method of analyzing the species of bacterial and algal communities in the seawater ponds with qualified water quality and adjusting the bacterial and algal communities in the seawater ponds with qualified water quality based on the results of the bacterial and algal community analysis is specifically as follows: After obtaining a seawater pond with qualified water quality, determine whether there are still any types of bacterial and algal communities in the seawater pond with qualified water quality whose concentration is not maintained within the standard concentration threshold; If not, the seawater pond with qualified water quality shall be calibrated as a seawater pond with qualified aquaculture ecology; If so, the species of bacterial and algal communities whose concentrations in the seawater ponds with qualified water quality do not maintain the standard concentration threshold are marked as abnormal bacterial and algal community species, and all bacterial and algal community species that may cause damage to the aquaculture ecology of the seawater ponds are retrieved from the big data network; Determine whether all the species of algae and bacteria that may damage the aquaculture ecology of the seawater pond include abnormal algae and bacteria. If so, mark the seawater pond with qualified water quality as a type of seawater pond to be optimized, and mark the target seawater pond sub-area where the algae and bacteria of the abnormal algae and bacteria exist in the type of seawater pond to be optimized as an abnormal algae and bacteria sub-area, and at the same time, enclose the abnormal algae and bacteria sub-area; Retrieving an inhibitor that can inhibit bacterial and algal communities of abnormal bacterial and algal community types in a big data network, marking the inhibitor as an abnormal bacterial and algal community inhibitor, and using the abnormal bacterial and algal community inhibitor to perform bacterial and algal community inhibition treatment in a sub-area of ​​the bacterial and algal community abnormal seawater pond until there is no abnormal bacterial and algal community type in a type of seawater pond to be optimized; When there is no abnormal bacterial and algal community species in the first type of seawater pond to be optimized, the enclosure of the sub-area of ​​the seawater pond with abnormal bacterial and algal community is released, and the first type of seawater pond to be optimized is marked as the second type of seawater pond to be optimized; A filtering device and an air flotation device are introduced into the second type of seawater pond to be optimized. The air flotation device is used to perform pressurized dissolved air treatment in the second type of seawater pond to be optimized, so that all bacterial and algal communities in the second type of seawater pond to be optimized float to the water surface. The bacterial and algal communities floating to the water surface are filtered by the filtering device, so that the concentrations of all types of bacterial and algal communities in the second type of seawater pond to be optimized are maintained within the standard concentration threshold, thereby obtaining a seawater pond with qualified aquaculture ecology.

2. According to the method for intelligently regulating the aquaculture ecology of bacteria and algae communities in seawater ponds as described in claim 1, it is characterized in that: The method of dividing the seawater pond into different zones and conducting water quality sampling and testing and bacterial and algal community species assessment in the seawater ponds in different zones is as follows: Marking the seawater pond that needs to be regulated for aquaculture ecology as the target seawater pond, and obtaining the area and shape of the target seawater pond; A device for intelligently regulating the aquaculture ecology of a target seawater pond is obtained and calibrated as a target regulating device, wherein a camera for image acquisition is inherited in the target regulating device and calibrated as a target camera; Acquire specification parameters of a target camera, wherein the specification parameters of the target camera include an image acquisition range of the target camera; Analyze the area and shape of the target seawater pond to obtain all partitioning schemes of the target seawater pond, analyze all the partitioning schemes of the target seawater pond, select a partitioning scheme in which all sub-areas of the target seawater pond after partitioning are smaller than the image acquisition range of the target camera, and mark it as the target partitioning scheme; Based on the target partitioning scheme, the target seawater pond is partitioned to obtain target seawater pond sub-areas, a water quality testing device is obtained, water samples are extracted from all target seawater pond sub-areas, and the water samples extracted from different target seawater pond sub-areas are introduced into the water quality testing device for water quality testing to obtain water quality data of different target seawater pond sub-areas; Using a target camera to perform bacterial and algal community image recognition in different target seawater pond sub-areas to obtain bacterial and algal community images, performing image preprocessing and image feature extraction processing on the bacterial and algal community images to obtain bacterial and algal community feature data of different target seawater pond sub-areas; Acquire a big data network, and retrieve a bacterial and algal community knowledge graph in the big data network, wherein the bacterial and algal community knowledge graph stores characteristic data of different types of bacterial and algal communities; The characteristic data of bacterial and algal communities in different target seawater pond sub-areas were imported into the bacterial and algal community knowledge graph for characteristic data matching analysis. Based on the characteristic data matching analysis results, the types of bacterial and algal communities existing in different target seawater pond sub-areas were determined respectively.

