A method and system for marking prawns

Abstract

The present application relates to the technical field of aquaculture, and particularly relates to a method and system for marking and thickening of marbled shrimp, obtaining a current marking and thickening time node of a marking and thickening pond and obtaining culture density information of shrimp fry in the marking and thickening pond, obtaining a real-time bait feeding scheme based on the current marking and thickening time node and the culture density information, obtaining actual environmental parameters of the marking and thickening shed within a preset time period, obtaining survival rates of each bacterium and alga corresponding to a bacterium-alga combination under different environmental parameters, determining an optimal treatment time period based on the actual environmental parameters within the preset time period and the survival rates of each bacterium and alga corresponding to the bacterium-alga combination under different environmental parameters, and formulating a bait feeding scheme at different marking and thickening stages through the method, and then predicting water quality data of the marking and thickening pond after feeding bait according to the formulated bait feeding scheme, so as to determine whether harmful bacterium-algae will breed in the marking and thickening pond, and thus formulating a harmful bacterium-algae inhibition treatment scheme.

Description

Technical Field

[0001] This invention relates to the field of aquaculture technology, and in particular to a method and system for raising tiger prawns. Background Technology

[0002] In recent years, the small-scale nursery model for Penaeus monodon farming has become increasingly popular. This model involves temporarily raising juvenile Penaeus monodon shrimp in a greenhouse for a period before transferring them to an external pond for further rearing. Nursery rearing saves costs, improves feed utilization, and conserves feed. However, during this process, some feed sinks into the water, decomposes, or even rots, leading to eutrophication and the proliferation of harmful algae such as blue-green algae, Vibrio, and Cytosporum. When these harmful algae proliferate and erupt, they severely impact the normal growth of shrimp larvae, even causing large-scale mortality and significant economic losses. Therefore, effectively predicting water quality data in the nursery pond and developing corresponding treatment measures to prevent the proliferation of harmful algae is an important research direction for the small-scale nursery model. Summary of the Invention

[0003] This invention overcomes the shortcomings of the prior art and provides a method and system for grading tiger prawns.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of this invention discloses a method for grading tiger prawns, comprising the following steps:

[0006] Obtain the current nursery time point and the stocking density information of shrimp larvae in the nursery pond, and obtain a real-time feed feeding plan based on the current nursery time point and stocking density information;

[0007] The historical feeding schemes of the nursery ponds are obtained through a big data network, and the historical water quality data of the nursery ponds after each historical feeding scheme is obtained through the big data network. Based on the historical feeding schemes and historical water quality data, the actual water quality data of the nursery ponds after the real-time feeding scheme is predicted.

[0008] The germination rates of various bacteria and algae under different water quality conditions are obtained through big data networks. Based on the germination rates of each bacteria and algae and the actual water quality data, a set of bacteria and algae that need to be suppressed after being fed with a real-time feed feeding program is obtained.

[0009] Based on the set of bacteria and algae that need to be suppressed, a big data network is searched to obtain multiple sub-processing schemes, and the sub-processing schemes are screened to obtain the final processing scheme.

[0010] The actual environmental parameters of the standard coagulation shed within a preset time period are obtained, and the survival rate of each bacterium and algae in the bacterium and algae ensemble under different environmental parameters is obtained. Based on the actual environmental parameters within the preset time period and the survival rate of each bacterium and algae in the bacterium and algae ensemble under different environmental parameters, the optimal treatment time period is determined.

[0011] Furthermore, in a preferred embodiment of the present invention, the current nursery time point and the stocking density information of shrimp larvae in the nursery are obtained, and a real-time feed feeding plan is obtained based on the current nursery time point and the stocking density information, specifically as follows:

[0012] By acquiring feed feeding characteristics information of shrimp larvae at each growth stage through a big data network, a database is constructed, and the feed feeding characteristics information of shrimp larvae at each growth stage is imported into the database to obtain a characteristic database; wherein, the feed feeding characteristics information includes feed type and feed amount required per shrimp larvae.

[0013] Obtain the current nursery time point of the nursery pond, import the current nursery time point into the characteristic database, and obtain the feed type required for shrimp larvae at the current nursery time point;

[0014] Obtain the stocking density information of shrimp larvae in the nursery pond, import the stocking density information into the characteristic database, and obtain the amount of feed required for the shrimp larvae at the current nursery time point;

[0015] A real-time feeding plan is generated based on the type and amount of feed required by the shrimp larvae at the current nursery stage, and the real-time feeding plan is output.

[0016] Furthermore, in a preferred embodiment of the present invention, historical feeding schemes for the nursery ponds are obtained through a big data network, and historical water quality data corresponding to the nursery ponds after being fed according to each historical feeding scheme are also obtained through the big data network. Based on the historical feeding schemes and historical water quality data, the actual water quality data of the nursery ponds after being fed according to the real-time feeding scheme is predicted, specifically:

[0017] Historical feeding schemes for the nursery ponds were obtained through big data networks, and historical water quality data for the nursery ponds after each historical feeding scheme was obtained through big data networks.

[0018] A water quality prediction model is constructed based on a convolutional neural network, and the historical water quality data corresponding to the pre-feeding pond after each historical feeding scheme is imported into the water quality prediction model for training, thus obtaining a trained water quality prediction model.

[0019] The real-time feeding scheme is imported into the trained water quality prediction model. The real-time feeding scheme is paired with each historical feeding scheme using grey relational analysis to obtain several pairing rates. A size sorting table is constructed, and the several pairing rates are imported into the size sorting table for sorting to obtain the maximum pairing rate.

[0020] Obtain the historical feeding scheme corresponding to the maximum pairing rate, and obtain the historical water quality data associated with the historical feeding scheme corresponding to the maximum pairing rate. Based on the historical water quality data associated with the historical feeding scheme corresponding to the maximum pairing rate, predict the actual water quality data of the nursery pond after feeding with the real-time feeding scheme.

