New prawn breeding data analysis and recommendation method, system and medium

Abstract

The invention relates to a new prawn breeding data analysis and recommendation method, a new prawn breeding data analysis and recommendation system and a medium, and belongs to the technical field of new prawn breeding. According to the method, survival rate data of a plurality of new prawn types in a current culture area are obtained, secondary selection is carried out on the survival rate data of the plurality of new prawn types in the current culture area, a final new prawn type is obtained, and finally, seedling culture arrangement is carried out on the current culture area based on the final new prawn type. And monitoring the breeding data of the new prawns in the current breeding area. According to the method, the optimal new prawn variety is recommended according to the survival rate data of each new prawn variety under each environment characteristic data, so that the recommended new prawn variety is more suitable for culture, the culture success rate is improved, and the economic benefits of farmers are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of selective breeding of Metapenaeus ensis, and particularly relates to a method, system and medium for data analysis and recommendation of selective breeding of Metapenaeus ensis. Background Art

[0002] With the development of science and technology, agricultural production is constantly being redefined. Especially in aquaculture, the intelligent level has been continuously improved thanks to the progress of disciplines such as biology, machinery, and automation. When Metapenaeus ensis is put into use, various types of Metapenaeus ensis often need to be considered. Since different types of Metapenaeus ensis have different living habits and the survival rates of Metapenaeus ensis are inconsistent under different climate environments, this situation is not considered in the prior art, resulting in a large number of deaths of Metapenaeus ensis in the process of aquaculture when encountering extremely cold or high-temperature weather, causing huge economic losses to farmers. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method, system and medium for data analysis and recommendation of selective breeding of Metapenaeus ensis.

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

[0005] The first aspect of the present invention provides a method for data analysis and recommendation of selective breeding of Metapenaeus ensis, specifically including:

[0006] Obtain the survival rate data of each Metapenaeus ensis species under each environmental characteristic data, and construct a Metapenaeus ensis survival rate prediction model according to the survival rate data of each Metapenaeus ensis species under each environmental characteristic data;

[0007] Obtain the survival rate data of each Metapenaeus ensis species at different time periods in the current aquaculture area through the Metapenaeus ensis survival rate prediction model, and initially select several Metapenaeus ensis species in the current aquaculture area according to the survival rate data of each Metapenaeus ensis species at different time periods in the current aquaculture area;

[0008] Obtain the survival rate data of several Metapenaeus ensis species in the current aquaculture area, and obtain the final Metapenaeus ensis species through secondary selection of the survival rate data of several Metapenaeus ensis species in the current aquaculture area;

[0009] Based on the final Metapenaeus ensis species, arrange seedling cultivation in the current aquaculture area, and monitor the aquaculture data of Metapenaeus ensis in the current aquaculture area.

[0010] Further, in this method, obtaining the survival rate data of each Metapenaeus ensis species under each environmental characteristic data and constructing a Metapenaeus ensis survival rate prediction model according to the survival rate data of each Metapenaeus ensis species under each environmental characteristic data specifically includes:

[0011] Obtain the survival rate data of each new shrimp species under each environmental characteristic data, introduce a graph neural network, and input the survival rate data of each new shrimp species under each environmental characteristic data into the graph neural network;

[0012] Take the environmental characteristic data as the first graph node, take the survival rate data of the new shrimp species as the second graph node, connect the first graph node and the second graph node through a directed edge to describe the relationship, construct a topological structure diagram, and obtain the relevant adjacency matrix based on the topological structure diagram;

[0013] Construct a new shrimp survival rate prediction model based on a deep neural network, input the relevant adjacency matrix into the new shrimp survival rate prediction model for training, and when the loss function of the new shrimp survival rate prediction model converges to a preset value, save the model parameters and output the new shrimp survival rate prediction model.

