KR102470326B1 - Method, device and system for analyzing and monitoring growth status of livestock to improve breeding effect - Google Patents

Abstract

The present invention relates to a method, apparatus and system for analyzing and monitoring the growth state of livestock to improve breeding effects. The method for analyzing and monitoring the growth state of livestock, according to the present invention, comprises the steps of: obtaining a first-first image generated through ultrasound examination of a first part of a first livestock at a first time point; generating a first input signal; obtaining a first output signal; setting a grade of the first part to a first grade at the first time point; obtaining a first-second image generated through ultrasound examination of the first part of the first livestock at a second time point; generating a second input signal; obtaining a second output signal; setting a grade of the first part to a second grade at the second time point; and analyzing a grade change trend of the first part during a first reference period. Therefore, the accuracy and efficiency can be increased.

Description

Livestock growth status analysis and monitoring method, apparatus and system for improving breeding effect {METHOD, DEVICE AND SYSTEM FOR ANALYZING AND MONITORING GROWTH STATUS OF LIVESTOCK TO IMPROVE BREEDING EFFECT}

The following examples relate to techniques for analyzing and monitoring the growth status of livestock in order to improve the breeding effect.

Recently, as the consumption of livestock products increases, the demand for methods for efficiently breeding livestock is increasing.

In particular, in order to efficiently breed livestock, analysis and monitoring of the growth state of livestock is required. Conventionally, since breeders directly analyze and monitor the growth state of livestock while breeding, there is a problem of poor accuracy and efficiency.

Therefore, there is an increasing demand for automatically analyzing and monitoring the growth status of livestock in order to improve the breeding effect, and research on related technologies is required.

Korean Patent Registration No. 10-2168641 Korean Patent Registration No. 10-2011401 Korean Patent Registration No. 10-1334607 Korean Patent Publication No. 10-2022-0064712

According to one embodiment, the growth state of livestock is analyzed and monitored through ultrasonic inspection, the growth state of livestock is analyzed and monitored through size tracking, and the breeding method of livestock is determined through the result of analyzing the growth state of livestock. Its purpose is to provide a method, apparatus and system for analyzing and monitoring the growth status of livestock to improve the breeding effect.

The object of the present invention is not limited to the object mentioned above, and other objects not mentioned will be clearly understood from the description below.

According to one embodiment, in the method for analyzing and monitoring the growth state of livestock to improve breeding effect, which is performed by an apparatus, an ultrasonic wave is applied to a first part of a first livestock using an ultrasound scanner at a first time point. acquiring a 1-1 image generated through an ultrasound examination of the first part of the first livestock at the first point in time when the inspection is in progress; generating a first input signal by encoding the 1-1 image; inputting the first input signal to an artificial neural network and obtaining a first output signal based on a result of the input of the artificial neural network; setting a grade of the first part to a first grade at the first time point based on the first output signal; When an ultrasound examination of the first part of the first livestock is performed using the ultrasound scanner at a second time point after a preset first reference period has passed from the first time point, the first livestock at the second time point acquiring first-second images generated through ultrasound examination of the first part of the body; generating a second input signal by encoding the first-second image; inputting the second input signal to an artificial neural network and obtaining a second output signal based on a result of the input of the artificial neural network; setting a grade of the first part to a second grade at the second time point based on the second output signal; And comparing the first grade and the second grade, analyzing the trend of grade change of the first part during the first reference period, a livestock growth state analysis and monitoring method for improving breeding effect. is provided.

The method for analyzing and monitoring the growth state of livestock for improving the breeding effect includes obtaining first image information, which is a 3D image generated by photographing the first livestock, from a camera that photographs the first livestock. ; extracting an image of an image acquired at the first viewpoint from the first image information as a 2-1 image; Dividing the area occupied by the first part in the 2-1 image into a first area based on the 2-1 image, and calculating the volume of the first area through the size of the first area step; if the volume of the first region is calculated as the first volume, setting the volume of the first part to the first volume at the first time point; extracting an image of an image acquired at the second viewpoint from the first image information as a 2-2 image; Dividing the area occupied by the first part in the 2-2 image into a second area based on the 2-2 image, and calculating the volume of the second area through the size of the second area step; setting the volume of the first part to the second volume at the second time point when the volume of the second region is calculated as the second volume; and comparing the first volume and the second volume to analyze a size change trend of the first part during the first reference period.

The method of analyzing and monitoring the growth state of livestock for improving the breeding effect, as a result of analyzing the size change trend of the first part, by subtracting the first volume from the second volume, Calculating a third volume, which is a value changed as the size of the first part increases; checking a fourth volume set as an average change value of the first part during the first reference period; calculating a fifth volume by subtracting the fourth volume from the third volume; When it is confirmed that the fifth volume is included within the preset reference range, as a result of analyzing the grade change trend of the first part, when the second grade is confirmed as a higher grade than the first grade, the first If it is determined that the current maintenance of the livestock breeding method is necessary, and the first grade and the second grade are confirmed to be the same grade or the second grade is confirmed to be a lower grade than the first grade, the first livestock Determining that additional payment for fattening feed is necessary; When it is confirmed that the fifth volume is outside the reference range and is greater than the maximum value of the reference range, as a result of analyzing the grade change trend of the first part, the second grade is a higher grade than the first grade. confirmed or if the first grade and the second grade are confirmed to be the same grade, it is determined that the current maintenance of the breeding method of the first livestock is necessary, and the second grade is confirmed as a lower grade than the first grade. If it is, determining that additional payment of fattening feed for the first livestock is necessary; And when it is confirmed that the fifth volume is out of the reference range and smaller than the minimum value of the reference range, as a result of analyzing the grade change trend of the first part, the second grade is a higher grade than the first grade. or if the first grade and the second grade are confirmed to be the same grade, it is determined that a change in the breeding method of the first livestock is necessary, and if the second grade is confirmed to be a lower grade than the first grade , Determining whether or not to maintain breeding of the first livestock may be further included.

According to one embodiment, by analyzing and monitoring the growth state of livestock through ultrasonic inspection, and by analyzing and monitoring the growth state of livestock through size tracking, analysis and monitoring of the growth state of livestock is automatically performed, and accuracy and efficiency can be increased.

In addition, according to one embodiment, by determining the breeding method of livestock through the result of analyzing the growth state of livestock, it is possible to provide a method for efficiently breeding livestock by improving the breeding effect.