[0021] Furthermore, in a preferred embodiment of the present invention, the germination rates of various bacteria and algae under different water quality data conditions are obtained through a big data network. Based on the germination rates of each bacteria and algae and the actual water quality data, a set of bacteria and algae that need to be suppressed after being fed with a real-time feed feeding scheme is obtained, specifically:

[0022] The germination rates of various bacteria and algae under different water quality conditions are obtained through big data networks. An evaluation model is constructed based on a deep learning network. The germination rates of various bacteria and algae under different water quality conditions are then imported into the evaluation model for training, resulting in a trained evaluation model.

[0023] Obtain the actual water quality data of the pre-feeding pond after feeding with a real-time feed program, import the actual water quality data into the evaluation model after training, and obtain the actual germination rate corresponding to the preset bacteria and algae.

[0024] Determine whether the actual germination rate of the preset bacteria and algae is greater than the preset germination rate. If it is greater, mark and aggregate the bacteria and algae corresponding to the actual germination rate that is greater than the preset germination rate to obtain a set of bacteria and algae that need to be suppressed after being fed by the real-time feed feeding scheme.

[0025] Furthermore, in a preferred embodiment of the present invention, a large data network is searched based on the set of bacteria and algae requiring suppression to obtain multiple sub-processing schemes, and the sub-processing schemes are filtered to obtain the final processing scheme, specifically as follows:

[0026] Obtain the name information of each bacterium and algae in the collection of bacteria and algae that need to be suppressed, set key search terms according to the name information of each bacterium and algae, search in the big data network according to the key search terms, obtain multiple sub-processing schemes, and aggregate the multiple sub-processing schemes to obtain an initial processing scheme collection.

[0027] Obtain the historical performance efficiency of each sub-processing scheme in the processing scheme set, and compare the historical performance efficiency of each sub-processing scheme with the preset performance efficiency;

[0028] Sub-processing schemes with historical performance efficiency not greater than the preset performance efficiency are removed from the initial processing scheme set, while sub-processing schemes with historical performance efficiency greater than the preset performance efficiency are retained from the initial processing scheme set, resulting in a processing scheme set after one filtering.

[0029] Obtain the physicochemical properties of each sub-processing scheme in the processing scheme set after the first screening, and determine whether the physicochemical properties are preset physicochemical properties; remove the sub-processing schemes with preset physicochemical properties from the processing scheme set after the first screening, and retain the sub-processing schemes with non-preset physicochemical properties from the processing scheme set after the first screening, to obtain the processing scheme set after the second screening.

[0030] Obtain the historical performance of each sub-processing scheme in the set of processing schemes after secondary filtering, construct a sequence list, import the historical performance of each sub-processing scheme in the set of processing schemes after secondary filtering into the sequence list and sort them from largest to smallest. After sorting, extract the maximum historical performance from the sequence list, obtain the sub-processing scheme corresponding to the maximum historical performance, and mark the sub-processing scheme corresponding to the maximum historical performance as the final processing scheme.

[0031] Furthermore, in a preferred embodiment of the present invention, the actual environmental parameters of the standard coagulation shed within a preset time period are obtained, and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters are obtained. Based on the actual environmental parameters within the preset time period and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters, the optimal treatment time period is determined, specifically as follows:

[0032] The actual environmental parameters of the standard roughing shed within a preset time period are obtained, the preset time period is divided into several sub-time periods, and the sub-actual environmental parameter information corresponding to each sub-time period is obtained; wherein, the environmental parameters include the temperature information, oxygen concentration information, and humidity information of the standard roughing shed;

[0033] The survival rates of each bacterium and algae in the bacterium and algae collection under different environmental parameters are obtained by big data network, a bacterium and algae survival rate prediction model is constructed, and the survival rates of each bacterium and algae in the bacterium and algae collection under different environmental parameters are imported into the bacterium and algae survival rate prediction model for training, so as to obtain the bacterium and algae survival rate prediction model after training.

[0034] The actual environmental parameter information corresponding to each sub-time period is imported into the trained bacterial and algal survival rate prediction model to obtain the actual survival rate of each bacterial and algal in the bacterial and algal aggregate within each sub-time period.

[0035] The correlation analysis method is used to analyze the correlation between the actual survival rate of each bacterium and algae in the bacterium and algae collection and the preset survival rate in each sub-time period. Based on the correlation, the weight vector information is determined. The weight vector information is analyzed by the analytic hierarchy process to obtain the evaluation score of the actual survival rate of each bacterium and algae in the bacterium and algae collection in each sub-time period.

[0036] A second sequence list is constructed, and the evaluation scores of the actual survival rates of each bacterium and algae in the bacterium and algae collection within each sub-time period are imported into the second sequence list and sorted by size to extract the lowest evaluation score. The sub-time period corresponding to the lowest evaluation score is obtained, and the sub-time period corresponding to the lowest evaluation score is marked as the optimal processing time period. The optimal processing time period is then output.

[0037] A second aspect of this invention discloses a marking system for tiger prawns, the system comprising a memory and a processor. The memory stores a marking method program for tiger prawns, and when the processor executes the marking method program, it performs the following steps:

[0038] Obtain the current nursery time point and the stocking density information of shrimp larvae in the nursery pond, and obtain a real-time feed feeding plan based on the current nursery time point and stocking density information;

[0039] The historical feeding schemes of the nursery ponds are obtained through a big data network, and the historical water quality data of the nursery ponds after each historical feeding scheme is obtained through the big data network. Based on the historical feeding schemes and historical water quality data, the actual water quality data of the nursery ponds after the real-time feeding scheme is predicted.

[0040] The germination rates of various bacteria and algae under different water quality conditions are obtained through big data networks. Based on the germination rates of each bacteria and algae and the actual water quality data, a set of bacteria and algae that need to be suppressed after being fed with a real-time feed feeding program is obtained.

