JP7814448B2 - Estimation system, estimation method, and program - Google Patents

Description

The present invention relates to an estimation system, an estimation method, and a program.

Patent Document 1 describes an "estimation system for estimating the health status of animals such as cows using a learning model." Patent Document 2 describes a "ruminant management device for managing the behavior of ruminants." Patent Document 3 describes a "livestock management system for managing livestock such as cows raised for meat consumption and a livestock bioimpedance measuring device for use therein." Patent Document 4 describes a "calculation unit for calculating a body type value related to the body type of an animal body" and an "estimation unit for estimating the weight of the animal body based on the body type value of the animal body."
[Prior art documents]
[Patent Documents]
[Patent Document 1] JP 2021-136868 A [Patent Document 2] JP 2011-103793 A [Patent Document 3] JP 2002-253523 A [Patent Document 4] JP 2021-016376 A

According to one embodiment of the present invention, an estimation system is provided. The estimation system may include a learning model storage unit that stores a learning model generated by machine learning using learning data including measurement data obtained by measuring the inside of the livestock and the internal components of the livestock. The estimation system may include a measurement data acquisition unit that acquires measurement data obtained by measuring the inside of the livestock that is the estimation target. The estimation system may include an estimation unit that estimates the internal components of the livestock that is the estimation target using the measurement data acquired by the measurement data acquisition unit and the learning model.

In the estimation system, the measurement data may include at least one of electrical measurement data generated by applying electricity to the livestock's body, elastic wave measurement data generated by irradiating elastic waves into the livestock's body, magnetic field measurement data generated by applying a magnetic field to the livestock's body, and electromagnetic wave measurement data generated by irradiating electromagnetic waves into the livestock's body. In any of the estimation systems, the measurement data may include two or more of the electrical measurement data, the elastic wave measurement data, the magnetic field measurement data, and the electromagnetic wave measurement data. In any of the estimation systems, the internal body components may include at least one of muscle, fat, bone, and internal organ elements.

In any of the above estimation systems, the estimation unit may estimate the fat content in the muscle of the livestock. In the estimation system, the estimation unit may estimate at least one of the carcass weight of the livestock being estimated and the meat grade of the livestock being estimated.

In any of the above estimation systems, the measurement data acquisition unit may acquire the measurement data in a time series, and the estimation unit may estimate the internal body components of the estimation target livestock in a time series by inputting the time series measurement data into the learning model. The estimation system may further include a determination unit that determines whether or not a change in the feeding method for the estimation target livestock is necessary, based on the internal body components in the time series estimated by the estimation unit.

In any of the above estimation systems, the learning model storage unit may store the learning model generated by machine learning using learning data including the measurement data and the internal components of the livestock, and attribute data of the livestock. The estimation system may further include an attribute data acquisition unit that acquires attribute data of the livestock to be estimated. The estimation unit may estimate the internal components of the livestock to be estimated by inputting the measurement data acquired by the measurement data acquisition unit and the attribute data acquired by the attribute data acquisition unit into the learning model.

Any of the estimation systems may further include a learning model generation unit that generates a learning model through machine learning using learning data including the measurement data obtained by measuring the inside of the livestock and the internal components of the livestock.

One embodiment of the present invention provides an estimation method executed by a computer. The estimation method may include a measurement data acquisition step of acquiring measurement data obtained by measuring the inside of the body of a livestock to be estimated, and an estimation step of estimating the inside components of the livestock to be estimated using a learning model generated by machine learning using learning data including the measurement data obtained in the measurement data acquisition step and the inside components of the livestock, and the measurement data acquired in the measurement data acquisition step.

According to one embodiment of the present invention, a program is provided for causing a computer to execute the estimation method.

Note that the above summary of the invention does not list all of the necessary features of the present invention. Subcombinations of these features may also constitute inventions.

1 illustrates a schematic diagram of an example estimation system 10. 10A and 10B show schematic diagrams of an example of training data. 10A and 10B show schematic diagrams of an example of training data. 1 illustrates a schematic diagram of an example estimation system 10. FIG. 2 is an explanatory diagram illustrating an example of a processing flow by the estimation system 10. 1 shows an example of a hardware configuration of a computer 1200 that functions as the estimation system 10 or the estimation device 100.

The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention as claimed. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

Traditionally, livestock farmers have relied on experience and observation to control the weight and food intake of their livestock. In recent years, technology has been reported that uses video data from livestock barns and data from body temperature, sound, and acceleration sensors attached to the livestock's necks to use AI (Artificial Intelligence) to estimate the health status (abnormalities such as infectious diseases) of individual livestock.

