Breeding method and system of marbled shrimp based on uniformity of growth traits

Abstract

The present application relates to a method and system for breeding of Marsupenaeus japonicus based on selection of uniformity of growth traits, belonging to the technical field of genetic breeding of Marsupenaeus japonicus. A plurality of breeding base parents of Marsupenaeus japonicus are obtained, a plurality of the breeding base parents are identified and evaluated by genotyping technology, and a plurality of the genomic combination information is introduced into a blank pairing table to obtain a uniformity pairing table of growth traits of Marsupenaeus japonicus. The coefficient of variation of the simulated growth record information is calculated based on the pairing table, the abnormality determination result of the growth traits is generated, the correlation degree of the operating mechanism and the environmental data is calculated based on the abnormality determination result of the growth traits to generate a correlation degree ranking table, the regulation scheme of the breeding equipment is formulated according to the correlation degree ranking table, the influence degree of the seedlings after regulation is calculated by establishing a linear regression model, and the final breeding scheme is obtained. The present application can solve the problem of genetic gene mutation caused by environmental differences in the breeding process of Marsupenaeus japonicus and improve the uniformity of growth traits.

Description

Technical Field

[0001] This invention relates to the field of genetic breeding technology for tiger prawns, and in particular to a method and system for breeding tiger prawns based on the uniformity of growth traits. Background Technology

[0002] The tiger prawn, also known as the black tiger prawn, is a benthic animal that typically inhabits estuaries, coastal bays, and shallow seas. It burrows into sandy or muddy bottoms and feeds primarily on sandworms, shellfish, zooplankton, and some aquatic plants. The tiger prawn is an important aquaculture species with high economic value and broad market demand. Its delicious meat is enjoyed by many, and tiger prawn farming can provide farmers with high economic returns. Maintaining uniform growth traits in tiger prawns can increase their economic value as marketable shrimp and reduce competition among individuals, thereby improving survival rates. However, current methods for cultivating Penaeus monodon with uniform growth traits cannot accurately select breeding parents with highly similar genomes, leading to variations in the growth traits of larvae after mating. This makes it impossible to fix the genetic characteristics of the next generation of parents, resulting in deviations in growth traits. Furthermore, the cultivation facilities and equipment are also important factors determining the growth environment of larvae. Abnormal operation of the cultivation facilities and equipment can also lead to differences in larval growth traits, making it impossible to guarantee uniformity. Therefore, there is an urgent need for a cultivation method that can maintain uniform growth traits to cultivate new strains of Penaeus monodon. Summary of the Invention

[0003] This invention overcomes the shortcomings of existing technologies and provides a method and system for intelligent agricultural resource allocation management based on dynamic prediction.

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

[0005] The first aspect of this invention provides a smart agricultural resource allocation management method based on dynamic prediction, comprising the following steps:

[0006] Several initial parental 3D models are constructed. The similarity between the several initial parental 3D models and the parental screening standard model is calculated based on the Jaccard similarity algorithm. It is then determined whether the similarity is greater than a preset similarity to obtain multiple basic breeding parents for Penaeus monodon.

[0007] Multiple reproductive parent lines were extracted and identified using genotyping technology to obtain multiple gene combination information. The multiple gene combination information was then imported into a blank pairing table and compared with the reference group in the blank pairing table to obtain a pairing table of uniformity of growth traits of Penaeus monodon.

[0008] Based on the pairing table, simulated mating is performed to obtain simulated growth records of several shrimp larvae models. The coefficient of variation of the simulated growth records is calculated, and the coefficient of variation is compared with the coefficient of variation of spontaneous mutations to generate anomaly determination results for growth traits.

[0009] Based on the abnormality determination results of the growth traits, data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data are obtained, and the correlation degree of each operating mechanism data and multiple current cultivation environment data is calculated to generate a correlation degree ranking table. Based on the correlation degree ranking table, an adjustment plan is formulated to obtain the control scheme of the cultivation equipment.

[0010] The control scheme of the cultivation equipment is set and controlled, and the growth measurement data of shrimp larvae after control are reacquired. A linear regression model is established to calculate the impact of control on shrimp larvae, and the final cultivation scheme is obtained.

[0011] Furthermore, in a preferred embodiment of the present invention, the step of constructing several initial parental 3D models, calculating the similarity between the several initial parental 3D models and the parental screening standard model based on the Jaccard similarity algorithm, and determining whether the similarity is greater than a preset similarity, to obtain multiple basic breeding parents for Penaeus monodon, specifically includes the following steps:

[0012] A number of individual tiger prawns to be bred are obtained, and these individuals are defined as initial parents. The genetic characteristics of each initial parent are obtained by extracting features from the initial parents based on a convolutional neural network.

[0013] Construct a spatial three-dimensional model, and import the genetic characteristics of each initial parent into the spatial three-dimensional model to obtain several initial parent three-dimensional models;

[0014] The breeding direction information of the new strain of Penaeus monodon is preset. By analyzing the breeding direction information, a first growth trait and a second growth trait are obtained. The first growth trait and the second growth trait are imported into the three-dimensional spatial model to obtain a three-dimensional model of the first strain of Penaeus monodon and a three-dimensional model of the new strain of Penaeus monodon, which are defined as the parent selection standard model. The first growth trait is the growth trait of the new strain of male Penaeus monodon, and the second growth trait is the growth trait of the new strain of female Penaeus monodon.

[0015] The similarity between the initial parent 3D models and the parent selection standard models is determined based on the Jaccard similarity algorithm. The initial parent 3D models and the parent selection standard models are set as two different sets, and the ratio of the number of intersection elements to the number of union elements of the two model parameter sets is calculated to obtain the model similarity.

[0016] Determine whether the similarity of the models is greater than a preset similarity. If it is greater, extract and label the initial parental 3D model to obtain multiple breeding parental lines for tiger prawns.

[0017] Furthermore, in a preferred embodiment of the present invention, the step of extracting and identifying multiple reproductive parents using genotyping technology to obtain multiple gene combination information, importing the multiple gene combination information into a blank pairing table, and comparing it with the reference group in the blank pairing table to obtain a pairing table of uniformity of growth traits of Penaeus monodon, specifically includes the following steps:

[0018] The reproductive basal parents of the tiger prawns were detected using molecular biology techniques to obtain information on the number of male and female parents, and a blank pairing table was drawn based on the information on the number of male and female parents.

[0019] Based on big data networks, the location information of genes of the new strain of Penaeus monodon on chromosomes is obtained. A genetic linkage map is constructed based on the location information. The growth trait characteristics of the new strain of male Penaeus monodon and the new strain of female Penaeus monodon are imported into the genetic linkage map for identification, so as to obtain the gene combination information of the new strain of male Penaeus monodon and the gene combination information of the new strain of female Penaeus monodon.