[0041] Based on the set of bacteria and algae that need to be suppressed, a big data network is searched to obtain multiple sub-processing schemes, and the sub-processing schemes are screened to obtain the final processing scheme.

[0042] The actual environmental parameters of the standard coagulation shed within a preset time period are obtained, and the survival rate of each bacterium and algae in the bacterium and algae ensemble under different environmental parameters is obtained. Based on the actual environmental parameters within the preset time period and the survival rate of each bacterium and algae in the bacterium and algae ensemble under different environmental parameters, the optimal treatment time period is determined.

[0043] Furthermore, in a preferred embodiment of the present invention, the current nursery time point and the stocking density information of shrimp larvae in the nursery are obtained, and a real-time feed feeding plan is obtained based on the current nursery time point and the stocking density information, specifically as follows:

[0044] By acquiring feed feeding characteristics information of shrimp larvae at each growth stage through a big data network, a database is constructed, and the feed feeding characteristics information of shrimp larvae at each growth stage is imported into the database to obtain a characteristic database; wherein, the feed feeding characteristics information includes feed type and feed amount required per shrimp larvae.

[0045] Obtain the current nursery time point of the nursery pond, import the current nursery time point into the characteristic database, and obtain the feed type required for shrimp larvae at the current nursery time point;

[0046] Obtain the stocking density information of shrimp larvae in the nursery pond, import the stocking density information into the characteristic database, and obtain the amount of feed required for the shrimp larvae at the current nursery time point;

[0047] A real-time feeding plan is generated based on the type and amount of feed required by the shrimp larvae at the current nursery stage, and the real-time feeding plan is output.

[0048] Furthermore, in a preferred embodiment of the present invention, a large data network is searched based on the set of bacteria and algae requiring suppression to obtain multiple sub-processing schemes, and the sub-processing schemes are filtered to obtain the final processing scheme, specifically as follows:

[0049] Obtain the name information of each bacterium and algae in the collection of bacteria and algae that need to be suppressed, set key search terms according to the name information of each bacterium and algae, search in the big data network according to the key search terms, obtain multiple sub-processing schemes, and aggregate the multiple sub-processing schemes to obtain an initial processing scheme collection.

[0050] Obtain the historical performance efficiency of each sub-processing scheme in the processing scheme set, and compare the historical performance efficiency of each sub-processing scheme with the preset performance efficiency;

[0051] Sub-processing schemes with historical performance efficiency not greater than the preset performance efficiency are removed from the initial processing scheme set, while sub-processing schemes with historical performance efficiency greater than the preset performance efficiency are retained from the initial processing scheme set, resulting in a processing scheme set after one filtering.

[0052] Obtain the physicochemical properties of each sub-processing scheme in the processing scheme set after the first screening, and determine whether the physicochemical properties are preset physicochemical properties; remove the sub-processing schemes with preset physicochemical properties from the processing scheme set after the first screening, and retain the sub-processing schemes with non-preset physicochemical properties from the processing scheme set after the first screening, to obtain the processing scheme set after the second screening.

[0053] Obtain the historical performance of each sub-processing scheme in the set of processing schemes after secondary filtering, construct a sequence list, import the historical performance of each sub-processing scheme in the set of processing schemes after secondary filtering into the sequence list and sort them from largest to smallest. After sorting, extract the maximum historical performance from the sequence list, obtain the sub-processing scheme corresponding to the maximum historical performance, and mark the sub-processing scheme corresponding to the maximum historical performance as the final processing scheme.

[0054] Furthermore, in a preferred embodiment of the present invention, the actual environmental parameters of the standard coagulation shed within a preset time period are obtained, and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters are obtained. Based on the actual environmental parameters within the preset time period and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters, the optimal treatment time period is determined, specifically as follows:

[0055] The actual environmental parameters of the standard roughing shed within a preset time period are obtained, the preset time period is divided into several sub-time periods, and the sub-actual environmental parameter information corresponding to each sub-time period is obtained; wherein, the environmental parameters include the temperature information, oxygen concentration information, and humidity information of the standard roughing shed;

[0056] The survival rates of each bacterium and algae in the bacterium and algae collection under different environmental parameters are obtained by big data network, a bacterium and algae survival rate prediction model is constructed, and the survival rates of each bacterium and algae in the bacterium and algae collection under different environmental parameters are imported into the bacterium and algae survival rate prediction model for training, so as to obtain the bacterium and algae survival rate prediction model after training.

[0057] The actual environmental parameter information corresponding to each sub-time period is imported into the trained bacterial and algal survival rate prediction model to obtain the actual survival rate of each bacterial and algal in the bacterial and algal aggregate within each sub-time period.

[0058] The correlation analysis method is used to analyze the correlation between the actual survival rate of each bacterium and algae in the bacterium and algae collection and the preset survival rate in each sub-time period. Based on the correlation, the weight vector information is determined. The weight vector information is analyzed by the analytic hierarchy process to obtain the evaluation score of the actual survival rate of each bacterium and algae in the bacterium and algae collection in each sub-time period.

[0059] A second sequence list is constructed, and the evaluation scores of the actual survival rates of each bacterium and algae in the bacterium and algae collection within each sub-time period are imported into the second sequence list and sorted by size to extract the lowest evaluation score. The sub-time period corresponding to the lowest evaluation score is obtained, and the sub-time period corresponding to the lowest evaluation score is marked as the optimal processing time period. The optimal processing time period is then output.

[0060] This invention addresses the technical deficiencies in the prior art and offers the following advantages: The method enables the development of feeding schemes for different stages of the nursery, achieving efficient and precise feeding. Furthermore, based on the developed feeding scheme, the water quality data of the nursery after feeding can be predicted, allowing for the determination of whether harmful bacteria and algae will proliferate. This leads to the development of a harmful bacteria and algae suppression treatment plan, preventing further outbreaks. Moreover, while ensuring a high success rate, the invention reduces the use of chemical treatments, further minimizing the impact on the water body, reducing subsequent water treatment processes, and lowering treatment costs. Attached Figure Description

[0061] 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.

