Method and system for monitoring whole process of new prawn culture and storage medium

Abstract

The invention relates to a method and a system for monitoring the whole process of new prawn culture and a storage medium, and belongs to the technical field of new prawn culture. Image information is identified through a disease transmission path identification model, and a disease transmission path identification result is obtained, so that the disease transmission path identification result is counted, and a new prawn culture process is obtained. The method comprises the steps of acquiring a disease transmission path identification result, performing disease transmission evaluation on the disease transmission path identification result to obtain an evaluation result, finally performing early warning on a new prawn culture area based on the evaluation result, generating early warning information, generating a related prevention and control scheme according to the early warning information, and performing prevention and control on the new prawn culture area according to the related prevention and control scheme. According to the method, the disease transmission path in the new prawn culture process is fully considered, and the disease condition in the new prawn culture process can be reflected from another aspect, so that the disease transmission path can be cut off, and diseases and diseases in the new prawn culture process are further avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of Metapenaeus ensis farming, and particularly to a method, a system and a storage medium for monitoring the whole process of Metapenaeus ensis farming. Background Art

[0002] Pond farming is the most important fishery production method in inland and coastal tidal flats of China. With the reduction of wild fishery resources, pond farming is also the main way to meet the consumption demand of shrimps for people at present. Although a relatively complete technical system has been formed for shrimp pond farming after years of development, the problems of water quality regulation and stability during the farming process and the pollution of surrounding environment by the tail water discharge in the middle and late stages of farming have not been effectively solved. At the same time, as a relatively open environment, many environmental factors in pond farming are difficult to be fully regulated. Especially in the initial stage of seedling release, shrimp larvae are easily affected by water temperature, salinity, pH value, dissolved oxygen level and other biological factors, resulting in large death losses. Such problems not only increase the uncertainty of Metapenaeus ensis farming, but also restrict the sustainable development of the industry in the long run. However, during the process of Metapenaeus ensis farming, certain diseases are likely to occur, and diseases usually have disease transmission routes. In the prior art, the possibility of disease occurrence is warned by detecting water quality, while the situations brought by other disease transmission routes are ignored, 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, a system and a storage medium for monitoring the whole process of Metapenaeus ensis farming.

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

[0005] In the first aspect of the present invention, a method for monitoring the whole process of Metapenaeus ensis farming is provided, including the following steps:

[0006] Obtain the historical disease data of Metapenaeus ensis during the farming process, and obtain the disease transmission routes related to the current farming area according to the historical disease data of Metapenaeus ensis during the farming process;

[0007] Construct a disease transmission route recognition model, obtain the image data information of the Metapenaeus ensis farming area, and identify the image information through the disease transmission route recognition model to obtain the disease transmission route recognition result;

[0008] Count the disease transmission route recognition results, and evaluate the disease transmission of the disease transmission route recognition results to obtain the evaluation result;

[0009] Based on the evaluation results, a warning is issued for the new penaeid shrimp farming area, warning information is generated, and a relevant prevention and control plan is generated according to the warning information. The new penaeid shrimp farming area is prevented and controlled according to the relevant prevention and control plan.

[0010] Further, in this method, historical disease data of new penaeid shrimps during the farming process is obtained, and the disease transmission routes related to the current farming area are obtained according to the historical disease data of new penaeid shrimps during the farming process. Specifically:

[0011] The historical disease data of new penaeid shrimps during the farming process is obtained through big data, and a retrieval tag is constructed according to the historical disease data of new penaeid shrimps during the farming process. Based on the retrieval tag, a search is conducted through big data to obtain the disease transmission routes corresponding to the historical disease data of new penaeid shrimps during the farming process;

[0012] A graph neural network is introduced, and the disease transmission routes corresponding to the historical disease data of new penaeid shrimps during the farming process are input into the graph neural network. The disease data is used as the first node, and the disease transmission routes are used as the second node.