[0020] In the blank pairing table, the gene combination information of the new male tiger prawn and the new female tiger prawn were set as reference groups. Gene extraction and identification were performed on multiple reproductive parents of the tiger prawn using genotyping technology to obtain multiple gene combination information.

[0021] Multiple gene combination information is imported into the blank pairing table for corresponding comparison. It is determined whether the multiple gene combination information is less than the reference group. If it is less, the unpaired gene combination is removed, and finally the growth trait uniformity pairing table of tiger prawn is obtained.

[0022] Furthermore, in a preferred embodiment of the present invention, the step of obtaining simulated growth records of several shrimp larvae models by simulating mating based on the pairing table, calculating the coefficient of variation of the simulated growth records, comparing the coefficient of variation with the coefficient of variation of spontaneous mutations, and generating anomaly determination results for growth traits specifically includes the following steps:

[0023] Obtain the initial design drawing parameters and current operating parameters of the shrimp breeding equipment, construct a simulation 3D model, import the initial design drawing parameters into the simulation 3D model to obtain the simulation 3D model of the breeding equipment, and import the current operating parameters into the simulation 3D model of the breeding equipment to obtain the simulation 3D model of the current breeding equipment.

[0024] Based on the growth trait uniformity pairing table of the tiger prawn, the simulation three-dimensional model of the current breeding equipment is controlled to simulate mating of the basic parents, resulting in several prawn larvae models, and the simulated growth records of the several prawn larvae models are retrieved.

[0025] Based on the simulated growth record, extract several growth measurement data, calculate the average value of the several growth measurement data, assign a relative index to the growth measurement data and define it as the standard deviation, calculate the percentage value between the average value and the standard deviation, and obtain the coefficient of variation of the shrimp larvae model.

[0026] Specific conditions for spontaneous mutation of shrimp larvae are obtained, keywords are determined based on the specific conditions for spontaneous mutation of shrimp larvae, and the coefficient of variation of spontaneous mutation of larvae is obtained by searching and calculating in the big data network according to the keywords. It is then determined whether the coefficient of variation of the shrimp larvae model is less than the coefficient of variation of spontaneous mutation of larvae. If it is less, the growth trait uniformity pairing table is marked as an anomaly.

[0027] If the value is greater than the specified value, the operation of the cultivation equipment will be marked as a type II anomaly and integrated with the type I anomaly to generate an anomaly determination result for the growth trait.

[0028] Furthermore, in a preferred embodiment of the present invention, the step of obtaining data from each operating mechanism of the cultivation equipment and multiple current cultivation environment data based on the abnormality determination result of the growth trait, calculating the correlation degree between the data from each operating mechanism and the multiple current cultivation environment data, generating a correlation degree ranking table, and selecting and formulating adjustment plans based on the correlation degree ranking table to obtain a control scheme for the cultivation equipment, specifically includes the following steps:

[0029] The abnormality determination results of the growth traits are analyzed to repair the mutation situation of shrimp larvae. If the abnormality determination result is a type of abnormality, the deviation threshold between the coefficient of variation of the shrimp larvae model and the spontaneous coefficient of variation of the larvae is calculated, and the uniformity pairing table of the growth traits is adjusted and optimized based on the deviation threshold.

[0030] If the anomaly determination result is a type II anomaly, then the data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data are obtained, and the correlation between the data of each operating mechanism and the current cultivation environment data is analyzed by the grey relational analysis method.

[0031] Construct an association matrix, eliminate the dimensional influence between each of the operating mechanism data and multiple current cultivation environment data, and place them in the association matrix. Calculate the association coefficient of the target factor in the association matrix using a grey analysis function and sort them to generate an association degree ranking table. If the association coefficient is greater than a preset coefficient, it indicates that one or more environmental factors in the cultivation equipment have a significant impact on the operation of a certain mechanism.

[0032] A preset correlation degree screening value is set, and the cultivation environment data that is at the forefront of the correlation degree screening value is extracted from the correlation degree ranking table. The operating institutions that have an impact are identified by the screened cultivation environment data, and the corresponding correlation coefficients of the operating institutions that have an impact are found in the correlation degree ranking table. An adjustment plan is formulated based on the found correlation coefficients to obtain the control scheme of the cultivation equipment.

[0033] Furthermore, in a preferred embodiment of the present invention, the step of setting and regulating the shrimp larvae according to the regulation scheme of the cultivation equipment and re-acquiring the growth measurement data of the shrimp larvae after regulation, establishing a linear regression model to calculate the impact of regulation on the shrimp larvae, and obtaining the final cultivation scheme specifically includes the following steps:

[0034] The parameters of the actual simulation three-dimensional model are set and adjusted according to the control scheme of the cultivation equipment, and the basic parent shrimp are re-simulated and mated a second time to obtain the growth measurement data of the shrimp larvae after the control.

[0035] A linear regression model was established based on the growth measurement data of shrimp larvae after the regulation. The growth measurement data was defined as the dependent variable, and the regulation scheme was defined as the independent variable. The growth measurement data and the regulation scheme were divided into training set and test set.

[0036] The training set is imported into the linear regression model for training. The parameters of the linear regression model are continuously adjusted based on the mean squared error loss function until they gradually fit the training data. The linear regression model is then tested using a test set to obtain the linear regression model of influence.

[0037] The growth measurement data and the regulation scheme are imported into the linear regression model of the influence degree to calculate the influence degree, and the influence degree of the regulation on the growth traits of shrimp larvae is obtained.

[0038] Determine whether the influence degree is less than the preset influence degree. If it is less, output the regulation scheme as the final cultivation scheme.

[0039] A second aspect of the present invention provides a Penaeus monodon breeding system based on uniformity of growth traits. The Penaeus monodon breeding system includes a memory and a processor. The memory stores a Penaeus monodon breeding method program based on uniformity of growth traits. When the processor executes the Penaeus monodon breeding method program based on uniformity of growth traits, it performs the following steps:

[0040] Several initial parental 3D models are constructed. The similarity between the several initial parental 3D models and the parental screening standard model is calculated based on the Jaccard similarity algorithm. It is then determined whether the similarity is greater than a preset similarity to obtain multiple basic breeding parents for Penaeus monodon.

[0041] Multiple reproductive parent lines were extracted and identified using genotyping technology to obtain multiple gene combination information. The multiple gene combination information was then imported into a blank pairing table and compared with the reference group in the blank pairing table to obtain a pairing table of uniformity of growth traits of Penaeus monodon.

