Livestock breeding combination recommendation system, device, and method using an artificial intelligence model

Abstract

According to an embodiment of the present invention, a mating combination recommendation device is disclosed that can determine at least one individual to be mated with the first livestock based on individual information of the first livestock among a livestock group and individual information of other livestock (hereinafter referred to as 'second livestock') among the livestock group excluding the first livestock.

Description

Technology Field

[0001] The present invention relates to a livestock breeding combination recommendation system, apparatus, and method utilizing an artificial intelligence model. Background Technology

[0002] Traditionally, selection focused on high-performing individuals led to the selection of offspring from specific mothers, resulting in the problem of increased inbreeding; this approach achieves only short-term goals and presents many issues regarding long-term direction.

[0003] Such crossbreeding of livestock has the problem that if one attempts to improve many aspects, genetic diversity decreases, and if one attempts to secure genetic diversity, improvement becomes slow.

[0004] Therefore, there is a need for technology that can satisfy genetic diversity and genetic improvement and recommend breeding combinations according to various conditions. Prior art literature

[0005] Republic of Korea Published Patent Application No. 10-2004-0027593, (April 1, 2004) Republic of Korea Published Patent Application No. 10-2022-0028923, (March 8, 2022) Republic of Korea Published Patent Application No. 10-2003-0076939, (September 29, 2003) Republic of Korea Published Patent Application No. 10-2010-0005910, (January 18, 2010) The problem to be solved

[0006] One objective of the present invention is to provide a livestock breeding combination recommendation system, apparatus, and method utilizing an artificial intelligence model.

[0007] Another objective of the present invention is to provide a system that recommends breeding combinations by considering the degree of inbreeding, breeding value, and inherent characteristics among livestock.

[0008] Another objective of the present invention is to provide a system for establishing optimal contribution selection and crossover plans using Optisel. means of solving the problem

[0009] One aspect of the present invention for achieving the above objective comprises: a memory storing at least one instruction; and a communication unit receiving individual information of each livestock included in a livestock group; and includes a processor that executes at least one instruction to determine at least one individual to be mated with the first livestock based on individual information of the first livestock among the livestock population and individual information of other livestock (hereinafter referred to as 'second livestock') among the livestock population excluding the first livestock, wherein the individual information includes pedigree information, genomic information, and breeding value, and the processor calculates the degree of inbreeding between the first livestock and the second livestock based on the pedigree information, calculates an expected breeding value for a hypothetical third livestock resulting from mating between the first livestock and the second livestock based on the pedigree information and the breeding value, calculates a genetic improvement score and a genetic diversity score for the third livestock, respectively, based on the genomic information and the calculated degree of inbreeding - the genetic improvement score and the genetic diversity score are inversely proportional - calculates the pedigree preservation degree for the third livestock based on information regarding the pure pedigree of the livestock population, the pedigree information, and the calculated degree of inbreeding, and the pedigree preservation degree, the expected The at least one individual is determined based on the breeding value, the genetic improvement score, and the genetic diversity score.

[0010] Additionally, the processor determines the at least one individual by further considering the importance of genetic diversity of the livestock population, the importance of genetic improvement of the livestock population, and the importance of pure bloodline, calculates the importance of genetic diversity and the importance of genetic improvement based on the trend of the number of individuals of the livestock population and the target number of individuals during a preset period, calculates the importance of pure bloodline according to the breed of the livestock population, determines a maximum inbreeding distance based on the importance of pure bloodline, determines a minimum inbreeding distance based on the importance of genetic diversity, and determines the at least one individual within the range of the minimum inbreeding distance to the maximum inbreeding distance.

[0011] One aspect of the present invention for achieving the above objective is that the processor calculates the importance of the genetic diversity based on the following mathematical formula 1 when the population trend of the livestock population is a decreasing trend and the slope (D) of the population trend is less than or equal to a preset slope (C), and when the slope (D) is less than or equal to a preset slope (B), sets an endangered stage according to the slope (D), and corrects the minimum inbreeding distance and the maximum inbreeding distance based on the set endangered stage.