3. According to the method for intelligently regulating the aquaculture ecology of bacteria and algae communities in seawater ponds as described in claim 1, it is characterized in that: The concentrations of different bacterial and algal community species in all target seawater pond sub-areas are determined, and the long-short-term memory network prediction model is constructed in combination with the water quality data of different target seawater pond sub-areas, specifically: Sampling bacterial and algal communities in all target seawater pond sub-areas to obtain bacterial and algal community samples, and obtaining fluorescent dyes, and using the fluorescent dyes to dye the bacterial and algal community samples to obtain bacterial and algal community fluorescent samples; Obtaining the sampling volume of the bacterial and algal community fluorescence sample and obtaining a flow cytometer, introducing the bacterial and algal community fluorescence sample into the flow cytometer, and combining the sampling volume of the bacterial and algal community fluorescence sample and the bacterial and algal community species existing in different target seawater pond sub-areas to obtain the fluorescence intensity of different types of bacterial and algal communities; In the bacterial and algal community fluorescence sample, the concentrations of the different types of bacterial and algal communities are obtained based on the fluorescence intensities of the different types of bacterial and algal communities, and the concentrations of the different types of bacterial and algal communities in the different target seawater pond sub-areas are determined based on the concentrations of the different types of bacterial and algal communities; A time step for predicting water quality in a seawater pond is preset and calibrated as a type of time step. Based on the type of time step, the model layer number and the number of single-layer neurons with the highest frequency of use of the long short-term memory network model under the type of time step are retrieved in a big data network and calibrated as the target model layer number and the target single-layer neuron number; Based on the target number of model layers and the target number of single-layer neurons, a long short-term memory network basic model is constructed, and the concentrations of different types of bacterial and algal communities in different target seawater pond sub-areas and water quality data of different target seawater pond sub-areas are imported into the long short-term memory network basic model for model training to obtain a long short-term memory network prediction model, which is a data model that can predict the water quality data of different target seawater pond sub-areas and the concentrations of different types of bacterial and algal communities within a class of time steps.

4. An intelligent regulation system for the cultivation of bacterial and algal communities in seawater ponds, characterized in that: The aquaculture ecological intelligent regulation system comprises a memory and a processor, wherein the memory stores an aquaculture ecological intelligent regulation method program, and when the aquaculture ecological intelligent regulation method program is executed by the processor, the aquaculture ecological intelligent regulation method steps as described in any one of claims 1 to 3 are implemented: Divide the ponds into different zones and conduct water quality sampling and assessment of bacterial and algal community species in the ponds in different zones; Determine the concentration of different bacterial and algal community species in all target seawater pond sub-areas, and build a long-short-term memory network prediction model based on the water quality data of different target seawater pond sub-areas; The aquaculture ecology of the target seawater ponds is evaluated and classified through the long short-term memory network prediction model, and the aquaculture ecology of the target seawater ponds is intelligently adjusted based on the aquaculture ecology evaluation and classification results; The aquaculture ecology of the target seawater pond is evaluated and classified by the long short-term memory network prediction model, and the aquaculture ecology of the target seawater pond is intelligently adjusted based on the aquaculture ecology evaluation and classification results, specifically: Based on the long short-term memory network prediction model, the water quality data of different target seawater pond sub-areas within a time step and the concentration of different types of bacterial and algal communities are predicted and obtained, and the standard water quality data thresholds of different target seawater pond sub-areas within a time step and the standard concentration thresholds of different types of bacterial and algal communities are preset; If, within a time step, the water quality data of all sub-areas of the target seawater pond remain within the standard water quality data threshold, and the concentrations of all types of bacterial and algal communities remain within the standard concentration threshold, the target seawater pond will be evaluated as a qualified seawater pond for aquaculture ecology; If, within a time step, the water quality data of the sub-area of ​​the target seawater pond does not remain within the standard water quality data threshold, or the concentration of any type of bacterial and algal community does not remain within the standard concentration threshold, the target seawater pond will be evaluated as a seawater pond for aquaculture ecology to be optimized, and an aquaculture ecology early warning signal will be generated in the target regulation device; When an aquaculture ecology early warning signal is generated in the target regulating device, the pollution source of the seawater pond to be optimized for aquaculture ecology is traced and isolated, and after the pollution source is traced and isolated, the water quality of the seawater pond to be optimized for aquaculture ecology is regulated through the target regulating device; The method of isolating the pollution source of the seawater pond whose aquaculture ecology is to be optimized and regulating the water quality of the seawater pond whose aquaculture ecology is to be optimized through target regulating equipment after tracing and isolating the pollution