[0042] Based on the pairing table, simulated mating is performed to obtain simulated growth records of several shrimp larvae models. The coefficient of variation of the simulated growth records is calculated, and the coefficient of variation is compared with the coefficient of variation of spontaneous mutations to generate anomaly determination results for growth traits.

[0043] Based on the abnormality determination results of the growth traits, data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data are obtained, and the correlation degree of each operating mechanism data and multiple current cultivation environment data is calculated to generate a correlation degree ranking table. Based on the correlation degree ranking table, an adjustment plan is formulated to obtain the control scheme of the cultivation equipment.

[0044] The control scheme of the cultivation equipment is set and controlled, and the growth measurement data of shrimp larvae after control are reacquired. A linear regression model is established to calculate the impact of control on shrimp larvae, and the final cultivation scheme is obtained.

[0045] Furthermore, in a preferred embodiment of the present invention, the step of setting and regulating the shrimp larvae according to the regulation scheme of the cultivation equipment and re-acquiring the growth measurement data of the shrimp larvae after regulation, establishing a linear regression model to calculate the impact of regulation on the shrimp larvae, and obtaining the final cultivation scheme specifically includes the following steps:

[0046] The parameters of the actual simulation three-dimensional model are set and adjusted according to the control scheme of the cultivation equipment, and the basic parent shrimp are re-simulated and mated a second time to obtain the growth measurement data of the shrimp larvae after the control.

[0047] A linear regression model was established based on the growth measurement data of shrimp larvae after the regulation. The growth measurement data was defined as the dependent variable, and the regulation scheme was defined as the independent variable. The growth measurement data and the regulation scheme were divided into training set and test set.

[0048] The training set is imported into the linear regression model for training. The parameters of the linear regression model are continuously adjusted based on the mean squared error loss function until they gradually fit the training data. The linear regression model is then tested using a test set to obtain the linear regression model of influence.

[0049] The growth measurement data and the regulation scheme are imported into the linear regression model of the influence degree to calculate the influence degree, and the influence degree of the regulation on the growth traits of shrimp larvae is obtained.

[0050] Determine whether the influence degree is less than the preset influence degree. If it is less, output the regulation scheme as the final cultivation scheme.

[0051] This invention addresses the technical deficiencies in the prior art, and its beneficial technical effects are as follows:

[0052] Multiple parent strains of *Litopenaeus monodon* were obtained, and their genetic information was extracted and identified using genotyping technology. This yielded multiple gene combinations, which were imported into a blank pairing table and compared with a reference group in the same table to obtain a pairing table for the uniformity of growth traits in *Litopenaeus monodon*. Based on this pairing table, the coefficient of variation of the simulated growth records was calculated, generating anomaly detection results for growth traits. Based on these anomaly detection results, data from various operating mechanisms of the cultivation equipment and multiple current breeding environment data were obtained. Correlation degrees were calculated, and a correlation degree ranking table was generated. Based on this ranking table, a control scheme for the cultivation equipment was selected and formulated. A linear regression model was established to calculate the impact of the control on shrimp larvae, resulting in the final cultivation scheme. This invention can address mutations or variations that occur in *Litopenaeus monodon* larvae during cultivation by improving the high degree of parent genome pairing and the operating environment of the cultivation equipment, thereby reducing the mutation rate and ensuring high uniformity of growth traits in *Litopenaeus monodon*. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.

[0054] Figure 1A flowchart of the first method for breeding Penaeus monodon based on the uniformity of growth traits is shown;

[0055] Figure 2 A flowchart of the second method for breeding tiger prawns based on the uniformity of growth traits is shown;

[0056] Figure 3 A flowchart of the third method for breeding tiger prawns based on the uniformity of growth traits is shown;

[0057] Figure 4 A system framework diagram of a Penaeus monodon breeding system based on selection for uniformity of growth traits is shown. Detailed Implementation

[0058] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0059] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0060] The first aspect of this invention provides a method for breeding tiger prawns based on selection for uniformity of growth traits, such as... Figure 1 As shown, it includes the following steps:

[0061] S102: Construct several initial parental 3D models, calculate the similarity between the several initial parental 3D models and the parental screening standard model based on the Jaccard similarity algorithm, and determine whether the similarity is greater than the preset similarity to obtain multiple breeding base parents of tiger prawns;

[0062] S104: Extract and identify multiple reproductive parent lines using genotyping technology to obtain multiple gene combination information, import the multiple gene combination information into a blank pairing table, and compare it with the reference group in the blank pairing table to obtain a pairing table of uniformity of growth traits of Penaeus monodon.

[0063] S106: Based on the pairing table, simulated mating is performed to obtain simulated growth records of several shrimp larvae models. The coefficient of variation of the simulated growth records is calculated, and the coefficient of variation is compared with the coefficient of variation of spontaneous mutation to generate anomaly determination results for growth traits.

[0064] S108: Based on the abnormality determination results of the growth traits, obtain the data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data, calculate the correlation degree of the data of each operating mechanism and multiple current cultivation environment data, generate a correlation degree ranking table, and formulate an adjustment plan according to the correlation degree ranking table to obtain the control scheme of the cultivation equipment.

[0065] S110: Set and regulate according to the regulation scheme of the cultivation equipment and reacquire the growth measurement data of shrimp larvae after regulation. Establish a linear regression model to calculate the impact of regulation on shrimp larvae and obtain the final cultivation scheme.

[0066] Furthermore, in a preferred embodiment of the present invention, the step of constructing several initial parental 3D models, calculating the similarity between the several initial parental 3D models and the parental screening standard model based on the Jaccard similarity algorithm, and determining whether the similarity is greater than a preset similarity, to obtain multiple basic breeding parents for Penaeus monodon, specifically includes the following steps:

[0067] A number of individual tiger prawns to be bred are obtained, and these individuals are defined as initial parents. The genetic characteristics of each initial parent are obtained by extracting features from the initial parents based on a convolutional neural network.

[0068] Construct a spatial three-dimensional model, and import the genetic characteristics of each initial parent into the spatial three-dimensional model to obtain several initial parent three-dimensional models;

[0069] The breeding direction information of the new strain of Penaeus monodon is preset. By analyzing the breeding direction information, a first growth trait and a second growth trait are obtained. The first growth trait and the second growth trait are imported into the three-dimensional spatial model to obtain a three-dimensional model of the first strain of Penaeus monodon and a three-dimensional model of the new strain of Penaeus monodon, which are defined as the parent selection standard model. The first growth trait is the growth trait of the new strain of male Penaeus monodon, and the second growth trait is the growth trait of the new strain of female Penaeus monodon.

[0070] The similarity between the initial parent 3D models and the parent selection standard models is determined based on the Jaccard similarity algorithm. The initial parent 3D models and the parent selection standard models are set as two different sets, and the ratio of the number of intersection elements to the number of union elements of the two model parameter sets is calculated to obtain the model similarity.