[0014] Further, in this method, obtaining the survival rate data of each new shrimp species at different time periods in the current aquaculture area through the new shrimp survival rate prediction model specifically includes:

[0015] Obtain the historical environmental characteristic data of the current aquaculture area at each time period through big data, and input the historical environmental characteristic data of the current aquaculture area at each time period into the new shrimp survival rate prediction model for prediction;

[0016] Through prediction, obtain the survival rate data of each new shrimp species at different time periods in the current aquaculture area, and output the survival rate data of each new shrimp species at different time periods in the current aquaculture area.

[0017] Further, in this method, initially selecting several new shrimp species in the current aquaculture area according to the survival rate data of each new shrimp species at different time periods in the current aquaculture area, specifically:

[0018] Set a survival rate threshold, and judge whether the survival rate data of each new shrimp species at different time periods in the current aquaculture area are all greater than the survival rate threshold;

[0019] When the survival rate data of the new shrimp species at different time periods in the current aquaculture area are all greater than the survival rate threshold, then initially select the corresponding new shrimp species as the new shrimp species in the current aquaculture area;

[0020] When the survival rate data of the new shrimp species at different time periods in the current aquaculture area are not all greater than the survival rate threshold, then do not take the corresponding new shrimp species as the new shrimp species in the current aquaculture area;

[0021] Statistically analyze the quantity information of new shrimp species in the current aquaculture area, generate several new shrimp species in the current aquaculture area, and output the several new shrimp species in the current aquaculture area.

[0022] Furthermore, in this method, obtain the survival rate data of several new shrimp species in the current aquaculture area, and through secondary selection of the survival rate data of the several new shrimp species in the current aquaculture area, obtain the final new shrimp species. Specifically:

[0023] Obtain the survival rate data of several new shrimp species in the current aquaculture area, statistically analyze the average value of the survival rate data of the several new shrimp species in the current aquaculture area, and obtain the average survival rate data of the several new shrimp species in the current aquaculture area.

[0024] Construct a survival rate ranking table for new shrimp species, and input the average survival rate data of the several new shrimp species in the current aquaculture area into the survival rate ranking table for new shrimp species for sorting.

[0025] Through sorting, obtain the survival rate ranking table of new shrimp species after sorting, and obtain the new shrimp species corresponding to the highest average survival rate data from the survival rate ranking table of new shrimp species after sorting.

[0026] Take the new shrimp species corresponding to the highest average survival rate data as the final new shrimp species, and output the final new shrimp species.

[0027] Furthermore, in this method, based on the final new shrimp species, arrange the seedling cultivation in the current aquaculture area, and monitor the aquaculture data of new shrimp in the current aquaculture area. Specifically:

[0028] Obtain the optimal quantity information of new shrimp seedlings under each aquaculture area, construct a knowledge graph, and input the optimal quantity information of new shrimp seedlings under each aquaculture area into the knowledge graph for storage.

[0029] Obtain the aquaculture area of the current aquaculture area, input the aquaculture area of the current aquaculture area into the knowledge graph for data matching, obtain the optimal quantity information of new shrimp seedlings in the current aquaculture area, and arrange the seedling cultivation in the current aquaculture area according to the optimal quantity information of new shrimp seedlings in the current aquaculture area.

[0030] Collect the natural enemy image information of new shrimp within a preset range through an image acquisition device, statistically analyze the natural enemy quantity information of new shrimp within the preset range, and determine whether the natural enemy quantity information of new shrimp within the preset range is greater than the preset quantity information.

[0031] When the number information of the natural enemies of the penaeus vannamei within the preset range is greater than the preset number information, the natural enemies are driven away by the pre-arranged driving device.