[0013] A directed description relationship is constructed, and the first node and the second node are connected based on the directed description relationship to form a topological structure diagram. Based on the topological structure diagram, an adjacency matrix is obtained, a knowledge graph is constructed, and the adjacency matrix is input into the knowledge graph for storage;

[0014] The environmental data information within the current new penaeid shrimp farming area is obtained, and a big data search is conducted according to the environmental data information within the current new penaeid shrimp farming area to obtain the possible disease data in the new penaeid shrimp farming area. The possible disease data in the new penaeid shrimp farming area is input into the knowledge graph for data matching to obtain the disease transmission routes related to the current farming area.

[0015] Further, in this method, a disease transmission route recognition model is constructed, specifically including:

[0016] A disease transmission route recognition model is constructed based on a deep neural network, and the image data information related to various disease transmission routes is obtained through big data. By classifying the obtained image data information related to various disease transmission routes, a training set related to various disease transmission route types is obtained;

[0017] Sample data in the training set related to various disease transmission route types is randomly selected, and the Euclidean distance value between the training sets related to various disease transmission route types is calculated to determine whether the Euclidean distance value is greater than a preset Euclidean distance threshold;

[0018] When the Euclidean distance value is greater than the preset Euclidean distance threshold, reselect the sample data in the training set related to various types of disease transmission routes until the Euclidean distance value is greater than the preset Euclidean distance threshold, and output the training set related to various types of disease transmission routes;

[0019] Input the training set related to various types of disease transmission routes into the disease transmission route recognition model for training in sequence. After the loss function of the disease transmission route recognition model converges to the preset value, output the disease transmission route recognition model.

[0020] Further, in this method, obtain the image data information of the new prawn farming area, and identify the image information through the disease transmission route recognition model to obtain the disease transmission route recognition result, specifically including:

[0021] Obtain the image data information of the new prawn farming area, and input the image data information of the new prawn farming area into the disease transmission route recognition model for recognition to determine whether there is a disease transmission route;

[0022] When there is a disease transmission route, output the disease transmission route recognition result.

[0023] Further, in this method, count the disease transmission route recognition result, and evaluate the disease transmission of the disease transmission route recognition result to obtain the evaluation result, specifically including:

[0024] Obtain the image data information of the disease transmission route within the preset time, and count the number of disease transmission organisms in the image data information of the disease transmission route within the preset time to obtain the number of disease transmission organisms per unit area;

[0025] Set the threshold of the number of disease transmission organisms per unit area, and determine whether the number of disease transmission organisms per unit area is greater than the threshold of the number of disease transmission organisms per unit area;

[0026] When the number of disease transmission organisms per unit area is greater than the threshold of the number of disease transmission organisms per unit area, generate an evaluation result of disease transmission and output the evaluation result of disease transmission;

[0027] When the number of disease transmission organisms per unit area is not greater than the threshold of the number of disease transmission organisms per unit area, generate an evaluation result of no disease transmission and output the evaluation result of no disease transmission.

[0028] Further, in this method, based on the evaluation result, a warning is issued for the new shrimp farming area, warning information is generated, and a relevant prevention and control plan is generated according to the warning information. The prevention and control of the new shrimp farming area is carried out according to the relevant prevention and control plan, specifically including:

[0029] If the evaluation result is an evaluation result of disease transmission, obtain the disease transmission organisms corresponding to the evaluation result of disease transmission, and obtain the types of diseases that may occur during the disease transmission process of the disease transmission organisms according to the disease transmission organisms corresponding to the evaluation result of disease transmission;

[0030] Generate relevant warning information according to the types of diseases that may occur during the disease transmission process of the disease transmission organisms, and issue a warning to the current new shrimp farming area based on the relevant warning information;

[0031] Retrieve through big data according to the types of diseases that may occur during the disease transmission process of the disease transmission organisms, and obtain a prevention and control plan related to the types of diseases that may occur during the disease transmission process of the disease transmission organisms through big data retrieval;

[0032] Arrange prevention and control for the current new shrimp farming area based on the prevention and control plan related to the types of diseases that may occur during the disease transmission process of the disease transmission organisms.