[0071] Determine whether the similarity of the models is greater than a preset similarity. If it is greater, extract and label the initial parental 3D model to obtain multiple breeding parental lines for tiger prawns.

[0072] It should be noted that the initial parent stock includes both male and female parents. To maintain a high degree of uniformity in the growth traits of the new strain of Penaeus monodon, it is necessary to ensure a high degree of overlap in the growth traits of the male and female parents during selection. Therefore, superior individuals need to be selected from the Penaeus monodon individuals to be bred as breeding parents. Three-dimensional models of all initial parents are obtained by constructing a spatial three-dimensional model. Parent selection must have a selection reference standard; therefore, a parent selection standard model can be constructed based on the uniformity of growth traits of the female and male parents of the new strain of Penaeus monodon to be bred. The similarity between the three-dimensional model of each initial parent and the parent selection standard model is compared using the Jaccard similarity algorithm. The Jaccard similarity algorithm is typically used to compare the similarity of model structures; it measures similarity by calculating the ratio of the intersection to the union of the parameter sets of two models. It is then determined whether the similarity of the models is greater than a preset similarity. If it is greater, the three-dimensional models of the initial parents are extracted and labeled, resulting in multiple basic breeding parents for Penaeus monodon. This method selects superior breeding parents by comparing the similarity between the initial three-dimensional model of the parents and the standard model of the parents, thereby improving the quality of parent pairing and the uniformity of growth traits, and providing a basis for parent pairing.

[0073] Furthermore, in a preferred embodiment of the present invention, multiple reproductive parent lines are extracted and identified using genotyping technology to obtain multiple gene combination information. This multiple gene combination information is then imported into a blank pairing table and compared with a reference group in the blank pairing table to obtain a pairing table for the uniformity of growth traits in *Litopenaeus monodon*. Figure 2 As shown, the specific steps include:

[0074] S202: Detect the reproductive basal parents of multiple tiger prawns using molecular biology techniques, obtain information on the number of male parents and female parents, and draw a blank pairing table based on the information on the number of male parents and female parents.

[0075] S204: Based on big data networks, obtain the location information of genes of the new strain of Penaeus monodon on chromosomes, construct a genetic linkage map based on the location information, and import the growth trait characteristics of the new strain of male Penaeus monodon and the new strain of female Penaeus monodon into the genetic linkage map for identification, thereby obtaining the gene combination information of the new strain of male Penaeus monodon and the gene combination information of the new strain of female Penaeus monodon.

[0076] S206: In the blank pairing table, the gene combination information of the new variety of male tiger prawn and the gene combination information of the new variety of female tiger prawn are set as reference groups. Gene extraction and identification are performed on multiple reproductive parent lines of the tiger prawn using genotyping technology to obtain multiple gene combination information.

[0077] S208: Import the information of multiple gene combinations into the blank pairing table for corresponding comparison, and determine whether the information of multiple gene combinations is less than the reference group. If it is less, remove the unpaired gene combinations, and finally obtain the growth trait uniformity pairing table of tiger prawn.

[0078] It should be noted that, since the sex ratio of the primary breeding stock of tiger prawns may be unequal, and it is necessary to ensure that each male and female parent is paired, a blank pairing table can be created to pair genomically similar male and female parents, improving pairing efficiency. The blank pairing table has two columns for entries: one for male parents and one for female parents. Each parent column also includes a parent reference field for screening the entered parents. Genetic linkage maps are maps showing the location and relative order of genes on chromosomes. These maps are used to determine gene combination patterns by mating the parent shrimp and analyzing the genotypes of their offspring. Genetic linkage maps were constructed to identify the gene combinations of male and female *Litopenaeus monodon* var. *monogamous* species. These gene combinations were then imported into a reference field in a blank pairing table. Genotyping techniques were used to detect the gene combinations of all basal breeding parents, and all gene combinations were imported into the male / female fields of the blank pairing table according to the number of males and females. It was determined whether multiple gene combinations were less than the reference group; if so, unpaired gene combinations were removed, resulting in a pairing table for the uniformity of growth traits in *Litopenaeus monodon*. This method pairs parents by comparing the differences between the gene combinations of basal breeding parents and the gene combinations of the new *Litopenaeus monodon* var. *monogamous* species, ensuring that the genetic makeup of male and female parents is equal, thereby improving genetic stability and fixing the uniformity of growth traits.

[0079] Furthermore, in a preferred embodiment of the present invention, the step of obtaining simulated growth records of several shrimp larvae models by simulating mating based on the pairing table, calculating the coefficient of variation of the simulated growth records, comparing the coefficient of variation with the coefficient of variation of spontaneous mutations, and generating anomaly determination results for growth traits specifically includes the following steps:

[0080] Obtain the initial design drawing parameters and current operating parameters of the shrimp breeding equipment, construct a simulation 3D model, import the initial design drawing parameters into the simulation 3D model to obtain the simulation 3D model of the breeding equipment, and import the current operating parameters into the simulation 3D model of the breeding equipment to obtain the simulation 3D model of the current breeding equipment.

[0081] Based on the growth trait uniformity pairing table of the tiger prawn, the simulation three-dimensional model of the current breeding equipment is controlled to simulate mating of the basic parents, resulting in several prawn larvae models, and the simulated growth records of the several prawn larvae models are retrieved.

[0082] Based on the simulated growth record, extract several growth measurement data, calculate the average value of the several growth measurement data, assign a relative index to the growth measurement data and define it as the standard deviation, calculate the percentage value between the average value and the standard deviation, and obtain the coefficient of variation of the shrimp larvae model.

[0083] Specific conditions for spontaneous mutation of shrimp larvae are obtained, keywords are determined based on the specific conditions for spontaneous mutation of shrimp larvae, and the coefficient of variation of spontaneous mutation of larvae is obtained by searching and calculating in the big data network according to the keywords. It is then determined whether the coefficient of variation of the shrimp larvae model is less than the coefficient of variation of spontaneous mutation of larvae. If it is less, the growth trait uniformity pairing table is marked as an anomaly.

[0084] If the value is greater than the specified value, the operation of the cultivation equipment will be marked as a type II anomaly and integrated with the type I anomaly to generate an anomaly determination result for the growth trait.