[0032] The second aspect of the present invention provides a penaeus vannamei breeding data analysis and recommendation system, the system includes a memory and a processor, the memory includes a penaeus vannamei breeding data analysis and recommendation method program, when the penaeus vannamei breeding data analysis and recommendation method program is executed by the processor, the following steps are realized:

[0033] Obtain the survival rate data of each penaeus vannamei species under each environmental characteristic data, and construct a penaeus vannamei survival rate prediction model according to the survival rate data of each penaeus vannamei species under each environmental characteristic data;

[0034] Obtain the survival rate data of each penaeus vannamei species at different time periods in the current breeding area through the penaeus vannamei survival rate prediction model, and initially select several penaeus vannamei species in the current breeding area according to the survival rate data of each penaeus vannamei species at different time periods in the current breeding area;

[0035] Obtain the survival rate data of several penaeus vannamei species in the current breeding area, and obtain the final penaeus vannamei species by performing secondary selection on the survival rate data of several penaeus vannamei species in the current breeding area;

[0036] Based on the final penaeus vannamei species, arrange seedlings in the current breeding area, and monitor the breeding data of penaeus vannamei in the current breeding area.

[0037] The third aspect of the present invention provides a computer-readable storage medium, the computer-readable storage medium includes a penaeus vannamei breeding data analysis and recommendation method program, when the penaeus vannamei breeding data analysis and recommendation method program is executed by a processor, the steps of any of the penaeus vannamei breeding data analysis and recommendation methods are realized.

[0038] The present invention solves the defects existing in the background technology, and the present invention has the following beneficial effects:

[0039] The present invention obtains the survival rate data of each new prawn species under each environmental characteristic data, constructs a new prawn survival rate prediction model according to the survival rate data of each new prawn species under each environmental characteristic data, and then obtains the survival rate data of each new prawn species at different time periods in the current aquaculture area through the new prawn survival rate prediction model. And according to the survival rate data of each new prawn species at different time periods in the current aquaculture area, several new prawn species in the current aquaculture area are initially selected. Thus, by obtaining the survival rate data of several new prawn species in the current aquaculture area and through secondary selection of the survival rate data of several new prawn species in the current aquaculture area, the final new prawn species are obtained. Finally, based on the final new prawn species, the seedling arrangement in the current aquaculture area is carried out, and the aquaculture data of the new prawns in the current aquaculture area are monitored. The present invention recommends the optimal new prawn variety according to the survival rate data of each new prawn species under each environmental characteristic data, so that the recommended new prawn variety is more suitable for aquaculture, improves the success rate of aquaculture, and further improves the economic benefits of farmers. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0041] Figure 1 Shows the overall flowchart of the new prawn breeding data analysis and recommendation method;

[0042] Figure 2 Shows a partial flowchart of the new prawn breeding data analysis and recommendation method;

[0043] Figure 3 Shows the system block diagram of the new prawn breeding data analysis and recommendation system. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] In order to be able to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0045] Many specific details are set forth in the following description in order to provide a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0046] AsFigure 1 As shown in the figure, the first aspect of the present invention provides a method for analyzing and recommending data for the breeding of new penaeid shrimps, specifically including:

[0047] S102: Obtain the survival rate data of each new penaeid shrimp species under each environmental characteristic data, and construct a new penaeid shrimp survival rate prediction model according to the survival rate data of each new penaeid shrimp species under each environmental characteristic data;

[0048] S104: Obtain the survival rate data of each new penaeid shrimp species at different time periods in the current aquaculture area through the new penaeid shrimp survival rate prediction model, and preliminarily select several new penaeid shrimp species in the current aquaculture area according to the survival rate data of each new penaeid shrimp species at different time periods in the current aquaculture area;

[0049] S106: Obtain the survival rate data of several new penaeid shrimp species in the current aquaculture area, and obtain the final new penaeid shrimp species through secondary selection of the survival rate data of several new penaeid shrimp species in the current aquaculture area;

[0050] S108: Based on the final new penaeid shrimp species, arrange seedlings in the current aquaculture area, and monitor the aquaculture data of new penaeid shrimps in the current aquaculture area.

[0051] It should be noted that the present invention recommends the optimal new penaeid shrimp variety according to the survival rate data of each new penaeid shrimp species under each environmental characteristic data, so that the recommended new penaeid shrimp variety is more suitable for aquaculture, improves the success rate of aquaculture, and further improves the economic benefits of farmers.

