Breeding water source water quality evaluation and planning method and system and storage medium

Abstract

The invention relates to a cultivation water source water quality evaluation and planning method and system and a storage medium, and belongs to the technical field of water source water quality evaluation.The method comprises the steps that water quality characteristic data information of each cultivation water source within preset time is recognized according to a water quality characteristic tracking model, and an abnormal cultivation water source is obtained; the method comprises the following steps: evaluating water quality characteristic data information of abnormal culture water sources to obtain a harmfulness evaluation membership degree of each abnormal culture water source, and obtaining culture water quantity data information required by aquaculture and fishery resources; and related planning information is generated based on the harmfulness evaluation membership degree of the abnormal culture water source and the culture water volume data information of the aquaculture and fishery resource demand, and planning is performed according to the related planning information. According to the method, the harmfulness of the culture water source is evaluated and monitored, so that the quoted water source is planned according to the harmfulness membership degree, the abnormal condition of the culture water source is found in time, and the planning rationality of culture can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water source quality evaluation, and in particular to a method, system and storage medium for evaluating and planning the quality of aquaculture water sources. Background Art

[0002] Aquaculture water is the habitat of aquatic animals, and water quality directly impacts the yield and quality of these animals. Regular water quality monitoring is essential during aquaculture, allowing farmers to make timely adjustments when water quality deteriorates, thereby reducing aquatic animal mortality and avoiding significant economic losses. In reality, some aquaculture areas maintain normal aquaculture water quality by diverting water from the aquaculture source to the aquaculture area. However, when the water quality of the aquaculture source deteriorates, it will affect the aquaculture water environment. If not detected in time, it will result in significant losses for farmers. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method, system and storage medium for evaluating and planning the quality of aquaculture water sources.

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

[0005] A first aspect of the present invention provides a method for evaluating and planning the quality of aquaculture water sources, comprising the following steps:

[0006] Acquire historical water quality anomaly characteristic data information of aquaculture water sources, and construct a water quality characteristic tracking model based on the historical water quality anomaly characteristic data information of aquaculture water sources, and track the water quality characteristics of each current aquaculture water source through the water quality characteristic tracking model;

[0007] Acquire water quality characteristic data information of each aquaculture water source within a preset time, identify the water quality characteristic data information of each aquaculture water source within the preset time according to the water quality characteristic tracking model, and acquire abnormal aquaculture water sources;

[0008] By evaluating the water quality characteristic data information of the abnormal aquaculture water source, obtaining the hazard evaluation membership of each abnormal aquaculture water source, and obtaining the aquaculture water quantity data information required by aquatic fishery resources;

[0009] Relevant planning information is generated based on the hazard assessment membership of the abnormal aquaculture water source and the aquaculture water volume data information required for aquatic fishery resources, and planning is carried out according to the relevant planning information.

[0010] Furthermore, in this method, the historical water quality abnormality characteristic data information of the aquaculture water source is obtained, specifically including:

[0011] Acquire historical water quality characteristic data information of aquaculture water sources, construct retrieval tags based on the historical water quality characteristic data information of aquaculture water sources, and perform a search through big data based on the retrieval tags to obtain relevant aquaculture abnormal event information;

[0012] Introducing a grey correlation analysis method to calculate the correlation degree information between the historical water quality characteristic data information of the aquaculture water source and the related aquaculture abnormal event information;

[0013] Determining whether the correlation degree information is greater than a preset correlation degree information, and when the correlation degree information is greater than the preset correlation degree information, using the water quality characteristic data information corresponding to the related aquaculture abnormal event information as the water quality abnormality characteristic data information;

[0014] Based on the water quality abnormality characteristic data information, historical water quality abnormality characteristic data information of the aquaculture water source is constructed, and the historical water quality abnormality characteristic data information of the aquaculture water source is output.

[0015] Furthermore, in this method, a water quality characteristic tracking model is constructed based on the historical water quality abnormality characteristic data information of the aquaculture water source, and the water quality characteristics of each current aquaculture water source are tracked by the water quality characteristic tracking model, specifically including:

[0016] Obtaining fishery resource data information of the current aquaculture area, and obtaining water quality anomaly feature data set information related to the fishery resource data information of the current aquaculture area based on the historical water quality anomaly feature data information of the aquaculture water source, and introducing a graph neural network;

[0017] Using the fishery resource data information of the current aquaculture area as the first graph node of the graph neural network, and using the water quality abnormality feature data set information related to the fishery resource data information of the current aquaculture area as the second graph node of the graph neural network;

[0018] Constructing an adjacency matrix based on the first graph nodes and the second graph nodes, calculating the Manhattan distances between the second graph nodes in the adjacency matrix using a Manhattan distance algorithm, obtaining second graph nodes with the same Manhattan distances, fusing the second graph nodes with the same Manhattan distances into one second graph node, and updating the adjacency matrix;

[0019] A water quality feature tracking model is constructed based on a deep neural network, and the adjacency matrix is ​​input into the water quality feature tracking model for training. After the training is completed, the water quality features of each current aquaculture water source are tracked by the water quality feature tracking model.