[0085] It should be noted that the initial design drawings of the shrimp cultivation equipment include parameters such as part dimensions, connection parameters, installation location parameters, and setting parameters for each mechanism. The current operating parameters include cultivation light intensity, dissolved oxygen, and seawater salinity. After pairing, the growth and mating of the tiger prawns are affected by the environment created by themselves or the cultivation equipment. Both of these factors can lead to gene mutations in the larvae produced, resulting in deviations in growth traits. Constructing a three-dimensional simulation model of the actual operation of the current cultivation equipment allows for simulated mating of the paired parent stock, facilitating more intuitive observation and recording of larval growth by aquaculture personnel, thereby obtaining simulated growth measurement data of the shrimp larvae. According to the data, the simulated growth measurement data includes growth size, growth rate, and morphological changes. The coefficient of variation (CV) is calculated based on the growth record of each larva, representing the degree of mutation during the larva's growth process. Specific conditions for spontaneous mutation in shrimp larvae include gene replication errors, chemical exposure, and gene damage. The CV of spontaneous mutations in the larvae is calculated, and finally, it is determined whether the CV of the shrimp larva model is less than the spontaneous CV of the larvae. If it is less, the uniformity of growth traits is marked as a Class I anomaly in the pairwise table; if it is greater, the operation of the cultivation equipment is marked as a Class II anomaly, and the Class I anomaly is integrated to generate an anomaly determination result for the growth trait. This method determines the cause of mutation by analyzing the degree of variation in larvae, thereby enabling the development of corresponding solutions to reduce the probability of deviation in the uniformity of shrimp larvae growth traits and improve genetic stability.

[0086] Furthermore, in a preferred embodiment of the present invention, the abnormality determination result of the growth trait is used to obtain data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data, and the correlation degree of the data of each operating mechanism and the multiple current cultivation environment data is calculated to generate a correlation degree ranking table. An adjustment plan is then formulated based on the correlation degree ranking table to obtain a control scheme for the cultivation equipment, such as... Figure 3 As shown, the specific steps include:

[0087] S302: Analyze the abnormality determination results of the growth traits to repair the mutation situation of shrimp larvae. If the abnormality determination result is a type of abnormality, then calculate the deviation threshold between the coefficient of variation of the shrimp larvae model and the spontaneous coefficient of variation of the larvae, and adjust and optimize the uniformity pairing table of the growth traits based on the deviation threshold.

[0088] S304: If the anomaly determination result is a type II anomaly, then obtain the data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data, and analyze the correlation between the data of each operating mechanism and the current cultivation environment data through the grey relational analysis method;

[0089] S306: Construct an association matrix, eliminate the dimensional influence between each of the operating mechanism data and multiple current cultivation environment data and place them in the association matrix, calculate the association coefficient of the target factor in the association matrix through the grey analysis function and sort them, and generate an association degree ranking table. If the association coefficient is greater than the preset coefficient, it indicates that one or more environmental factors in the cultivation equipment have a significant impact on the operation of a certain mechanism.

[0090] S308: Preset correlation degree screening value, extract the cultivation environment data that is at the front of the correlation degree screening value in the correlation degree ranking table, determine the operating mechanism that has an impact through the screened cultivation environment data, and find the corresponding correlation coefficient in the correlation degree ranking table based on the operating mechanism that has an impact, formulate an adjustment plan based on the found correlation coefficient, and obtain the control scheme of the cultivation equipment.

[0091] It should be noted that when the abnormality determination result of the growth trait is shown as a Class I abnormality, it indicates that there is an error or mistake in the genome pairing in the growth trait uniformity pairing table of Penaeus monodon. In this case, the spontaneous mutation of the shrimp larvae can be improved and repaired by readjusting the pairing of the male and female parent genomes in the pairing table. If the abnormality determination result is shown as a Class II abnormality, the growth environment of the shrimp larvae in the cultivation equipment can be improved. Therefore, the operation of the cultivation equipment needs to be adjusted. The cultivation equipment has multiple operating mechanisms, and each operating mechanism will create one or more different growth environments. The mutation of the shrimp larvae may be caused by one or more of the growth environments. Therefore, by determining the current cultivation environment that causes the mutation and calculating the correlation between this environmental data and each mechanism, the cultivation equipment can be precisely controlled to solve the problem of larvae mutation caused by environmental abnormalities. The correlation coefficient of the target factor in the correlation matrix is ​​calculated by the grey analysis function. If the correlation coefficient is greater than the preset coefficient, a certain environmental factor in the cultivation equipment has a significant impact on the operation of a certain mechanism. The abnormal operating mechanism is determined by screening the correlation coefficients at the top of the correlation coefficients through the correlation threshold, and a control plan is formulated based on the corresponding correlation coefficients. This method can determine the solution based on the anomaly determination result. For Class I anomalies, the pairing table is adjusted. For Class II anomalies, the correlation coefficient between the environmental factors that caused the mutation and the equipment operating mechanism that created the environmental factors is calculated. Based on the correlation coefficient, the abnormal operating mechanism of the equipment is adjusted to effectively avoid the phenomenon of mutation in shrimp larvae and improve the uniformity of growth traits.

[0092] Furthermore, in a preferred embodiment of the present invention, the step of setting and regulating the shrimp larvae according to the regulation scheme of the cultivation equipment and re-acquiring the growth measurement data of the shrimp larvae after regulation, establishing a linear regression model to calculate the impact of regulation on the shrimp larvae, and obtaining the final cultivation scheme specifically includes the following steps:

[0093] The parameters of the actual simulation three-dimensional model are set and adjusted according to the control scheme of the cultivation equipment, and the basic parent shrimp are re-simulated and mated a second time to obtain the growth measurement data of the shrimp larvae after the control.

[0094] A linear regression model was established based on the growth measurement data of shrimp larvae after the regulation. The growth measurement data was defined as the dependent variable, and the regulation scheme was defined as the independent variable. The growth measurement data and the regulation scheme were divided into training set and test set.

[0095] The training set is imported into the linear regression model for training. The parameters of the linear regression model are continuously adjusted based on the mean squared error loss function until they gradually fit the training data. The linear regression model is then tested using a test set to obtain the linear regression model of influence.

[0096] The growth measurement data and the regulation scheme are imported into the linear regression model of the influence degree to calculate the influence degree, and the influence degree of the regulation on the growth traits of shrimp larvae is obtained.

[0097] Determine whether the influence degree is less than the preset influence degree. If it is less, output the regulation scheme as the final cultivation scheme.