While it is possible to estimate the health status of livestock based on their behavior using video footage or sensors attached to their necks, it has been difficult to estimate their detailed internal components (such as body weight and body fat percentage). The estimation system according to this embodiment uses a learning model generated by machine learning using training data including measurement data obtained by measuring the inside of the livestock and the internal components of the livestock to estimate the internal components of the livestock from measurement data obtained by measuring the inside of the livestock.

Figure 1 schematically illustrates an example of an estimation system 10. The estimation system 10 includes an estimation device 100. The estimation device 100 may include a measurement data acquisition unit 110, a learning model storage unit 120, and an estimation unit 130. The estimation system 10 may include a measurement device 200. The measurement device 200 measures the inside of the livestock 50 and generates measurement data 20. The measurement device 200 measures the inside of the livestock 50 by, for example, applying a non-invasive signal to the inside of the livestock 50. The livestock 50 may be, for example, a cow, pig, sheep, etc.

The type of measuring device 200 included in the estimation system 10 is not particularly limited. For example, the measuring device 200 may be a measuring device that applies electricity to the inside of the body of the livestock 50. For example, the measuring device 200 may be a measuring device that irradiates elastic waves into the body of the livestock 50. For example, the measuring device 200 may be a measuring device that applies a magnetic field to the inside of the body of the livestock 50. For example, the measuring device 200 may be a measuring device that irradiates electromagnetic waves into the body of the livestock 50.

The measuring device 200 may have the function of emitting electricity, elastic waves, magnetic fields, electromagnetic waves, etc. (sometimes referred to as electricity, etc.), and the function of receiving electricity, etc. If the estimation system 10 has multiple measuring devices 200, the function of emitting electricity, etc. and the function of receiving electricity, etc. may be distributed among the multiple measuring devices 200. For example, electricity, etc. emitted by a measuring device 200 installed in one ear of the livestock 50 may be received by a measuring device 200 installed in the other ear of the livestock 50. For example, electricity, etc. emitted by a measuring device 200 installed in the ear of the livestock 50 may be received by a measuring device 200 installed in the buttocks of the livestock 50. For example, electricity, etc. emitted by one measuring device 200 may be received by one measuring device 200. For example, electricity, etc. emitted by multiple measuring devices 200 may be received by multiple measuring devices 200. The measurement data 20 may be data based on the intensity, phase, frequency, etc. of the transmitted electricity, etc. and the received electricity, etc.

The type of measurement data 20 is not particularly limited. For example, the measurement data 20 may be data generated by applying electricity to the body of the livestock 50 (sometimes referred to as electrical measurement data). For example, the measurement data 20 may be data generated by irradiating elastic waves (sometimes referred to as elastic wave measurement data). For example, the measurement data 20 may be data generated by applying a magnetic field to the body of the livestock 50 (sometimes referred to as magnetic field measurement data). For example, the measurement data 20 may be data generated by irradiating electromagnetic waves to the body of the livestock 50 (sometimes referred to as electromagnetic wave measurement data).

Electrical measurement data includes, for example, electrical conductivity and electrical resistance. Elastic wave measurement data includes, for example, the conductivity of ultrasound, sound waves, and low-frequency vibrations, and the frequency dependence of conductivity. Magnetic field measurement data includes, for example, the conductivity of an irradiated magnetic field. Magnetic field measurement data may be data measuring weak changes in magnetic flux density caused by blood flow, etc. in the livestock 50. Electromagnetic wave measurement data may be data measuring phenomena such as scattering, refraction, reflection, diffraction, interference, and transmission of X-rays, ultraviolet rays, visible light, infrared rays, radio waves, etc. irradiated to the livestock 50.

The measurement data 20 may include data measuring the dimensions of the livestock 50 (sometimes referred to as dimension data), data measuring weight (sometimes referred to as weight data), data measuring blood (sometimes referred to as blood data), data measuring saliva (sometimes referred to as saliva data), data measuring locomotion (sometimes referred to as locomotion data), data measuring body temperature (sometimes referred to as body temperature data), etc. The dimension data may be data representing the dimensions of any part of the livestock 50. For example, the dimension data may be the body length, waist circumference, torso width, etc. of the livestock 50. The blood data may be data representing the amount, ratio, etc. of any component in the blood of the livestock 50. For example, the blood data is data representing the amount, ratio, etc. of blood cells, blood glucose, cholesterol, protein, inorganic salts, oxygen, carbon dioxide, enzymes, etc. The locomotion data may be data representing acceleration generated by installing an accelerometer or the like as a measuring device 200 on the livestock 50.

