Pond culture management method and system based on tuna behavior analysis
By analyzing the behavior and environmental characteristics of tuna, a metabolic analysis model was constructed, and the feeding plan was dynamically adjusted. This solved the problem of feeding amount control in tuna pond culture, reduced disease risk and water pollution, and optimized aquaculture management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-06
- Publication Date
- 2026-03-31
AI Technical Summary
In existing tuna pond farming, the control of feeding amount mainly relies on quantity relationships, which leads to overfeeding, resulting in increased farming costs, water pollution, and increased disease risk.
By acquiring image data of tuna, analyzing their behavior and activity characteristics, constructing a metabolic analysis model, predicting metabolic data characteristics, dynamically adjusting feeding plans, and providing early warnings for water quality to avoid food accumulation and water pollution.
This technology enables dynamic adjustments to feeding plans based on the behavior and environmental characteristics of tuna, reducing disease risks and optimizing aquaculture costs and water quality management.
Smart Images
Figure CN121753735A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of tuna farming technology, and in particular to a pond farming management method and system based on tuna behavior analysis. Background Technology
[0002] Tuna, a high-value seafood, has traditionally relied primarily on ocean fishing. However, with increasing market demand and dwindling wild resources, aquaculture has become an important supplementary method. Although tuna is generally considered a marine organism, theoretically, they can also be cultured in ponds under specific conditions. However, this method faces numerous challenges, including but not limited to water quality management, temperature control, and feed supply. Tuna has very high requirements for water quality, necessitating that the pond water be clear, unpolluted, and contain sufficient dissolved oxygen. Furthermore, water temperature is a crucial factor affecting tuna growth, with an ideal range of approximately 18-24°C. Maintaining these conditions may require the use of recirculating aquaculture systems or other advanced water treatment technologies to stabilize water quality. Tuna are carnivorous, primarily feeding on small fish and shrimp. Therefore, providing high-quality, nutritionally balanced food is essential in pond culture. Using specially formulated adult fish pellet feed can meet the needs of tuna at different growth stages while minimizing environmental impact. In addition, properly managing the amount and frequency of feeding is also key to ensuring the healthy growth of tuna. However, current tuna farming practices only consider feeding based on quantity, which leads to excessive feeding. This results in two problems: firstly, it increases farming costs, and secondly, excess feed accumulates in the pond, polluting the water and increasing the probability of tuna diseases. Summary of the Invention
[0003] This invention overcomes the shortcomings of the prior art and provides a solution.
[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows: The first aspect of this invention provides a pond aquaculture management method based on tuna behavior analysis, comprising: Image data of tuna in a pond aquaculture area is acquired, and the behavior of tuna is tracked and analyzed based on the image data of tuna in the pond aquaculture area. The environmental characteristics of the pond aquaculture area were obtained, and a metabolic analysis model was constructed by combining the activity characteristics data of tuna. The metabolic data characteristics of tuna in the current pond aquaculture area are predicted based on the metabolic analysis model described above. Initialize the feeding plan for the current aquaculture area and issue an early warning for the aquaculture water quality based on the metabolic data characteristics of tuna in the current pond aquaculture area.
[0005] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, image data of tuna in the pond aquaculture area is acquired, and the behavior of the tuna is tracked and analyzed based on the image data of the tuna in the pond aquaculture area, specifically including: Image data of tuna in a pond aquaculture area is acquired, and behavioral characteristic data of tuna are obtained based on the image data of tuna in the pond aquaculture area. Construct timestamps, obtain tuna behavioral feature data for each timestamp, and construct time-series-based tuna behavioral feature data based on the tuna behavioral feature data for each timestamp. By evaluating the time-series-based behavioral characteristic data of tuna, activity characteristic data is generated. The activity characteristic data is used as the model output, and the behavioral characteristic data of tuna is used as the model input. A tuna activity prediction model is constructed based on a deep neural network. The time-series-based tuna behavior feature data is input into the tuna activity prediction model for training, and the trained tuna activity prediction model is obtained. The trained tuna activity prediction model is used to identify the behavioral characteristics of tuna within a preset time period, thereby obtaining the tuna activity characteristics data within the preset time period.