On the other hand, the effects according to the embodiments are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a diagram schematically showing the configuration of a system according to an embodiment.
Figure 2 is a flow chart for explaining a process of analyzing and monitoring the growth state of livestock through ultrasonic inspection according to an embodiment.
3 is a flowchart illustrating a process of analyzing and monitoring the growth state of livestock through size tracking according to an embodiment.
4 is a flowchart illustrating a process of determining a breeding method of livestock based on a result of analyzing a growth state of livestock according to an embodiment.
5 is a flowchart illustrating a process of determining a breeding method of livestock when it is confirmed that a fifth volume is included within a reference range according to an embodiment.
6 is a flowchart illustrating a process of determining a breeding method of livestock when it is confirmed that a fifth volume is greater than the maximum value of the reference range according to an embodiment.
7 is a flowchart illustrating a process of determining a breeding method of livestock when it is confirmed that a fifth volume is smaller than the minimum value of the reference range according to an embodiment.
8 is a flowchart illustrating a process of calculating a price for a part expected to grow in the future according to an embodiment.
9 is a flowchart illustrating a process of determining whether to breed livestock through a price for each part expected to grow in the future according to an embodiment.
10 is a flowchart illustrating a process of recording and storing an image of a specific region at a specific time point according to an embodiment.
11 is a diagram for explaining an artificial neural network according to an embodiment.
12 is a diagram for explaining a method of learning an artificial neural network according to an embodiment.
13 is an exemplary diagram of a configuration of a device according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes can be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents or substitutes to the embodiments are included within the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be modified and implemented in various forms. Therefore, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

The embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

In an embodiment, an artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, a machine learns and judges on its own. The more the AI system is used, the higher the recognition rate and the more accurately the seller's taste can be understood, so the existing rule-based smart system is gradually being replaced by a deep learning-based AI system.

Artificial intelligence technology consists of machine learning and element technologies using machine learning. Machine learning is an algorithm technology that classifies/learns the characteristics of input data by itself, and element technology is a technology that uses machine learning algorithms such as deep learning to mimic functions such as recognition and judgment of the human brain. It consists of technical fields such as understanding, inference/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology for recognizing and applying/processing human language/characters, including natural language processing, machine translation, dialogue systems, question and answering, voice recognition/synthesis, and the like. Visual understanding is a technology for recognizing and processing objects like human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, space understanding, image improvement, and the like. Inference prediction is a technique of reasoning and predicting logically by judging information, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data creation/classification) and knowledge management (data utilization). Motion control is a technology for controlling the autonomous driving of a vehicle and the movement of a robot, and includes motion control (navigation, collision, driving), manipulation control (action control), and the like.

In general, in order to apply machine learning algorithms to real life, learning is performed in a trial and error method due to the nature of the basic methodology of machine learning. In particular, deep learning requires hundreds of thousands of iterations. It is impossible to execute this in an actual physical external environment, so instead, the actual physical external environment is virtually implemented on a computer and learning is performed through simulation.

1 is a diagram schematically showing the configuration of a system according to an embodiment.

Referring to FIG. 1 , a system according to an embodiment may include an ultrasonic inspection device 100, a camera 200, a weight measuring device 300, and an apparatus 400.

The ultrasound scanner 100 is a device that performs an ultrasound scan on livestock and generates an image through the ultrasound scan.

The ultrasound examination machine 100 may perform an ultrasound examination of a specific part of livestock. For example, the ultrasound examination machine 100 may perform an ultrasound examination on the back of a livestock and generate an image of the back through the ultrasound examination.

The ultrasonic inspection device 100 may be connected to the device 400 through a network and may be operated by a control signal received from the device 400 .

The camera 200 is a device that generates image information by taking pictures of livestock, and may be implemented as a 3D camera, LIDAR, or the like.

The camera 200 may be connected to the device 400 through a network and may be operated by a control signal received from the device 400 .

The weight measuring device 300 is a device for generating weight information by measuring the weight of livestock, and may be implemented as a weight sensor or the like.

For example, a weight measuring device 300 may be installed on the floor of a barn, and the weight measuring device 300 may measure the weight of livestock in the barn and generate weight information through weight measurement.

The weight measuring device 300 may be connected to the device 400 through a network, and may be operated by a control signal received from the device 400 .

The device 400 may be a server owned by a person or organization that provides services using the device 400, may be a cloud server, or may be a peer-to-peer (p2p) set of distributed nodes. may be The device 400 may be configured to perform all or part of the arithmetic function, storage/reference function, input/output function, and control function of a normal computer.

The device 400 may be configured to communicate with the ultrasound inspection device 100 by wire or wirelessly, and through the ultrasound inspection device 100, it is possible to control which part of the livestock to perform an ultrasound examination to generate an image, and Overall operation of the inspection device 100 may be controlled.

The device 400 may be configured to communicate with the camera 200 by wire or wirelessly, and control which area in the barn is photographed through the camera 200 to generate image information, and the device 400 may control the overall You can control the action.

The device 400 may be configured to communicate with the weight measuring device 300 by wire or wirelessly, and may control whether to generate weight information by measuring the weight of livestock through the weight measuring device 300, and the weight measuring device 300 can control the entire operation of

According to an embodiment, the device 400 may obtain an image generated by the ultrasound scanner 100 and determine a grade of a corresponding part based on the obtained image. Here, the grade is a grade to indicate quality, and can be determined through the ratio occupied by muscle and the ratio occupied by fat, and can be classified into ++1, +1, 1 grade, 2 grade, 3 grade, etc. . The higher the grade, the better the quality, and the lower the grade, the worse the quality.

For example, when an ultrasonic test is performed on the back of a livestock through the ultrasonic inspection machine 100, the ratio occupied by muscle and the ratio occupied by fat are respectively confirmed through the ultrasound examination, and the grade for the back is determined. It can be.

That is, it is possible to analyze and monitor the growth status of livestock by tracking the change in grade for a specific part of livestock. A detailed description related to this will be described later with reference to FIG. 2 .

As described above, the grade for a specific part of livestock may be determined through ultrasound examination, and in addition, the grade for a specific part of livestock may be determined through MRI, X-ray, 3D scan, and the like.

According to one embodiment, the apparatus 400 may acquire image information of livestock photographed from the camera 200, and monitor how the size of a specific part of the livestock increases based on the obtained image information. . At this time, the device 400 may determine the breeding direction by analyzing whether the increase in size is a genetic factor or a factor according to a breeding method.

That is, by tracking the change in the size of a specific part of the livestock, the growth state of the livestock can be analyzed and monitored. A detailed description related to this will be described later with reference to FIG. 3 .