[0052] Further, in this method, obtaining the survival rate data of each new penaeid shrimp species under each environmental characteristic data and constructing a new penaeid shrimp survival rate prediction model according to the survival rate data of each new penaeid shrimp species under each environmental characteristic data specifically includes:

[0053] Obtain the survival rate data of each new penaeid shrimp species under each environmental characteristic data, introduce a graph neural network, and input the survival rate data of each new penaeid shrimp species under each environmental characteristic data into the graph neural network;

[0054] Take the environmental characteristic data as the first graph node, take the survival rate data of the new penaeid shrimp species as the second graph node, connect the first graph node and the second graph node through a directed edge to describe the relationship, construct a topological structure diagram, and obtain the relevant adjacency matrix based on the topological structure diagram;

[0055] Construct a new penaeid shrimp survival rate prediction model based on a deep neural network, input the relevant adjacency matrix into the new penaeid shrimp survival rate prediction model for training, and when the loss function of the new penaeid shrimp survival rate prediction model converges to a preset value, save the model parameters and output the new penaeid shrimp survival rate prediction model.

[0056] It should be noted that the environmental characteristic data includes data such as temperature, humidity, and light radiation amount. Since different environmental characteristic data will result in inconsistent survival rates of various new shrimp species, a prediction model for the survival rate of new shrimp can be constructed through this method.

[0057] Furthermore, in this method, survival rate data of various new shrimp species in different time periods in the current farming area are obtained through the prediction model for the survival rate of new shrimp, specifically including:

[0058] Historical environmental characteristic data in each time period of the current farming area is obtained through big data, and the historical environmental characteristic data in each time period of the current farming area is input into the prediction model for the survival rate of new shrimp for prediction;

[0059] Through prediction, survival rate data of various new shrimp species in different time periods in the current farming area are obtained, and the survival rate data of various new shrimp species in different time periods in the current farming area are output.

[0060] Furthermore, in this method, several new shrimp species in the current farming area are initially selected according to the survival rate data of various new shrimp species in different time periods in the current farming area, specifically:

[0061] A survival rate threshold is set, and it is judged whether the survival rate data of various new shrimp species in different time periods in the current farming area are all greater than the survival rate threshold;

[0062] When the survival rate data of new shrimp species in different time periods in the current farming area are all greater than the survival rate threshold, the corresponding new shrimp species are initially selected as the new shrimp species in the current farming area;

[0063] When the survival rate data of new shrimp species in different time periods in the current farming area are not all greater than the survival rate threshold, the corresponding new shrimp species are not used as the new shrimp species in the current farming area;

[0064] The quantity information of the new shrimp species in the current farming area is counted, and several new shrimp species in the current farming area are generated, and the several new shrimp species in the current farming area are output.

[0065] It should be noted that when the survival rate data of new shrimp species in all time periods are not all greater than the survival rate threshold, it indicates that the corresponding new shrimp variety is not suitable for farming, and vice versa. Through this method, relatively excellent new shrimp varieties can be obtained and recommended to users.

[0066] Further, in this method, survival rate data of several new prawn species in the current aquaculture area are obtained, and the final new prawn species are obtained by secondarily selecting the survival rate data of several new prawn species in the current aquaculture area. Specifically:

[0067] Obtain the survival rate data of several new prawn species in the current aquaculture area, and calculate the average value of the survival rate data of several new prawn species in the current aquaculture area to obtain the average survival rate data of several new prawn species in the current aquaculture area.

[0068] Construct a survival rate ranking table for new prawn species, and input the average survival rate data of several new prawn species in the current aquaculture area into the survival rate ranking table for new prawn species for sorting.

[0069] Through sorting, obtain the survival rate ranking table of new prawn species after sorting, and obtain the new prawn species corresponding to the highest average survival rate data from the survival rate ranking table of new prawn species after sorting.