[0098] It should be noted that after adjusting the equipment according to the control plan, the breeding parents are re-mating. The growth measurement data of the new shrimp larvae will inevitably differ from the historical growth measurement data. This indicates that the adjusted operating parameters of the cultivation equipment have a certain impact on the new shrimp larvae growth measurement data. Therefore, it is necessary to obtain the degree of influence of this control plan on the new growth measurement data to determine the feasibility of the control plan. A linear regression model is constructed; linear regression is a method for predicting the relationship between independent and dependent variables. The goodness of fit and prediction accuracy of the linear regression model are used to determine the degree of influence of equipment control on larvae growth. The growth measurement data and the control plan are divided into training and testing sets. The linear regression model is trained and tested to obtain a linear regression model of influence. Based on the linear regression model of influence, the degree of influence of the control on the growth traits of the shrimp larvae is obtained. It is determined whether the degree of influence is less than a preset degree of influence. If it is less, the control plan is output as the final cultivation plan. This method evaluates the feasibility of a control scheme by calculating the impact of the control scheme on the growth measurement data obtained from the second mating, thereby significantly improving the accuracy and stability of the control of the cultivation equipment, avoiding control errors, better improving the growth environment of tiger prawn larvae, and maintaining the uniformity of growth traits.

[0099] Furthermore, the method for breeding tiger prawns based on uniformity of growth traits also includes the following steps:

[0100] Based on big data networks, the mortality rate of Penaeus monodon under different breeding density combinations is obtained. A Penaeus monodon mortality rate prediction model is constructed using deep learning network algorithms. The mortality rates of Penaeus monodon under different breeding density combinations are then imported into the Penaeus monodon mortality rate prediction model for training, resulting in a trained Penaeus monodon mortality rate prediction model.

[0101] The cultivation density information of tiger prawns in the cultivation equipment is obtained, and the cultivation density is imported into the trained tiger prawn mortality prediction model to obtain the tiger prawn mortality rate.

[0102] The mortality rate of the tiger prawn is defined as the search keyword. Based on the search keyword, a search is conducted in the big data network to obtain several solutions for the mortality of tiger prawn, and the cure rate corresponding to each solution is obtained.

[0103] Construct a gradient table, import the cure rates corresponding to each disease-causing solution into the gradient table, sort them by gradient, generate a solution cure rate gradient table, and extract the maximum cure rate based on the solution cure rate gradient table;

[0104] Determine whether the maximum cure rate is greater than the preset cure rate. If it is greater, set the mortality solution corresponding to the maximum cure rate as the cultivation density adjustment scheme and upload it to the cultivation equipment terminal. If it is less than the maximum cure rate, verify the cure rates ranked after the maximum cure rate until a suitable mortality solution is matched.

[0105] It should be noted that while appropriate shrimp stocking density can help improve production efficiency in Penaeus monodon cultivation, excessively high density may increase the risk of disease and mortality. High-density shrimp farming is more susceptible to disease transmission and spread, leading to a significant increase in mortality and hindering the uniformity of growth traits in new Penaeus monodon strains. Therefore, stocking density should be reasonably controlled. This method predicts the mortality rate of Penaeus monodon at the current density and finds corresponding solutions based on this mortality rate, thereby effectively curing disease problems that occur in Penaeus monodon during high-density cultivation, reducing shrimp mortality, and improving the consolidation of parental gene inheritance. It has high reliability.

[0106] A second aspect of the present invention provides a Penaeus monodon breeding system based on uniform selection of growth traits. The Penaeus monodon breeding system includes a memory 41 and a processor 42. The memory 41 stores a Penaeus monodon breeding method program based on uniform selection of growth traits. When the Penaeus monodon breeding method program based on uniform selection of growth traits is executed by the processor 42, such as... Figure 4 As shown, the following steps are performed:

[0107] Several initial parental 3D models are constructed. The similarity between the several initial parental 3D models and the parental screening standard model is calculated based on the Jaccard similarity algorithm. It is then determined whether the similarity is greater than a preset similarity to obtain multiple basic breeding parents for Penaeus monodon.

[0108] Multiple reproductive parent lines were extracted and identified using genotyping technology to obtain multiple gene combination information. The multiple gene combination information was then imported into a blank pairing table and compared with the reference group in the blank pairing table to obtain a pairing table of uniformity of growth traits of Penaeus monodon.

[0109] Based on the pairing table, simulated mating is performed to obtain simulated growth records of several shrimp larvae models. The coefficient of variation of the simulated growth records is calculated, and the coefficient of variation is compared with the coefficient of variation of spontaneous mutations to generate anomaly determination results for growth traits.

[0110] Based on the abnormality determination results of the growth traits, data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data are obtained, and the correlation degree of each operating mechanism data and multiple current cultivation environment data is calculated to generate a correlation degree ranking table. Based on the correlation degree ranking table, an adjustment plan is formulated to obtain the control scheme of the cultivation equipment.

[0111] The control scheme of the cultivation equipment is set and controlled, and the growth measurement data of shrimp larvae after control are reacquired. A linear regression model is established to calculate the impact of control on shrimp larvae, and the final cultivation scheme is obtained.

[0112] Furthermore, in a preferred embodiment of the present invention, the step of setting and regulating the shrimp larvae according to the regulation scheme of the cultivation equipment and re-acquiring the growth measurement data of the shrimp larvae after regulation, establishing a linear regression model to calculate the impact of regulation on the shrimp larvae, and obtaining the final cultivation scheme specifically includes the following steps:

[0113] The parameters of the actual simulation three-dimensional model are set and adjusted according to the control scheme of the cultivation equipment, and the basic parent shrimp are re-simulated and mated a second time to obtain the growth measurement data of the shrimp larvae after the control.

[0114] A linear regression model was established based on the growth measurement data of shrimp larvae after the regulation. The growth measurement data was defined as the dependent variable, and the regulation scheme was defined as the independent variable. The growth measurement data and the regulation scheme were divided into training set and test set.

[0115] The training set is imported into the linear regression model for training. The parameters of the linear regression model are continuously adjusted based on the mean squared error loss function until they gradually fit the training data. The linear regression model is then tested using a test set to obtain the linear regression model of influence.

[0116] The growth measurement data and the regulation scheme are imported into the linear regression model of the influence degree to calculate the influence degree, and the influence degree of the regulation on the growth traits of shrimp larvae is obtained.

[0117] Determine whether the influence degree is less than the preset influence degree. If it is less, output the regulation scheme as the final cultivation scheme.