According to one embodiment, the apparatus 400 analyzes the breeding method of livestock using the result of analyzing the trend of grade change of a specific part and the result of analyzing the trend of size change, and determines the breeding direction. can do.

That is, as a result of analyzing and monitoring the growth state of livestock, it is possible to analyze and determine how to best breed livestock in the future. A detailed description related to this will be described later with reference to FIGS. 4 to 7 .

Figure 2 is a flow chart for explaining a process of analyzing and monitoring the growth state of livestock through ultrasonic inspection according to an embodiment.

Referring to FIG. 2, first, in step S201, when the ultrasound examination of the first part of the first livestock is performed using the ultrasound scanner 100 at a first time point, the device 400 performs a first step at a first time point. A 1-1 image generated through ultrasound examination of the first part of the livestock may be acquired.

Specifically, the ultrasound scanner 100 may perform an ultrasound examination on the first part of the first livestock at a first time point, and through the ultrasound examination on the first part of the first livestock performed at the first time point, the first - 1 image can be created.

For example, the ultrasound examination machine 100 may perform an ultrasound scan on the cow's back at a specific time point and generate a 1-1 image that is an ultrasound image of the cow's back.

The apparatus 400 may acquire the 1-1 image from the ultrasound scanner 100 when the 1-1 image is generated through the ultrasound examination of the first part of the first domestic animal at the first time point.

In the present invention, the first point of time may be used as a meaning including from the time of ultrasound examination to the time of obtaining an ultrasound image. That is, at a first point in time, the ultrasound scanner 100 may perform an ultrasound scan to generate a 1-1 image, and at the first point in time, the device 400 may acquire the 1-1 image from the ultrasound scanner 100. have.

In step S202, the apparatus 400 may generate a first input signal by encoding the 1-1 image.

Specifically, the device 400 may generate the first input signal by encoding the pixels of the 1-1 image as color information. Color information may include RGB color information, brightness information, and chroma information, but is not limited thereto. The apparatus 400 may convert color information into digitized values, and may encode an image in the form of a data sheet including these values.

In step S203 , the device 400 may input the first input signal to the artificial neural network trained in advance in the device 400 .

According to an embodiment, the artificial neural network is implemented as a convolutional neural network, the convolutional neural network is composed of a feature extraction neural network and a classification neural network, and the feature extraction neural network sequentially stacks an input signal through a convolutional layer and a pooling layer. The convolution layer includes convolution operations, convolution filters, and activation functions. The calculation of the convolution filter is adjusted according to the matrix size of the target input, but a 9X9 matrix is generally used. As the activation function, a ReLU function, a sigmoid function, and a tanh function are generally used, but are not limited thereto. The pooling layer is a layer that reduces the matrix size of the input, and uses a method of extracting a representative value by grouping pixels in a specific area. The calculation of the pooling layer generally uses average values or maximum values, but is not limited thereto. The operation is performed using a square matrix, and a 9X9 matrix is generally used. The convolutional layer and the pooling layer are alternately repeated until the corresponding input is sufficiently small while maintaining the difference.

According to one embodiment, the classification neural network has a hidden layer and an output layer. Classification of Artificial Neural Network for Grade Classification According to Quality The neural network is composed of 5 or less hidden layers and may include a total of 50 or less hidden layer nodes. The activation function of the hidden layer uses, but is not limited to, a ReLU function, a sigmoid function, and a tanh function. There is a total of one output layer node of the classification neural network, and an output value for classification according to quality can be output to the output layer node. A detailed description of the artificial neural network will be described later with reference to FIG. 11 .

In step S204, the apparatus 400 may obtain a first output signal that is an output value of the artificial neural network, based on a result of the input of the artificial neural network. Here, the first output signal may include an output value indicating to which grade the grade of the first part is classified at the first time point.

In step S205, the device 400 may set the grade of the first part as the first grade at the first time point based on the first output signal.

For example, as a result of checking the output value of the first output signal, when the output value is 1, the device 400 determines that the first part corresponds to the first level at the first time, and sets the first level to the first level. When the output value is 2, it is determined that the grade of the first part corresponds to the second grade at the first time point, and the second grade may be set as the first grade.

In step S206, the device 400 performs an ultrasound scan on the first part of the first livestock at the second time point, when the ultrasound scan is performed on the first part of the first livestock using the ultrasonic scanner 100 at the second time point. A first-second image generated through inspection may be acquired. Here, the second point in time means a time point after the first reference period has passed from the first point in time, and the first reference period may be set differently according to embodiments. For example, if the first time point is January 1st and the first reference period is set to 10th, the second time point may be January 11th.

Specifically, the ultrasound scanner 100 may perform an ultrasound examination on the first part of the first livestock at a second time point, and through the ultrasound examination on the first part of the first livestock performed at the second time point, the first - 2 images can be created.

The apparatus 400 may obtain the first-second image from the ultrasound examination machine 100 when the first-second image is generated through the ultrasound examination of the first part of the first livestock performed at the second time point.

In the present invention, the second point of view may be used as a meaning including from a point in time of ultrasound examination to a point in time of obtaining an ultrasound image. That is, at a second time point, the ultrasound scanner 100 may perform an ultrasound scan to generate a 1-2 image, and at the second time point, the device 400 may acquire the 1-2 image from the ultrasound scan device 100. there is 4

In step S207, the apparatus 400 may generate a second input signal by encoding the 1-2 images.

In step S208 , the device 400 may input the second input signal to the artificial neural network trained in advance in the device 400 .

In step S209 , the apparatus 400 may obtain a second output signal, which is an output value of the artificial neural network, based on a result of the input of the artificial neural network.

In step S210, the device 400 may set the grade of the first part to a second grade at a second time point based on the second output signal.

In step S211, the device 400 may compare the first grade and the second grade to analyze a grade change trend of the first part during the first reference period.

That is, since the first grade indicates the grade of the first part at the first time point and the second grade indicates the grade of the first part at the second time point, the device 400 compares the first grade and the second grade. Thus, it is possible to analyze the change trend of how the grade of the first part has changed from the first time point to the second time point.

3 is a flowchart illustrating a process of analyzing and monitoring the growth state of livestock through size tracking according to an embodiment.

Referring to FIG. 3 , first, in step S301, when the camera 200 is photographing the first livestock, the device 400 displays a 3D image generated by photographing the first livestock from the camera 200. First image information may be obtained. In this case, the first image information may be generated as a 3D image by photographing the first livestock.

That is, when the camera 200 is installed in a barn where the first livestock is located, the camera 200 may generate first image information by capturing the first livestock, and the device 400 may generate the first image information. When is generated, first image information may be obtained from the camera 200 .