[0070] Take the new prawn species corresponding to the highest average survival rate data as the final new prawn species, and output the final new prawn species.

[0071] As Figure 2 shown, further, in this method, based on the final new prawn species, seedling arrangement is carried out in the current aquaculture area, and the aquaculture data of new prawns in the current aquaculture area are monitored. Specifically:

[0072] S202: Obtain the optimal new prawn seedling quantity information under each aquaculture area, and construct a knowledge graph, and input the optimal new prawn seedling quantity information under each aquaculture area into the knowledge graph for storage.

[0073] S204: Obtain the aquaculture area of the current aquaculture area, input the aquaculture area of the current aquaculture area into the knowledge graph for data matching, obtain the optimal new prawn seedling quantity information of the current aquaculture area, and carry out seedling arrangement in the current aquaculture area according to the optimal new prawn seedling quantity information of the current aquaculture area.

[0074] S206: Collect natural enemy image information of new prawns within a preset range through an image acquisition device, count the natural enemy quantity information of new prawns within a preset range, and judge whether the natural enemy quantity information of new prawns within a preset range is greater than the preset quantity information.

[0075] S208: When the natural enemy quantity information of new prawns within a preset range is greater than the preset quantity information, drive the natural enemies through a pre-arranged driving device.

[0076] It should be noted that in the breeding process, it is also vulnerable to natural enemies, resulting in economic losses. Through this method, the rationality in breeding can be improved.

[0077] In addition, this method may further include:

[0078] Obtain the image data information of the breeding area within a preset time, perform biometric identification of disease transmission on the image data information of the breeding area within the preset time, obtain and count the number of disease-transmitting organisms, and obtain the number of disease-transmitting organisms per unit area;

[0079] Set a threshold for the number of disease-transmitting organisms per unit area, and determine whether the number of disease-transmitting organisms per unit area is greater than the threshold for the number of disease-transmitting organisms per unit area;

[0080] When the number of disease-transmitting organisms per unit area is greater than the threshold for the number of disease-transmitting organisms per unit area, an evaluation result of disease transmission occurrence is generated, the evaluation result of disease transmission occurrence is output, and a warning is issued for the disease type caused by the disease-transmitting organisms;

[0081] When the number of disease-transmitting organisms per unit area is not greater than the threshold for the number of disease-transmitting organisms per unit area, an evaluation result of no disease transmission occurrence is generated, and the evaluation result of no disease transmission occurrence is output.

[0082] It should be noted that when the number of disease-transmitting organisms per unit area is greater than the threshold for the number of disease-transmitting organisms per unit area, it indicates that the probability of disease occurrence is very high. Through this method, the disease type in the process of new shrimp breeding can be timely warned.

[0083] As Figure 3 shown, the second aspect of the present invention provides a new shrimp breeding data analysis and recommendation system 4. The system 4 includes a memory 41 and a processor 42. The memory 41 includes a program for new shrimp breeding data analysis and recommendation method. When the program for new shrimp breeding data analysis and recommendation method is executed by the processor 42, the following steps are implemented:

[0084] Obtain the survival rate data of each new shrimp species under each environmental characteristic data, and construct a new shrimp survival rate prediction model according to the survival rate data of each new shrimp species under each environmental characteristic data;

[0085] Obtain the survival rate data of each new shrimp species at different time periods in the current breeding area through the new shrimp survival rate prediction model, and initially select several new shrimp species in the current breeding area according to the survival rate data of each new shrimp species at different time periods in the current breeding area;

[0086] Obtain the survival rate data of several new shrimp species in the current aquaculture area, and obtain the final new shrimp species by reselecting the survival rate data of several new shrimp species in the current aquaculture area.

[0087] Based on the final new shrimp species, arrange the seedling cultivation in the current aquaculture area, and monitor the aquaculture data of the new shrimp in the current aquaculture area.