[0062] Figure 1 A flowchart of the first method for grading tiger prawns;

[0063] Figure 2 This is a flowchart of the second method of a method for grading tiger prawns;

[0064] Figure 3 This is a flowchart of a third method for grading tiger prawns;

[0065] Figure 4 This is a system block diagram of a piglet peddling system for tiger prawns. Detailed Implementation

[0066] 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.

[0067] 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.

[0068] The first aspect of this invention discloses a method for grading tiger prawns, such as... Figure 1 As shown, it includes the following steps:

[0069] S102: Obtain the current nursery time point of the nursery pond and the stocking density information of shrimp larvae in the nursery pond, and obtain a real-time feed feeding plan based on the current nursery time point and stocking density information;

[0070] S104: Obtain historical feeding schemes for the nursery pond through a big data network, and obtain historical water quality data corresponding to the nursery pond after feeding with each historical feeding scheme through a big data network. Based on the historical feeding schemes and historical water quality data, predict the actual water quality data of the nursery pond after feeding with the real-time feeding scheme.

[0071] S106: Obtain the germination rate of each bacterium and algae under different water quality data conditions through big data network, and obtain the set of bacterium and algae that need to be suppressed after feeding with real-time feed feeding scheme based on the germination rate of each bacterium and algae and the actual water quality data.

[0072] S108: Based on the set of bacteria and algae that need to be suppressed, the big data network is searched to obtain multiple sub-processing schemes, and the sub-processing schemes are screened to obtain the final processing scheme;

[0073] S110: Obtain the actual environmental parameters of the standard coagulation shed within a preset time period, obtain the survival rate of each bacterium and algae in the bacterium and algae collection under different environmental parameters, and determine the optimal treatment time period based on the actual environmental parameters within the preset time period and the survival rate of each bacterium and algae in the bacterium and algae collection under different environmental parameters.

[0074] It should be noted that this method can formulate feeding plans for different stages of the nursery, thereby achieving efficient and precise feeding. Simultaneously, based on the formulated feeding plans, the water quality data of the nursery after feeding can be predicted, thus determining whether harmful bacteria and algae will proliferate. This allows for the development of harmful bacteria and algae suppression treatment plans, preventing further outbreaks. Furthermore, while ensuring a high success rate, it can reduce the use of chemical treatment measures, further minimizing the impact on the water body, reducing subsequent water treatment processes, and lowering treatment costs.

[0075] Furthermore, in a preferred embodiment of the present invention, the current nursery time point and the stocking density information of shrimp larvae in the nursery are obtained, and a real-time feed feeding plan is obtained based on the current nursery time point and the stocking density information, specifically as follows:

[0076] By acquiring feed feeding characteristics information of shrimp larvae at each growth stage through a big data network, a database is constructed, and the feed feeding characteristics information of shrimp larvae at each growth stage is imported into the database to obtain a characteristic database; wherein, the feed feeding characteristics information includes feed type and feed amount required per shrimp larvae.

[0077] Obtain the current nursery time point of the nursery pond, import the current nursery time point into the characteristic database, and obtain the feed type required for shrimp larvae at the current nursery time point;

[0078] Obtain the stocking density information of shrimp larvae in the nursery pond, import the stocking density information into the characteristic database, and obtain the amount of feed required for the shrimp larvae at the current nursery time point;

[0079] A real-time feeding plan is generated based on the type and amount of feed required by the shrimp larvae at the current nursery stage, and the real-time feeding plan is output.

[0080] It should be noted that during the shrimp larvae rearing process, shrimp larvae have corresponding growth stages at different rearing time points, and the required feed amount and type vary at different growth stages. For example, when shrimp larvae are in the hepatocellular stage, high-quality feed should be used. Hepatoprotective bile acids can be added to the feed to improve the shrimp larvae's intestinal health, enhance immunity, provide antibacterial and antiviral effects, and reduce stress. Immunopolysaccharides can also be used to protect the hepatocellular carcinoma, enhance immunity and survival rate, ensure successful hepatocellular transition, and guarantee rapid growth and fewer diseases in the shrimp larvae. This method can effectively obtain the required feed type and amount at different rearing time points (different growth stages of shrimp larvae) from a characteristic database, thereby developing a real-time feed feeding plan. This achieves efficient and precise feeding for rearing, and can further predict water quality changes in the rearing pond after feeding based on the real-time feed feeding plan.

[0081] Furthermore, in a preferred embodiment of the present invention, historical feeding schemes for the nursery ponds are obtained through a big data network, and historical water quality data corresponding to the nursery ponds after being fed according to each historical feeding scheme are also obtained through the big data network. Based on the historical feeding schemes and historical water quality data, the actual water quality data of the nursery ponds after being fed according to the real-time feeding scheme is predicted, such as... Figure 2 As shown, specifically:

[0082] S202: Obtain historical feeding plans for the pre-nursing ponds through a big data network, and obtain historical water quality data for the pre-nursing ponds after each historical feeding plan through a big data network.

[0083] S204: Construct a water quality prediction model based on a convolutional neural network, and import the historical water quality data corresponding to the pre-feeding pond after each historical feeding scheme into the water quality prediction model for training, to obtain a trained water quality prediction model.

[0084] S206: Import the real-time feeding scheme into the trained water quality prediction model, and use grey relational analysis to pair the real-time feeding scheme with each historical feeding scheme to obtain several pairing rates; construct a size sorting table, and import the several pairing rates into the size sorting table for sorting to obtain the maximum pairing rate;

[0085] S208: Obtain the historical feeding scheme corresponding to the maximum pairing rate, and obtain the historical water quality data associated with the historical feeding scheme corresponding to the maximum pairing rate. Based on the historical water quality data associated with the historical feeding scheme corresponding to the maximum pairing rate, predict the actual water quality data of the nursery pond after feeding with the real-time feeding scheme.