The installation position of the measuring device 200 is not particularly limited. For example, the installation position of the measuring device 200 is on the surface of the body of the livestock 50. For example, the installation position of the measuring device 200 is the head, torso, legs, and buttocks of the livestock 50. For example, the installation position of the measuring device 200 is the ears, nose, back, abdomen, groin, hooves, and tail. The installation position of the measuring device 200 does not have to be a position that comes into contact with the livestock 50, and may be a position that does not come into contact with the livestock 50.

The installation location of the measuring device 200 may be selected depending on the nature of the measurement performed by the measuring device 200. For example, if the measuring device 200 applies electricity to the livestock 50 to generate electrical measurement data, a portion of the livestock 50's body surface where the hair is thin may be selected as the installation location of the measuring device 200. For example, if the measuring device 200 irradiates the livestock 50 with elastic waves to generate elastic wave measurement data, a relatively hard part of the livestock 50 may be selected as the installation location of the measuring device 200. For example, a part of the livestock 50 where the skin and subcutaneous tissue are thin and where the bones are close may be selected as the installation location of the measuring device 200. For example, the horns, skull, spine, or hooves may be selected as the installation location of the measuring device 200. Processing may be performed to improve the accuracy of measurements of the livestock 50 performed by the measuring device 200. For example, processing such as hair removal from the body surface of the livestock 50 or embedding part of the measuring device 200 into the outermost surface of the livestock 50's skin may be performed.

The measuring device 200 may be selected according to the part of the body of the livestock 50 that is of interest. For example, the installation position of the measuring device 200 is selected so that the part of the body of the livestock 50 of interest is sandwiched between the measuring device 200 that emits electricity, etc. and the measuring device 200 that receives electricity, etc. For example, the installation position of the measuring device 200 is selected according to the internal component of the livestock 50 that is of interest. Internal components include, for example, muscle, fat, bone, and internal organs. For example, when focusing on internal organs, the installation position of the measuring device 200 is selected so that the part of the body of the livestock 50 that is used to determine the grade of the livestock 50 is sandwiched between the measuring device 200 and the measuring device 200. For example, if the livestock 50 is a cow and the destination for the cow's carcass is Japan, the installation position of the measuring device 200 may be selected so that it is positioned to sandwich the area between the sixth and seventh ribs, which is used to determine the grade of the carcass in Japan.

A carcass is the flesh of a livestock50 after the head, tail, extremities, etc. have been removed and the skin and internal organs have been removed. The ratio of carcass to live weight is called carcass yield.

The measuring device 200 may be selected so that the data volume of the measurement data 20 is small. The measuring device 200 may be selected so that the calibration frequency of the measuring device 200 is reduced. As a specific example, the measuring device 200 is a measuring device 200 that does not use video data. Video data has a large data volume, so communication resources for data transmission are large and computational resources for data analysis are also large. By not using video data, communication resources and computational resources can be reduced. Video data requires calibration to identify individual livestock 50, and calibration is required each time the livestock 50 is moved to a different barn. By not using video data, the labor required for calibration can be reduced.

The number of measuring devices 200 included in the estimation system 10 is not particularly limited. The number of measuring devices 200 may be one or more.

The timing at which the estimation system 10 measures the livestock 50 using the measuring device 200, and the measurement posture of the livestock 50 when the estimation system 10 measures the livestock 50 using the measuring device 200, may be measurement timing and measurement posture that provide high repeatability of the measurement data 20. For example, the measurement timing is when the livestock 50 is hungry, just before the livestock 50 is about to eat. Because the livestock 50 moves little and has little content in its digestive organs, it can be expected that the measurement data 20 will have high repeatability. For example, the measurement posture is an upright posture rather than a lying posture. For example, because electricity, etc. emitted from the measuring device 200 is less likely to escape into the ground, it can be expected that the measurement data 20 will have high repeatability.

The estimation device 100 may be connected to the network 90. The estimation device 100 may be wirelessly connected to the network 90. The estimation device 100 may be connected to the network 90 via a wireless base station. The estimation device 100 may be connected to the network 90 via a Wi-Fi (registered trademark) access point. The estimation device 100 may be wired to the network 90.

The measuring device 200 may be wirelessly connected to the network 90. The measuring device 200 may be connected to the network 90 via a wireless base station. The measuring device 200 may be connected to the network 90 via a Wi-Fi (registered trademark) access point.