In step S302, the device 400 may extract an image of an image obtained at a first viewpoint from the first image information as a 2-1 image. In this case, since the first image information is a 3D image, the 2-1 image may be extracted as a 3D image.

Specifically, the device 400 acquires the first image information from the camera 200 before the first point in time, and when the 1-1 image is acquired from the ultrasound scanner 100 at the first point in time, the first A point in time when the image was obtained may be determined as a first point of view, and an image of an image obtained at the first point in time may be extracted from the first image information as a 2-1 image.

In step S303, the device 400 may classify an area occupied by the first part in the 2-1 image as a first area. At this time, since the 2-1 image is a 3D image, the first area may be divided into a 3D space.

That is, the device 400 may recognize each part of the first livestock based on the 2-1 image, and divide the area occupied by each part of the first livestock into each region.

In step S304, the device 400 may calculate the volume of the first region through the size of the first region.

That is, when the regions occupied by each part of the first livestock are divided based on the 2-1 image, the apparatus 400 may calculate the volume of each divided region.

When calculating the volume of the first region, the apparatus 400 classifies the region occupied by the reference object in the 2-1 image as the reference region, compares the sizes of the reference region and the first region, and determines the size of the first region. volume can be calculated. Here, the reference object may be placed adjacent to the first livestock to be used to calculate the volume.

Specifically, the camera 200 may generate first image information by photographing the first livestock and the reference object together, and the device 400 may generate the first image generated by photographing the first livestock and the reference object together. information can be obtained.

Thereafter, the device 400 may extract the image of the image acquired at the first point of view from the first image information as the 2-1 image, and the area occupied by the first part in the 2-1 image is the first area. , and the area occupied by the reference object can be classified as the reference area.

Then, the apparatus 400 may estimate and calculate the volume of the first region based on the size of the first region, the size of the reference region, and the actual size of the reference object.

That is, the apparatus 400 may calculate a reference ratio, which is a ratio between the size of the reference area and the actual size of the reference object, and apply the reference ratio to the size of the first area to calculate the volume of the first area.

For example, when the size of the first area is 20 cm ³ , the size of the reference area is 10 cm ³ , and the actual size of the reference object is 15 cm ³ , the device 400 determines the size of the reference area and the reference object. The volume of the first region may be calculated as 30 cm ³ by calculating the reference ratio as 1.5 using the actual size and applying the reference ratio to the size of the first region.

In step S305 , the apparatus 400 may determine that the volume of the first region is calculated as the first volume as a result of calculating the volume of the first region through the size of the first region.

In step S306, when the volume of the first region is calculated as the first volume, the device 400 may set the volume of the first part as the first volume at a first time point.

In step S307, the device 400 may extract an image of an image acquired at a second viewpoint from the first image information as a 2-2 image. At this time, since the first image information is a 3D image, the 2-2 image may be extracted as a 3D image.

Specifically, the device 400 acquires the first image information from the camera 200 before the first point of view, and when the first-2nd image is acquired from the ultrasound scanner 100 at the second point of view, the first-2nd image information is acquired. A point in time when the image was obtained may be recognized as a second point of view, and an image of an image obtained at the second point in time may be extracted from the first image information as a 2-2 image.

In step S308, the device 400 may classify the area occupied by the first part as a second area in the 2-2 image. At this time, since the 2-2 image is a 3D image, the second region may be divided into a 3D space.

In step S309, the device 400 may calculate the volume of the second region through the size of the second region.

In step S310 , the apparatus 400 may determine that the volume of the second region is calculated as the second volume as a result of calculating the volume of the second region through the size of the second region.

In step S311, when the volume of the second region is calculated as the second volume, the device 400 may set the volume of the first part to the second volume at a second time point.

In step S312 , the device 400 may compare the first volume and the second volume to analyze a size change trend of the first part during the first reference period.

That is, since the first volume represents the volume of the first region at the first time point and the second volume represents the volume of the first region at the second time point, the device 400 compares the first region and the second region. Thus, it is possible to analyze the change trend of how the size of the first part changes from the first time point to the second time point.

4 is a flowchart illustrating a process of determining a breeding method of livestock based on a result of analyzing a growth state of livestock according to an embodiment.

Referring to FIG. 4 , first, in step S401, the apparatus 400 calculates a third volume by subtracting the first volume from the second volume as a result of analyzing the size change trend of the first part during the first reference period. can do. Here, the third volume may refer to a value changed due to an increase in the size of the first part during the first reference period.

In step S402, the device 400 may check the fourth volume set as the average change value of the first part during the first reference period. To this end, the database of the device 400 stores information on average fluctuation values classified by region and period.

For example, when the first reference period is 1 month and the first part is the back, the device 400 searches information stored in the database, and the average change is set as the average increase in the first part during 1 month. The numerical value can be confirmed, and the identified average fluctuation value can be identified as the fourth volume.

In step S403 , the apparatus 400 may calculate a fifth volume by subtracting the fourth volume from the third volume.

In step S404, the device 400 may check whether the fifth volume is included in the reference range. Here, the reference range may be set differently according to embodiments.

If it is confirmed in step S404 that the fifth volume is included within the reference range, step S501 may be performed, and a detailed description related to this will be described later with reference to FIG. 5 .

For example, if the reference range is set to -10 cm ³ to 10 cm ³ and the fifth volume is calculated as 5 cm ³ , the device 400 may confirm that the fifth volume is included in the reference range.

If it is confirmed that the fifth volume is out of the reference range in step S404, in step S405, the device 400 may determine whether the fifth volume is greater than the maximum value of the reference range.

If it is confirmed in step S405 that the fifth volume is greater than the maximum value of the reference range, step S601 may be performed, and a detailed description related to this will be described later with reference to FIG. 6 .

If it is determined in step S405 that the fifth volume is smaller than the maximum value of the standard range, since the fifth volume is out of the standard range, it can be confirmed that the fifth volume is smaller than the minimum value of the standard range, and in step S405 the fifth volume is smaller than the minimum value of the standard range. If it is confirmed that the volume is smaller than the minimum value of the reference range, step S701 may be performed, and a detailed description related to this will be described later with reference to FIG. 7 .

5 is a flowchart illustrating a process of determining a breeding method of livestock when it is confirmed that a fifth volume is included within a reference range according to an embodiment.

Referring to FIG. 5 , in step S501, when it is confirmed that the fifth volume is within the reference range, the device 400 analyzes the trend of grade change in the first part during the first reference period, and as a result, the second grade is obtained. It is possible to check whether the level is higher than the first level.

