A breeding guidance method and device based on an intelligent optimization algorithm

Abstract

The present invention relates to the field of artificial intelligence, and particularly relates to a breeding guidance method and device based on an intelligent optimization algorithm. The method includes: disclosing an optimal strategy guidance method for breeding the expected genes of a population based on an intelligent optimization algorithm, aiming at the time and economic costs in the process of obtaining the expected genes, considering constraints such as the lifespan, lethal genes, and quantity of the population, and optimizing the mating process by using an intelligent optimization algorithm for social learning particle swarm of the population mating sampling, so as to guide the experimenters to determine which genotypes of the population should be put together in each generation of the mating process, thereby achieving the purpose of guiding the population mating.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and more particularly, to a breeding guidance method and device based on an intelligent optimization algorithm. Background Art

[0002] In the field of biomedicine, transgenic mice have unique advantages and practical values and play a significant role; especially the multi-genotype mouse disease model obtained by mating is indispensable in drug research and development and mechanism research. However, in actual operation, the process of breeding multi-genotype mouse models often requires a large amount of time and economic costs; although breeding strategies can be formulated with reference to Mendel's genetic law and finally the desired genotype mouse model can be obtained, there is no reasonable guidance strategy on how to breed the fastest and most efficiently.

[0003] When conducting biomedical-related experiments, it is often necessary to obtain some pre-expected gene types, and these genes need to be finally obtained by continuously mating experimental organisms (taking mice as an example). Since the mouse mating process strictly follows Mendel's genetic law, that is, the genotypes obtained after each generation of mouse mating are obtained according to a certain probability, a large amount of time and economic costs are often required in the process of obtaining the desired genotype. In addition, due to the lack of a reasonable guidance strategy, many mating links are useless in the mouse mating process, which undoubtedly further increases the relevant costs.

[0004] Usually, when researchers obtain the desired genotype by mating mice, they often arrange the mating of each generation of mice manually based on experience, which usually obtains a large number of genotypes that are not desired, with too much randomness, and correspondingly causes a lot of additional time and economic costs; therefore, it is necessary to design an effective mouse mating guidance strategy to provide reasonable mating guidance for breeding mice in the process of obtaining the desired gene. Summary of the Invention

[0005] Embodiments of the present invention provide a breeding guidance method and device based on an intelligent optimization algorithm, which can provide the fastest and most efficient mating strategy guidance for the breeding of a population.

[0006] According to an embodiment of the present invention, a breeding guidance method based on an intelligent optimization algorithm is provided, including the following steps:

[0007] Obtain the initial parameters of the initial generation of the population, where the initial parameters include genotype, desired genotype, lifespan information, and lethal gene information;

[0008] Divide the population into male and female groups, and obtain the genotypes of the second generation of the population generated by randomly mating the male and female groups;

[0009] Query whether there is a desired gene in the genotypes of the second generation;

[0010] If there is an expected gene, calculate the time and economic costs of obtaining the expected genotype throughout the mating process, and initialize the initial parameters; if no expected gene is found, continue to randomly mate the first generation of the population until an expected gene appears.

[0011] Repeat to obtain the genotypes of the second generation of the population produced by randomly mating two groups of male and female until the population size reaches the preset scale.

[0012] When the population size reaches the preset scale, implement the mating strategy of selecting the male and female individuals with the fastest and most efficient reproduction until the number of selections reaches the preset number of selections.

[0013] Furthermore, if there is an expected gene, the specific calculation of the time and economic costs of obtaining the expected genotype throughout the mating process is as follows:

[0014] Calculate the time and economic costs of obtaining the expected genotype throughout the mating process through the total cost calculation formula.

[0015] The total cost calculation formula is:

[0016]

[0017] Among them, C represents the total cost required to reach the expected gene, which includes time cost and economic cost, Ng represents the current generation number, n represents the number of generations required to reach the final expected gene, T(Ng) represents the time required to complete each generation of mating, β*C mouse *N mouse (Ng) represents the economic cost required to complete each generation of mating, C mouse represents the economic cost required to complete one generation of mating, including food and labor, N mouse (Ng) represents the total number of individuals that can participate in mating in this generation. α and β are weight coefficients respectively, which can be preset and adjusted according to actual requirements, that is, if more attention is paid to time cost rather than economic cost, α can be made greater than β.