[0020] Furthermore, in this method, water quality characteristic data information of each aquaculture water source within a preset time is obtained, and the water quality characteristic data information of each aquaculture water source within the preset time is identified according to the water quality characteristic tracking model to obtain abnormal aquaculture water sources, specifically including:

[0021] Acquire water quality characteristic data information of each aquaculture water source within a preset time, and input the water quality characteristic data information of each aquaculture water source within the preset time into the water quality characteristic tracking model for identification, and obtain an identification result;

[0022] determining whether the recognition result is a preset recognition result, and when the recognition result is the preset recognition result, treating the aquaculture water source corresponding to the preset recognition result as an abnormal aquaculture water source;

[0023] When the recognition result is not a preset recognition result, the aquaculture water source corresponding to the recognition result that is not a preset recognition result is regarded as a normal aquaculture water source, and the abnormal aquaculture water source is output.

[0024] Furthermore, in this method, by evaluating the water quality characteristic data information of the abnormal aquaculture water source, the hazard evaluation membership of each abnormal aquaculture water source is obtained, which specifically includes:

[0025] A decision tree algorithm is introduced, and several hazard membership threshold standards are set. A root node is generated according to the water quality characteristic data information of the abnormal aquaculture water source, and the root node is initialized and split based on the hazard membership threshold standards to generate several leaf nodes.

[0026] Determining whether there is only one sample data of the harmfulness membership threshold standard in the leaf node, and outputting the leaf node when there is only one sample data of the harmfulness membership threshold standard in the leaf node;

[0027] When more than one sample data of the harmfulness membership threshold standard exists in the leaf node, the leaf node is continuously split until only one sample data of the harmfulness membership threshold standard exists in the leaf node, and the corresponding leaf node is output;

[0028] The hazard evaluation membership of the aquaculture water source corresponding to the leaf node is obtained, and the hazard evaluation membership of the aquaculture water source corresponding to the leaf node is counted to generate the hazard evaluation membership of each abnormal aquaculture water source.

[0029] Furthermore, in this method, relevant planning information is generated based on the hazard assessment membership of the abnormal aquaculture water source and the aquaculture water quantity data information required by aquatic fishery resources, and planning is performed according to the relevant planning information, specifically including:

[0030] Determining whether the hazard assessment membership of the abnormal aquaculture water source is greater than a preset hazard assessment membership; when the hazard assessment membership of the abnormal aquaculture water source is greater than the preset hazard assessment membership, treating the corresponding aquaculture water source as a non-drainage water source;

[0031] When the hazard assessment membership of the abnormal aquaculture water source is not greater than the preset hazard assessment membership, the corresponding aquaculture water source is used as a drainage water source, and a genetic algorithm is introduced to obtain safe water level data information of each drainage water source;

[0032] Initializing the water volume information of each drainage water source, using the safe water level data information of each drainage water source as a constraint condition, inputting the water volume information of each drainage water source and the aquaculture water volume data information required by aquatic fishery resources into the genetic algorithm for calculation;

[0033] When the water volume information of each diversion water source meets the constraint condition, the water volume information of each diversion water source is output, relevant planning information is generated according to the water volume information of each diversion water source, and planning is performed according to the relevant planning information.

[0034] A second aspect of the present invention provides an aquaculture water source quality evaluation and planning system, the system comprising a memory and a processor, the memory comprising an aquaculture water source quality evaluation and planning method program, and when the aquaculture water source quality evaluation and planning method program is executed by the processor, the following steps are implemented:

[0035] Acquire historical water quality anomaly characteristic data information of aquaculture water sources, and construct a water quality characteristic tracking model based on the historical water quality anomaly characteristic data information of aquaculture water sources, and track the water quality characteristics of each current aquaculture water source through the water quality characteristic tracking model;

[0036] Acquire water quality characteristic data information of each aquaculture water source within a preset time, identify the water quality characteristic data information of each aquaculture water source within the preset time according to the water quality characteristic tracking model, and acquire abnormal aquaculture water sources;

[0037] By evaluating the water quality characteristic data information of the abnormal aquaculture water source, obtaining the hazard evaluation membership of each abnormal aquaculture water source, and obtaining the aquaculture water quantity data information required by aquatic fishery resources;

[0038] Relevant planning information is generated based on the hazard assessment membership of the abnormal aquaculture water source and the aquaculture water volume data information required for aquatic fishery resources, and planning is carried out according to the relevant planning information.