[0012] [Mathematical Formula 1]

[0013] , (K: Target population of the above breed ÷ Current population of the above breed)

[0014] One aspect of the present invention for achieving the above objective is that the processor determines the livestock population as a population stable population when the population trend of the livestock population is increasing, assigns a weight to the genetic improvement score in proportion to the population stable stage, corrects the genetic diversity score so that it decreases inversely proportionally as the weight is assigned to the genetic improvement score, calculates the population stable stage based on the target population, the current population, and the slope of the population trend, and corrects the minimum inbreeding distance and the maximum inbreeding distance based on the population stable stage.

[0015] One aspect of the present invention for achieving the above objective includes a prediction model in which a method for selecting individuals for mating of the livestock population is learned, and the processor inputs input data to the prediction model to obtain a target trait for the third livestock resulting from mating between the first livestock and the second livestock based on individual information of each livestock, requests a generative model for the economic value expected according to future expected preference of the livestock types of the livestock population, the difficulty of rearing according to future climate change, the importance of genetic diversity required according to future climate change, and the trend of the number of individuals, requests the output of an optimal target trait based on the output value of the request, and additionally inputs the target trait output from the generative model into the prediction model to request the output of at least one individual according to the feasibility of achieving the target trait. Effects of the invention

[0016] According to one embodiment of the present invention, a breeding combination recommendation system that considers genetic improvement and diversity can be provided.

[0017] According to one embodiment of the present invention, a system that recommends breeding combinations by considering the degree of inbreeding, breeding value, and inherent characteristics among livestock can be provided.

[0018] According to one embodiment of the present invention, a system for establishing optimal contribution selection and crossbreeding plans using Optisel can be provided. Brief explanation of the drawing

[0019] FIG. 1 is a schematic diagram of a mating combination recommendation system according to an embodiment of the present disclosure. Figure 2 is a diagram illustrating a livestock group. Figure 3 is a diagram illustrating how a mating combination recommendation system determines a mating combination in the livestock population of Figure 2. FIG. 4 is a block diagram of a breeding combination recommendation server according to an embodiment of the present disclosure. Figure 5 is a diagram illustrating a server architecture. Figure 6 is a diagram illustrating the process configuration of an OCS system. FIG. 7 is a flowchart of a method for recommending a cross combination according to an embodiment of the present disclosure. Figure 8 is a diagram illustrating the trend of population decline. Figure 9 is a diagram illustrating the crisis stage based on the trend of population decline. Figure 10 is a diagram illustrating the trend of increasing population size. Figure 11 is a diagram illustrating the acquisition of a target trait using a prediction model. Figure 12 is a diagram illustrating the acquisition of optimal target traits using a generative model. Specific details for implementing the invention

[0020] The present invention is susceptible to various modifications and may have various embodiments; specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the invention to specific embodiments, and it should be understood that the invention includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention. Similar reference numerals have been used for similar components in the description of each drawing.

[0021] Terms such as first, second, A, B, etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and / or" includes a combination of a plurality of related described items or any of a plurality of related described items.

[0022] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0023] The terms used in this application are used merely to describe specific embodiments and are not intended to limit the invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "having" are intended to specify the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0024] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0025] Functions related to artificial intelligence according to the present disclosure are operated through a processor and memory. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in memory. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0026] The predefined rules of operation or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a predefined rules of operation or artificial intelligence models configured to perform desired characteristics (or objectives) are created by a basic artificial intelligence model being trained using multiple learning data by a learning algorithm. Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0027] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, multiple weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. Artificial neural networks may include deep neural networks (DNNs), such as Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), or Deep Q-Networks, but are not limited to the examples mentioned above.

[0028] The memory may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk. Additionally, the breeding combination recommendation device may operate a web storage or cloud server that performs the memory storage function over the internet.

[0029] Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the attached drawings.

[0030] FIG. 1 is a schematic diagram of a mating combination recommendation system (1) according to an embodiment of the present disclosure.

[0031] FIG. 2 is a diagram illustrating a livestock group, and FIG. 3 is a diagram illustrating a mating combination recommendation system (1) determining a mating combination in the livestock group of FIG. 2.

[0032] Referring to FIG. 1, the server (100) provides a service that recommends breeding combinations.

[0033] The breeding combination recommendation server (100) can receive individual information of each livestock included in the livestock group to receive breeding combination recommendations from an external server (100).