source is specifically as follows: In the seawater pond where the aquaculture ecology is to be optimized, all water sources connected to the seawater pond where the aquaculture ecology is to be optimized are obtained and marked as water sources to be analyzed; Sampling and testing all water sources to be analyzed, and determining whether there are water quality data of the water sources to be analyzed that are not within the preset threshold. If so, the corresponding water sources to be analyzed are marked as polluted water sources, and an isolation barrier is set at the connection between the polluted water source and the seawater pond to be optimized for aquaculture ecology, so that the seawater pond to be optimized for aquaculture ecology is not connected to the polluted water source; In the seawater pond to be optimized for aquaculture ecology, a target seawater pond sub-region whose water quality data is not maintained within the standard water quality data threshold is marked as a seawater pond sub-region with abnormal water quality, and based on the water quality data of the seawater pond sub-region with abnormal water quality, the types of restoration microorganisms that can act on the seawater pond sub-region with abnormal water quality and can maintain the water quality data of the seawater pond sub-region with abnormal water quality within the standard water quality data threshold are retrieved in the big data network and marked as a type of restoration microorganisms; Combine and analyze the water quality data of the abnormal water quality seawater pond sub-area and the first type of remediation microorganism to determine the release concentration of the first type of remediation microorganism, and release the first type of remediation microorganism in the abnormal water quality seawater pond sub-area with a concentration equal to the release concentration of the first type of remediation microorganism through the target adjustment device; After a type of repair microorganism is released, a repair time is preset, and the repair rate of the type of repair microorganism is measured within the repair time. If the repair rate of the type of repair microorganism is less than the preset value, a chemical agent that improves the repair rate of the type of repair microorganism is searched in the big data network and marked as a target chemical agent; Control the microorganism delivery device to deliver the target chemical agent during the process of the first type of repair microorganisms repairing the sub-area of ​​the seawater pond with abnormal water quality, so that the repair rate of the first type of repair microorganisms is greater than a preset value, and the water quality data of the sub-area of ​​the seawater pond with abnormal water quality is maintained within the standard water quality data threshold, so as to obtain a seawater pond with qualified water quality; Conduct bacterial and algal community species analysis on seawater ponds with qualified water quality, and adjust bacterial and algal community in seawater ponds with qualified water quality based on the results of bacterial and algal community species analysis; The method of analyzing the species of bacterial and algal communities in the seawater ponds with qualified water quality and adjusting the bacterial and algal communities in the seawater ponds with qualified water quality based on the results of the bacterial and algal community analysis is specifically as follows: After obtaining a seawater pond with qualified water quality, determine whether there are still any types of bacterial and algal communities in the seawater pond with qualified water quality whose concentration is not maintained within the standard concentration threshold; If not, the seawater pond with qualified water quality shall be calibrated as a seawater pond with qualified aquaculture ecology; If so, the species of bacterial and algal communities whose concentrations in the seawater ponds with qualified water quality do not maintain the standard concentration threshold are marked as abnormal bacterial and algal community species, and all bacterial and algal community species that may cause damage to the aquaculture ecology of the seawater ponds are retrieved from the big data network; Determine whether all the species of algae and bacteria that may damage the aquaculture ecology of the seawater pond include abnormal algae and bacteria. If so, mark the seawater pond with qualified water quality as a type of seawater pond to be optimized, and mark the target seawater pond sub-area where the algae and bacteria of the abnormal algae and bacteria exist in the type of seawater pond to be optimized as an abnormal algae and bacteria sub-area, and at the same time, enclose the abnormal algae and bacteria sub-area; Retrieving an inhibitor that can inhibit bacterial and algal communities of abnormal bacterial and algal community types in a big data network, marking the inhibitor as an abnormal bacterial and algal community inhibitor, and using the abnormal bacterial and algal community inhibitor to perform bacterial and algal community inhibition treatment in a sub-area of ​​the bacterial and algal community abnormal seawater pond until there is no abnormal bacterial and algal community type in a type of seawater pond to be optimized; When there is no abnormal bacterial and algal community species in the first type of seawater pond to be optimized, the enclosure of the sub-area of ​​the seawater pond with abnormal bacterial and algal community is released, and the first type of seawater pond to be optimized is marked as the second type of seawater pond to be optimized; A filtering device and an air flotation device are introduced into the second type of seawater pond to be optimized. The air flotation device is used to perform pressurized dissolved air treatment in the second type of seawater pond to be optimized, so that all bacterial and algal communities in the second type of seawater pond to be optimized float to the water surface. The bacterial and algal communities floating to the water surface are filtered by the filtering device, so that the concentrations of all types of bacterial and algal communities in the second type of seawater pond to be optimized are maintained within the standard concentration threshold, thereby obtaining a seawater pond with qualified aquaculture ecology.