[0039] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for evaluating and planning the water quality of an aquaculture water source. When the program for evaluating and planning the water quality of an aquaculture water source is executed by a processor, the steps of any one of the methods for evaluating and planning the water quality of an aquaculture water source are implemented.

[0040] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0041] The present invention obtains historical water quality anomaly characteristic data information of aquaculture water sources, and constructs a water quality characteristic tracking model based on the historical water quality anomaly characteristic data information of aquaculture water sources. The water quality characteristic tracking model is used to track the water quality characteristics of each current aquaculture water source, thereby obtaining the water quality characteristic data information of each aquaculture water source within a preset time. The water quality characteristic data information of each aquaculture water source within a preset time is identified according to the water quality characteristic tracking model, and abnormal aquaculture water sources are obtained. Then, the water quality characteristic data information of the abnormal aquaculture water sources is evaluated, and the hazard evaluation membership of each abnormal aquaculture water source is obtained. The aquaculture water quantity data information required by aquatic fishery resources is obtained. Finally, relevant planning information is generated based on the hazard evaluation membership of the abnormal aquaculture water source and the aquaculture water quantity data information required by aquatic fishery resources, and planning is performed according to the relevant planning information. The present invention evaluates and monitors the hazard of aquaculture water sources, thereby planning the reference water source according to the hazard membership and timely discovering the abnormality of the aquaculture water source, which can improve the rationality of aquaculture planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0043] Figure 1 A flow chart showing an overall method of aquaculture water source quality assessment and planning method is shown;

[0044] Figure 2 A first method flow chart of a method for evaluating and planning aquaculture water quality is shown;

[0045] Figure 3 A second method flow chart of a method for evaluating and planning aquaculture water quality is shown;

[0046] Figure 4 Shown is a system block diagram of an aquaculture water source quality evaluation and planning system. DETAILED DESCRIPTION

[0047] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0049] like Figure 1 As shown, the first aspect of the present invention provides a method for evaluating and planning the water quality of an aquaculture water source, comprising the following steps:

[0050] S102: Obtain historical water quality anomaly characteristic data information of aquaculture water sources, and construct a water quality characteristic tracking model based on the historical water quality anomaly characteristic data information of aquaculture water sources, and track the water quality characteristics of each current aquaculture water source through the water quality characteristic tracking model;

[0051] S104: Obtaining water quality characteristic data information of each aquaculture water source within a preset time, identifying the water quality characteristic data information of each aquaculture water source within the preset time according to the water quality characteristic tracking model, and obtaining abnormal aquaculture water sources;

[0052] S106: Evaluate the water quality characteristic data of the abnormal aquaculture water source to obtain the hazard evaluation membership of each abnormal aquaculture water source, and obtain the aquaculture water quantity data information required by aquatic fishery resources;

[0053] S108: Generate relevant planning information based on the hazard assessment affiliation of abnormal aquaculture water sources and aquaculture water volume data information required for aquatic fishery resources, and carry out planning based on the relevant planning information.

[0054] It should be noted that the present invention can improve the rationality of aquaculture planning by evaluating and monitoring the hazard of aquaculture water sources, thereby planning the water sources based on the hazard affiliation and timely discovering abnormal conditions of aquaculture water sources.

[0055] like Figure 2 As shown, further, in this method, the historical water quality abnormality characteristic data information of the aquaculture water source is obtained, specifically including:

[0056] S202: Obtain historical water quality characteristic data information of the aquaculture water source, construct a search tag based on the historical water quality characteristic data information of the aquaculture water source, and search through big data based on the search tag to obtain relevant aquaculture abnormal event information;

[0057] S204: Introducing a grey correlation analysis method to calculate the correlation between the historical water quality characteristic data information of the aquaculture water source and the related aquaculture abnormal event information;

[0058] S206: Determine whether the correlation degree information is greater than the preset correlation degree information. If the correlation degree information is greater than the preset correlation degree information, use the water quality characteristic data information corresponding to the related aquaculture abnormal event information as the water quality abnormality characteristic data information.