[0086] It should be noted that by acquiring historical feeding plans and historical water quality data of the nursery ponds after feeding according to the historical feeding plans, and combining this with the currently formulated real-time feeding plan, the actual water quality data of the nursery ponds after feeding according to the real-time feeding plan can be predicted. By acquiring historical data through big data and then using grey relational analysis for pairing comparison, the predicted actual water quality data has high reliability. Furthermore, the system does not require a large amount of complex calculations, which can improve the calculation speed and thus improve the robustness of the system.

[0087] Furthermore, in a preferred embodiment of the present invention, the germination rates of various bacteria and algae under different water quality data conditions are obtained through a big data network. Based on the germination rates of each bacteria and algae and the actual water quality data, a set of bacteria and algae that need to be suppressed after being fed with a real-time feed feeding scheme is obtained, specifically:

[0088] The germination rates of various bacteria and algae under different water quality conditions are obtained through big data networks. An evaluation model is constructed based on a deep learning network. The germination rates of various bacteria and algae under different water quality conditions are then imported into the evaluation model for training, resulting in a trained evaluation model.

[0089] Obtain the actual water quality data of the pre-feeding pond after feeding with a real-time feed program, import the actual water quality data into the evaluation model after training, and obtain the actual germination rate corresponding to the preset bacteria and algae.

[0090] Determine whether the actual germination rate of the preset bacteria and algae is greater than the preset germination rate. If it is greater, mark and aggregate the bacteria and algae corresponding to the actual germination rate that is greater than the preset germination rate to obtain a set of bacteria and algae that need to be suppressed after being fed by the real-time feed feeding scheme.

[0091] It should be noted that the preset bacteria and algae include, but are not limited to, harmful bacteria and algae such as cyanobacteria, Vibrio, and monotypic bacteria. Due to varying water quality conditions, the germination rates of different bacteria and algae differ. For example, cyanobacteria thrive in water environments with low salinity, high pH, ​​and high organic phosphorus concentrations. After predicting the actual water quality data of the nursery pond after feeding according to the real-time feeding plan, the system further predicts whether the water environment after feeding is suitable for the germination and growth of the preset bacteria and algae. When the actual germination rate of a certain type of bacteria and algae is greater than the preset germination rate, it indicates a higher probability of proliferation and outbreak after feeding. In this case, the bacteria and algae with actual germination rates greater than the preset germination rate are marked and aggregated to obtain a set of bacteria and algae that require suppression treatment after feeding according to the real-time feeding plan.

[0092] Furthermore, in a preferred embodiment of the present invention, a large data network is searched based on the set of bacteria and algae requiring suppression to obtain multiple sub-processing schemes, and the sub-processing schemes are filtered to obtain the final processing scheme, specifically as follows:

[0093] Obtain the name information of each bacterium and algae in the collection of bacteria and algae that need to be suppressed, set key search terms according to the name information of each bacterium and algae, search in the big data network according to the key search terms, obtain multiple sub-processing schemes, and aggregate the multiple sub-processing schemes to obtain an initial processing scheme collection.

[0094] Obtain the historical performance efficiency of each sub-processing scheme in the processing scheme set, and compare the historical performance efficiency of each sub-processing scheme with the preset performance efficiency;

[0095] Sub-processing schemes with historical performance efficiency not greater than the preset performance efficiency are removed from the initial processing scheme set, while sub-processing schemes with historical performance efficiency greater than the preset performance efficiency are retained from the initial processing scheme set, resulting in a processing scheme set after one filtering.

[0096] Obtain the physicochemical properties of each sub-processing scheme in the processing scheme set after the first screening, and determine whether the physicochemical properties are preset physicochemical properties; remove the sub-processing schemes with preset physicochemical properties from the processing scheme set after the first screening, and retain the sub-processing schemes with non-preset physicochemical properties from the processing scheme set after the first screening, to obtain the processing scheme set after the second screening.

[0097] Obtain the historical performance of each sub-processing scheme in the set of processing schemes after secondary filtering, construct a sequence list, import the historical performance of each sub-processing scheme in the set of processing schemes after secondary filtering into the sequence list and sort them from largest to smallest. After sorting, extract the maximum historical performance from the sequence list, obtain the sub-processing scheme corresponding to the maximum historical performance, and mark the sub-processing scheme corresponding to the maximum historical performance as the final processing scheme.

[0098] It should be noted that, based on the names of the corresponding harmful bacteria and algae, a search is performed on a large data network to obtain a set of initial treatment schemes for suppressing and treating the corresponding harmful bacteria and algae. This set of initial treatment schemes includes both physical and chemical treatment schemes. For example, when suppressing cyanobacteria, cyanobacterial purification agents can be used, or physical methods such as appropriately lowering the water temperature can be employed. The physicochemical properties of each sub-treatment scheme refer to their physical and chemical properties. The preset physicochemical properties are the chemical properties. This method allows for the retrieval of initial treatment schemes for bacteria and algae from the set of bacteria and algae to be suppressed. These initial schemes are then filtered to obtain the final treatment scheme, enabling staff to treat the harmful bacteria and algae according to the final scheme, thus improving the success rate of initial treatment. Furthermore, this method, while ensuring a high success rate, reduces the use of chemical treatment measures, further minimizing the impact on the water body, reducing subsequent water treatment steps, and lowering treatment costs.