If the second grade is confirmed to be higher than the first grade in step S501, in step S503, the apparatus 400 may determine that the current maintenance of the breeding method of the first livestock is necessary.

That is, when it is confirmed that the grade of the first part increases as the size of the first part increases by the average value during the first reference period, the apparatus 400 may determine that the current maintenance of the breeding method of the first livestock is necessary. .

If the second grade is determined to be a grade not higher than the first grade in step S501, the device 400 may determine whether the first grade and the second grade are the same grade in step S502.

In step S502, if the first grade and the second grade are determined to be the same grade, in step S504, the apparatus 400 may determine that additional payment of feed for the first livestock is required.

That is, when the apparatus 400 determines that the grade of the first part is maintained while the size of the first part increases by the average value during the first reference period, additional payment of fattening feed for the first livestock is required to increase the grade. can be judged to be

If the first grade and the second grade are not identified as the same grade in step S502, the second grade may be identified as a lower grade than the first grade, and the second grade may be identified as a lower grade than the first grade in step S502. If confirmed, in step S504, the device 400 may determine that additional payment of the fattening feed for the first livestock is necessary.

That is, when the apparatus 400 determines that the grade of the first part has decreased as the size of the first part increases by the average value during the first reference period, additional payment of fattening feed for the first livestock is required to increase the grade. can judge

6 is a flowchart illustrating a process of determining a breeding method of livestock when it is confirmed that a fifth volume is greater than the maximum value of the reference range according to an embodiment.

Referring to FIG. 6, in step S601, when it is determined that the fifth volume is out of the reference range and greater than the maximum value of the reference range, the device 400 analyzes the grade change trend of the first part during the first reference period. As a result, it can be confirmed whether the second grade is a higher grade than the first grade.

If the second grade is confirmed to be higher than the first grade in step S601, in step S603, the device 400 may determine that it is necessary to maintain the current breeding method of the first livestock.

That is, when it is confirmed that the grade of the first part increases as the size of the first part increases more than the average value during the first reference period, the apparatus 400 determines that the current maintenance of the breeding method of the first livestock is necessary. can

If the second grade is determined to be a grade not higher than the first grade in step S601, the device 400 may determine whether the first grade and the second grade are the same grade in step S602.

If the first grade and the second grade are determined to be the same grade in step S602, in step S604, the device 400 may determine that the current maintenance of the breeding method of the first livestock is necessary.

That is, when the apparatus 400 determines that the size of the first part increases more than the average value during the first reference period and the grade of the first part is maintained, it is determined that the current maintenance of the breeding method of the first livestock is necessary. can do.

If the first grade and the second grade are not identified as the same grade in step S602, the second grade may be identified as a lower grade than the first grade, and the second grade may be identified as a lower grade than the first grade in step S602. If confirmed, in step S604, the device 400 may determine that additional payment of the fattening feed for the first livestock is necessary.

That is, if the device 400 determines that the size of the first part has increased more than the average value during the first reference period, but the grade of the first part has decreased, the apparatus 400 additionally provides fattening feed for the first livestock to increase the grade. This can be judged necessary.

7 is a flowchart illustrating a process of determining a breeding method of livestock when it is confirmed that a fifth volume is smaller than the minimum value of the reference range according to an embodiment.

Referring to FIG. 7 , in step S701, when it is determined that the fifth volume is out of the reference range and smaller than the minimum value of the reference range, the result of analyzing the grade change trend of the first part during the first reference period , it is possible to determine whether the second grade is a higher grade than the first grade.

If the second grade is confirmed to be higher than the first grade in step S701, in step S703, the device 400 may determine that the breeding method of the first livestock needs to be changed.

That is, if it is confirmed that the size of the first part has increased less than the average value even though the grade of the first part increases during the first reference period, the apparatus 400 determines that the breeding method of the first livestock needs to be changed. can

In step S701, if the second grade is determined to be a grade not higher than the first grade, in step S702, the device 400 may determine whether the first grade and the second grade are the same grade.

In step S702, if the first grade and the second grade are determined to be the same grade, in step S704, the apparatus 400 may determine that a change in the breeding method of the first livestock is required.

That is, when it is confirmed that the size of the first part increases less than the average value during the first reference period and the grade of the first part is maintained, the apparatus 400 determines that a change in the breeding method of the first livestock is necessary. can

In step S702, if the first grade and the second grade are not identified as the same grade, the second grade may be identified as a lower grade than the first grade, and the second grade may be identified as a lower grade than the first grade in step S702. If confirmed, in step S704, the device 400 may determine that it is necessary to determine whether to maintain breeding of the first livestock.

That is, when it is confirmed that the grade of the first part decreases as the size of the first part increases less than the average value during the first reference period, the apparatus 400 determines that it is necessary to decide whether to maintain breeding of the first livestock. can Details of determining whether or not to maintain breeding of the first livestock will be described later with reference to FIGS. 8 and 9 .

As shown in FIGS. 5 to 7 , when it is determined how to breed the first livestock, the apparatus 400 identifies the breeder who breeds the first livestock, and sends the determination result to the identified breeder. can notify At this time, the device 400 may transmit a notification message for the determination result to the breeder terminal.

8 is a flowchart illustrating a process of calculating a price for a part expected to grow in the future according to an embodiment.

Referring to FIG. 8, first, in step S801, when the weight of the first livestock is measured using the weight measuring device 300 at a first time, the device 400 measures the weight of the first livestock at a first time, Information on the generated first weight may be obtained.

Specifically, the weight measuring device 300 may generate information about the first weight by measuring the weight of the first livestock at the first time point. Here, the information on the first weight is information on the weight of the first livestock measured at the first point in time.

When information on the first weight is generated, the device 400 may obtain information on the first weight from the weight measuring device 300 .

In step S802, when the weight of the first livestock is measured using the weighing device 300 at a second time point, the device 400 measures the weight of the first livestock at a second time point and generates information about the second weight. can be obtained.

Specifically, the weight measuring device 300 may measure the weight of the first livestock at a second time point to generate information about the second weight. Here, the information on the second weight is information on the weight of the first livestock measured at the second time point.

When information on the second weight is generated, the device 400 may obtain information on the second weight from the weight measuring device 300 .

In step S803, the apparatus 400 may compare the first weight and the second weight to analyze a weight variation trend of the first livestock during the first reference period.

That is, since the first weight represents the weight of the first livestock at the first time point and the second weight represents the weight of the first livestock at the second time point, the device 400 compares the first weight and the second weight. Thus, it is possible to analyze the change trend of how the weight of the first livestock fluctuates from the first time point to the second time point.