[0006] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, a metabolic analysis model is constructed using the activity characteristic data of tuna, specifically including: Different environmental characteristics are set, and test conditions are constructed based on the different environmental characteristics and the activity characteristics data of tuna. The metabolic data of tuna is tested under the test conditions to obtain the metabolic data under the test conditions. A metabolic analysis model is constructed based on a generative adversarial network. The test conditions are used as the model input, the metabolic data are used as the model output, and the test conditions are used to train the metabolic analysis model. The generator generates an initial prediction result of metabolic data based on the test conditions, and inputs the initial prediction result of metabolic data into the discriminator for judgment to determine whether to accept the initial prediction result of metabolic data. If accepted, the initial prediction result of the metabolic data is output; if not accepted, the generator continues to generate the next prediction result until the current metabolic data prediction result is accepted, and the metabolic analysis model is completed.
[0007] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, the metabolic data characteristics of tuna in the current pond aquaculture area are predicted according to the metabolic analysis model, specifically including: A sampling survey is conducted on the target pond, and the activity characteristics of the sampled tuna are tracked within a preset time period. The environmental characteristics of the pond aquaculture area and the activity characteristics of the sampled tuna within the preset time period are input into the metabolic analysis model. The generator generates initial prediction results of metabolic data based on the environmental characteristics of the pond aquaculture area and the activity characteristics data of tuna sampled within a preset time period. The initial prediction results of the metabolic data are input into the discriminator for judgment to determine whether to accept the initial prediction results of the metabolic data. If accepted, the initial prediction result of metabolic data is output. If not accepted, the generator continues to generate the next prediction result until the current metabolic data prediction result is accepted, and outputs the metabolic data characteristics of the sampled tuna in the current pond aquaculture area.
[0008] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, the feeding plan for the current aquaculture area is initialized, specifically including: Based on the metabolic data characteristics of the sampled tuna in the current pond aquaculture area, the metabolic data characteristics of a single tuna are calculated, and the quantity information of tuna in the current aquaculture area is statistically analyzed. Based on the quantity information of tuna in the current aquaculture area and the metabolic data characteristics of a single tuna, the total metabolic data characteristics of the current aquaculture area are calculated, and the feeding amount data of tuna under each historical metabolic data characteristic is obtained. Based on the feeding data of tuna under the historical metabolic data characteristics and the overall metabolic data characteristics, the feeding data of tuna in the current breeding area is generated, and a feeding plan for the current breeding area is generated based on the feeding data of tuna in the current breeding area.
[0009] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, early warning of aquaculture water quality is issued based on the metabolic data characteristics of tuna in the current pond aquaculture area, specifically including: Set a threshold for metabolic deposition data and obtain the water flow characteristics of the current pond aquaculture area. Based on the metabolic data characteristics of tuna in the current pond aquaculture area and the water flow characteristics of the current pond aquaculture area, estimate the metabolic deposition data of the current pond aquaculture area. Determine whether the metabolic deposition data of the former pond aquaculture area is greater than the metabolic deposition data threshold; If the metabolic sedimentation data in the former pond aquaculture area exceeds the metabolic sedimentation data threshold, an early warning will be issued for the aquaculture water quality.
[0010] If the metabolic sedimentation data in the former pond aquaculture area is not greater than the metabolic sedimentation data threshold, the aquaculture water quality will be continuously monitored.
[0011] A second aspect of the present invention provides a pond aquaculture management system based on tuna behavior analysis, including a memory and a processor. The memory includes a pond aquaculture management method program based on tuna behavior analysis. When the processor executes the pond aquaculture management method program based on tuna behavior analysis, it implements the steps of any of the pond aquaculture management methods based on tuna behavior analysis described in the present invention.
[0012] A third aspect of the present invention provides a computer-readable storage medium including a pond aquaculture management method program based on tuna behavior analysis, wherein when the pond aquaculture management method program based on tuna behavior analysis is executed by a processor, it implements the steps of any of the pond aquaculture management methods based on tuna behavior analysis described in the present invention.