[0018] Furthermore, before calculating the time and economic costs of obtaining the expected genotype throughout the mating process if there is an expected gene, it also includes:

[0019] Conduct constraint processing on the population, and the constraint processing includes lifespan constraint, lethal gene constraint, and population size constraint.

[0020] Furthermore, the lifespan constraint is:

[0021] Consider the lifespan problem of individuals during the mating process of the population. Individuals exceeding the preset years are regarded as lifespan inactivated individuals in the population; the expression of lifespan inactivated individuals is:

[0022]

[0023] In the formula, Mouse life represents the current survival status of the mouse. 1 indicates an individual in the population that can mate normally, and 0 indicates that the preset survival generation in the population has been exceeded and is set to be inactivated. Mouse Ng represents the number of generations that the current individual has survived, life max represents the maximum number of generations that an individual can survive.

[0024] Furthermore, the lethal gene is restricted as:

[0025] The genotype in the population that causes an individual to lose fertility and die is regarded as a lethal gene. An individual with a lethal gene is regarded as an inactivated lethal gene individual. The expression of the inactivated lethal gene individual is:

[0026]

[0027] Among them, Gene death represents the lethal gene. If this lethal gene appears, all individuals carrying this genotype are regarded as inactivated individuals.

[0028] Furthermore, the population quantity restriction is specifically:

[0029] The preset population individual quantity, and those exceeding the preset individual quantity are regarded as quantity inactivated individuals.

[0030] Furthermore, for the preset individual quantity of the population, those exceeding the preset quantity are regarded as quantity inactivated individuals specifically as:

[0031] Individuals with more mating times of parameters are preferentially regarded as inactivated individuals in turn.

[0032] Furthermore, a social learning particle swarm optimization algorithm is used to select the mating strategies of the fastest and most efficient male and female individuals. The expression of the social learning particle swarm optimization algorithm is:

[0033]

[0034] Δx ij (t + 1) = r 1 (t)Δx i，j (t) + r 2 (t)I i，j φr 3 (t)C i，j (t)

[0035] Among them, x i，j (t) represents the jth dimension of the ith individual at the tth generation, Δx i，j(t + 1) is the amount learned from i superior individuals, I i，j (t) represents the difference between the j-th dimension of i individuals and the corresponding dimension of individuals superior to i individuals, C j，t represents the difference between the j-th dimension of i individuals and the average value of the j-th dimension of all individuals in the current population, r 1 (t), r 2 (t) and r 3 (t) are all random numbers between 0 and 1, φ is a number related to the problem dimension and population size, and the set value of φ is 1.

[0036] Furthermore, when the number of the population reaches the preset scale, a mating strategy for selecting the male and female individuals with the highest fitness is carried out until after the selection times reach the preset selection times, and it also includes:

[0037] When the selection times reach the preset selection times, the mating strategy of the male and female individuals with the highest fitness is output to the display module for display.

[0038] A breeding guidance device based on an intelligent optimization algorithm, comprising:

[0039] A data acquisition module, configured to acquire the initial parameters of the initial generation of the population, and the initial parameters include genotype, expected genotype, lifespan information, and lethal gene information;

[0040] A first acquisition module, configured to divide the population into male and female groups, and acquire the genotypes of the second generation of the population generated by randomly mating the male and female groups,

[0041] A query module, configured to query whether there is an expected gene in the genotype of the second generation,

[0042] A cost calculation module, configured to calculate the time and economic costs of obtaining the expected genotype during the entire mating process and initialize the initial parameters if there is an expected gene; if no expected gene is found, continue to randomly mate the initial generation of the population until an expected gene appears;

[0043] A second acquisition module, configured to repeatedly acquire the genotypes of the second generation of the population generated by randomly mating the male and female groups until the number of the population reaches the preset scale;

[0044] A strategy selection module, configured to, when the number of the population reaches the preset scale, carry out a mating strategy for selecting the male and female individuals with the highest fitness until the selection times reach the preset selection times.