In step S804, the apparatus 400 may predict a third weight expected as the weight of the first livestock at a third point in time as a result of analyzing the weight change trend of the first livestock. Here, the third point in time means a time point after the second reference period has passed from the second point in time, and the second reference period may be set differently according to embodiments.

That is, the apparatus 400 may predict how the weight of the first livestock will change in the future by predicting how the weight of the first livestock will change based on the result of analyzing the trend of the weight change of the first livestock. In this case, the apparatus 400 may predict how the weight of the first livestock will fluctuate by further considering the type of the first livestock, the genetic factors of the first livestock, and the like, and through this, the weight of the first livestock in the future. A growth curve may be generated by estimating how much the livestock will weigh, and a third weight expected as the weight of the first livestock at a third time point may be confirmed using the growth curve.

Meanwhile, in step S805, the device 400 may determine that the first livestock belongs to the first category of livestock. That is, livestock may be classified into categories such as cows, pigs, and chickens, and the device 400 may determine which category of livestock the first livestock belongs to.

In step S806, the device 400 may check a first ratio, which is a ratio occupied by the first part in the livestock of the first category. To this end, the database of the device 400 stores information on ratios classified by category and region.

For example, if the first category is a cow and the first part is a back part, the device 400 may check information stored in the database to check the ratio set as the back part in the cow, and confirm the The ratio can be identified as the first ratio.

In step S807 , the apparatus 400 may calculate a fourth weight by multiplying the second weight by the first ratio, and calculate a fifth weight by multiplying the third weight by the first ratio.

When the fourth weight is calculated, the device 400 may set the weight of the first part as the fourth weight at a second time point, and set the weight of the first part at a third time point to the fifth weight when the fifth weight is calculated. can be set to

In step S808, the apparatus 400 may calculate the sixth weight by subtracting the fourth weight from the fifth weight. Here, the sixth weight may refer to a value expected to fluctuate as the first part becomes heavy during the second reference period.

In step S809, the device 400 may calculate the price for the first part expected to grow during the second reference period by multiplying the price per weight set in the second grade by the sixth weight.

For example, if the price per weight is set to 10 won per 1g for the second grade of the first part and the sixth weight is calculated as 30g, the device 400 is expected to grow during the second reference period. The price for one part can be calculated as 300 won.

9 is a flowchart illustrating a process of determining whether to breed livestock through a price for each part expected to grow in the future according to an embodiment.

Referring to FIG. 9 , first, in step S901 , the apparatus 400 may calculate a price for each part of the first livestock that is expected to grow during the second reference period for each part.

That is, the apparatus 400 calculates the price for each part of the first livestock expected to grow during the second reference period in the same way as the method for calculating the price for the first part expected to grow during the second reference period. price can be calculated.

In step S902, the device 400 may calculate a first amount by summing the prices of each part, when the price for each part expected to grow during the second reference period is calculated for each part of the first livestock. have.

On the other hand, in step S903, the apparatus 400 sets a second amount, which is an estimated cost to raise the first livestock during the second reference period, in consideration of the birth time, the second time point, and the third time point of the first livestock. Predictable.

To this end, the database of the device 400 stores information on breeding costs classified by category and growth period.

For example, when the first category is cattle, the second time point is 3 months after the first livestock is born, and the third time point is 6 months after the first livestock is born, the device 400 The user may inquire information stored in the database to check the breeding cost necessary for raising the cow from 3 months to 6 months after birth, and check the confirmed breeding cost as a second amount.

In step S904, the device 400 may determine whether the first amount is greater than the second amount.

That is, the first amount is revenue generated by the growth of the first livestock when the first livestock is grown during the second reference period, and the second amount is the amount generated by breeding the first livestock when the first livestock is raised during the second reference period. This is the consumed expenditure, and the apparatus 400 may determine whether the revenue generated by the growth of the first livestock is greater than the expenditure consumed by breeding the first livestock.

If it is determined that the first amount is greater than the second amount in step S904, in step S905, the apparatus 400 may determine that breeding of the first livestock is maintained.

If it is determined in step S904 that the second amount is greater than the first amount, in step S906, the apparatus 400 may determine that the breeding of the first livestock is not maintained.

As shown in FIG. 9 , when it is determined how to raise or not to raise the first livestock, the apparatus 400 may transmit a notification message about whether to breed the first livestock to the breeder terminal.

10 is a flowchart illustrating a process of recording and storing an image of a specific region at a specific time point according to an embodiment.

Referring to FIG. 10 , first, in step S1001, the apparatus 400 may classify an area occupied by the first part in the 2-1 image as a first area.

Specifically, the device 400 may analyze the 2-1 image, recognize all shapes on the 2-1 image, and determine the location of the first part located at the leftmost part on the 2-1 image. It is identified as the first position, the position of the first part positioned at the top on the image 2-1 is identified as the second position, and the position of the first part positioned at the far right on the image 2-1 is identified as the third position. position, and the position of the letter located at the bottom on the 2-1 image can be confirmed as the fourth position.

Thereafter, the device 400 generates a first straight line that extends in the vertical direction based on the first position, generates a second straight line that extends in the left and right direction based on the second position, and creates a vertical and horizontal line based on the third position. A third straight line extending in a direction may be generated, and a fourth straight line extending in a left-right direction based on the fourth position may be generated.

Thereafter, the device 400 may set an area connecting the first straight line, the second straight line, the third straight line, and the fourth straight line as the first area, and then distinguish the first area from the 2-1 image.

In step S1002, the apparatus 400 may divide the portion of the 2-1 image where the first area is located, and extract the divided image as the 3-1 image.

In step S1003, the device 400 may check whether it is recognized that there is a breeder in the 3-1 image. That is, the device 400 may check whether a human-shaped object other than the first part is recognized on the 3-1 image, and determine whether there is a breeder raising the first livestock in the 3-1 image.

If it is confirmed in step S1003 that there is a breeder in the 3-1 image, in step S1004, the device 400 may classify the area occupied by the breeder in the 3-1 image as a third area. In this case, the device 400 may divide the third region from the 3-1 image in the same way as the first region from the 2-1 image.

In step S1005, the apparatus 400 may reproduce and analyze the first image information in reverse time order from the first viewpoint.

In step S1006, the device 400 reproduces and analyzes the first image information in reverse chronological order from the first time point, and as a result, it can be confirmed that there is no breeder in the third area at the 0th time point.