[0034] And, the server (100) analyzes the received object information and recommends a breeding combination.

[0035] Traditionally, selection focused on high-performing individuals led to the selection of offspring from specific mothers, resulting in the problem of increased inbreeding; this approach achieves only short-term goals and presents many issues regarding long-term direction.

[0036] Such crossbreeding of livestock has the problem that if one attempts to improve many aspects, genetic diversity decreases, and if one attempts to secure genetic diversity, improvement becomes slow.

[0037] The breeding recommendation server (100) according to the embodiment of the present disclosure can recommend breeding combinations using various algorithms, and through such breeding combination recommendations, it can present an optimal breeding combination that preserves the bloodline and simultaneously satisfies genetic improvement and genetic diversity.

[0038] That is, when the server (100) receives information about a livestock group as shown in Fig. 2, it analyzes it based on previously stored commands and algorithms and suggests / recommends a breeding combination as shown in Fig. 3.

[0039] At this time, the server (100) may recommend a breeding combination with the highest priority for breeders, may recommend a breeding combination with the highest priority for pure bloodlines, or may recommend a breeding combination with the highest priority for genetic improvement or genetic diversity. That is, the server (100) may recommend a breeding combination by considering the required information or the characteristics of each livestock group.

[0040] FIG. 4 is a block diagram of a cross combination recommendation server (100) according to an embodiment of the present disclosure.

[0041] Referring to FIG. 4, a crossbreeding combination recommendation server (100) according to an embodiment of the present disclosure includes a processor (110), a communication unit (120), and a memory (1300).

[0042] Here, at least one processor (110) may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor (110) on which methods according to embodiments of the present invention are performed. Each of the memory (1300) and the storage device may be composed of at least one of a volatile storage medium and a non-volatile storage medium.

[0043] The processor (110) typically controls the overall operation of the breeding combination recommendation device. For example, the processor (110) can control the breeding combination recommendation device overall by executing programs stored in memory (1300). The breeding combination recommendation device may include at least one processor (110).

[0044] The processor (110) may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input / output operations. Instructions may be provided to the processor (110) from memory (1300) or received through a communication unit (120) and provided to the processor (110). For example, the processor (110) may be configured to execute instructions according to program code stored in a recording device such as memory (1300).

[0045] A memory (1300) according to one embodiment can store one or more instructions, and at least one processor (110) of the server (100) described above can perform an operation according to one embodiment by executing the one or more instructions stored in the memory (1300).

[0046] Memory (1300) may be one of read-only memory (1300 (read only memory, ROM) and random access memory (1300 (random access memory, RAM)), and storage device may be flash memory (1300 (flash-memory), hard disk drive (HDD), solid state drive (SSD), or various memory (1300) cards (e.g., micro SD card).

[0047] Additionally, the server (100) may include a transceiver that performs communication via a wireless network. Additionally, the server (100) may further include an input interface device, an output interface device, a storage device, etc. Each component included in the server (100) may be connected by a bus to communicate with one another.

[0048] Examples of the server (100) may be a communicable desktop computer, laptop computer, notebook, smartphone, tablet PC, mobile phone, smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital video recorder, digital video player, PDA (Personal Digital Assistant), etc.

[0049] The communication unit (120) may include one or more components that enable the electronic device to communicate with the server (100) or an external device. For example, the communication unit (120) may include a short-range communication unit (120), a mobile communication unit (120), and a broadcast receiving unit.

[0050] FIG. 5 is a diagram illustrating the architecture of a server (100).

[0051] The server (100) communicates with the client device (510) and the Admin (520) and can operate in the front-end and back-end as shown in FIG. 5.

[0052] The client device may be a communicable desktop computer, laptop computer, notebook, smartphone, tablet PC, mobile phone, smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital video recorder, digital video player, PDA (Personal Digital Assistant), etc.

[0053] Figure 6 is a diagram illustrating the process configuration of the OCS system (1).

[0054] Referring to FIG. 6, the OCS system (1) may be composed of the steps of: constructing a relationship matrix (610), performing a planned mating process (620), preparing a pedigree of a livestock group (630), summarizing the pedigree and generating statistics (640), calculating a kinship matrix (650), adjusting the valid range of generation intervals (660), selecting mating candidates (670), and outputting / confirming the final result (680).