The network 90 may include a mobile communication network. The mobile communication network may be compliant with 5G (5th Generation). The mobile communication network may be compliant with LTE (Long Term Evolution). The mobile communication network may be compliant with 6G (6th Generation) or later communication systems. The network 90 may include the Internet. The network 90 may include the cloud. The network 90 may include a LAN (Local Area Network).

The measurement data acquisition unit 110 acquires the measurement data 20. The measurement data acquisition unit 110 may acquire the measurement data 20 via the network 90. The measurement data acquisition unit 110 may also acquire the measurement data 20 from the measurement device 200 via short-range wireless communication or the like, without via the network 90.

The learning model storage unit 120 stores a learning model generated by machine learning using learning data including the measurement data 20 and the internal components of the livestock 50. The learning model storage unit 120 may store a learning model that takes as input the measurement data 20 obtained by measuring the inside of the livestock 50 that is the estimation target, and outputs the internal components of the livestock 50.

The estimation unit 130 estimates the internal body components of the target livestock 50 using measurement data 20 obtained by measuring the inside of the livestock 50 and a learning model. The internal body components of the livestock 50 are the types, weights, volumes, and/or proportions of the components that make up the body of the livestock 50. For example, the internal body components are muscle, fat, bone, and internal organs. For example, the internal body components are the weights, volumes, and/or proportions of muscle, fat, bone, and internal organs. For example, the internal body components are the body weight of the livestock 50. For example, the internal body components are the weights of each part of the livestock 50. For example, the internal body components are the weight of the carcass when the livestock 50 is slaughtered. For example, the internal body components are the weights of each part of the carcass when the carcass is butchered. For example, the internal body components are the weights of the meat when each part of the meat is butchered.

The estimation unit 130 may input the measurement data 20 obtained by measuring the inside of the livestock 50 to be estimated, acquired by the measurement data acquisition unit 110, into the learning model stored in the learning model storage unit 120, and output the internal components of the livestock 50. The estimation unit 130 may use the output internal components as the estimation result. For example, the estimation unit 130 may derive the internal components to be used as the estimation result based on the output internal components. For example, the estimation unit 130 may derive the fat ratio based on the output amounts of muscle, fat, bone, and internal organs. For example, the estimation unit 130 may derive the carcass weight based on the output body weight, head weight, tail weight, weight of the tips of the four legs, and internal organ weight.

The estimation unit 130 may estimate the internal components of the livestock 50 by statistical analysis of a dataset including the measurement data 20 and the internal components of the livestock 50. In this case, the estimation device 100 may not be equipped with a learning model storage unit 120. The analysis method used by the estimation unit 130 is not particularly limited. For example, the analysis method may be multiple regression analysis, principal component analysis, principal component regression, etc. The estimation unit 130 may select the type of measurement data 20 to use depending on the type of internal component to be estimated, rather than using the entire dataset. For example, when estimating muscle or fat as the internal component, electrical measurement data may be selected as the measurement data 20. For example, when estimating bone as the internal component, elastic wave measurement data may be selected as the measurement data 20.

The estimation unit 130 may estimate the fat content in the muscle of the livestock 50. For example, the measurement data 20 may include electrical measurement data measured across a muscular part of the livestock 50, and learning data including the fat content in the muscle of the livestock 50 as an internal component may be used to estimate the fat content in the muscle of the livestock 50 by inputting the electrical measurement data measured across the same part of the livestock 50 to be estimated as measurement data 20 into a learning model generated by machine learning. The estimation unit 130 may estimate the fat content in the muscle of each part of the livestock 50. For example, the part of the livestock 50 is a part for each slaughtering method according to the type of livestock 50. For example, if the livestock 50 is a cow, the part of the livestock 50 may be the forepart, loin, ham, rib, etc. For example, if the livestock 50 is a cow, the parts of the livestock 50 include the neck, shoulder loin, shank, shoulder, shoulder belly, sirloin, rib roast, outer thigh, ribeye, inner thigh, ball, and fillet.

The estimation unit 130 may estimate at least one of the carcass weight and meat grade of the livestock 50. For example, the estimation unit 130 may estimate the carcass weight of the livestock 50 to be estimated by inputting the measurement data 20 of the livestock 50 to be estimated into a learning model generated by machine learning using the measurement data 20 of the livestock 50 and learning data including the carcass weight of the livestock 50 as an internal component. For example, the estimation unit 130 may estimate the body weight, head weight, tail weight, weight of the tips of the four legs, weight of the internal organs of the livestock 50 to be estimated by inputting the measurement data 20 of the livestock 50 to be estimated into a learning model generated by machine learning using the measurement data 20 of the livestock 50 and learning data including the body weight, head weight, tail weight, weight of the tips of the four legs, weight of the internal organs, etc. of the livestock 50 to be estimated, and derive the carcass weight by performing calculations on these.