[0013] This invention addresses the shortcomings of the prior art and has the following beneficial effects: This invention acquires image data of tuna in a pond aquaculture area, tracks and analyzes tuna behavior based on this data, and then obtains environmental characteristics of the pond aquaculture area. A metabolic analysis model is constructed by combining tuna activity data, and this model predicts the metabolic characteristics of the tuna in the current pond aquaculture area. Finally, a feeding plan for the current aquaculture area is initialized, and water quality is monitored based on the metabolic characteristics of the tuna. This invention analyzes the metabolism of tuna by combining their behavior and environmental characteristics, thereby dynamically adjusting the feeding plan to avoid overfeeding, which can lead to excessive feed accumulation in the pond and water pollution, thus reducing the probability of tuna disease. Attached Figure Description
[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.
[0015] Figure 1 A flowchart illustrating the overall process of pond aquaculture management based on tuna behavior analysis is provided. Figure 2 A schematic diagram of a pond aquaculture management system based on tuna behavior analysis is shown. Detailed Implementation
[0016] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.
[0017] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.
[0018] like Figure 1 As shown, the first aspect of this invention provides a pond aquaculture management method based on tuna behavior analysis, comprising: Acquire image data of tuna in pond aquaculture areas, and track and analyze the behavior of tuna based on the image data of tuna in pond aquaculture areas; The environmental characteristics of the pond aquaculture area were obtained, and a metabolic analysis model was constructed by combining the activity characteristics data of tuna. Predict the metabolic characteristics of tuna in the current pond aquaculture area based on metabolic analysis models; Initialize the feeding plan for the current aquaculture area and issue early warnings for aquaculture water quality based on the metabolic data characteristics of tuna in the current pond aquaculture area.
[0019] It should be noted that this invention analyzes the metabolism of tuna by combining their behavior and environmental characteristics, thereby dynamically adjusting the feeding plan to avoid overfeeding, which would increase farming costs and cause excess feed to accumulate in the pond, polluting the water and reducing the probability of tuna diseases.
[0020] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, image data of tuna in the pond aquaculture area is acquired, and the behavior of tuna is tracked and analyzed based on the image data of tuna in the pond aquaculture area, specifically including: Image data of tuna in pond aquaculture areas is acquired, and behavioral characteristic data of tuna are obtained based on the image data of tuna in pond aquaculture areas. It should be noted that image data of tuna can be obtained by installing cameras in the pond aquaculture area.
[0021] Construct timestamps, obtain behavioral feature data of tuna at each timestamp, and construct time series-based behavioral feature data of tuna based on the behavioral feature data of tuna at each timestamp. It should be noted that the behavioral characteristics data of tuna include mental characteristics, behavioral characteristics, etc.
[0022] By evaluating the behavioral characteristics of tuna based on time series data, activity characteristic data is generated. For example, a large swimming distance within a certain time period indicates high activity, and a good mental state within a certain period indicates high activity. Activity characteristic data includes descriptions such as high activity, moderate activity, and low activity.
[0023] The activity feature data is used as the model output, and the tuna behavior feature data is used as the model input. A tuna activity prediction model is constructed based on a deep neural network. Time-series tuna behavior feature data is input into the tuna activity prediction model for training, and the trained tuna activity prediction model is obtained. The trained tuna activity prediction model is used to identify the behavioral characteristics of tuna within a preset time period, thereby obtaining the tuna activity characteristics data within the preset time period.
[0024] It should be noted that this method can obtain data on the activity characteristics of tuna within the current preset time period, thereby enabling a more reasonable feeding plan.
[0025] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, a metabolic analysis model is constructed using the activity characteristic data of tuna, specifically including: Different environmental characteristics were set up, and test conditions were constructed based on the different environmental characteristics and the activity characteristics data of tuna. The metabolic data of tuna was tested under the test conditions to obtain the metabolic data under the test conditions. A metabolic analysis model is constructed based on generative adversarial networks. The test conditions are used as the model input, and the metabolic data are used as the model output. The test conditions are used to train the metabolic analysis model. The generator generates initial prediction results of metabolic data based on the test conditions, and inputs the initial prediction results of metabolic data into the discriminator for judgment to determine whether to accept the initial prediction results of metabolic data. If accepted, the initial prediction result of the metabolic data is output; if not accepted, the generator continues to generate the next prediction result until the current metabolic data prediction result is accepted, and the metabolic analysis model is completed.
[0026] It should be noted that metabolic data of tuna can vary due to different environments and the activity levels of the tuna. For example, tuna metabolic data is low when the water temperature is low and the activity level is low, and high when the temperature is suitable and the activity level is high. Metabolic data refers to various quantitative and qualitative information related to the metabolic processes of an organism, which usually involves the types, concentrations, metabolic pathways, and metabolic rates of metabolites. This method can be used to construct metabolic analysis models to predict metabolic data.