[0055] FIG. 7 is a flowchart of a method for recommending a cross combination according to an embodiment of the present disclosure.

[0056] Referring to FIG. 7, the process of the mating combination recommendation device, server (100), and method will be described in detail.

[0057] The processor (110) receives individual livestock information from the outside through the communication unit (120). (S710)

[0058] At this time, the processor (110) can receive individual information of a livestock group from an external server (100) or a client device.

[0059] For example, when a server (100) provides a service through a service application, it may receive individual information of a group of livestock raised by a user through a web or app and use it to provide a service.

[0060] And, the processor (110) can determine at least one individual to be mated with the first livestock based on the individual information of the first livestock among the livestock group and the individual information of other livestock (hereinafter, 'second livestock') excluding the first livestock among the livestock group.

[0061] At this time, individual information includes pedigree information, genomic information, and breeding value.

[0062] The processor (110) calculates the degree of inbreeding between the first livestock and the second livestock. (S720)

[0063] The processor (110) can calculate the degree of inbreeding between the first livestock and the second livestock based on pedigree information.

[0064] In one embodiment, the processor (110) can find a common ancestor based on the pedigree information of livestock and calculate the degree of inbreeding.

[0065] In one embodiment, the processor (110) can calculate the degree of inbreeding by directly comparing genetic similarity between individuals using a genetic marker.

[0066] In one embodiment, the processor (110) can calculate the degree of inbreeding based on the distance of inbreeding and the generation interval based on the pedigree information of livestock.

[0067] At this time, the higher the degree of inbreeding produced by the processor (110), the closer the relationship is in terms of pedigree, and the higher the possibility of inbreeding.

[0068] The processor (110) calculates the expected breeding value of a virtual third livestock resulting from the crossbreeding of the first livestock and the second livestock. (S730)

[0069] The processor (110) can calculate the expected breeding value for a virtual third livestock resulting from the crossbreeding of the first livestock and the second livestock based on pedigree information and breeding value.

[0070] In the embodiments of the present disclosure, the breeding value may refer to the value of livestock.

[0071] In the embodiments of the present disclosure, the Expected Breeding Value (EBV) refers to the value of livestock as a breeding stock, and may represent the degree of ability passed down to future generations among the genetic abilities of the livestock.

[0072] In one example, breeder value is a measure indicating how effectively an individual can transmit superior genetic traits to the next generation. Simply put, it can be described as a numerical value representing an individual's genetic potential for a specific trait.

[0073] In other words, the higher the estimated breeding value, the more it can be said to have a direction for variety improvement.

[0074] In one embodiment, the processor (110) may determine that the breeding value of the third livestock is as high as that of the first and second livestock if the breeding values ​​of the first and second livestock are high and are similar or close in pedigree. For example, the processor (110) may determine the upper percentile of the breeding value of the third livestock by considering the extent to which both the first and second livestock have breeding values ​​higher than the average.

[0075] The processor (110) calculates a genetic improvement score and a genetic diversity score. (S740)

[0076] The processor (110) can calculate a genetic improvement score and a genetic diversity score for the third livestock, respectively, based on genomic information and inbreeding.

[0077] In this case, the genetic improvement score and the genetic diversity score may have an inverse relationship.

[0078] The processor (110) can calculate a lower genetic diversity score as the first livestock and the second livestock are genetically similar. The processor (110) can calculate a higher genetic diversity score as the first livestock and the second livestock are genetically different.

[0079] The processor (110) can calculate a high genetic improvement score if at least one of the first livestock and the second livestock is genetically superior / inferior.

[0080] The processor (110) can identify the traits possessed by the ancestors of an individual based on lineage information and predict the genetic potential of the individual based on this, and can determine that an individual with many ancestors possessing superior traits has high genetic potential for those traits.

[0081] In one embodiment, the processor (110) can identify genetic complementarity between individuals based on pedigree information, and individuals with high genetic complementarity can produce a high breeding value even if other conditions are lacking.

[0082] For example, the memory (1300) may store combination scores between traits, and the processor (110) may use this to compare individual information between livestock to calculate combination scores and further use this to calculate breeding values.