[0088] Further, in this system, obtain the survival rate data of each new shrimp species under each environmental characteristic data, and construct a new shrimp survival rate prediction model according to the survival rate data of each new shrimp species under each environmental characteristic data, specifically including:

[0089] Obtain the survival rate data of each new shrimp species under each environmental characteristic data, introduce a graph neural network, and input the survival rate data of each new shrimp species under each environmental characteristic data into the graph neural network.

[0090] Take the environmental characteristic data as the first graph node, take the survival rate data of the new shrimp species as the second graph node, connect the first graph node and the second graph node through a directed edge to describe the relationship, construct a topological structure graph, and obtain the relevant adjacency matrix based on the topological structure graph.

[0091] Construct a new shrimp survival rate prediction model based on a deep neural network, input the relevant adjacency matrix into the new shrimp survival rate prediction model for training, and when the loss function of the new shrimp survival rate prediction model converges to a preset value, save the model parameters and output the new shrimp survival rate prediction model.

[0092] Further, in this system, obtain the survival rate data of each new shrimp species in different time periods in the current aquaculture area through the new shrimp survival rate prediction model, specifically including:

[0093] Obtain the historical environmental characteristic data of the current aquaculture area in each time period through big data, and input the historical environmental characteristic data of the current aquaculture area in each time period into the new shrimp survival rate prediction model for prediction.

[0094] Through prediction, obtain the survival rate data of each new shrimp species in different time periods in the current aquaculture area, and output the survival rate data of each new shrimp species in different time periods in the current aquaculture area.

[0095] Further, in this system, initially select several new shrimp species in the current aquaculture area according to the survival rate data of each new shrimp species in different time periods in the current aquaculture area, specifically:

[0096] Set a survival rate threshold and determine whether the survival rate data of each new shrimp species at different time periods in the current aquaculture area are all greater than the survival rate threshold;

[0097] When the survival rate data of the new shrimp species at different time periods in the current aquaculture area are all greater than the survival rate threshold, then initially select the corresponding new shrimp species as the new shrimp species in the current aquaculture area;

[0098] When the survival rate data of the new shrimp species at different time periods in the current aquaculture area are not all greater than the survival rate threshold, then do not take the corresponding new shrimp species as the new shrimp species in the current aquaculture area;

[0099] Statistically analyze the quantity information of the new shrimp species in the current aquaculture area, generate several new shrimp species in the current aquaculture area, and output the several new shrimp species in the current aquaculture area.

[0100] Furthermore, in this system, obtain the survival rate data of several new shrimp species in the current aquaculture area, and through a secondary selection of the survival rate data of the several new shrimp species in the current aquaculture area, obtain the final new shrimp species. Specifically:

[0101] Obtain the survival rate data of several new shrimp species in the current aquaculture area, and statistically analyze the average value of the survival rate data of the several new shrimp species in the current aquaculture area to obtain the average survival rate data of the several new shrimp species in the current aquaculture area.

[0102] Construct a survival rate ranking table for new shrimp species, and input the average survival rate data of the several new shrimp species in the current aquaculture area into the survival rate ranking table for new shrimp species for sorting;

[0103] Through sorting, obtain the survival rate ranking table for new shrimp species after sorting is completed, and obtain the new shrimp species corresponding to the highest average survival rate data from the survival rate ranking table for new shrimp species after sorting is completed;

[0104] Take the new shrimp species corresponding to the highest average survival rate data as the final new shrimp species, and output the final new shrimp species.