[0033] The second aspect of the present invention provides a whole-process monitoring system for new shrimp farming. The system includes a memory and a processor. The memory includes a program for the whole-process monitoring method of new shrimp farming. When the program for the whole-process monitoring method of new shrimp farming is executed by the processor, the following steps are realized;

[0034] Obtain the historical disease data of new shrimp during the farming process, and obtain the disease transmission routes related to the current farming area according to the historical disease data of new shrimp during the farming process;

[0035] Construct a disease transmission route recognition model, obtain the image data information of the new shrimp farming area, and identify the image information through the disease transmission route recognition model to obtain the disease transmission route recognition result;

[0036] Count the disease transmission route recognition results, and evaluate the disease transmission of the disease transmission route recognition results to obtain an evaluation result;

[0037] Based on the evaluation result, a warning is issued for the new shrimp farming area, warning information is generated, and a relevant prevention and control plan is generated according to the warning information. The prevention and control of the new shrimp farming area is carried out according to the relevant prevention and control plan.

[0038] In a third aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a program for monitoring the entire process of new shrimp farming. When the program for monitoring the entire process of new shrimp farming is processed and executed, the steps of any of the described methods for monitoring the entire process of new shrimp farming are implemented.

[0039] The present invention solves the defects in the background art and has the following beneficial effects:

[0040] The present invention obtains historical disease data of new shrimp during the farming process, obtains the disease transmission routes related to the current farming area based on the historical disease data of new shrimp during the farming process, then constructs a disease transmission route recognition model, obtains image data information of the new shrimp farming area, identifies the image information through the disease transmission route recognition model to obtain a disease transmission route recognition result, thus counts the disease transmission route recognition result, evaluates the disease transmission based on the disease transmission route recognition result to obtain an evaluation result, and finally issues a warning for the new shrimp farming area based on the evaluation result, generates a warning message, and generates a relevant prevention and control plan according to the warning message, and conducts prevention and control on the new shrimp farming area according to the relevant prevention and control plan. The present invention fully considers the disease transmission routes during the new shrimp farming process, can reflect the disease situation during the new shrimp farming process from another aspect, thereby can cut off the disease transmission routes, and further avoid the occurrence of diseases and pests during the new shrimp farming process. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in 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 based on these drawings.

[0042] Figure 1 Shows the overall flowchart of the method for monitoring the entire process of new shrimp farming;

[0043] Figure 2 Shows a partial flowchart of the method for monitoring the entire process of new shrimp farming;

[0044] Figure 3 Shows the system block diagram of the system for monitoring the entire process of new shrimp farming. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying 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.

[0046] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0047] As Figure 1 shown, in the first aspect of the present invention, a method for monitoring the whole process of new shrimp farming is provided, including the following steps:

[0048] S102: Obtain the historical disease data of new shrimps during the farming process, and obtain the disease transmission routes related to the current farming area according to the historical disease data of the new shrimps during the farming process;

[0049] S104: Construct a disease transmission route recognition model, obtain the image data information of the new shrimp farming area, and identify the image information through the disease transmission route recognition model to obtain the disease transmission route recognition result;

[0050] S106: Statistically analyze the disease transmission route recognition results, and evaluate the disease transmission of the disease transmission route recognition results to obtain the evaluation results;

[0051] S108: Based on the evaluation results, give an early warning to the new shrimp farming area, generate early warning information, and generate a relevant prevention and control plan according to the early warning information, and carry out prevention and control on the new shrimp farming area according to the relevant prevention and control plan.

[0052] It should be noted that the present invention fully considers the disease transmission routes in the process of new shrimp farming, can reflect the disease situation in the process of new shrimp farming from another aspect, so as to cut off the disease transmission routes and further avoid the occurrence of diseases and pests in the process of new shrimp farming.