[0027] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, the metabolic data characteristics of tuna in the current pond aquaculture area are predicted according to the metabolic analysis model, specifically including: A sampling survey was conducted on the target pond, and the activity characteristics of the sampled tuna were tracked within a preset time period. The environmental characteristics of the pond aquaculture area and the activity characteristics of the sampled tuna within the preset time period were input into the metabolic analysis model. The generator generates initial predictions of metabolic data based on the environmental characteristics of the pond aquaculture area and the activity characteristics of tuna sampled within a preset time period. The initial prediction results of metabolic data are input into the discriminator for judgment, which determines whether to accept the initial prediction results of metabolic data. If accepted, the initial prediction result of metabolic data is output. If not accepted, the generator continues to generate the next prediction result until the current metabolic data prediction result is accepted, and outputs the metabolic data characteristics of the sampled tuna in the current pond aquaculture area.
[0028] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, the feeding plan for the current aquaculture area is initialized, specifically including: Based on the metabolic data characteristics of a sample of tuna in the current pond aquaculture area, the metabolic data characteristics of a single tuna are calculated, and the quantity information of tuna in the current aquaculture area is statistically analyzed. Based on the current tuna quantity information and the metabolic data characteristics of a single tuna in the current aquaculture area, the total metabolic data characteristics of the current aquaculture area are calculated, and the feeding amount data of tuna under each historical metabolic data characteristic is obtained. Based on the feeding data of tuna under the characteristics of each historical metabolic data and the overall metabolic data characteristics, the feeding data of tuna in the current breeding area is generated, and the feeding plan for the current breeding area is generated based on the feeding data of tuna in the current breeding area.
[0029] It should be noted that this method fully considers the activity data and environmental characteristics data of tuna, therefore, the feeding plan generated by this method is more reasonable.
[0030] Furthermore, in the pond aquaculture management method based on tuna behavior analysis, early warning of aquaculture water quality is issued based on the metabolic data characteristics of tuna in the current pond aquaculture area, specifically including: Set a threshold for metabolic deposition data and obtain the water flow characteristics of the current pond aquaculture area. Based on the metabolic data characteristics of tuna in the current pond aquaculture area and the water flow characteristics of the current pond aquaculture area, estimate the metabolic deposition data of the current pond aquaculture area. It should be noted that water flow characteristics include the amount of water exchanged per unit time. Although some sedimentation will occur in the metabolic data of tuna in the current pond aquaculture area, some of it can be carried away by the water flow. However, only a portion is carried away. Virtual simulation technology can simulate and predict the water flow characteristics of the current pond aquaculture area. Based on the metabolic data characteristics of tuna in the current pond aquaculture area and the actual metabolic sedimentation data of the current pond aquaculture area under the current water flow characteristics, the prediction accuracy of metabolite data can be improved.
[0031] This may also include the following technical solutions: Initialize the water exchange equipment to measure the water exchange volume per unit time, and calculate the metabolic deposit characteristics that can be eliminated per unit time based on the water exchange volume per unit time. Introduce a genetic algorithm and set the number of generations based on the genetic algorithm. Estimate the metabolic sediment characteristic data within a unit time in the current pond, and determine whether the metabolic sediment characteristic data that can be eliminated within the unit time is greater than the metabolic sediment characteristic data within the current pond within the unit time. When the metabolic sediment characteristic data that can be eliminated within a unit time is greater than the metabolic sediment characteristic data in the current pond within a unit time, the water exchange volume of the current water exchange equipment within a unit time is output, and water exchange control is performed according to the water exchange volume of the current water exchange equipment within a unit time. When the metabolic sediment feature data that can be eliminated within a unit time is not greater than the metabolic sediment feature data within a unit time in the current pond, then genetic inheritance is performed based on the number of generations. By using genetics, the water exchange volume of the current water exchange equipment within a unit time is reset until it exceeds the metabolic sediment characteristic data of the current pond within a unit time. When the metabolic sediment characteristic data of the current pond within a unit time is lower than a preset threshold, the water exchange equipment stops working.