For example, the meat grade of the livestock 50 can be estimated by inputting the measurement data 20 of the livestock 50 to a learning model generated by machine learning using measurement data 20 of the livestock 50 and learning data containing the meat grade of the livestock 50 in internal components. For example, the estimation unit 130 may derive the meat grade based on the output information indicating the grade of the livestock 50 to be estimated. This makes it possible to estimate, for example, the meat grade of the livestock 50 at each growth stage and the weight of the carcass that can actually be sold, allowing fattening farmers to devise feeding methods based on this information. Ultimately, it becomes possible to more effectively produce meat with higher commercial value.

The estimation unit 130 may estimate the internal components of the livestock 50 in a form that corresponds to the distribution stage of the livestock 50. Examples of the form that corresponds to the distribution stage of the livestock 50 include carcass, cuts of meat, and dressed meat.

The estimation unit 130 may output the estimated internal body components. For example, the estimation unit 130 may display the estimated internal body components on a display provided in the estimation device 100. The estimation unit 130 may also transmit the estimated internal body components to a device other than the estimation device 100. For example, the other device may be a smartphone, tablet terminal, PC (Personal Computer), etc. owned by the fattening farmer. The estimation unit 130 may print out the estimated internal body components from a printer or the like provided in the estimation device 100.

Figure 2 schematically shows an example of training data. The training data includes measurement data 20 and corresponding internal components. The measurement data 20 included in the training data may include various types of measurement data 20. For example, the measurement data 20 includes at least one of electrical measurement data, elastic wave measurement data, magnetic field measurement data, and electromagnetic wave measurement data. The measurement data 20 may include multiple types of electrical measurement data, elastic wave measurement data, magnetic field measurement data, and electromagnetic wave measurement data. In the example shown in Figure 2, the measurement data 20 includes electrical resistance values as electrical measurement data and bone conduction vibration values as elastic wave measurement data. The measurement data 20 may include multiple pieces of measurement data 20 measured at different installation positions of the measuring device 200. For example, the measurement data 20 may include electrical measurement data measured by placing the measuring device 200 on both ears of the livestock 50, and electrical measurement data measured by placing the measuring device 200 on one ear and the buttocks of the livestock 50.

The internal body components included in the training data may include various internal body components of the livestock 50. For example, the internal body components include at least one of muscle, fat, bone, and visceral elements. The internal body components may include a combination of muscle, fat, bone, and visceral elements. The example shown in Figure 2 shows the internal body components of a cow at the time of slaughter. In the example shown in Figure 2, the internal body components include body weight immediately before slaughter, carcass weight, carcass ratio, muscle weight, muscle ratio, fat weight, fat ratio, bone weight, bone ratio, visceral weight, and visceral ratio. The internal body components may also include information indicating the meat grade of the livestock 50. In the example shown in Figure 2, the internal body components include carcass grade, yield grade, yield standard value, longissimus thoracis muscle area, meat quality grade, fat marbling, meat color and luster, meat firmness and texture, and fat color and luster and quality.

Figure 3 shows a schematic diagram of an example of training data. In the example shown in Figure 3, the measurement data 20 included in the training data is time-series measurement data 20. The measurement intervals of the time series of the measurement data 20 may be constant. The measurement intervals do not have to be constant. The measurement times of the measurement data 20 may be determined according to the growth stage of the livestock. In the example shown in Figure 3, the measurement times of the measurement data 20 are the rearing period at the breeding farm, the start of fattening period at the fattening farm, the fattening period at the fattening farm, the slaughter decision period, and the slaughter period. Each measurement period may include multiple measurements.

The measurement data acquisition unit 110 may acquire time-series measurement data 20 of the livestock 50 that is the subject of estimation. The estimation unit 130 may estimate the internal body components of the time-series estimation subject livestock 50 by inputting the time-series measurement data 20 acquired by the measurement data acquisition unit 110 into a learning model stored in the learning model storage unit 120. This allows the internal body components to be estimated based on multiple pieces of measurement data 20 measured at different times, which is expected to improve the accuracy of estimating the internal body components.

Figure 4 shows a schematic diagram of an example of an estimation system 10. In the example shown in Figure 4, differences from Figure 1 will be mainly described. In the example shown in Figure 4, the estimation system 10 includes a determination unit 140.