[0099] Furthermore, in a preferred embodiment of the present invention, the actual environmental parameters of the standard coagulation shed within a preset time period are obtained, and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters are obtained. Based on the actual environmental parameters within the preset time period and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters, the optimal treatment time period is determined, such as... Figure 3 As shown, specifically:

[0100] S302: Obtain the actual environmental parameters of the standard burial shed within a preset time period, divide the preset time period into several sub-time periods, and obtain the sub-actual environmental parameter information corresponding to each sub-time period; wherein, the environmental parameters include the temperature information, oxygen concentration information, and humidity information of the standard burial shed;

[0101] S304: Obtain the survival rate of each bacterium and algae in the bacterium and algae collection under different environmental parameters through big data network, construct a bacterium and algae survival rate prediction model, and import the survival rate of each bacterium and algae in the bacterium and algae collection under different environmental parameters into the bacterium and algae survival rate prediction model for training, and obtain the trained bacterium and algae survival rate prediction model.

[0102] S306: Import the sub-actual environmental parameter information corresponding to each sub-time period into the trained bacterial and algal survival rate prediction model to obtain the actual survival rate of each bacterial and algal in the bacterial and algal aggregate within each sub-time period.

[0103] S308: The correlation between the actual survival rate of each bacterium and algae in the bacterium and algae collection and the preset survival rate in each sub-time period is analyzed by correlation analysis. Based on the correlation, the weight vector information is determined. The weight vector information is analyzed by the analytic hierarchy process to obtain the evaluation score of the actual survival rate of each bacterium and algae in the bacterium and algae collection in each sub-time period.

[0104] A second sequence list is constructed, and the evaluation scores of the actual survival rates of each bacterium and algae in the bacterium and algae collection within each sub-time period are imported into the second sequence list and sorted by size to extract the lowest evaluation score. The sub-time period corresponding to the lowest evaluation score is obtained, and the sub-time period corresponding to the lowest evaluation score is marked as the optimal processing time period. The optimal processing time period is then output.

[0105] It should be noted that correlation analysis refers to analyzing two or more correlated variables to measure the degree of correlation between them. Correlation analysis requires a certain connection or probability between the correlated elements. Grey relational analysis, on the other hand, measures the degree of correlation between factors based on the similarity or dissimilarity of their development trends, i.e., the "grey relational degree." Specifically, the weight vector information represents the close relationship between the actual survival rate of each bacterium and algae in the bacterium-algae aggregate and the preset survival rate under the adjustment of actual environmental parameters. The preset survival rate is set below 5%. The lower the evaluation score, the lower the relative survival rate and relative activity of each bacterium and algae in the aggregate, and the better the treatment effect during this time period.

[0106] It should be noted that during the nursery process, the environmental parameters inside the nursery shed need to be adjusted according to actual needs. For example, when shrimp larvae are in the hepatocellular stage, they are highly sensitive to changes in the external environment and have weak resistance, making them most susceptible to disease. Therefore, the temperature and humidity inside the shed need to be controlled at a low level to prevent further bacterial growth in the air, which could harm the normal growth of the shrimp larvae. At the same time, the survival rates of bacteria and algae vary depending on the environmental parameters of the shed. For example, blue-green algae have a lower survival rate and lower growth activity at lower temperatures. Therefore, this method utilizes this characteristic to select the time period when the actual survival rate of each bacterium and algae in the bacterium-algae mixture is at its lowest to treat and inhibit these harmful bacteria and algae. Treating and inhibiting harmful bacteria and algae during their lowest activity period not only improves the treatment effect but also reduces energy consumption.

[0107] The second aspect of this invention discloses a marking system for tiger prawns, the marking system comprising a memory 41 and a processor 62, wherein the memory 41 stores a marking method program for tiger prawns, and when the marking method program for tiger prawns is executed by the processor 62, such as... Figure 4 As shown, the following steps are performed:

[0108] Obtain the current nursery time point and the stocking density information of shrimp larvae in the nursery pond, and obtain a real-time feed feeding plan based on the current nursery time point and stocking density information;

[0109] The historical feeding schemes of the nursery ponds are obtained through a big data network, and the historical water quality data of the nursery ponds after each historical feeding scheme is obtained through the big data network. Based on the historical feeding schemes and historical water quality data, the actual water quality data of the nursery ponds after the real-time feeding scheme is predicted.

[0110] The germination rates of various bacteria and algae under different water quality conditions are obtained through big data networks. Based on the germination rates of each bacteria and algae and the actual water quality data, a set of bacteria and algae that need to be suppressed after being fed with a real-time feed feeding program is obtained.

[0111] Based on the set of bacteria and algae that need to be suppressed, a big data network is searched to obtain multiple sub-processing schemes, and the sub-processing schemes are screened to obtain the final processing scheme.

[0112] The actual environmental parameters of the standard coagulation shed within a preset time period are obtained, and the survival rate of each bacterium and algae in the bacterium and algae ensemble under different environmental parameters is obtained. Based on the actual environmental parameters within the preset time period and the survival rate of each bacterium and algae in the bacterium and algae ensemble under different environmental parameters, the optimal treatment time period is determined.

[0113] Furthermore, in a preferred embodiment of the present invention, the current nursery time point and the stocking density information of shrimp larvae in the nursery are obtained, and a real-time feed feeding plan is obtained based on the current nursery time point and the stocking density information, specifically as follows:

[0114] By acquiring feed feeding characteristics information of shrimp larvae at each growth stage through a big data network, a database is constructed, and the feed feeding characteristics information of shrimp larvae at each growth stage is imported into the database to obtain a characteristic database; wherein, the feed feeding characteristics information includes feed type and feed amount required per shrimp larvae.

[0115] Obtain the current nursery time point of the nursery pond, import the current nursery time point into the characteristic database, and obtain the feed type required for shrimp larvae at the current nursery time point;

[0116] Obtain the stocking density information of shrimp larvae in the nursery pond, import the stocking density information into the characteristic database, and obtain the amount of feed required for the shrimp larvae at the current nursery time point;

[0117] A real-time feeding plan is generated based on the type and amount of feed required by the shrimp larvae at the current nursery stage, and the real-time feeding plan is output.