[0045] The breeding guidance method and device based on intelligent optimization algorithm in the embodiments of the present invention, the method includes: Disclosed is an optimal strategy guidance method for breeding the expected genes of a population based on an intelligent optimization algorithm. Aiming at the time and economic costs in the process of obtaining the expected genes, considering constraints such as the lifespan of the population, lethal genes, and quantity, an intelligent optimization algorithm that samples social learning particle swarms for population mating is used to optimize the mating process, so as to guide the experimenters which genotypes of the population should be put together in each generation of mating process, thereby achieving the purpose of guiding the population mating. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The illustrative embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0047] Figure 1 is a flowchart of the liver segmentation method for abdominal volume images based on deep learning of the present invention;

[0048] Figure 2 is a module diagram of the liver segmentation device for abdominal volume images based on deep learning of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0050] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0051] See Figure 1 , according to an embodiment of the present invention, a breeding guidance method based on an intelligent optimization algorithm is provided, including the following steps:

[0052] S100: Obtain the initial parameters of the initial generation of the population. The initial parameters include genotype, expected genotype, lifespan information, and lethal gene information.

[0053] First, initialize the data. Obtain the genotype of the initial generation of mice, the genotype of the expected mice, as well as information such as the lifespan and lethal genes of the mice. The process of mouse mating strictly follows Mendel's genetic law, and the genotype of the next generation is generated strictly according to relevant probabilities. In addition, in combination with the actual situation, the number of mice obtained from each mating is specified to follow a Gaussian distribution.

[0054] S200: Divide the population into male and female groups, and obtain the genotypes of the second generation of the population generated by randomly mating the male and female groups.

[0055] Specifically, the population of the algorithm is defined as all mice that can participate in mating. In the mating process, the population is first divided into male and female populations, and then the principle of random mating is adopted. Individuals are randomly selected from the two populations for mating. The male and female probabilities of the offspring generated after mating also strictly follow Mendel's genetic law, that is, the probability of male or female is both 1 / 2.

[0056] S300: Query whether there is an expected gene in the genotype of the second generation.

[0057] Specifically, step S300 includes:

[0058] S301: Calculate the time and economic costs of obtaining the expected genotype during the entire mating process through the total cost calculation formula;

[0059] The total cost calculation formula is:

[0060]

[0061] Among them, C represents the total cost required to reach the expected gene. This cost includes time cost and economic cost. Ng represents the current generation number, n represents the number of generations required to reach the final expected gene, T(Ng) represents the time required to complete each generation of mating. In combination with the actual situation, this cost is usually a constant; β*C mouse *N mouse (Ng) represents the economic cost required to complete each generation of mating, C mouse represents the economic cost required for each mouse to complete one generation of mating, including food, labor, etc., N mouse (Ng) represents the total number of mice that can participate in mating in this generation. α and β are weight coefficients respectively, which can be preset and adjusted by experimenters according to actual requirements. That is, if more attention is paid to time cost rather than economic cost, α can be made greater than β.

[0062] S400: If there is a desired gene, calculate the time and economic cost of obtaining the desired genotype throughout the mating process and initialize the initial parameters; if no desired gene is found, continue to randomly mate the initial generation of the population until a desired gene appears.

[0063] Specifically, before step S400, it also includes:

[0064] Perform constraint processing on the population. The constraint processing includes lifespan constraint, lethal gene constraint, and population quantity constraint; among them,

[0065] The lifespan constraint is:

[0066] Since the lifespan of mice is limited, the lifespan issue of mice must be considered during the mouse mating process. Mice that exceed the maximum lifespan must be inactivated in the population; during the mating process of the population, consider the lifespan issue of individuals. Individuals that exceed the preset number of years are regarded as lifespan-inactivated individuals in the population; the expression of lifespan-inactivated individuals is:

[0067]

[0068] In the formula, Mouse life represents the current survival status of the mouse. 1 indicates that the mouse is alive and can mate normally, and 0 indicates that the mouse has exceeded the maximum survival generation and has died. Mouse Ng represents the number of generations that the current mouse has survived, and life max represents the maximum number of generations that the mouse can survive.