[0118] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for breeding of Penaeus monodon based on uniformity of growth traits, characterized by, Includes the following steps: Several initial parental 3D models are constructed. The similarity between the several initial parental 3D models and the parental screening standard model is calculated based on the Jaccard similarity algorithm. It is then determined whether the similarity is greater than a preset similarity to obtain multiple basic breeding parents for Penaeus monodon. Multiple reproductive parent lines were extracted and identified using genotyping technology to obtain multiple gene combination information. The multiple gene combination information was then imported into a blank pairing table and compared with the reference group in the blank pairing table to obtain a pairing table of uniformity of growth traits of Penaeus monodon. Based on the growth trait uniformity pairing table, simulated mating is performed to obtain simulated growth records of several shrimp larvae models. The coefficient of variation of the simulated growth records is calculated, and the coefficient of variation is compared with the coefficient of variation of spontaneous mutations to generate anomaly determination results for growth traits. Based on the abnormality determination results of the growth traits, data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data are obtained, and the correlation degree of each operating mechanism data and multiple current cultivation environment data is calculated to generate a correlation degree ranking table. Based on the correlation degree ranking table, an adjustment plan is formulated to obtain the control scheme of the cultivation equipment. The control scheme of the cultivation equipment is set and controlled, and the growth measurement data of shrimp larvae after control are reacquired. A linear regression model is established to calculate the impact of control on shrimp larvae and obtain the final cultivation scheme. The process of constructing several initial parental 3D models, calculating the similarity between these initial parental 3D models and the parental selection standard model based on the Jaccard similarity algorithm, and determining whether the similarity is greater than a preset similarity, to obtain multiple basic breeding parents for Penaeus monodon, specifically includes the following steps: A number of individual tiger prawns to be bred are obtained, and these individuals are defined as initial parents. The genetic characteristics of each initial parent are obtained by extracting features from the initial parents based on a convolutional neural network. Construct a spatial three-dimensional model, and import the genetic characteristics of each initial parent into the spatial three-dimensional model to obtain several initial parent three-dimensional models; The breeding direction information of the new strain of Penaeus monodon is preset. By analyzing the breeding direction information, a first growth trait and a second growth trait are obtained. The first growth trait and the second growth trait are imported into the three-dimensional spatial model to obtain a three-dimensional model of the first strain of Penaeus monodon and a three-dimensional model of the new strain of Penaeus monodon, which are defined as the parent selection standard model. The first growth trait is the growth trait of the new strain of male Penaeus monodon, and the second growth trait is the growth trait of the new strain of female Penaeus monodon. The similarity between the initial parent 3D models and the parent selection standard models is determined based on the Jaccard similarity algorithm. The initial parent 3D models and the parent selection standard models are set as two different sets, and the ratio of the number of intersection elements to the number of union elements of the two model parameter sets is calculated to obtain the model similarity. Determine whether the similarity of the models is greater than a preset similarity. If it is greater, extract and label the initial parental 3D model to obtain multiple breeding parental lines for tiger prawns.

2. The method for breeding tiger prawns based on uniformity of growth traits according to claim 1, characterized in that, The process involves extracting and identifying multiple reproductive parents using genotyping technology to obtain multiple gene combination information. This information is then imported into a blank pairing table and compared with a reference group in the blank pairing table to obtain a pairing table for the uniformity of growth traits in Penaeus monodon. The specific steps include: The reproductive basal parents of the tiger prawns were detected using molecular biology techniques to obtain information on the number of male and female parents, and a blank pairing table was drawn based on the information on the number of male and female parents. Based on big data networks, the location information of genes of the new strain of Penaeus monodon on chromosomes is obtained. A genetic linkage map is constructed based on the location information. The growth trait characteristics of the new strain of male Penaeus monodon and the new strain of female Penaeus monodon are imported into the genetic linkage map for identification, so as to obtain the gene combination information of the new strain of male Penaeus monodon and the gene combination information of the new strain of female Penaeus monodon. In the blank pairing table, the gene combination information of the new male tiger prawn and the gene combination information of the new female tiger prawn are set as the reference group. Gene extraction and identification are performed on multiple reproductive parents of the tiger prawn using genotyping technology to obtain multiple gene combination information. Multiple gene combination information is imported into the blank pairing table for corresponding comparison. It is determined whether the multiple gene combination information is less than the reference group. If it is less, the unpaired gene combination is removed, and finally the growth trait uniformity pairing table of tiger prawn is obtained.

3. The method for breeding tiger prawns based on uniformity of growth traits according to claim 1, characterized in that, The process of obtaining simulated growth records of several shrimp larvae models through simulated mating based on the pairing table, calculating the coefficient of variation of the simulated growth records, comparing the coefficient of variation with the coefficient of variation of spontaneous mutations, and generating anomaly determination results for growth traits specifically includes the following steps: Obtain the initial design drawing parameters and current operating parameters of the shrimp breeding equipment, construct a simulation 3D model, import the initial design drawing parameters into the simulation 3D model to obtain the simulation 3D model of the breeding equipment, and import the current operating parameters into the simulation 3D model of the breeding equipment to obtain the simulation 3D model of the current breeding equipment. Based on the growth trait uniformity pairing table of the tiger prawn, the simulation three-dimensional model of the current breeding equipment is controlled to simulate mating of the basic parents, resulting in several prawn larvae models, and the simulated growth records of the several prawn larvae models are retrieved. Based on the simulated growth record, extract several growth measurement data, calculate the average value of the several growth measurement data, assign a relative index to the growth measurement data and define it as the standard deviation, calculate the percentage value between the average value and the standard deviation, and obtain the coefficient of variation of the shrimp larvae model. Specific conditions for spontaneous mutation of shrimp larvae are obtained, keywords are determined based on the specific conditions for spontaneous mutation of shrimp larvae, and the coefficient of variation of spontaneous mutation of shrimp larvae is obtained by searching and calculating in the big data network according to the keywords. It is then determined whether the coefficient of variation of the shrimp larvae model is less than the coefficient of variation of spontaneous mutation of shrimp larvae. If it is less, the uniformity of growth traits in the pairing table is marked as an anomaly. If the value is greater than the specified value, the operation of the cultivation equipment will be marked as a type II anomaly and integrated with the type I anomaly to generate an anomaly determination result for the growth trait.

4. The method for breeding tiger prawns based on uniformity of growth traits according to claim 1, characterized in that, The process involves obtaining data from each operating mechanism of the cultivation equipment and multiple current cultivation environment data based on the abnormality determination results of the growth traits, calculating the correlation between the data from each operating mechanism and the multiple current cultivation environment data, generating a correlation ranking table, and formulating an adjustment plan based on the correlation ranking table to obtain a control scheme for the cultivation equipment. Specifically, this includes the following steps: The abnormality determination results of the growth traits are analyzed to repair the spontaneous mutation of shrimp larvae. If the abnormality determination result is a type of abnormality, the deviation threshold between the coefficient of variation of the shrimp larvae model and the spontaneous coefficient of variation of the larvae is calculated, and the uniformity pairing table of the growth traits is adjusted and optimized based on the deviation threshold. If the anomaly determination result is a type II anomaly, then the data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data are obtained, and the correlation between the data of each operating mechanism and the current cultivation environment data is analyzed by the grey relational analysis method. Construct an association matrix, eliminate the dimensional influence between each of the operating mechanism data and multiple current cultivation environment data, and place them in the association matrix. Calculate the association coefficient of the target factor in the association matrix using a grey analysis function and sort them to generate an association degree ranking table. If the association coefficient is greater than a preset coefficient, it indicates that one or more environmental factors in the cultivation equipment have a significant impact on the operation of a certain mechanism. A preset correlation degree screening value is set, and the cultivation environment data that is at the forefront of the correlation degree screening value is extracted from the correlation degree ranking table. The operating institutions that have an impact are identified by the screened cultivation environment data, and the corresponding correlation coefficients of the operating institutions that have an impact are found in the correlation degree ranking table. An adjustment plan is formulated based on the found correlation coefficients to obtain the control scheme of the cultivation equipment.