[0118] Furthermore, in a preferred embodiment of the present invention, a large data network is searched based on the set of bacteria and algae requiring suppression to obtain multiple sub-processing schemes, and the sub-processing schemes are filtered to obtain the final processing scheme, specifically as follows:

[0119] Obtain the name information of each bacterium and algae in the collection of bacteria and algae that need to be suppressed, set key search terms according to the name information of each bacterium and algae, search in the big data network according to the key search terms, obtain multiple sub-processing schemes, and aggregate the multiple sub-processing schemes to obtain an initial processing scheme collection.

[0120] Obtain the historical performance efficiency of each sub-processing scheme in the processing scheme set, and compare the historical performance efficiency of each sub-processing scheme with the preset performance efficiency;

[0121] Sub-processing schemes with historical performance efficiency not greater than the preset performance efficiency are removed from the initial processing scheme set, while sub-processing schemes with historical performance efficiency greater than the preset performance efficiency are retained from the initial processing scheme set, resulting in a processing scheme set after one filtering.

[0122] Obtain the physicochemical properties of each sub-processing scheme in the processing scheme set after the first screening, and determine whether the physicochemical properties are preset physicochemical properties; remove the sub-processing schemes with preset physicochemical properties from the processing scheme set after the first screening, and retain the sub-processing schemes with non-preset physicochemical properties from the processing scheme set after the first screening, to obtain the processing scheme set after the second screening.

[0123] Obtain the historical performance of each sub-processing scheme in the set of processing schemes after secondary filtering, construct a sequence list, import the historical performance of each sub-processing scheme in the set of processing schemes after secondary filtering into the sequence list and sort them from largest to smallest. After sorting, extract the maximum historical performance from the sequence list, obtain the sub-processing scheme corresponding to the maximum historical performance, and mark the sub-processing scheme corresponding to the maximum historical performance as the final processing scheme.

[0124] Furthermore, in a preferred embodiment of the present invention, the actual environmental parameters of the standard coagulation shed within a preset time period are obtained, and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters are obtained. Based on the actual environmental parameters within the preset time period and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters, the optimal treatment time period is determined, specifically as follows:

[0125] The actual environmental parameters of the standard roughing shed within a preset time period are obtained, the preset time period is divided into several sub-time periods, and the sub-actual environmental parameter information corresponding to each sub-time period is obtained; wherein, the environmental parameters include the temperature information, oxygen concentration information, and humidity information of the standard roughing shed;

[0126] The survival rates of each bacterium and algae in the bacterium and algae collection under different environmental parameters are obtained by big data network, a bacterium and algae survival rate prediction model is constructed, and the survival rates of each bacterium and algae in the bacterium and algae collection under different environmental parameters are imported into the bacterium and algae survival rate prediction model for training, so as to obtain the bacterium and algae survival rate prediction model after training.

[0127] The actual environmental parameter information corresponding to each sub-time period is imported into the trained bacterial and algal survival rate prediction model to obtain the actual survival rate of each bacterial and algal in the bacterial and algal aggregate within each sub-time period.

[0128] The correlation analysis method is used to analyze the correlation between the actual survival rate of each bacterium and algae in the bacterium and algae collection and the preset survival rate in each sub-time period. Based on the correlation, the weight vector information is determined. The weight vector information is analyzed by the analytic hierarchy process to obtain the evaluation score of the actual survival rate of each bacterium and algae in the bacterium and algae collection in each sub-time period.

[0129] A second sequence list is constructed, and the evaluation scores of the actual survival rates of each bacterium and algae in the bacterium and algae collection within each sub-time period are imported into the second sequence list and sorted by size to extract the lowest evaluation score. The sub-time period corresponding to the lowest evaluation score is obtained, and the sub-time period corresponding to the lowest evaluation score is marked as the optimal processing time period. The optimal processing time period is then output.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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 method for juvenile tiger prawns, characterized in that, Includes the following steps: Obtain the current nursery time point and the stocking density information of shrimp larvae in the nursery pond, and obtain a real-time feed feeding plan based on the current nursery time point and stocking density information; The historical feeding schemes of the nursery ponds are obtained through a big data network, and the historical water quality data of the nursery ponds after each historical feeding scheme is obtained through the big data network. Based on the historical feeding schemes and historical water quality data, the actual water quality data of the nursery ponds after the real-time feeding scheme is predicted. The germination rates of various bacteria and algae under different water quality conditions are obtained through big data networks. Based on the germination rates of each bacteria and algae and the actual water quality data, a set of bacteria and algae that need to be suppressed after being fed with a real-time feed feeding program is obtained. Based on the set of bacteria and algae requiring suppression, a search is performed on the big data network to obtain multiple sub-processing schemes. These sub-processing schemes are then filtered to obtain the final processing scheme, specifically: Obtain the name information of each bacterium and algae in the collection of bacteria and algae that need to be suppressed, set key search terms according to the name information of each bacterium and algae, search in the big data network according to the key search terms, obtain multiple sub-processing schemes, and aggregate the multiple sub-processing schemes to obtain an initial processing scheme collection. Obtain the historical performance efficiency of each sub-processing scheme in the processing scheme set, and compare the historical performance efficiency of each sub-processing scheme with the preset performance efficiency; Sub-processing schemes with historical performance efficiency not greater than the preset performance efficiency are removed from the initial processing scheme set, while sub-processing schemes with historical performance efficiency greater than the preset performance efficiency are retained from the initial processing scheme set, resulting in a processing scheme set after one filtering. Obtain the physicochemical properties of each sub-processing scheme in the processing scheme set after the first screening, and determine whether the physicochemical properties are preset physicochemical properties; remove the sub-processing schemes with preset physicochemical properties from the processing scheme set after the first screening, and retain the sub-processing schemes with non-preset physicochemical properties from the processing scheme set after the first screening, to obtain the processing scheme set after the second screening. Obtain the historical performance of each sub-processing scheme in the set of processing schemes after secondary screening, construct a sequence list, import the historical performance of each sub-processing scheme in the set of processing schemes after secondary screening into the sequence list and sort them from largest to smallest. After sorting, extract the maximum historical performance from the sequence list, obtain the sub-processing scheme corresponding to the maximum historical performance, and mark the sub-processing scheme corresponding to the maximum historical performance as the final processing scheme. The actual environmental parameters of the standard coagulation shed within a preset time period are obtained, and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters are obtained. Based on the actual environmental parameters within the preset time period and the survival rates of each bacterium and algae in the bacterium-algae aggregate under different environmental parameters, the optimal treatment time period is determined, specifically as follows: The actual environmental parameters of the standard roughing shed within a preset time period are obtained, the preset time period is divided into several sub-time periods, and the sub-actual environmental parameter information corresponding to each sub-time period is obtained; wherein, the environmental parameters include the temperature information, oxygen concentration information, and humidity information of the standard roughing shed; The survival rates of each bacterium and algae in the bacterium and algae collection under different environmental parameters are obtained by big data network, a bacterium and algae survival rate prediction model is constructed, and the survival rates of each bacterium and algae in the bacterium and algae collection under different environmental parameters are imported into the bacterium and algae survival rate prediction model for training, so as to obtain the bacterium and algae survival rate prediction model after training. The actual environmental parameter information corresponding to each sub-time period is imported into the trained bacterial and algal survival rate prediction model to obtain the actual survival rate of each bacterial and algal in the bacterial and algal aggregate within each sub-time period. The correlation analysis method is used to analyze the correlation between the actual survival rate of each bacterium and algae in the bacterium and algae collection and the preset survival rate in each sub-time period. Based on the correlation, the weight vector information is determined. The weight vector information is analyzed by the analytic hierarchy process to obtain the evaluation score of the actual survival rate of each bacterium and algae in the bacterium and algae collection in each sub-time period. A second sequence list is constructed, and the evaluation scores of the actual survival rates of each bacterium and algae in the bacterium and algae collection within each sub-time period are imported into the second sequence list and sorted by size to extract the lowest evaluation score. The sub-time period corresponding to the lowest evaluation score is obtained, and the sub-time period corresponding to the lowest evaluation score is marked as the optimal processing time period. The optimal processing time period is then output.