[0069] The lethal gene constraint is:

[0070] Since during the mating process, some genotypes of mice will cause the mice to lose their fertility, and some genes will cause the mice to die directly. These genotypes are all recognized as lethal genes, and mice with such genotypes must be inactivated; therefore, the genotypes in the population that cause individuals to lose their fertility and die are regarded as lethal genes, and individuals with lethal genes are regarded as lethal gene-inactivated individuals; the expression of lethal gene-inactivated individuals is:

[0071]

[0072] Among them, Gene death represents the lethal gene. If this lethal gene appears, all individuals carrying this genotype are regarded as inactivated individuals.

[0073] The specific mouse quantity constraint is:

[0074] Preset the number of individuals in the population. Those exceeding the preset number of individuals are regarded as quantity-inactivated individuals, and those with more mating times of parameters are preferentially regarded as inactivated individuals in turn.

[0075] Specifically, in addition to the lifespan constraint and the lethal gene constraint, it should also include the constraint on the maximum number of mice. Due to the limitations of experimental conditions, the number of mice participating in mating cannot be infinite. When the total number of mice is greater than the extreme value, the mice exceeding the extreme value should be inactivated, and the mice that have participated in more mating times should be inactivated preferentially.

[0076] S500: Repeatedly obtain the genotypes of the second generation of the population generated by randomly mating male and female groups until the number of the population reaches the preset scale.

[0077] Specifically, in the initial stage of the algorithm framework, after obtaining the expected genotype, the genotypes of the initial generation of mice, and other relevant information, the optimization process can be started; when setting the iterative process of the algorithm, as long as the expected genotype does not appear, it is necessary to continue to arrange mouse mating; when the expected genotype appears, an individual is considered to be formally obtained. At this time, the data and parameters should be initialized, and then the next individual can be obtained until the specified or preset population scale is reached; after reaching the specified population scale, the SLSPSO (Social Learning Particle Swarm Optimization) can be started to iterate the optimization process, so as to finally obtain the optimal mating strategy.

[0078] S600: When the number of the population reaches the preset scale, select the mating strategy of the male and female individuals with the fastest and most efficient reproduction until the number of selections reaches the preset number of selections.

[0079] The present invention uses the Social Learning Particle Swarm Optimization (SLPSO) to select the mating strategy of the male and female individuals with the fastest and most efficient reproduction. SLPSO is a heuristic intelligent optimization method, which iteratively optimizes by making the individuals in the population continuously learn from the individuals better than themselves (with higher fitness values), and finally obtains the optimal result. The expression of SLPSO is:

[0080]

[0081] Δx i，j (t + 1) = r 1 (t)Δx i，j (t) + r 2 (t)I i，j (t) + φr 3 (t)C i，j (t)

[0082] Among them, x i，j (t) represents the j-th dimension of the i-th individual at the t-th generation, and Δx i，j (t + 1) is the amount learned from the individuals better than the i-th individual, and I i，j (t) represents the difference between the j-th dimension of the i-th individual and the corresponding dimension of the individual better than the i-th individual, and Cj，t represents the difference between the j-th dimension of the i-th individual and the average value of the j-th dimension of all individuals in the current population, r 1 (t), r 2 (t) and r 3 (t) are all random numbers between 0 and 1, φ is a number related to the problem dimension and population size. In order to accelerate the calculation time in this algorithm, the set value of φ is 1; in the context of the present invention, each individual mainly includes the mating scheme from the initial stage to the process of finally obtaining the expected genotype (i.e., recording the genotypes of the parents and offspring for each mating).

[0083] In the embodiment, after step S600, it further includes:

[0084] S601: When the selection times reach the preset selection times, output the mating strategy of the male and female individuals with the highest fitness to the display module for display.