[0032] It should be noted that this method can eliminate more metabolic sediment characteristics per unit time than the current metabolic sediment characteristics per unit time in the pond, thereby reducing the probability of tuna diseases during aquaculture.
[0033] Determine whether the metabolic deposition data in the pre-pond aquaculture area exceeds the metabolic deposition data threshold; If the metabolic sedimentation data in the former pond aquaculture area exceeds the metabolic sedimentation data threshold, an early warning will be issued for the aquaculture water quality.
[0034] If the metabolic sedimentation data in the former pond aquaculture area is not greater than the metabolic sedimentation data threshold, the aquaculture water quality will be continuously monitored.
[0035] In addition, this method also includes: By using big data on the impact of metabolites on dissolved oxygen in pond water, the concentration characteristics of dissolved oxygen in the current pond water can be obtained. Based on the metabolic deposition characteristic data within the preset time, the characteristic data of the impact of metabolites on dissolved oxygen in the pond water, and the current dissolved oxygen concentration characteristics in the pond water, the characteristic data of dissolved oxygen change in the pond within the preset time are calculated. Set a dissolved oxygen characteristic data threshold and determine whether there are any data points below the dissolved oxygen characteristic data threshold in the dissolved oxygen change characteristic data of the current pond within a preset time period; When the dissolved oxygen change data of the current pond within a preset time period contains data below the dissolved oxygen characteristic data threshold, the time node is obtained, an early warning is issued based on the time node, and the aerator is controlled in advance to perform oxygenation treatment.
[0036] It should be noted that metabolites may contain dissolved oxygen and react with it, leading to a decrease in dissolved oxygen in the water, which is detrimental to tuna farming. This method can further optimize the tuna farming process.
[0037] like Figure 2 As shown, the second aspect of the present invention provides a pond aquaculture management system based on tuna behavior analysis, including a memory and a processor. The memory includes a pond aquaculture management method program based on tuna behavior analysis. When the processor executes the pond aquaculture management method program based on tuna behavior analysis, it implements the steps of any one of the pond aquaculture management methods based on tuna behavior analysis.
[0038] A third aspect of the present invention provides a computer-readable storage medium including a pond aquaculture management method program based on tuna behavior analysis, wherein when the pond aquaculture management method program based on tuna behavior analysis is executed by a processor, it implements the steps of any one of the pond aquaculture management methods based on tuna behavior analysis.
[0039] 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 illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.
[0040] The units described above as separate components may or may not be physically separate. The components shown 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 to achieve the purpose of this embodiment according to actual needs.
[0041] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.
[0042] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0043] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.
[0044] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those 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 determined by the scope of the claims.
Claims
1. A pond aquaculture management method based on tuna behavior analysis, characterized in that, include: Image data of tuna in a pond aquaculture area is acquired, and the behavior of tuna is tracked and analyzed based on the image data of tuna in the pond aquaculture area. The environmental characteristics of the pond aquaculture area were obtained, and a metabolic analysis model was constructed by combining the activity characteristics data of tuna. The metabolic data characteristics of tuna in the current pond aquaculture area are predicted based on the metabolic analysis model described above. Initialize the feeding plan for the current aquaculture area and issue an early warning for the aquaculture water quality based on the metabolic data characteristics of tuna in the current pond aquaculture area.
2. The pond aquaculture management method based on tuna behavior analysis according to claim 1, characterized in that, Acquire image data of tuna in a pond aquaculture area, and track and analyze the behavior of the tuna based on the image data, specifically including: Image data of tuna in a pond aquaculture area is acquired, and behavioral characteristic data of tuna are obtained based on the image data of tuna in the pond aquaculture area. Construct timestamps, obtain tuna behavioral feature data for each timestamp, and construct time-series-based tuna behavioral feature data based on the tuna behavioral feature data for each timestamp. By evaluating the time-series-based behavioral characteristic data of tuna, activity characteristic data is generated. The activity characteristic data is used as the model output, and the behavioral characteristic data of tuna is used as the model input. A tuna activity prediction model is constructed based on a deep neural network. The time-series-based tuna behavior feature data is input into the tuna activity prediction model for training, and the trained tuna activity prediction model is obtained. The trained tuna activity prediction model is used to identify the behavioral characteristics of tuna within a preset time period, thereby obtaining the tuna activity characteristics data within the preset time period.