[0059] S208: Constructing historical water quality abnormality characteristic data information of the aquaculture water source based on the water quality abnormality characteristic data information, and outputting the historical water quality abnormality characteristic data information of the aquaculture water source.

[0060] It should be noted that the water quality characteristic data information includes data such as the chemical composition and chemical component concentration in the water quality. When the correlation degree information is greater than the preset correlation degree information, it means that the water quality has caused related abnormal aquaculture events, such as abnormal death of fish. This method can screen out the historical water quality abnormal characteristic data information of aquaculture water sources, which can improve the accuracy of water quality monitoring.

[0061] like Figure 3 As shown, further, in this method, a water quality characteristic tracking model is constructed based on the historical water quality abnormality characteristic data information of the aquaculture water source, and the water quality characteristics of each current aquaculture water source are tracked by the water quality characteristic tracking model, specifically including:

[0062] S302: Obtain fishery resource data information of the current aquaculture area, and obtain water quality anomaly feature data set information related to the fishery resource data information of the current aquaculture area based on the historical water quality anomaly feature data information of the aquaculture water source, and introduce the graph neural network;

[0063] S304: Using the fishery resource data information of the current aquaculture area as the first graph node of the graph neural network, and using the water quality abnormality feature data set information related to the fishery resource data information of the current aquaculture area as the second graph node of the graph neural network;

[0064] S306: constructing an adjacency matrix based on the first graph nodes and the second graph nodes, calculating the Manhattan distances between the second graph nodes in the adjacency matrix using the Manhattan distance algorithm, obtaining the second graph nodes with the same Manhattan distances, fusing the second graph nodes with the same Manhattan distances into one second graph node, and updating the adjacency matrix;

[0065] S308: Construct a water quality feature tracking model based on a deep neural network, and input the adjacency matrix into the water quality feature tracking model for training. After the training is completed, the water quality characteristics of each current aquaculture water source are tracked through the water quality feature tracking model.

[0066] It should be noted that the current fishery resource data information in the aquaculture area includes fish, shrimp, shellfish and other organisms. Among them, there may be a variety of fishery resources in the aquaculture water body. By merging the second graph nodes with the same Manhattan distance into one second graph node and updating the adjacency matrix, the same water quality factor data can be fused, thereby reducing the computational complexity of the model and optimizing the water quality feature tracking model.

[0067] Furthermore, in this method, water quality characteristic data information of each aquaculture water source within a preset time is obtained, and the water quality characteristic data information of each aquaculture water source within the preset time is identified according to the water quality characteristic tracking model to obtain abnormal aquaculture water sources, specifically including:

[0068] Obtaining water quality characteristic data information of each aquaculture water source within a preset time, and inputting the water quality characteristic data information of each aquaculture water source within the preset time into a water quality characteristic tracking model for identification, and obtaining an identification result;

[0069] determining whether the recognition result is a preset recognition result, and when the recognition result is the preset recognition result, treating the aquaculture water source corresponding to the preset recognition result as an abnormal aquaculture water source;

[0070] When the recognition result is not a preset recognition result, the aquaculture water source corresponding to the recognition result that is not the preset recognition result is regarded as a normal aquaculture water source, and the abnormal aquaculture water source is output.

[0071] Furthermore, in this method, by evaluating the water quality characteristic data information of abnormal aquaculture water sources, the hazard evaluation membership of each abnormal aquaculture water source is obtained, specifically including:

[0072] A decision tree algorithm is introduced, and several hazard membership threshold standards are set. A root node is generated based on the abnormal water quality characteristic data of the aquaculture water source, and the root node is initialized and split based on the hazard membership threshold standards to generate several leaf nodes.

[0073] Determine whether there is only one sample data of the harmfulness membership threshold standard in the leaf node, and output the leaf node when there is only one sample data of the harmfulness membership threshold standard in the leaf node;

[0074] When there is more than one sample data of the hazard membership threshold standard in the leaf node, the leaf node is continuously split until there is only one sample data of the hazard membership threshold standard in the leaf node, and the corresponding leaf node is output;

[0075] The hazard evaluation membership of the aquaculture water source corresponding to the leaf node is obtained, and the hazard evaluation membership of the aquaculture water source corresponding to the leaf node is counted to generate the hazard evaluation membership of each abnormal aquaculture water source.