[0085] Specifically, the entire learning framework will perform optimization according to the pattern of the above steps. When the set maximum training times are reached, the mating strategy of the group of mice with the highest fitness can be output, and this result can be visualized to guide the experimenter to arrange the mice for mating according to this strategy; the highest fitness includes the mating strategy with the fastest and most efficient reproduction of mice.

[0086] It should be noted that since mice are most commonly used in the laboratory for experiments; therefore, the embodiments of the present application are described by taking mice as an example, but it does not mean that the method of the present invention is only applicable to mice.

[0087] See Figure 2 , according to an embodiment of the present invention, there is provided a breeding guidance device based on an intelligent optimization algorithm, which is characterized in that it includes:

[0088] A data acquisition module 100, configured to acquire the initial parameters of the initial generation of the population, and the initial parameters include genotype, expected genotype, lifespan information, and lethal gene information;

[0089] A first acquisition module 200, configured to divide the population into male and female groups, and acquire the genotypes of the second generation of the population generated by randomly mating the male and female groups,

[0090] A query module 300, configured to query whether there is an expected gene in the genotype of the second generation,

[0091] A cost calculation module 400, configured to, if there is an expected gene, calculate the time and economic cost of obtaining the expected genotype during the entire mating process, and initialize the initial parameters; if no expected gene is found, continue to randomly mate the initial generation of the population until an expected gene appears;

[0092] A second acquisition module 500, configured to repeatedly acquire the genotypes of the second generation of the population generated by randomly mating two groups of male and female until the number of the population reaches a preset scale;

[0093] A strategy selection module 600, configured to, when the number of the population reaches the preset scale, select the mating strategy of the group of male and female individuals with the highest fitness until the number of selections reaches the preset number of selections.

[0094] The present application discloses a method for guiding an optimal strategy for breeding expected genes of a population based on an intelligent optimization algorithm. With the time and economic costs in the process of obtaining expected genes as the goal, considering constraints such as the lifespan of the population, lethal genes, and quantity, an intelligent optimization algorithm for a population mating sampling social learning particle swarm is used to optimize the mating process, so as to guide experimenters which genotypes of the population should be put together in each generation of mating process, thereby achieving the purpose of guiding the population mating.

[0095] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A breeding guidance method based on intelligent optimization algorithms, characterized in that, it includes the following steps: Obtain the initial parameters of the initial generation of the population, where the initial parameters include genotype, expected genotype, lifespan information, and lethal gene information; Divide the population into male and female groups, and obtain the genotypes of the second generation of the population generated by randomly mating the male and female groups; Query whether there is the expected gene in the genotypes of the second generation; If there is the expected gene, calculate the time and economic cost of obtaining the expected genotype during the entire mating process, and initialize the initial parameters; If no expected gene is found, continue to randomly mate the initial generation of the population until the expected gene appears; Repeat obtaining the genotypes of the second generation of the population generated by randomly mating the male and female groups until the number of the population reaches a preset scale; When the number of the population reaches the preset scale, select the mating strategy of the male and female individuals with the fastest and most efficient reproduction until the number of selections reaches the preset number of selections; The specific calculation of the time and economic cost of obtaining the expected genotype during the entire mating process when there is the expected gene is as follows: Calculate the time and economic cost of obtaining the expected genotype during the entire mating process through the total cost calculation formula; The total cost calculation formula is: Among them, C represents the total cost required to reach the desired gene, which includes time cost and economic cost, N g represents the current generation number, n represents the number of generations required to reach the final desired gene, T(Ng) represents the time required to complete each generation of mating, β*C mouse *N mouse (Ng) represents the economic cost required to complete each generation of mating, C mouse represents the economic cost required to complete one generation of mating, including food and labor, N mouse (Ng) represents the number of individuals that can participate in mating in this generation. α and β are weight coefficients respectively, which can be preset and adjusted according to actual requirements. That is, if more attention is paid to time cost rather than economic cost, α can be made greater than β; Use the social learning particle swarm algorithm to select the mating strategy of the male and female individuals with the fastest and most efficient reproduction, and the expression of the social learning particle swarm algorithm is: Δx i,j (t + 1) = r 1 (t)Δx i,j (t) + r 2 (t)I i,j (t) + φr 3 (t)C i,j (t) Among them, x i,j (t) represents the j-th dimension of the i-th individual at the t-th generation, and Δx i,j (t + 1) is the amount learned from the individuals superior to the i-th individual, and I i,j (t) represents the difference between the j-th dimension of the i-th individual and the corresponding dimension of the individual superior to the i-th individual, and C j,t represents the difference between the j-th dimension of the i-th individual and the average value of the j-th dimension of all individuals in the current population, and r 1 (t), r 2 (t) and r 3 (t) are all random numbers between 0 and 1, and φ is a number related to the problem dimension and population size, and the set value of φ is 1.