The determination unit 140 may determine whether or not a change in the feeding method for the livestock 50 being estimated is necessary, based on the internal components of the livestock 50 being estimated by the estimation unit 130. For example, the determination unit 140 may determine that a change in the feeding method is unnecessary if the internal components meet a predetermined criterion, and may determine that a change in the feeding method is necessary if the internal components do not meet the predetermined criterion. The predetermined criterion may be a combination of criteria set for multiple internal components. The determination unit 140 may determine that a change in the feeding method is unnecessary if the fat content in the muscle of the livestock 50 is equal to or greater than a predetermined threshold, and may determine that a change in the feeding method is necessary if the fat content is less than the predetermined threshold. The threshold may be set according to the growth stage of the livestock 50.

The determination unit 140 may output the determination result as to whether a change in the feeding method is necessary. The determination unit 140 may output the reason for the determination together with the determination result of the feeding method. If the determination unit 140 determines that a change in the feeding method is necessary, it may also output information on a recommended feeding method. For example, the determination unit 140 outputs the determination result that a change in the feeding method is necessary, the reason for the determination that the fat content in the muscle of the livestock 50 is lower than a predetermined threshold, and a feeding method that increases the feed amount and/or changes the feed type to more nutritious feed. This allows fattening farmers to rationally and efficiently change the feeding method at an appropriate time depending on the fattening status of the livestock 50. This ultimately enables more effective production of meat with higher commercial value. If the determination unit 140 determines that a change in the feeding method is not necessary, it may output a determination result indicating that a change in the feeding method is not necessary. If the determination unit 140 determines that a change in the feeding method is not necessary, it does not have to output the determination result.

The determination unit 140 may determine whether the livestock 50 to be estimated should be slaughtered based on the internal components of the livestock 50 estimated by the estimation unit 130. For example, the determination unit 140 may determine that the livestock 50 can be slaughtered if the internal components meet predetermined standards, and may determine that the livestock 50 should not be slaughtered and should continue to be fattened if the internal components do not meet the predetermined standards. The predetermined standards may be a combination of standards set for multiple internal components. For example, the determination unit 140 may determine that the livestock 50 can be slaughtered if the weight of the livestock 50 meets predetermined standards and the grade of the meat of the livestock 50 is a predetermined grade or higher, and may determine that the livestock 50 should not be slaughtered and should continue to be fattened if the internal components do not meet the predetermined standards.

The determination unit 140 may output the determination result of whether or not the animal should be slaughtered. The determination unit 140 may also output the estimated internal components together with the determination result of whether or not the animal should be slaughtered. This allows, for example, fattening farmers to know the carcass weight and meat grade of the livestock 50 before shipping the livestock 50. Ultimately, it allows them to estimate expected sales in advance.

As illustrated in FIG. 4, the determination unit 140 may be located outside the estimation device 100. For example, a device other than the estimation device 100 may include the determination unit 140, and the device may communicate with the estimation device 100 via the network 90. The estimation device 100 may also include the determination unit 140.

When the determination unit 140 is located outside the estimation device 100, the determination unit 140 may transmit and output the determination result, etc. to the estimation device 100. The determination unit 140 may also transmit and output the determination result, etc. to a device other than the estimation device 100. For example, the other device is a smartphone, tablet terminal, PC, etc. owned by the fattening farmer. When the estimation device 100 is equipped with the determination unit 140, the determination unit 140, for example, displays and outputs the determination result on a display equipped in the estimation device 100. The determination unit 140 may also transmit and output the determination result to a device other than the estimation device 100. The determination unit 140 may print out the determination result from a printer, etc. equipped in the estimation device 100.

In the example shown in FIG. 4, the estimation system 10 includes a learning model generation unit 150. The learning model generation unit 150 generates a learning model. The learning model generation unit 150 may generate the learning model by machine learning using learning data including measurement data 20 obtained by measuring the inside of the livestock 50 and the internal components of the livestock 50. The learning model may be a learning model that receives the measurement data 20 of the livestock 50 to be estimated as input and outputs the internal components of the livestock 50. The measurement data 20 of the learning data may include electrical measurement data, elastic wave measurement data, magnetic field measurement data, and electromagnetic wave measurement data. The internal components of the learning data may include muscle, fat, bone, and internal organs. The internal components of the learning data may include the carcass weight of the livestock 50 and the meat grade of the livestock 50. According to the learning model, the internal components of the livestock 50 can be estimated from the measurement data 20 of the livestock 50 without actually slaughtering the livestock 50. This allows, for example, the grade of meat at each stage of livestock 50 growth to be estimated, allowing fattening farmers to devise feeding methods. Ultimately, this makes it possible to more effectively produce meat with higher commercial value.