2. The method for raising tiger prawns according to claim 1, characterized in that, The current nursery time point and the stocking density information of shrimp larvae in the nursery are obtained. Based on the current nursery time point and stocking density information, a real-time feed feeding plan is obtained, specifically as follows: By acquiring feed feeding characteristics information of shrimp larvae at each growth stage through a big data network, a database is constructed, and the feed feeding characteristics information of shrimp larvae at each growth stage is imported into the database to obtain a characteristic database; wherein, the feed feeding characteristics information includes feed type and feed amount required per shrimp larvae. Obtain the current nursery time point of the nursery pond, import the current nursery time point into the characteristic database, and obtain the feed type required for shrimp larvae at the current nursery time point; Obtain the stocking density information of shrimp larvae in the nursery pond, import the stocking density information into the characteristic database, and obtain the amount of feed required for the shrimp larvae at the current nursery time point; A real-time feeding plan is generated based on the type and amount of feed required by the shrimp larvae at the current nursery stage, and the real-time feeding plan is output.

3. The method for raising tiger prawns according to claim 1, characterized in that, Historical feeding schemes for the nursery ponds are obtained through a big data network, and historical water quality data corresponding to these schemes after feeding under each scheme are also obtained. Based on these historical feeding schemes and water quality data, the actual water quality data of the nursery ponds after feeding under a real-time feeding scheme is predicted. Specifically: Historical feeding schemes for the nursery ponds were obtained through big data networks, and historical water quality data for the nursery ponds after each historical feeding scheme was obtained through big data networks. A water quality prediction model is constructed based on a convolutional neural network, and the historical water quality data corresponding to the pre-feeding pond after each historical feeding scheme is imported into the water quality prediction model for training, thus obtaining a trained water quality prediction model. The real-time feeding scheme is imported into the trained water quality prediction model. The real-time feeding scheme is paired with each historical feeding scheme using grey relational analysis to obtain several pairing rates. A size sorting table is constructed, and the several pairing rates are imported into the size sorting table for sorting to obtain the maximum pairing rate. Obtain the historical feeding scheme corresponding to the maximum pairing rate, and obtain the historical water quality data associated with the historical feeding scheme corresponding to the maximum pairing rate. Based on the historical water quality data associated with the historical feeding scheme corresponding to the maximum pairing rate, predict the actual water quality data of the nursery pond after feeding with the real-time feeding scheme.

4. The method for raising tiger prawns according to claim 1, characterized in that, The germination rates of various bacteria and algae under different water quality conditions were obtained through big data networks. Based on the germination rates of these bacteria and algae and the actual water quality data, a set of bacteria and algae that require suppression treatment after being fed with a real-time feed program was obtained, specifically: The germination rates of various bacteria and algae under different water quality conditions are obtained through big data networks. An evaluation model is constructed based on a deep learning network. The germination rates of various bacteria and algae under different water quality conditions are then imported into the evaluation model for training, resulting in a trained evaluation model. Obtain the actual water quality data of the pre-feeding pond after feeding with a real-time feed program, import the actual water quality data into the evaluation model after training, and obtain the actual germination rate corresponding to the preset bacteria and algae. Determine whether the actual germination rate of the preset bacteria and algae is greater than the preset germination rate. If it is greater, mark and aggregate the bacteria and algae corresponding to the actual germination rate that is greater than the preset germination rate to obtain a set of bacteria and algae that need to be suppressed after being fed by the real-time feed feeding scheme.

5. A grading system for tiger prawns, characterized in that, The tiger prawn grading system includes a memory and a processor. The memory stores a tiger prawn grading method program. When the tiger prawn grading method program is executed by the processor, it implements the steps of the tiger prawn grading method as described in any one of claims 1 to 4.

Images