2. The breeding guidance method based on intelligent optimization algorithms according to claim 1, characterized in that, before calculating the time and economic cost of obtaining the expected genotype during the entire mating process when there is the expected gene, it further includes: Perform constraint processing on the population, and the constraint processing includes lifespan constraint, lethal gene constraint, and population quantity constraint.

3. The breeding guidance method based on intelligent optimization algorithms according to claim 2, characterized in that, The lifespan constraint is: During the mating process of the population, consider the lifespan problem of individuals. Individuals exceeding the preset number of years are regarded as lifespan inactivated individuals in the population; the expression of the lifespan inactivated individuals is: where Mouse life represents the current survival status of the mouse. 1 indicates an individual in the population that can mate normally, and 0 indicates that the individual in the population has exceeded the preset survival generations and is set to be inactivated. Mouse Ng represents the number of generations that the current individual has survived, and life max represents the maximum number of generations that an individual can survive.

4. The breeding guidance method based on intelligent optimization algorithms according to claim 2, characterized in that, The lethal gene constraint is: The genotypes in the population that cause individuals to lose fertility and die are regarded as lethal bases, and the individuals with the lethal gene are regarded as lethal gene inactivated individuals; the expression of the lethal gene inactivated individuals is: Among them, Gene death represents a lethal gene. If this lethal gene appears, individuals carrying this genotype are regarded as inactivated individuals.

5. The breeding guidance method based on intelligent optimization algorithms according to claim 2, characterized in that, The specific population quantity constraint is: Preset the number of individuals in the population, and regard individuals exceeding the preset number as quantity inactivated individuals.

6. The breeding guidance method based on intelligent optimization algorithms according to claim 5, characterized in that, Regarding the preset number of individuals in the population and regarding individuals exceeding the preset number as quantity inactivated individuals specifically: Give priority to regarding individuals with more mating times of parameters as inactivated individuals in turn.

7. The breeding guidance method based on intelligent optimization algorithms according to claim 1, characterized in that, When the number of the population reaches the preset scale, a mating strategy for selecting the male and female individuals with the highest fitness is carried out until after the number of selections reaches the preset number of selections, further including: When the number of selections reaches the preset number of selections, the mating strategy of the male and female individuals with the highest fitness is output to the display module for display.

8. A breeding guidance method based on an intelligent optimization algorithm according to any one of claims 1 to 7, characterized in that, it further includes a breeding guidance device based on an intelligent optimization algorithm, and the device includes: a data acquisition module, configured to acquire initial parameters of the initial generation of the population, where the initial parameters include genotype, expected genotype, lifespan information, and lethal gene information; a first acquisition module, configured to divide the population into male and female groups, and acquire the genotypes of the second generation of the population generated by randomly mating the male and female groups; a query module, configured to query whether the expected gene exists in the genotypes of the second generation; a cost calculation module, configured to, if the expected gene exists, calculate the time and economic costs for obtaining the expected genotype during the entire mating process, and initialize the initial parameters; if the expected gene is not found, continue to randomly mate the initial generation of the population until the expected gene appears; a second acquisition module, configured to repeatedly acquire the genotypes of the second generation of the population generated by randomly mating the male and female groups until the number of the population reaches the preset scale; a strategy selection module, configured to, when the number of the population reaches the preset scale, carry out a mating strategy for selecting the male and female individuals with the highest fitness until the number of selections reaches the preset number of selections.

Images