[0083] The processor (110) calculates the pedigree preservation degree for the third livestock. (S750)

[0084] In one embodiment, the processor (110) can calculate the degree of pedigree preservation for a third livestock based on information about the pure bloodline of a livestock group, pedigree information of individual information, and the calculated degree of inbreeding.

[0085] Pedigree preservation refers to the preservation level required to maintain the pedigree and genetic characteristics of a specific type or breed and to pass them on to future generations. In other words, the higher the pedigree preservation level, the higher the ability to preserve the corresponding pedigree.

[0086] The processor (110) determines at least one individual to be mated with the first livestock. (S760)

[0087] The processor (110) determines at least one individual to be mated with the first livestock based on pedigree preservation, expected breeding value, genetic improvement score and genetic diversity score.

[0088] In one embodiment, the processor (110) can receive the importance of genetic diversity of the livestock population, the importance of genetic improvement of the livestock population, and the importance of pure bloodline through the communication unit (120).

[0089] And, the processor (110) can determine at least one individual to be mated with the first livestock by further considering at least one of the importance of genetic diversity of the livestock population, the importance of genetic improvement of the livestock population, and the importance of pure bloodline.

[0090] The processor (110) can calculate the importance of genetic diversity and the importance of genetic improvement based on the population size trends and target population size of the livestock population over a set period.

[0091] The processor (110) can calculate the importance of pure bloodlines according to the breed of the livestock group.

[0092] The processor (110) can determine a maximum inbreeding distance based on the importance of pure bloodline and a minimum inbreeding distance based on the importance of genetic diversity.

[0093] And, the processor (110) can determine at least one individual to be mated with the first livestock within a minimum to maximum distance from the first livestock.

[0094] Figure 8 is a diagram illustrating the trend of population decline.

[0095] Referring to FIG. 8, a graph (810) showing the trend of the number of livestock over time is illustrated. When the trend of the number of livestock population is decreasing, the processor (110) can calculate the importance of genetic diversity based on Equation 1 when the slope (D, 820) of the number trend is less than or equal to a preset slope (C, 830).

[0096]

[0097] (K: Target population of the above breed ÷ Current population of the above breed)

[0098] Figure 9 is a diagram illustrating the crisis stage based on the trend of population decline.

[0099] Referring to FIG. 9, a graph (910) showing the trend of the number of livestock over time is illustrated. If the slope (D, 920) is less than or equal to a preset slope (B, 930), the processor (110) can set the extinction risk level of the livestock according to the slope (D).

[0100] For example, the more severe the extinction risk, the higher the level can be set from 1 to 5.

[0101] The processor (110) can adjust the minimum and maximum values ​​of the distance between relatives based on the set endangered stage.

[0102] If the livestock is at risk of extinction, increasing the population and genetic diversity is a priority, so the processor (110) can control the range of inbreeding allowed to be expanded.

[0103] Figure 10 is a diagram illustrating the trend of increasing population size.

[0104] Referring to FIG. 10, a graph (1010) showing the trend of the number of livestock over time is illustrated. When the number of livestock in a livestock population is increasing, the processor (110) determines the livestock population as a population stable population and assigns a weight to the genetic improvement score in proportion to the population stable stage, and corrects the genetic diversity score so that it decreases inversely proportional to the weight assigned to the genetic improvement score.

[0105] And, the processor (110) can calculate a population stability stage based on the target population, the current population, and the slope of the population trend, and correct at least one of the minimum inbreeding distance and the maximum inbreeding distance based on the calculated population stability stage.

[0106] The stability level of the population can be set to a higher level as the level of safety increases.

[0107] The processor (110) can expand the range of possible inbreeding to ensure genetic diversity as the population size stability level of the livestock population increases.

[0108] FIG. 11 is a diagram illustrating the acquisition of a target trait using a prediction model (140).

[0109] The breeding combination recommendation server (100) may further include a prediction model (140) that has learned a method for selecting individuals for breeding a livestock group.

[0110] The processor (110) can input input data into a prediction model to obtain a target trait for a third livestock resulting from crossbreeding between a first livestock and a second livestock based on individual information of each livestock.

[0111] Figure 12 is a diagram illustrating the acquisition of optimal target traits using a generative model.