[0053] As Figure 2 shown, further, in this method, obtaining the historical disease data of new shrimps during the farming process, and obtaining the disease transmission routes related to the current farming area according to the historical disease data of the new shrimps during the farming process, specifically:

[0054] S102: Obtain the historical disease data of the new shrimp during the breeding process through big data, construct a retrieval tag based on the historical disease data of the new shrimp during the breeding process, and retrieve through big data based on the retrieval tag to obtain the disease transmission routes corresponding to the historical disease data of the new shrimp during the breeding process;

[0055] S104: Introduce a graph neural network, input the disease transmission routes corresponding to the historical disease data of the new shrimp during the breeding process into the graph neural network, use the disease data as the first node, and use the disease transmission route as the second node,

[0056] S106: Construct a directed description relationship, connect the first node and the second node based on the directed description relationship to form a topological structure diagram, obtain an adjacency matrix based on the topological structure diagram, construct a knowledge graph, and input the adjacency matrix into the knowledge graph for storage;

[0057] S108: Obtain the environmental data information within the current new shrimp breeding area range, perform big data retrieval based on the environmental data information within the current new shrimp breeding area range, obtain the possible disease data in the new shrimp breeding area, input the possible disease data in the new shrimp breeding area into the knowledge graph for data matching, and obtain the disease transmission routes related to the current breeding area.

[0058] It should be noted that some diseases of the new shrimp are mainly transmitted through some organisms, such as diseases caused by algae, explosive epidemic shrimp diseases. For example, explosive epidemic shrimp diseases transmit viruses or bacteria through certain organisms, such as organisms like mosquitoes and flies. Through this method, the disease transmission routes related to the current breeding area can be obtained. The environmental data information within the current new shrimp breeding area range includes temperature, humidity, salinity, etc. Due to the influence of the environment, the organisms that transmit diseases may not be adapted to this environment. By performing big data retrieval based on the environmental data information within the current new shrimp breeding area range and obtaining the possible disease data in the new shrimp breeding area, the prediction accuracy of the possible disease data in the new shrimp breeding area can be improved.

[0059] Furthermore, in this method, constructing a disease transmission route recognition model specifically includes:

[0060] Construct a disease transmission route recognition model based on a deep neural network, obtain image data information related to various disease transmission routes through big data, and classify the obtained image data information related to various disease transmission routes to obtain a training set related to various disease transmission route types;

[0061] Randomly select the sample data in the training sets related to various types of disease transmission routes, calculate the Euclidean distance values between the training sets related to various types of disease transmission routes, and determine whether the Euclidean distance value is greater than a preset Euclidean distance threshold;

[0062] When the Euclidean distance value is greater than the preset Euclidean distance threshold, re-select the sample data in the training sets related to various types of disease transmission routes until the Euclidean distance value is greater than the preset Euclidean distance threshold, and output the training sets related to various types of disease transmission routes;

[0063] Input the training sets related to various types of disease transmission routes into the disease transmission route recognition model for training in sequence. After the loss function of the disease transmission route recognition model converges to a preset value, output the disease transmission route recognition model.

[0064] It should be noted that since there may be images of multiple organisms in the sample data of the training sets related to various types of disease transmission routes, such as an image with multiple disease-transmitting organisms, there will be a certain interference to the model's recognition at this time. By re-selecting the sample data in the training sets related to various types of disease transmission routes until the Euclidean distance value is greater than the preset Euclidean distance threshold and outputting the training sets related to various types of disease transmission routes, it is possible to continuously reduce the interference of multi-scale data on the model training and improve the recognition accuracy of the model.

[0065] Furthermore, in this method, obtain the image data information of the new prawn farming area, and identify the image information through the disease transmission route recognition model to obtain the disease transmission route recognition result, specifically including:

[0066] Obtain the image data information of the new prawn farming area, and input the image data information of the new prawn farming area into the disease transmission route recognition model for recognition to determine whether there is a disease transmission route;

[0067] When there is a disease transmission route, output the disease transmission route recognition result.