[0076] It should be noted that the hazard assessment membership includes no hazard membership, low hazard membership, medium hazard membership, high hazard membership, etc. Among them, the hazard assessment membership of abnormal aquaculture water sources can be one or more. Since the hazards of different fish affected by different water qualities are inconsistent, for example, although it is harmful to a certain fish, it is not harmful to another fish or shrimp. Technical personnel in this field can set it according to actual conditions.

[0077] Furthermore, in this method, relevant planning information is generated based on the hazard assessment membership of abnormal aquaculture water sources and the aquaculture water quantity data information required by aquatic fishery resources, and planning is performed based on the relevant planning information, specifically including:

[0078] Determine whether the hazard assessment membership of the abnormal aquaculture water source is greater than the preset hazard assessment membership. When the hazard assessment membership of the abnormal aquaculture water source is greater than the preset hazard assessment membership, the corresponding aquaculture water source is treated as a non-drainage water source;

[0079] When the hazard assessment membership of the abnormal aquaculture water source is not greater than the preset hazard assessment membership, the corresponding aquaculture water source is used as the drainage water source, and a genetic algorithm is introduced to obtain the safe water level data information of each drainage water source;

[0080] Initialize the water volume information of each diversion water source, use the safe water level data information of each diversion water source as a constraint condition, input the water volume information of each diversion water source and the aquaculture water volume data information required by aquatic fishery resources into the genetic algorithm for calculation;

[0081] When the water volume information of each diversion water source meets the constraint conditions, the water volume information of each diversion water source is output, relevant planning information is generated according to the water volume information of each diversion water source, and planning is performed according to the relevant planning information.

[0082] It should be noted that this method can improve the rationality of aquaculture planning, keep the aquaculture water at a stable level, control it from the source, and select a suitable drainage water source.

[0083] In addition, the method may further comprise the following steps:

[0084] After genetic iteration, if the water volume information of each drainage water source does not meet the constraint conditions, the water volume information of the largest drainage water source that can be drained is calculated, and the water volume information that needs to be increased is calculated based on the water volume information of the largest drainage water source that can be drained and the constraint conditions;

[0085] Obtaining the water quality hazard assessment membership of each drainage water source, and searching through big data based on the water quality hazard assessment membership of the drainage water source to obtain the purification cost information of the water volume that needs to be increased and corresponding to the water quality hazard assessment membership of each drainage water source to purify it to a preset water quality hazard assessment membership;

[0086] Constructing a purification cost ranking table, and inputting the purification cost information of the water volume that needs to be increased corresponding to the water quality hazard assessment membership of each diversion water source to the preset water quality hazard assessment membership into the purification cost ranking table for ranking, and obtaining a ranking result;

[0087] The water source with the minimum purification cost in the sorting results is obtained as the reference water source, and the water quality of the reference water source is purified. When the water quality hazard evaluation membership of the reference water source is not greater than the preset water quality hazard evaluation membership, the drainage operation will be performed according to the water volume information that can be drained by the largest drainage water source and the water volume information that needs to be increased.

[0088] It should be noted that this method can improve the rationality of planning.

[0089] like Figure 4 As shown, the second aspect of the present invention provides an aquaculture water source quality evaluation and planning system 4, which includes a memory 41 and a processor 42. The memory 41 includes an aquaculture water source quality evaluation and planning method program. When the aquaculture water source quality evaluation and planning method program is executed by the processor 42, the following steps are implemented:

[0090] Obtain historical water quality anomaly characteristic data information of aquaculture water sources, and build a water quality characteristic tracking model based on the historical water quality anomaly characteristic data information of aquaculture water sources, and track the water quality characteristics of each current aquaculture water source through the water quality characteristic tracking model;

[0091] Obtain water quality characteristic data information of each aquaculture water source within a preset time, identify the water quality characteristic data information of each aquaculture water source within a preset time according to a water quality characteristic tracking model, and obtain abnormal aquaculture water sources;

[0092] By evaluating the water quality characteristic data information of abnormal aquaculture water sources, the hazard evaluation membership of each abnormal aquaculture water source is obtained, and the aquaculture water quantity data information required by aquatic fishery resources is obtained;

[0093] Based on the hazard assessment affiliation of abnormal aquaculture water sources and aquaculture water volume data information required for aquatic fishery resources, relevant planning information is generated, and planning is carried out according to the relevant planning information.