3. The pond aquaculture management method based on tuna behavior analysis according to claim 1, characterized in that, A metabolic analysis model was constructed by combining data on the activity characteristics of tuna, specifically including: Different environmental characteristics are set, and test conditions are constructed based on the different environmental characteristics and the activity characteristics data of tuna. The metabolic data of tuna is tested under the test conditions to obtain the metabolic data under the test conditions. A metabolic analysis model is constructed based on a generative adversarial network. The test conditions are used as the model input, the metabolic data are used as the model output, and the test conditions are used to train the metabolic analysis model. The generator generates an initial prediction result of metabolic data based on the test conditions, and inputs the initial prediction result of metabolic data into the discriminator for judgment to determine whether to accept the initial prediction result of metabolic data. If accepted, the initial prediction result of the metabolic data is output; if not accepted, the generator continues to generate the next prediction result until the current metabolic data prediction result is accepted, and the metabolic analysis model is completed.
4. The pond aquaculture management method based on tuna behavior analysis according to claim 1, characterized in that, The metabolic data characteristics of tuna in the current pond aquaculture area are predicted based on the metabolic analysis model, specifically including: A sampling survey is conducted on the target pond, and the activity characteristics of the sampled tuna are tracked within a preset time period. The environmental characteristics of the pond aquaculture area and the activity characteristics of the sampled tuna within the preset time period are input into the metabolic analysis model. The generator generates initial prediction results of metabolic data based on the environmental characteristics of the pond aquaculture area and the activity characteristics data of tuna sampled within a preset time period. The initial prediction results of the metabolic data are input into the discriminator for judgment to determine whether to accept the initial prediction results of the metabolic data. If accepted, the initial prediction result of metabolic data is output. If not accepted, the generator continues to generate the next prediction result until the current metabolic data prediction result is accepted, and outputs the metabolic data characteristics of the sampled tuna in the current pond aquaculture area.
5. The pond aquaculture management method based on tuna behavior analysis according to claim 1, characterized in that, Initialize the feeding plan for the current breeding area, specifically including: Based on the metabolic data characteristics of the sampled tuna in the current pond aquaculture area, the metabolic data characteristics of a single tuna are calculated, and the quantity information of tuna in the current aquaculture area is statistically analyzed. Based on the quantity information of tuna in the current aquaculture area and the metabolic data characteristics of a single tuna, the total metabolic data characteristics of the current aquaculture area are calculated, and the feeding amount data of tuna under each historical metabolic data characteristic is obtained. Based on the feeding data of tuna under the historical metabolic data characteristics and the overall metabolic data characteristics, the feeding data of tuna in the current breeding area is generated, and a feeding plan for the current breeding area is generated based on the feeding data of tuna in the current breeding area.
6. The pond aquaculture management method based on tuna behavior analysis according to claim 1, characterized in that, Based on the metabolic data characteristics of tuna in the current pond aquaculture area, an early warning system for aquaculture water quality is issued, specifically including: Set a threshold for metabolic deposition data and obtain the water flow characteristics of the current pond aquaculture area. Based on the metabolic data characteristics of tuna in the current pond aquaculture area and the water flow characteristics of the current pond aquaculture area, estimate the metabolic deposition data of the current pond aquaculture area. Determine whether the metabolic deposition data of the former pond aquaculture area is greater than the metabolic deposition data threshold; If the metabolic sedimentation data in the previous pond aquaculture area is greater than the metabolic sedimentation data threshold, an early warning will be issued for the aquaculture water quality. If the metabolic sedimentation data in the former pond aquaculture area is not greater than the metabolic sedimentation data threshold, the aquaculture water quality will be continuously monitored.
7. A pond aquaculture management system based on tuna behavior analysis, characterized in that, The device includes a memory and a processor. The memory includes a pond aquaculture management method program based on tuna behavior analysis. When the processor executes the pond aquaculture management method program based on tuna behavior analysis, it implements the steps of the pond aquaculture management method based on tuna behavior analysis as described in any one of claims 1-6.
8. A computer-readable storage medium, characterized in that, The method includes a pond aquaculture management program based on tuna behavior analysis, which, when executed by a processor, implements the steps of the pond aquaculture management method based on tuna behavior analysis as described in any one of claims 1-6.