That is, the device 400 may reproduce the first image information in reverse order in time from the first point of view to monitor that the breeder in the third area moves in reverse, and the breeder in the third area is determined to be out of the third area. The confirmation time point may be set as the zeroth time point.

In step S1007, the device 400 may extract an image of an image obtained at the 0th point of view from the first image information as an image 2-0.

In step S1008, the apparatus 400 may extract a 3-0 image by dividing a portion of the 2-0 image in which the third area is located.

In step S1009, the device 400 may replace a portion of the 3-1 image with the third area with the 3-0 image.

Specifically, if it is confirmed that there is a breeder in the 3-1 image, the device 400 may classify the area occupied by the breeder in the 3-1 image as a third area, and may divide the third area in the 3-1 image. By deleting the part with the , and inserting the 3-0 image at the deleted position, the 3-1 image in which the 3-1 image and the 3-0 image are combined may be created. That is, in the image 3-1, the part with the third area is replaced with the image 3-0, the breeder in the image 3-1 is deleted, and the part without the breeder is added in the deleted position, In the -1 image, the breeder may no longer be recognized.

If it is recognized that there is no breeder in the 3-1 image in step S1003, or if the portion with the third region in the 3-1 image is replaced with the 3-0 image in step S1009, in step S1010, the device 400 may record the 3-1 image as an image of the first part of the first viewpoint and store it in a database.

11 is a diagram for explaining an artificial neural network according to an embodiment.

The artificial neural network 1100 according to an embodiment may take an input signal generated by encoding data as an input, and output information about which grade a part is classified into.

Encoding according to an embodiment may be performed by storing color information for each pixel of an image in the form of a digitized data sheet. The color information includes RGB color, brightness information, saturation information, and depth information of one pixel. You can, but are not limited to this.

According to an embodiment, the artificial neural network 1100 is composed of a feature extraction neural network 1110 and a classification neural network 1120, and the feature extraction neural network 1110 separates a region region and a background region from an image. In addition, the classification neural network 1120 may perform an operation of determining whether a grade of a part in an image is classified into a grade.

The method for the feature extraction neural network 1110 to distinguish between the body region and the background region is that the change in each value of color information from the data sheet of the input signal encoding the image is 30% at 6 or more out of 8 pixels including one pixel. A bundle of pixels detected as having an abnormal change may be used as a boundary between the region region and the background region, but is not limited thereto.

The feature extraction neural network 1110 proceeds by sequentially stacking the convolution layer and the pooling layer on the input signal. The convolution layer includes convolution operations, convolution filters, and activation functions. The calculation of the convolution filter is adjusted according to the matrix size of the target input, but a 9X9 matrix is generally used. As the activation function, a ReLU function, a sigmoid function, and a tanh function are generally used, but are not limited thereto. The pooling layer is a layer that reduces the matrix size of the input, and uses a method of extracting a representative value by grouping pixels in a specific area. The calculation of the pooling layer generally uses average values or maximum values, but is not limited thereto. The operation is performed using a square matrix, and a 9X9 matrix is generally used. The convolutional layer and the pooling layer are alternately repeated until the corresponding input is sufficiently small while maintaining the difference.

The classification neural network 1120 checks the surface of the local region separated from the background through the feature extraction neural network 1110, and determines whether the surface state of the local region is similar to a predefined graded surface state, to which grade the surface of the local region is classified. can figure out whether Information stored in a database can be used to compare surface conditions by grade.

The classification neural network 1120 has a hidden layer and an output layer, and is composed of 5 or less hidden layers, including a total of 50 or less hidden layer nodes, and the activation function of the hidden layer is a ReLU function and a sigmoid function. and tanh functions, etc. are used, but are not limited thereto.

The classification neural network 1120 may include only one output layer node in total.

The output of the classification neural network 1120 is an output value indicating to which grade the surface of the region region is classified, and may indicate which grade it corresponds to. For example, if the output value is 1, it may indicate that the surface of the part region corresponds to the first grade, and if the output value is 2, it may indicate that the surface of the part region corresponds to the second grade.

According to an embodiment, the artificial neural network 1100 may learn by receiving a first learning signal generated by a correction correct answer input by the user when a problem is detected in the output of the artificial neural network 1100 . A problem with the output according to the artificial neural network 1100 may refer to a case in which output values classified into different grades are output for the surface of the partial region.

The first learning signal according to an embodiment is created based on the error between the correct answer and the output value, and in some cases, SGD using delta, a batch method, or a method following a backpropagation algorithm may be used. The artificial neural network 1100 performs learning by modifying existing weights according to the first learning signal, and may use momentum in some cases. A cost function can be used to calculate the error, and a cross entropy function can be used as the cost function. Hereinafter, learning contents of the artificial neural network 1100 will be described with reference to FIG. 12 .

12 is a diagram for explaining a method of learning an artificial neural network according to an embodiment.

According to an embodiment, the learning device may train the artificial neural network 1100. The learning device may be a separate subject different from the device 400, but is not limited thereto.

According to an embodiment, the artificial neural network 1100 may include an input layer inputting training samples and an output layer outputting training outputs, and may be learned based on a difference between the training outputs and the first labels. Here, the first labels may be defined based on representative images registered for each grade of the part. The artificial neural network 1100 is connected to a group of a plurality of nodes, and is defined by weights between the connected nodes and an activation function that activates the nodes.

The learning device may train the artificial neural network 1100 using a gradient descent (GD) technique or a stochastic gradient descent (SGD) technique. The learning device may use a loss function designed by the outputs and labels of the artificial neural network 1100 .

The learning device may calculate a training error using a predefined loss function. The loss function may be predefined with labels, outputs, and parameters as input variables, where the parameters may be set by weights in the artificial neural network 1100 . For example, the loss function may be designed in a mean square error (MSE) form, an entropy form, and the like, and various techniques or methods may be employed in an embodiment in which the loss function is designed.

The learning device may find weights affecting the training error using a backpropagation technique. Here, weights are relationships between nodes in the artificial neural network 1100 . The learning device may use the SGD technique using labels and outputs to optimize the weights found through the backpropagation technique. For example, the learning device may update weights of a loss function defined based on labels, outputs, and weights using the SGD technique.

According to an embodiment, the learning device may obtain representative images 1201 for each grade of the labeled training part from the database. The learning device may obtain information prelabeled in each of the representative images 1201 for each part grade, and the representative images 1201 for each part grade may be labeled according to the pre-classified part grade.

According to an embodiment, the learning apparatus may acquire 1000 labeled training part graded representative images 1201, and based on the labeled training part graded representative images 1201, first training part graded vectors ( 1202) can be created. Various methods may be employed to extract the vectors 1202 for each class of the first training region.