[0094] Furthermore, in this system, historical water quality abnormality characteristic data information of aquaculture water sources is obtained, including:

[0095] Obtain historical water quality characteristic data information of aquaculture water sources, and construct retrieval tags based on the historical water quality characteristic data information of aquaculture water sources. Based on the retrieval tags, search through big data to obtain relevant aquaculture abnormal event information;

[0096] The grey correlation analysis method is introduced to calculate the correlation degree between the historical water quality characteristic data information of aquaculture water sources and the related aquaculture abnormal event information;

[0097] Determine whether the correlation degree information is greater than the preset correlation degree information. When the correlation degree information is greater than the preset correlation degree information, use the water quality characteristic data information corresponding to the related aquaculture abnormal event information as the water quality abnormal characteristic data information;

[0098] Based on the water quality abnormality characteristic data information, historical water quality abnormality characteristic data information of the aquaculture water source is constructed, and the historical water quality abnormality characteristic data information of the aquaculture water source is output.

[0099] Furthermore, in this system, a water quality characteristic tracking model is constructed based on the historical water quality abnormality characteristic data information of the aquaculture water source. The water quality characteristics of each current aquaculture water source are tracked by the water quality characteristic tracking model, specifically including:

[0100] Obtain fishery resource data information in the current aquaculture area, and obtain water quality anomaly feature data sets related to the fishery resource data information in the current aquaculture area based on the historical water quality anomaly feature data of the aquaculture water source, and introduce graph neural networks;

[0101] The fishery resource data information of the current aquaculture area is used as the first graph node of the graph neural network, and the water quality abnormality feature set information related to the fishery resource data information of the current aquaculture area is used as the second graph node of the graph neural network;

[0102] Construct an adjacency matrix based on the first graph nodes and the second graph nodes, calculate the Manhattan distance between the second graph nodes in the adjacency matrix using the Manhattan distance algorithm, obtain the second graph nodes with the same Manhattan distance, merge the second graph nodes with the same Manhattan distance into one second graph node, and update the adjacency matrix;

[0103] A water quality feature tracking model is constructed based on a deep neural network, and the adjacency matrix is ​​input into the water quality feature tracking model for training. After the training is completed, the water quality characteristics of each current aquaculture water source are tracked through the water quality feature tracking model.

[0104] Furthermore, in this system, water quality characteristic data information of each aquaculture water source within a preset time is obtained, and the water quality characteristic data information of each aquaculture water source within a preset time is identified according to the water quality characteristic tracking model to obtain abnormal aquaculture water sources, specifically including:

[0105] Obtaining water quality characteristic data information of each aquaculture water source within a preset time, and inputting the water quality characteristic data information of each aquaculture water source within the preset time into a water quality characteristic tracking model for identification, and obtaining an identification result;

[0106] determining whether the recognition result is a preset recognition result, and when the recognition result is the preset recognition result, treating the aquaculture water source corresponding to the preset recognition result as an abnormal aquaculture water source;

[0107] When the recognition result is not a preset recognition result, the aquaculture water source corresponding to the recognition result that is not the preset recognition result is regarded as a normal aquaculture water source, and the abnormal aquaculture water source is output.

[0108] Furthermore, in this system, by evaluating the water quality characteristic data information of abnormal aquaculture water sources, the hazard evaluation membership of each abnormal aquaculture water source is obtained, specifically including:

[0109] A decision tree algorithm is introduced, and several hazard membership threshold standards are set. A root node is generated based on the abnormal water quality characteristic data of the aquaculture water source, and the root node is initialized and split based on the hazard membership threshold standards to generate several leaf nodes.

[0110] Determine whether there is only one sample data of the harmfulness membership threshold standard in the leaf node, and output the leaf node when there is only one sample data of the harmfulness membership threshold standard in the leaf node;

[0111] When there is more than one sample data of the hazard membership threshold standard in the leaf node, the leaf node is continuously split until there is only one sample data of the hazard membership threshold standard in the leaf node, and the corresponding leaf node is output;

[0112] The hazard evaluation membership of the aquaculture water source corresponding to the leaf node is obtained, and the hazard evaluation membership of the aquaculture water source corresponding to the leaf node is counted to generate the hazard evaluation membership of each abnormal aquaculture water source.