[0068] Furthermore, in this method, count the disease transmission route recognition results and evaluate the disease transmission for the disease transmission route recognition results to obtain an evaluation result, specifically including:

[0069] Obtain the image data information of the disease transmission route within a preset time, and count the number of disease-transmitting organisms in the image data information of the disease transmission route within the preset time to obtain the number of disease-transmitting organisms per unit area;

[0070] Set the threshold for the number of disease - spreading organisms per unit area, and determine whether the number of disease - spreading organisms within the unit area is greater than the threshold for the number of disease - spreading organisms within the unit area;

[0071] When the number of disease - spreading organisms within the unit area is greater than the threshold for the number of disease - spreading organisms within the unit area, generate an evaluation result of disease spread and output the evaluation result of disease spread;

[0072] When the number of disease - spreading organisms within the unit area is not greater than the threshold for the number of disease - spreading organisms within the unit area, generate an evaluation result of no disease spread and output the evaluation result of no disease spread.

[0073] It should be noted that when the number of disease - spreading organisms within the unit area is greater than the threshold for the number of disease - spreading organisms within the unit area, it indicates that the probability of disease occurrence is very high. Through this method, the evaluation accuracy of diseases in newly - hatched shrimp can be improved.

[0074] Furthermore, in this method, based on the evaluation result, a warning is issued for the newly - hatched shrimp farming area, a warning message is generated, and a relevant prevention and control plan is generated according to the warning message. The prevention and control of the newly - hatched shrimp farming area is carried out according to the relevant prevention and control plan, specifically including:

[0075] If the evaluation result is an evaluation result of disease spread, obtain the disease - spreading organisms corresponding to the evaluation result of disease spread, and obtain the types of diseases that may occur during the disease - spreading process of the disease - spreading organisms according to the disease - spreading organisms corresponding to the evaluation result of disease spread;

[0076] Generate relevant warning information according to the types of diseases that may occur during the disease - spreading process of the disease - spreading organisms, and issue a warning for the current newly - hatched shrimp farming area based on the relevant warning information;

[0077] Retrieve through big data according to the types of diseases that may occur during the disease - spreading process of the disease - spreading organisms. Through big data retrieval, obtain the prevention and control plans related to the types of diseases that may occur during the disease - spreading process of the disease - spreading organisms;

[0078] Carry out prevention and control layout for the current newly - hatched shrimp farming area based on the prevention and control plans related to the types of diseases that may occur during the disease - spreading process of the disease - spreading organisms.

[0079] It should be noted that the relevant prevention and control plans include physical prevention and control plans and chemical prevention and control plans. Through this method, the disease - spreading route can be cut off, and the probability of diseases in newly - hatched shrimp during the farming process can be reduced.

[0080] As Figure 3 shown, the second aspect of the present invention provides a whole-process monitoring system 4 for the cultivation of Metapenaeus ensis. The system 4 includes a memory 41 and a processor 42. The memory 41 includes a program for the whole-process monitoring method of Metapenaeus ensis cultivation. When the program for the whole-process monitoring method of Metapenaeus ensis cultivation is executed by the processor 42, the following steps are implemented;

[0081] Obtain the historical disease data of Metapenaeus ensis during the cultivation process, and obtain the disease transmission routes related to the current cultivation area according to the historical disease data of Metapenaeus ensis during the cultivation process;

[0082] Construct a disease transmission route recognition model, obtain the image data information of the Metapenaeus ensis cultivation area, and identify the image information through the disease transmission route recognition model to obtain the disease transmission route recognition result;

[0083] Statistically analyze the disease transmission route recognition results, and evaluate the disease transmission of the disease transmission route recognition results to obtain an evaluation result;

[0084] Based on the evaluation result, give an early warning to the Metapenaeus ensis cultivation area, generate a warning message, and generate a relevant prevention and control plan according to the warning message, and carry out prevention and control on the Metapenaeus ensis cultivation area according to the relevant prevention and control plan.