The learning model generation unit 150 may be located outside the estimation device 100, as illustrated in FIG. 4. For example, a device other than the estimation device 100 may include the learning model generation unit 150, and the device may communicate with the estimation device 100 via the network 90. The estimation device 100 may also include the learning model generation unit 150.

The learning data may include attribute data of the livestock 50. The attribute data may include, for example, at least one of the breed, pedigree, sex, breeding farm, date of birth, age at slaughter, and medical history of the livestock 50. For example, the attribute data includes the breed of the livestock 50. For example, the attribute data includes the pedigree of the livestock 50. For example, the attribute data includes the sex of the livestock 50. For example, the attribute data includes the breeding farm of the livestock 50. For example, the attribute data includes the date of birth of the livestock 50. For example, the attribute data includes the age at slaughter of the livestock 50. For example, the attribute data includes the medical history of the livestock 50. The learning model storage unit 120 may store a learning model generated by machine learning using learning data including the measurement data 20, internal components, and attribute data of the livestock 50.

In the example shown in FIG. 4, the estimation system 10 includes an attribute data acquisition unit 160. The attribute data acquisition unit 160 may acquire attribute data of the livestock 50 to be estimated. The estimation unit 130 may estimate the internal components of the livestock 50 to be estimated by inputting the measurement data 20 acquired by the measurement data acquisition unit 110 and the attribute data acquired by the attribute data acquisition unit 160 into a learning model stored in the learning model storage unit 120.

Figure 5 is an explanatory diagram illustrating an example of the processing flow by the estimation system 10. Here, we will explain the process in which the estimation system 10 uses a learning model to estimate the internal components of the livestock 50 that is the estimation target, and determines whether or not the feeding method needs to be changed based on the estimation results. We will explain the starting state as a state in which a learning model has already been prepared and the learning model storage unit 120 has finished storing the learning model.

In step (sometimes abbreviated as S) 102, the measurement data acquisition unit 110 acquires measurement data 20 of the livestock 50 that is the subject of estimation. The measurement data acquisition unit 110 receives the measurement data 20 from one or more measurement devices 200.

In S104, the estimation unit 130 estimates the internal components of the livestock 50 being estimated using the measurement data 20 acquired by the measurement data acquisition unit 110 in S102 and the learning model stored in the learning model storage unit 120.

In S106, the determination unit 140 determines whether or not a change in the feeding method for the livestock 50 being estimated is necessary, based on the internal components estimated by the estimation unit 130 in S104. If it is determined that a change in the feeding method is necessary, the process proceeds to S108; if it is determined that a change in the feeding method is not necessary, the process proceeds to S110.

In S108, the estimation unit 130 outputs a determination result indicating that a change in feeding method is necessary.

In S110, the estimation unit 130 does not output a determination result. The estimation unit 130 may output a determination result indicating that a change in the feeding method is not necessary.

Figure 6 shows a schematic diagram of an example of the hardware configuration of a computer 1200 that functions as the estimation system 10 or estimation device 100. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of an apparatus according to the present embodiment, or to perform operations or one or more "parts" associated with an apparatus according to the present embodiment, and/or to perform a process or steps of the process according to the present embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

The computer 1200 according to this embodiment includes a CPU 1212, RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input/output units such as a communications interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input/output controller 1220. The DVD drive may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid-state drive, or the like. The computer 1200 also includes a ROM 1230 and legacy input/output units such as a keyboard, which are connected to the input/output controller 1220 via an input/output chip 1240.

The CPU 1212 operates according to programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer provided in the RAM 1214 or into the graphics controller itself, and causes the image data to be displayed on the display device 1218.

The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive reads programs or data from a DVD-ROM or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and/or writes programs and data to an IC card.

ROM 1230 stores therein a boot program and the like that is executed by computer 1200 upon activation, and/or programs that depend on the hardware of computer 1200. I/O chip 1240 may also connect various I/O units to I/O controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

The programs are provided on a computer-readable storage medium such as a DVD-ROM or IC card. The programs are read from the computer-readable storage medium, installed in storage device 1224, RAM 1214, or ROM 1230, which are also examples of computer-readable storage media, and executed by CPU 1212. The information processing described in these programs is read by computer 1200, resulting in cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing the operation or processing of information in accordance with the use of computer 1200.