[0113] Furthermore, in this system, relevant planning information is generated based on the hazard assessment degree of abnormal aquaculture water sources and the aquaculture water quantity data information required by aquatic fishery resources, and planning is carried out according to the relevant planning information, specifically including:

[0114] Determine whether the hazard assessment membership of the abnormal aquaculture water source is greater than the preset hazard assessment membership. When the hazard assessment membership of the abnormal aquaculture water source is greater than the preset hazard assessment membership, the corresponding aquaculture water source is treated as a non-drainage water source;

[0115] When the hazard assessment membership of the abnormal aquaculture water source is not greater than the preset hazard assessment membership, the corresponding aquaculture water source is used as the drainage water source, and a genetic algorithm is introduced to obtain the safe water level data information of each drainage water source;

[0116] Initialize the water volume information of each diversion water source, use the safe water level data information of each diversion water source as a constraint condition, input the water volume information of each diversion water source and the aquaculture water volume data information required by aquatic fishery resources into the genetic algorithm for calculation;

[0117] When the water volume information of each diversion water source meets the constraint conditions, the water volume information of each diversion water source is output, relevant planning information is generated according to the water volume information of each diversion water source, and planning is performed according to the relevant planning information.

[0118] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for evaluating and planning the water quality of aquaculture water sources. When the program for evaluating and planning the water quality of aquaculture water sources is executed by a processor, it implements any step of the method for evaluating and planning the water quality of aquaculture water sources.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0120] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0121] 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.

[0122] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0123] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of 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.

[0124] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for evaluating and planning the quality of aquaculture water sources, characterized in that: The following steps are involved: Acquire historical water quality anomaly characteristic data information of aquaculture water sources, and construct a water quality characteristic tracking model based on the historical water quality anomaly characteristic data information of aquaculture water sources, and track the water quality characteristics of each current aquaculture water source through the water quality characteristic tracking model; Acquire water quality characteristic data information of each aquaculture water source within a preset time, identify the water quality characteristic data information of each aquaculture water source within the preset time according to the water quality characteristic tracking model, and acquire abnormal aquaculture water sources; By evaluating the water quality characteristic data information of the abnormal aquaculture water source, obtaining the hazard evaluation membership of each abnormal aquaculture water source, and obtaining the aquaculture water quantity data information required by aquatic fishery resources; Relevant planning information is generated based on the hazard assessment membership of the abnormal aquaculture water source and the aquaculture water volume data information required for aquatic fishery resources, and planning is carried out according to the relevant planning information.

2. A method for evaluating and planning aquaculture water quality according to claim 1, characterized in that: Obtain historical water quality abnormality characteristic data information of aquaculture water sources, including: Acquire historical water quality characteristic data information of aquaculture water sources, construct retrieval tags based on the historical water quality characteristic data information of aquaculture water sources, and perform a search through big data based on the retrieval tags to obtain relevant aquaculture abnormal event information; Introducing a grey correlation analysis method to calculate the correlation degree information between the historical water quality characteristic data information of the aquaculture water source and the related aquaculture abnormal event information; Determining whether the correlation degree information is greater than a preset correlation degree information, and when the correlation degree information is greater than the preset correlation degree information, using the water quality characteristic data information corresponding to the related aquaculture abnormal event information as the water quality abnormality characteristic data information; Based on the water quality abnormality characteristic data information, historical water quality abnormality characteristic data information of the aquaculture water source is constructed, and the historical water quality abnormality characteristic data information of the aquaculture water source is output.

3. A method for evaluating and planning aquaculture water quality according to claim 1, characterized in that: A water quality characteristic tracking model is constructed based on the historical water quality abnormality characteristic data information of the aquaculture water source, and the water quality characteristics of each current aquaculture water source are tracked by the water quality characteristic tracking model, specifically including: Obtaining fishery resource data information of the current aquaculture area, and obtaining water quality anomaly feature data set information related to the fishery resource data information of the current aquaculture area based on the historical water quality anomaly feature data information of the aquaculture water source, and introducing a graph neural network; Using the fishery resource data information of the current aquaculture area as the first graph node of the graph neural network, and using the water quality abnormality feature data set information related to the fishery resource data information of the current aquaculture area as the second graph node of the graph neural network; Constructing an adjacency matrix based on the first graph nodes and the second graph nodes, calculating the Manhattan distances between the second graph nodes in the adjacency matrix using a Manhattan distance algorithm, obtaining second graph nodes with the same Manhattan distances, fusing the second graph nodes with the same Manhattan distances into one second graph node, and updating the adjacency matrix; A water quality feature tracking model is constructed based on a deep neural network, and the adjacency matrix is ​​input into the water quality feature tracking model for training. After the training is completed, the water quality features of each current aquaculture water source are tracked by the water quality feature tracking model.