[0085] Furthermore, in this system, obtaining the historical disease data of Metapenaeus ensis during the cultivation process and obtaining the disease transmission routes related to the current cultivation area according to the historical disease data of Metapenaeus ensis during the cultivation process are specifically as follows:

[0086] Obtain the historical disease data of Metapenaeus ensis during the cultivation process through big data, construct a retrieval tag according to the historical disease data of Metapenaeus ensis during the cultivation process, and retrieve through big data based on the retrieval tag to obtain the disease transmission routes corresponding to the historical disease data of Metapenaeus ensis during the cultivation process;

[0087] Introduce a graph neural network, input the disease transmission routes corresponding to the historical disease data of Metapenaeus ensis during the cultivation process into the graph neural network, use the disease data as the first node, and use the disease transmission routes as the second node,

[0088] Construct a directed description relationship, connect the first node and the second node based on the directed description relationship to form a topological structure diagram, obtain an adjacency matrix based on the topological structure diagram, construct a knowledge graph, and input the adjacency matrix into the knowledge graph for storage;

[0089] Obtain the environmental data information within the current new shrimp farming area, and conduct big data retrieval based on the environmental data information within the current new shrimp farming area to obtain the disease data that may occur in the new shrimp farming area. Input the disease data that may occur in the new shrimp farming area into the knowledge graph for data matching to obtain the disease transmission routes related to the current farming area.

[0090] Further, in this system, a disease transmission route recognition model is constructed, specifically including:

[0091] Construct a disease transmission route recognition model based on a deep neural network, and obtain the image data information related to various disease transmission routes through big data. Classify the obtained image data information related to various disease transmission routes to obtain the training sets related to various disease transmission route types;

[0092] Randomly select the sample data in the training sets related to various disease transmission route types, and calculate the Euclidean distance values between the training sets related to various disease transmission route types. Determine whether the Euclidean distance value is greater than the preset Euclidean distance threshold;

[0093] When the Euclidean distance value is greater than the preset Euclidean distance threshold, re-select the sample data in the training sets related to various disease transmission route types until the Euclidean distance value is greater than the preset Euclidean distance threshold, and output the training sets related to various disease transmission route types.

[0094] Input the training sets related to various disease transmission route types into the disease transmission route recognition model for training in sequence. After the loss function of the disease transmission route recognition model converges to the preset value, output the disease transmission route recognition model.

[0095] Further, in this system, obtain the image data information of the new shrimp farming area, and identify the disease transmission route through the disease transmission route recognition model for the image information. The specific steps include:

[0096] Obtain the image data information of the new shrimp farming area, and input the image data information of the new shrimp farming area into the disease transmission route recognition model for recognition to determine whether there is a disease transmission route;

[0097] When there is a disease transmission route, output the disease transmission route recognition result.

[0098] Further, in this system, count the disease transmission route recognition results, and conduct an assessment of disease transmission on the disease transmission route recognition results to obtain an assessment result. The specific steps include:

[0099] Obtain the image data information of the disease transmission route within the preset time, and count the number of disease transmission organisms in the image data information of the disease transmission route within the preset time to obtain the number of disease transmission organisms per unit area;

[0100] Set the threshold of the number of disease transmission organisms per unit area, and determine whether the number of disease transmission organisms per unit area is greater than the threshold of the number of disease transmission organisms per unit area;

[0101] When the number of disease transmission organisms per unit area is greater than the threshold of the number of disease transmission organisms per unit area, generate an evaluation result of disease transmission and output the evaluation result of disease transmission;

[0102] When the number of disease transmission organisms per unit area is not greater than the threshold of the number of disease transmission organisms per unit area, generate an evaluation result of no disease transmission and output the evaluation result of no disease transmission.

[0103] Furthermore, in this system, based on the evaluation result, a warning is issued for the new prawn farming area, a warning message is generated, and a relevant prevention and control plan is generated according to the warning message. The new prawn farming area is prevented and controlled according to the relevant prevention and control plan, specifically including:

[0104] If the evaluation result is an evaluation result of disease transmission, obtain the disease transmission organisms corresponding to the evaluation result of disease transmission, and obtain the types of diseases that may be caused by the disease transmission organisms during the disease transmission process according to the disease transmission organisms corresponding to the evaluation result of disease transmission;

[0105] Generate relevant warning information according to the types of diseases that may be caused by the disease transmission organisms during the disease transmission process, and issue a warning for the current new prawn farming area based on the relevant warning information;

[0106] Through big data retrieval according to the types of diseases that may be caused by the disease transmission organisms during the disease transmission process, obtain the prevention and control plan related to the types of diseases that may be caused by the disease transmission organisms during the disease transmission process;

[0107] Arrange prevention and control for the current new prawn farming area based on the prevention and control plan related to the types of diseases that may be caused by the disease transmission organisms during the disease transmission process.