[0105] Furthermore, in this system, based on the final new shrimp species, arrange the seedling cultivation in the current aquaculture area, and monitor the aquaculture data of the new shrimp in the current aquaculture area. Specifically:

[0106] Obtain the optimal new shrimp seedling quantity information under each aquaculture area, and construct a knowledge graph, and input the optimal new shrimp seedling quantity information under each aquaculture area into the knowledge graph for storage;

[0107] Obtain the aquaculture area of the current aquaculture region, input the aquaculture area of the current aquaculture region into the knowledge graph for data matching, obtain the optimal number information of new shrimp seedlings for the current aquaculture region, and arrange the seedlings for the current aquaculture region according to the optimal number information of new shrimp seedlings for the current aquaculture region;

[0108] Collect the natural enemy image information of new shrimp within a preset range through an image acquisition device, count the natural enemy quantity information of new shrimp within the preset range, and determine whether the natural enemy quantity information of new shrimp within the preset range is greater than the preset quantity information;

[0109] When the natural enemy quantity information of new shrimp within the preset range is greater than the preset quantity information, drive the natural enemies through the pre-arranged driving device.

[0110] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for analyzing and recommending data on the selection and breeding of new shrimp. When the program for analyzing and recommending data on the selection and breeding of new shrimp is executed by a processor, the steps of any one of the methods for analyzing and recommending data on the selection and breeding of new shrimp are implemented.

[0111] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed with each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0112] The units described as separate components above may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0113] In addition, each functional unit in the embodiments of the present invention can be all integrated in one processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in one unit; the above integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0114] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed 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 including those of the above method embodiments. The aforementioned storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0115] Alternatively, if the above integrated units are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

[0116] The above are only the specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A new shrimp breeding data analysis and recommendation method, characterized in that: Specifically include: Acquire the survival rate data of each new shrimp species under each environmental characteristic data, and construct a new shrimp survival rate prediction model according to the survival rate data of each new shrimp species under each environmental characteristic data; Obtaining the survival rate data of each new shrimp species in different time periods in the current breeding area through the new shrimp survival rate prediction model, and preliminarily selecting a number of new shrimp species in the current breeding area according to the survival rate data of each new shrimp species in different time periods in the current breeding area; Obtaining survival rate data of several new shrimp species in the current breeding area, and performing secondary selection on the survival rate data of several new shrimp species in the current breeding area to obtain the final new shrimp species; The current culture area is arranged to breed new shrimps based on the final new shrimp species, and the culture data of the new shrimps in the current culture area is monitored.

2. A new shrimp breeding data analysis and recommendation method according to claim 1, characterized in that: Obtaining the survival rate data of each new shrimp species under each environmental characteristic data, and constructing a new shrimp survival rate prediction model according to the survival rate data of each new shrimp species under the environmental characteristic data, specifically including: Obtaining the survival rate data of each new shrimp species under each environmental characteristic data, introducing a graph neural network, and inputting the survival rate data of each new shrimp species under each environmental characteristic data into the graph neural network; Using environmental feature data as a first graph node, using survival rate data of a new shrimp species as a second graph node, connecting the first graph node and the second graph node through directed edge description relationships, constructing a topological structure graph, and obtaining a related adjacency matrix based on the topological structure graph; A new shrimp survival rate prediction model is constructed based on a deep neural network, and the relevant adjacency matrix is ​​input into the new shrimp survival rate prediction model for training. When the loss function of the new shrimp survival rate prediction model converges to a preset value, the model parameters are saved and the new shrimp survival rate prediction model is output.

3. A new shrimp breeding data analysis and recommendation method according to claim 1, characterized in that: The survival rate data of each new shrimp species in different time periods in the current breeding area are obtained by using the new shrimp survival rate prediction model, specifically including: Obtain historical environmental characteristic data of the current breeding area in each time period through big data, and input the historical environmental characteristic data of the current breeding area in each time period into the new shrimp survival rate prediction model for prediction; By prediction, the survival rate data of each new shrimp species in different time periods in the current breeding area are obtained, and the survival rate data of each new shrimp species in different time periods in the current breeding area are output.