[0112] And, the processor (110) requests the generative model (150) the economic value expected according to future expected preference for the types of livestock in the livestock population, the difficulty of raising due to future climate change, the importance of genetic diversity required due to future climate change, and the population trend, and requests the model to output the optimal target trait based on the output values ​​requested.

[0113] The processor (110) may request that the target trait output from the generative model (150) be additionally input into the prediction model to output at least one individual according to the feasibility of achieving the target trait.

[0114] In the embodiments of the present disclosure, the target trait in livestock breeding is one of the core concepts of breed improvement and refers to a trait intended to be improved through livestock breed improvement. That is, the server (100) uses an artificial intelligence model to identify a target trait that is judged to be advantageous to the livestock in the future and can recommend a breeding combination to acquire such a target trait.

[0115] The methods according to the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the computer-readable medium may be those specifically designed and configured for the present invention, or they may be those known and available to those skilled in the art of computer software.

[0116] Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions may include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The aforementioned hardware devices may be configured to operate as at least one software module to perform the operation of the present invention, and vice versa.

[0117] In addition, the above-described method or device may be implemented by combining all or part of its configuration or function, or by implementing it separately.

[0118] Although the present invention has been described above with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as described in the following claims. Explanation of the symbols

[0119] 1: System 100: Server 110: Processor 120: Communications Department 130: Memory 140: Prediction Model 150: Generative Model 200: External server

Claims

Claim 1 A memory storing at least one instruction; a communication unit receiving individual information of each livestock included in a livestock group; and a processor that executes the at least one instruction to determine at least one individual to be mated with the first livestock based on individual information of the first livestock among the livestock group and individual information of other livestock (hereinafter referred to as 'second livestock') among the livestock group excluding the first livestock, wherein the individual information includes pedigree information, genomic information, and breeding value, and the processor calculates the degree of inbreeding between the first livestock and the second livestock based on the pedigree information, calculates an expected breeding value for a virtual third livestock resulting from mating between the first livestock and the second livestock based on the pedigree information and the breeding value, and respectively calculates a genetic improvement score and a genetic diversity score for the third livestock based on the genomic information and the calculated degree of inbreeding - the genetic improvement score and the genetic diversity score are inversely proportional - based on information regarding the pure pedigree of the livestock group, the pedigree information, and the calculated degree of inbreeding Calculate pedigree preservation for the third livestock, determine at least one individual based on the pedigree preservation, the estimated breeding value, the genetic improvement score, and the genetic diversity score, determine at least one individual by further considering the importance of genetic diversity of the livestock population, the importance of genetic improvement of the livestock population, and the importance of pure pedigree, calculate the importance of genetic diversity and the importance of genetic improvement based on the population trend and target population of the livestock population during a preset period, calculate the importance of pure pedigree according to the breed of the livestock population, determine a maximum inbreeding distance based on the importance of pure pedigree, determine a minimum inbreeding distance based on the importance of genetic diversity, and determine at least one individual within the range of the minimum inbreeding distance to the maximum inbreeding distance.If the population trend of the above livestock population is increasing, the above livestock population is determined to be a population stable population; a population stability stage is calculated based on the target population, current population, and slope of the population trend of the above livestock population, wherein the population stability stage is calculated as a higher stage as the level of safety increases; a weight is assigned to the genetic improvement score in proportion to the population stability stage, and the genetic diversity score is corrected to decrease inversely proportionally as the weight is assigned to the genetic improvement score; the minimum and maximum values ​​of the inbreeding distance are corrected based on the population stability stage; and the system includes a prediction model in which a method for selecting individuals for mating of the above livestock population is learned; the processor inputs input data into the prediction model to obtain the target trait for the above third livestock resulting from the mating between the above first livestock and the above second livestock based on the individual information of each livestock; requests the generative model for the economic value expected according to future expected preference of the livestock types of the above livestock population, the difficulty of rearing according to future climate change, the importance of genetic diversity required according to future climate change, and the population trend. A cross combination recommendation server characterized by requesting the output of an optimal target trait based on a requested output value, and additionally inputting the target trait output from the generative model into the prediction model to request the output of at least one individual according to the feasibility of achieving the target trait.

Images