4. The method for evaluating and planning aquaculture water quality according to claim 1, wherein: Acquiring water quality characteristic data information of each aquaculture water source within a preset time, identifying the water quality characteristic data information of each aquaculture water source within the preset time according to the water quality characteristic tracking model, and obtaining abnormal aquaculture water sources, specifically including: Acquire water quality characteristic data information of each aquaculture water source within a preset time, and input the water quality characteristic data information of each aquaculture water source within the preset time into the water quality characteristic tracking model for identification, and obtain an identification result; determining whether the recognition result is a preset recognition result, and when the recognition result is the preset recognition result, treating the aquaculture water source corresponding to the preset recognition result as an abnormal aquaculture water source; When the recognition result is not a preset recognition result, the aquaculture water source corresponding to the recognition result that is not a preset recognition result is regarded as a normal aquaculture water source, and the abnormal aquaculture water source is output.

5. The method for evaluating and planning aquaculture water quality according to claim 1, wherein: By evaluating the water quality characteristic data information of the abnormal aquaculture water source, the hazard evaluation membership of each abnormal aquaculture water source is obtained, specifically including: A decision tree algorithm is introduced, and several hazard membership threshold standards are set. A root node is generated according to the water quality characteristic data information of the abnormal aquaculture water source, and the root node is initialized and split based on the hazard membership threshold standards to generate several leaf nodes. Determining whether there is only one sample data of the harmfulness membership threshold standard in the leaf node, and outputting the leaf node when there is only one sample data of the harmfulness membership threshold standard in the leaf node; When more than one sample data of the harmfulness membership threshold standard exists in the leaf node, the leaf node is continuously split until only one sample data of the harmfulness membership threshold standard exists in the leaf node, and the corresponding leaf node is output; The hazard evaluation membership of the aquaculture water source corresponding to the leaf node is obtained, and the hazard evaluation membership of the aquaculture water source corresponding to the leaf node is counted to generate the hazard evaluation membership of each abnormal aquaculture water source.

6. A method for evaluating and planning aquaculture water quality according to claim 1, characterized in that: Generate relevant planning information based on the hazard assessment membership of the abnormal aquaculture water source and the aquaculture water quantity data information required by aquatic fishery resources, and perform planning based on the relevant planning information, specifically including: Determining whether the hazard assessment membership of the abnormal aquaculture water source is greater than a preset hazard assessment membership; when the hazard assessment membership of the abnormal aquaculture water source is greater than the preset hazard assessment membership, treating the corresponding aquaculture water source as a non-drainage water source; When the hazard assessment membership of the abnormal aquaculture water source is not greater than the preset hazard assessment membership, the corresponding aquaculture water source is used as a drainage water source, and a genetic algorithm is introduced to obtain safe water level data information of each drainage water source; Initializing the water volume information of each drainage water source, using the safe water level data information of each drainage water source as a constraint condition, inputting the water volume information of each drainage water source and the aquaculture water volume data information required by aquatic fishery resources into the genetic algorithm for calculation; When the water volume information of each diversion water source meets the constraint condition, the water volume information of each diversion water source is output, relevant planning information is generated according to the water volume information of each diversion water source, and planning is performed according to the relevant planning information.

7. A system for evaluating and planning aquaculture water quality, characterized in that: The system includes a memory and a processor. The memory includes a method program for evaluating and planning the quality of aquaculture water sources. When the method program for evaluating and planning the quality of aquaculture water sources is executed by the processor, the following steps are implemented: Acquire historical water quality anomaly characteristic data information of aquaculture water sources, and construct a water quality characteristic tracking model based on the historical water quality anomaly characteristic data information of aquaculture water sources, and track the water quality characteristics of each current aquaculture water source through the water quality characteristic tracking model; Acquire water quality characteristic data information of each aquaculture water source within a preset time, identify the water quality characteristic data information of each aquaculture water source within the preset time according to the water quality characteristic tracking model, and acquire abnormal aquaculture water sources; By evaluating the water quality characteristic data information of the abnormal aquaculture water source, obtaining the hazard evaluation membership of each abnormal aquaculture water source, and obtaining the aquaculture water quantity data information required by aquatic fishery resources; Relevant planning information is generated based on the hazard assessment membership of the abnormal aquaculture water source and the aquaculture water volume data information required for aquatic fishery resources, and planning is carried out according to the relevant planning information.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes an aquaculture water source water quality evaluation and planning method program. When the aquaculture water source water quality evaluation and planning method program is executed by a processor, the steps of the aquaculture water source water quality evaluation and planning method as described in any one of claims 1-6 are implemented.

Images