[0108] In a third aspect of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a program for the whole-process monitoring method of Metapenaeus ensis farming. When the program for the whole-process monitoring method of Metapenaeus ensis farming is processed and executed, the steps of any of the whole-process monitoring methods of Metapenaeus ensis farming are implemented.

[0109] 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 merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed 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.

[0110] The units described above as separate components may or may not be physically separated. 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.

[0111] In addition, in each embodiment of the present invention, the functional units can all be 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-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0112] 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 foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical discs.

[0113] Alternatively, if the above integrated units of the present invention are implemented in the form of software function 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 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. This 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 such as removable storage devices, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0114] 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 method for monitoring the whole process of shrimp farming, characterized in that: The following steps are involved: Obtain historical disease data of the new shrimp during the breeding process, and obtain disease transmission pathways related to the current breeding area based on the historical disease data of the new shrimp during the breeding process; Constructing a disease transmission pathway identification model, obtaining image data information of a new shrimp breeding area, identifying the image information through the disease transmission pathway identification model, and obtaining a disease transmission pathway identification result; Counting the disease transmission pathway identification results, and evaluating the disease transmission of the disease transmission pathway identification results to obtain evaluation results; Based on the evaluation results, an early warning is issued for the new shrimp breeding area, early warning information is generated, and a relevant prevention and control plan is generated according to the early warning information, and the new shrimp breeding area is controlled according to the relevant prevention and control plan.

2. A new shrimp farming whole process monitoring method according to claim 1, characterized in that: Obtain historical disease data of the new shrimp during the breeding process, and obtain the disease transmission pathways related to the current breeding area based on the historical disease data of the new shrimp during the breeding process, specifically: Obtain historical disease data of the new shrimp during the breeding process through big data, and construct retrieval tags based on the historical disease data of the new shrimp during the breeding process, and perform retrieval through big data based on the retrieval tags to obtain the disease transmission pathways corresponding to the historical disease data of the new shrimp during the breeding process; A graph neural network is introduced, and the disease transmission pathway corresponding to the historical disease data of the new shrimp during the breeding process is input into the graph neural network, with the disease data as the first node and the disease transmission pathway as the second node. Constructing a directed description relationship, connecting the first node with the second node based on the directed description relationship to form a topological structure graph, obtaining an adjacency matrix based on the topological structure graph, constructing a knowledge graph, and inputting the adjacency matrix into the knowledge graph for storage; Obtain environmental data information within the current new shrimp breeding area, perform big data retrieval based on the environmental data information within the current new shrimp breeding area, obtain disease data that may occur in the new shrimp breeding area, input the disease data that may occur in the new shrimp breeding area into the knowledge graph for data matching, and obtain disease transmission pathways related to the current breeding area.

3. A new shrimp farming whole process monitoring method according to claim 1, characterized in that: Construct a disease transmission pathway identification model, including: Construct a disease transmission pathway recognition model based on a deep neural network, and obtain image data information related to various disease transmission pathways through big data, and obtain training sets related to various disease transmission pathway types by classifying the image data information related to various disease transmission pathways; Randomly select sample data from the training sets related to the various disease transmission pathway types, calculate the Euclidean distance value between the training sets related to the various disease transmission pathway types, and determine whether the Euclidean distance value is greater than a preset Euclidean distance threshold; When the Euclidean distance value is greater than the preset Euclidean distance threshold, sample data in the training set related to the various disease transmission pathway types are reselected until the Euclidean distance value is greater than the preset Euclidean distance threshold, and the training sets related to the various disease transmission pathway types are output; The training sets related to the various disease transmission pathway types are sequentially input into the disease transmission pathway identification model for training. When the loss function of the disease transmission pathway identification model converges to a preset value, the disease transmission pathway identification model is output.