According to an embodiment, the learning device may obtain first training outputs 1203 by applying the vectors 1202 for each grade of the first training part to the artificial neural network 1100 . The learning device may train the artificial neural network 1100 based on the first training outputs 1203 and the first labels 1204 . The learning device may train the artificial neural network 1100 by calculating training errors corresponding to the first training outputs 1203 and optimizing a connection relationship of nodes in the artificial neural network 1100 to minimize the training errors. .

13 is an exemplary diagram of a configuration of a device according to an embodiment.

An apparatus 400 according to an embodiment includes a processor 410 and a memory 420. The processor 410 may include at least one device described above with reference to FIGS. 1 to 12 or may perform at least one method described above with reference to FIGS. 1 to 12 . A person or organization using the device 400 may provide services related to some or all of the methods described above with reference to FIGS. 1 to 12 .

The memory 420 may store information related to the methods described above or a program in which the methods described below are implemented. Memory 420 may be volatile memory or non-volatile memory.

The processor 410 may execute a program and control the device 400 . Program codes executed by the processor 410 may be stored in the memory 420 . The device 400 may be connected to an external device (eg, a personal computer or network) through an input/output device (not shown) and exchange data through wired/wireless communication.

Apparatus 400 may be used to train an artificial neural network or to use a trained artificial neural network. Memory 420 may include a learning or learned artificial neural network. The processor 410 may learn or execute an artificial neural network algorithm stored in the memory 420 . The device 400 for learning the artificial neural network and the device 400 using the learned artificial neural network may be the same or separate.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

The method according to the embodiment 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. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. The device can be commanded. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (3)

In the method of analyzing and monitoring the growth status of livestock to improve the breeding effect, performed by the device,
When the ultrasound examination of the first part of the first livestock is performed using the ultrasonic scanner at the first time point, the 1-1 generated through the ultrasound examination of the first part of the first livestock at the first time point acquiring an image;
generating a first input signal by encoding the 1-1 image;
inputting the first input signal to an artificial neural network and obtaining a first output signal based on a result of the input of the artificial neural network;
setting a grade of the first part to a first grade at the first time point based on the first output signal;
When an ultrasound examination of the first part of the first livestock is performed using the ultrasound scanner at a second time point after a preset first reference period has passed from the first time point, the first livestock at the second time point acquiring first-second images generated through ultrasound examination of the first part of the body;
generating a second input signal by encoding the first-second image;
inputting the second input signal to an artificial neural network and obtaining a second output signal based on a result of the input of the artificial neural network;
setting a grade of the first part to a second grade at the second time point based on the second output signal;
comparing the first grade and the second grade and analyzing a grade change trend of the first part during the first reference period;
obtaining first image information, which is a 3D image generated by photographing the first livestock, from a camera that photographs the first livestock;
extracting an image of an image acquired at the first viewpoint from the first image information as a 2-1 image;
Dividing the area occupied by the first part in the 2-1 image into a first area based on the 2-1 image, and calculating the volume of the first area through the size of the first area step;
if the volume of the first region is calculated as the first volume, setting the volume of the first part to the first volume at the first time point;
extracting an image of an image acquired at the second viewpoint from the first image information as a 2-2 image;
Dividing the area occupied by the first part in the 2-2 image into a second area based on the 2-2 image, and calculating the volume of the second area through the size of the second area step;
setting the volume of the first part to the second volume at the second time point when the volume of the second region is calculated as the second volume;
comparing the first volume and the second volume, and analyzing a size change trend of the first part during the first reference period;
As a result of analyzing the size change trend of the first part, the first volume is subtracted from the second volume to calculate a third volume, which is a value changed as the size of the first part increases during the first reference period. step;
checking a fourth volume set as an average change value of the first part during the first reference period;
calculating a fifth volume by subtracting the fourth volume from the third volume;
When it is confirmed that the fifth volume is included within the preset reference range, as a result of analyzing the grade change trend of the first part, when the second grade is confirmed as a higher grade than the first grade, the first If it is determined that the current maintenance of the livestock breeding method is necessary, and the first grade and the second grade are confirmed to be the same grade or the second grade is confirmed to be a lower grade than the first grade, the first livestock Determining that additional payment for fattening feed is necessary;
When it is confirmed that the fifth volume is outside the reference range and is greater than the maximum value of the reference range, as a result of analyzing the grade change trend of the first part, the second grade is a higher grade than the first grade. confirmed or if the first grade and the second grade are confirmed to be the same grade, it is determined that the current maintenance of the breeding method of the first livestock is necessary, and the second grade is confirmed as a lower grade than the first grade. If it is, determining that additional payment of fattening feed for the first livestock is necessary; and
When it is confirmed that the fifth volume is out of the reference range and is smaller than the minimum value of the reference range, as a result of analyzing the grade change trend of the first part, the second grade is confirmed to be a higher grade than the first grade. or if the first grade and the second grade are confirmed to be the same grade, it is determined that a change in the breeding method of the first livestock is necessary, and if the second grade is confirmed to be a lower grade than the first grade, Determining whether to maintain breeding of the first livestock is necessary;
The step of determining that a decision on whether to maintain breeding of the first livestock is necessary,
obtaining information on a first weight generated by measuring the weight of the first livestock at the first time point when the weight of the first livestock is measured using a weighing machine at the first time point;
obtaining information on a second weight generated by measuring the weight of the first livestock at the second time point when the weight of the first livestock is measured using the weighing machine at the second time point;
comparing the first weight and the second weight to analyze a weight variation trend of the first livestock during the first reference period;
predicting a third weight expected as the weight of the first livestock at a third time point after a second reference period set in advance from the second time point as a result of analyzing the weight change trend of the first livestock;
checking a first ratio, which is a ratio occupied by the first part, in the livestock of the first category, when the first livestock belongs to livestock of the first category;
calculating a fourth weight by multiplying the second weight by the first ratio, and setting the weight of the first part at the second time point to the fourth weight;
calculating a fifth weight by multiplying the third weight by the first ratio, and setting the weight of the first portion to be the fifth weight at the third point in time;
calculating a sixth weight, which is a value expected to fluctuate as the first part becomes heavier during the second reference period, by subtracting the fourth weight from the fifth weight; and
Calculating a price for the first part expected to grow during the second reference period by multiplying the price per weight set in the second grade by the sixth weight,
A method for analyzing and monitoring the growth status of livestock to improve the breeding effect. delete delete

Images