5. The method for breeding tiger prawns based on uniformity of growth traits according to claim 1, characterized in that, The process of setting and regulating the shrimp larvae according to the regulation scheme of the cultivation equipment, re-acquiring the growth measurement data of the shrimp larvae after regulation, establishing a linear regression model to calculate the impact of regulation on the shrimp larvae, and obtaining the final cultivation scheme specifically includes the following steps: The parameters of the actual simulation three-dimensional model are set and adjusted according to the control scheme of the cultivation equipment, and the basic parent shrimp are re-simulated and mated a second time to obtain the growth measurement data of the shrimp larvae after the control. A linear regression model was established based on the growth measurement data of shrimp larvae after the regulation. The growth measurement data was defined as the dependent variable, and the regulation scheme was defined as the independent variable. The growth measurement data and the regulation scheme were divided into training set and test set. The training set is imported into the linear regression model for training. The parameters of the linear regression model are continuously adjusted based on the mean squared error loss function until they gradually fit the training data. The linear regression model is then tested using a test set to obtain the linear regression model of influence. The growth measurement data and the regulation scheme are imported into the linear regression model of the influence degree to calculate the influence degree, and the influence degree of the regulation on the growth traits of shrimp larvae is obtained. Determine whether the influence degree is less than the preset influence degree. If it is less, output the regulation scheme as the final cultivation scheme.

6. A tiger prawn breeding system based on selection for uniformity of growth traits, characterized in that, The Penaeus monodon breeding system based on uniformity of growth traits includes a memory and a processor. The memory stores a Penaeus monodon breeding method program based on uniformity of growth traits. When the processor executes the Penaeus monodon breeding method program based on uniformity of growth traits, it performs the following steps: Several initial parental 3D models are constructed. The similarity between the several initial parental 3D models and the parental screening standard model is calculated based on the Jaccard similarity algorithm. It is then determined whether the similarity is greater than a preset similarity to obtain multiple basic breeding parents for Penaeus monodon. Multiple reproductive parent lines were extracted and identified using genotyping technology to obtain multiple gene combination information. The multiple gene combination information was then imported into a blank pairing table and compared with the reference group in the blank pairing table to obtain a pairing table of uniformity of growth traits of Penaeus monodon. Based on the growth trait uniformity pairing table, simulated mating is performed to obtain simulated growth records of several shrimp larvae models. The coefficient of variation of the simulated growth records is calculated, and the coefficient of variation is compared with the coefficient of variation of spontaneous mutations to generate anomaly determination results for growth traits. Based on the abnormality determination results of the growth traits, data of each operating mechanism of the cultivation equipment and multiple current cultivation environment data are obtained, and the correlation degree of each operating mechanism data and multiple current cultivation environment data is calculated to generate a correlation degree ranking table. Based on the correlation degree ranking table, an adjustment plan is formulated to obtain the control scheme of the cultivation equipment. The control scheme of the cultivation equipment is set and controlled, and the growth measurement data of shrimp larvae after control are reacquired. A linear regression model is established to calculate the impact of control on shrimp larvae and obtain the final cultivation scheme. The process of constructing several initial parental 3D models, calculating the similarity between these initial parental 3D models and the parental selection standard model based on the Jaccard similarity algorithm, and determining whether the similarity is greater than a preset similarity, to obtain multiple basic breeding parents for Penaeus monodon, specifically includes the following steps: A number of individual tiger prawns to be bred are obtained, and these individuals are defined as initial parents. The genetic characteristics of each initial parent are obtained by extracting features from the initial parents based on a convolutional neural network. Construct a spatial three-dimensional model, and import the genetic characteristics of each initial parent into the spatial three-dimensional model to obtain several initial parent three-dimensional models; The breeding direction information of the new strain of Penaeus monodon is preset. By analyzing the breeding direction information, a first growth trait and a second growth trait are obtained. The first growth trait and the second growth trait are imported into the three-dimensional spatial model to obtain a three-dimensional model of the first strain of Penaeus monodon and a three-dimensional model of the new strain of Penaeus monodon, which are defined as the parent selection standard model. The first growth trait is the growth trait of the new strain of male Penaeus monodon, and the second growth trait is the growth trait of the new strain of female Penaeus monodon. The similarity between the initial parent 3D models and the parent selection standard models is determined based on the Jaccard similarity algorithm. The initial parent 3D models and the parent selection standard models are set as two different sets, and the ratio of the number of intersection elements to the number of union elements of the two model parameter sets is calculated to obtain the model similarity. Determine whether the similarity of the models is greater than a preset similarity. If it is greater, extract and label the initial parental 3D model to obtain multiple breeding parental lines for tiger prawns.

7. The tiger prawn breeding system based on uniformity of growth traits according to claim 6, characterized in that, The process of setting and regulating the shrimp larvae according to the regulation scheme of the cultivation equipment, re-acquiring the growth measurement data of the shrimp larvae after regulation, establishing a linear regression model to calculate the impact of regulation on the shrimp larvae, and obtaining the final cultivation scheme specifically includes the following steps: The parameters of the actual simulation three-dimensional model are set and adjusted according to the control scheme of the cultivation equipment, and the basic parent shrimp are re-simulated and mated a second time to obtain the growth measurement data of the shrimp larvae after the control. A linear regression model was established based on the growth measurement data of shrimp larvae after the regulation. The growth measurement data was defined as the dependent variable, and the regulation scheme was defined as the independent variable. The growth measurement data and the regulation scheme were divided into training set and test set. The training set is imported into the linear regression model for training. The parameters of the linear regression model are continuously adjusted based on the mean squared error loss function until they gradually fit the training data. The linear regression model is then tested using a test set to obtain the linear regression model of influence. The growth measurement data and the regulation scheme are imported into the linear regression model of the influence degree to calculate the influence degree, and the influence degree of the regulation on the growth traits of shrimp larvae is obtained. Determine whether the influence degree is less than the preset influence degree. If it is less, output the regulation scheme as the final cultivation scheme.

Images