4. A new shrimp breeding data analysis and recommendation method according to claim 1, characterized in that: According to the survival rate data of each new shrimp species in the current breeding area at different time periods, several new shrimp species in the current breeding area are initially selected, specifically: Setting a survival rate threshold, and determining whether the survival rate data of each new shrimp species in different time periods in the current breeding area are all greater than the survival rate threshold; When the survival rate data of the new shrimp species in different time periods in the current breeding area are all greater than the survival rate threshold, the corresponding new shrimp species are preliminarily selected as the new shrimp species in the current breeding area; When the survival rate data of the new shrimp species in different time periods in the current breeding area are not all greater than the survival rate threshold, the corresponding new shrimp species will not be used as the new shrimp species in the current breeding area; Counting the quantity information of the new shrimp species in the current breeding area, generating several new shrimp species in the current breeding area, and outputting the several new shrimp species in the current breeding area.

5. The method for analyzing and recommending new shrimp breeding data according to claim 1, characterized in that: Obtain survival rate data of several new shrimp species in the current breeding area, and perform secondary selection on the survival rate data of several new shrimp species in the current breeding area to obtain the final new shrimp species, specifically: Obtain the survival rate data of several new shrimp species in the current breeding area, and calculate the average survival rate data of several new shrimp species in the current breeding area, and obtain the average survival rate data of several new shrimp species in the current breeding area. Constructing a survival rate ranking table of new shrimp species, and inputting average survival rate data of several new shrimp species in the current breeding area into the survival rate ranking table of the new shrimp species for ranking; Obtaining a survival rate ranking table of the sorted new shrimp species through sorting, and obtaining the new shrimp species corresponding to the highest average survival rate data from the survival rate ranking table of the sorted new shrimp species; The new shrimp species corresponding to the highest average survival rate data is used as the final new shrimp species, and the final new shrimp species is output.

6. A new shrimp breeding data analysis and recommendation method according to claim 1, characterized in that: Arrange the seedlings in the current breeding area based on the final new shrimp species, and monitor the breeding data of the new shrimp in the current breeding area, specifically: Obtaining the optimal number of new shrimp seedlings for each breeding area, and constructing a knowledge graph, and inputting the optimal number of new shrimp seedlings for each breeding area into the knowledge graph for storage; Obtaining the breeding area of ​​the current breeding area, inputting the breeding area of ​​the current breeding area into the knowledge graph for data matching, obtaining the optimal number of new shrimp seedlings in the current breeding area, and arranging seedlings in the current breeding area according to the optimal number of new shrimp seedlings in the current breeding area; The image acquisition device is used to collect image information of natural enemies of the new shrimp within a preset range, and the number information of the natural enemies of the new shrimp within the preset range is counted to determine whether the number information of the natural enemies of the new shrimp within the preset range is greater than the preset number information; When the number information of the natural enemies of the new shrimp within the preset range is greater than the preset number information, the natural enemies are driven away by the driving device arranged in advance.

7. A new shrimp breeding data analysis and recommendation system, characterized in that: The system includes a memory and a processor, wherein the memory includes a new shrimp breeding data analysis and recommendation method program, and when the new shrimp breeding data analysis and recommendation method program is executed by the processor, the following steps are implemented: Acquire the survival rate data of each new shrimp species under each environmental characteristic data, and construct a new shrimp survival rate prediction model according to the survival rate data of each new shrimp species under each environmental characteristic data; Obtaining the survival rate data of each new shrimp species in different time periods in the current breeding area through the new shrimp survival rate prediction model, and preliminarily selecting a number of new shrimp species in the current breeding area according to the survival rate data of each new shrimp species in different time periods in the current breeding area; Obtaining survival rate data of several new shrimp species in the current breeding area, and performing secondary selection on the survival rate data of several new shrimp species in the current breeding area to obtain the final new shrimp species; The current culture area is arranged to breed new shrimps based on the final new shrimp species, and the culture data of the new shrimps in the current culture area is monitored.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a new shrimp breeding data analysis and recommendation method program, and when the new shrimp breeding data analysis and recommendation method program is executed by a processor, the steps of the new shrimp breeding data analysis and recommendation method according to any one of claims 1 to 6 are implemented.

Images