4. A new shrimp farming whole process monitoring method according to claim 1, characterized in that: Obtaining image data information of a new shrimp breeding area, identifying the image information through the disease transmission pathway identification model, and obtaining a disease transmission pathway identification result, specifically including: Acquire image data information of a new shrimp breeding area, and input the image data information of the new shrimp breeding area into the disease transmission pathway identification model for identification to determine whether there is a disease transmission pathway; When there is a disease transmission pathway, the disease transmission pathway identification result will be output.

5. A new shrimp farming whole process monitoring method according to claim 1, characterized in that: The disease transmission pathway identification results are counted, and the disease transmission is evaluated on the disease transmission pathway identification results to obtain the evaluation results, specifically including: Obtaining image data information of a disease transmission pathway within a preset time, and counting the number of disease transmission organisms in the image data information of the disease transmission pathway within the preset time, to obtain the number of disease transmission organisms within a unit area; Setting a threshold value for the number of disease-transmitting organisms within a unit area, and determining whether the number of disease-transmitting organisms within the unit area is greater than the threshold value for the number of disease-transmitting organisms within the unit area; When the number of disease-transmitting organisms within the unit area is greater than a threshold number of disease-transmitting organisms within the unit area, an evaluation result of disease transmission is generated, and the evaluation result of disease transmission is output; When the number of disease-transmitting organisms within the unit area is not greater than the threshold value of the number of disease-transmitting organisms within the unit area, an assessment result that no disease transmission will occur is generated and the assessment result that no disease transmission will occur is output.

6. A new shrimp farming whole process monitoring method according to claim 1, characterized in that: Based on the evaluation results, an early warning is given to the new shrimp farming area, and early warning information is generated. According to the early warning information, a relevant prevention and control plan is generated, and the new shrimp farming area is prevented and controlled according to the relevant prevention and control plan, specifically including: If the assessment result is an assessment result of disease transmission, obtaining the disease transmission organism corresponding to the assessment result of disease transmission, and obtaining the type of disease that may be generated by the disease transmission organism in the process of disease transmission according to the disease transmission organism corresponding to the assessment result of disease transmission; Generate relevant warning information according to the types of diseases that may be caused by the disease-transmitting organisms in the process of spreading the disease, and issue a warning to the current new shrimp farming area based on the relevant warning information; According to the types of diseases that may be generated by the disease-transmitting organisms in the process of transmitting the disease, through big data retrieval, prevention and control plans related to the types of diseases that may be generated by the disease-transmitting organisms in the process of transmitting the disease are obtained; Based on the prevention and control scheme related to the types of diseases that may be caused by the disease-transmitting organisms in the process of spreading diseases, prevention and control are deployed in the current new shrimp farming areas.

7. A new shrimp farming whole process monitoring system, characterized in that: The system includes a memory and a processor, wherein the memory includes a new shrimp farming whole process monitoring method program, and when the new shrimp farming whole process monitoring method program is executed by the processor, the following steps are implemented; Obtain historical disease data of the new shrimp during the breeding process, and obtain disease transmission pathways related to the current breeding area based on the historical disease data of the new shrimp during the breeding process; Constructing a disease transmission pathway identification model, obtaining image data information of a new shrimp breeding area, identifying the image information through the disease transmission pathway identification model, and obtaining a disease transmission pathway identification result; Counting the disease transmission pathway identification results, and evaluating the disease transmission of the disease transmission pathway identification results to obtain evaluation results; Based on the evaluation results, an early warning is issued for the new shrimp breeding area, early warning information is generated, and a relevant prevention and control plan is generated according to the early warning information, and the new shrimp breeding area is controlled according to the relevant prevention and control plan.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a new shrimp farming whole process monitoring method program, and when the new shrimp farming whole process monitoring method program is processed and executed, the steps of the new shrimp farming whole process monitoring method according to any one of claims 1 to 6 are implemented.

Images