For example, when communication is performed between computer 1200 and an external device, CPU 1212 may execute a communication program loaded into RAM 1214 and instruct communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of CPU 1212, communication interface 1222 reads transmission data stored in a transmission buffer area provided in RAM 1214, storage device 1224, DVD-ROM, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

The CPU 1212 may also cause all or a necessary portion of a file or database stored on an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), an IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write the processed data back to the external recording medium.

Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. CPU 1212 may perform various types of processing on data read from RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search/replacement, etc., as described throughout this disclosure and specified by the program's instruction sequence, and write the results back to RAM 1214. CPU 1212 may also search for information in files, databases, etc. on the recording medium. For example, if multiple entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored on the recording medium, CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

The programs or software modules described above may be stored on computer-readable storage media on or near computer 1200. Recording media such as a hard disk or RAM provided within a server system connected to a dedicated communications network or the Internet can also be used as computer-readable storage media, thereby providing the programs to computer 1200 via the network.

The blocks in the flowcharts and block diagrams in this embodiment may represent stages of a process in which an operation is performed or "parts" of a device responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and/or a processor provided with computer-readable instructions stored on a computer-readable storage medium. Dedicated circuitry may include digital and/or analog hardware circuitry, and may include integrated circuits (ICs) and/or discrete circuits. Programmable circuitry may include reconfigurable hardware circuitry including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements, such as field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs).

A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device. As a result, a computer-readable storage medium having instructions stored thereon comprises an article of manufacture, including instructions that can be executed to create means for performing the operations specified in the flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray disc, memory stick, integrated circuit card, etc.

The computer-readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages such as the "C" programming language or similar programming languages.

The computer-readable instructions may be provided to a general-purpose computer, a special-purpose computer, or another programmable data processing device processor or programmable circuit, either locally or via a local area network (LAN) or a wide area network (WAN) such as the Internet, so that the processor or programmable circuit of the programmable data processing device, such as a computer, executes the computer-readable instructions to generate means for performing the operations specified in the flowchart or block diagram. Here, the computer may be a personal computer (PC), tablet computer, smartphone, workstation, server computer, general-purpose computer, special-purpose computer, etc., or may be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system, and is a broad definition of computer. In a distributed computing system, multiple computers collectively execute a program by each executing a portion of the program and passing data between computers as needed during program execution.

Examples of processors include computer processors, central processing units, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc. A computer may have one processor or multiple processors. In a multiprocessor system with multiple processors, each processor executes a portion of a program and passes data between processors as needed during program execution, allowing the multiple processors to collectively execute the program. For example, in multitasking, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at each time slice. In this case, which portion of a program each processor executes changes dynamically. Which portion of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

The present invention has been described above using embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be clear to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

The order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before" or "prior to," and it should be noted that processes can be performed in any order unless the output of a previous process is used in a subsequent process. Even if the operational flow in the claims, specifications, and drawings is described using terms such as "first," "next," etc. for convenience, this does not mean that the processes must be performed in that order.

10 Estimation system, 20 Measurement data, 50 Livestock, 90 Network, 100 Estimation device, 110 Measurement data acquisition unit, 120 Learning model storage unit, 130 Estimation unit, 140 Determination unit, 150 Learning model generation unit, 160 Attribute data acquisition unit, 200 Measurement device, 1200 Computer, 1210 Host controller, 1212 CPU, 1214 RAM, 1216 Graphics controller, 1218 Display device, 1220 Input/output controller, 1222 Communication interface, 1224 Storage device, 1230 ROM, 1240 Input/output chip

Claims (17)

a learning model storage unit that stores a learning model generated by machine learning using learning data including measurement data obtained by measuring the inside of the livestock and internal components of the livestock;
a measurement data acquisition unit that acquires measurement data obtained by measuring the inside of the livestock that is the subject of estimation;
an estimation unit that estimates the internal components of the estimation target livestock using the measurement data acquired by the measurement data acquisition unit and the learning model,
An estimation system, wherein the measurement data includes at least one of electrical measurement data generated by applying electricity to the body of the livestock and electromagnetic wave measurement data generated by irradiating the body of the livestock with electromagnetic waves. The estimation system of claim 1, wherein the measurement data includes a plurality of the electrical measurement data, magnetic field measurement data generated by applying a magnetic field inside the livestock's body, the electromagnetic wave measurement data, and elastic wave measurement data generated by irradiating the livestock's body with elastic waves. The estimation system of claim 1, wherein the internal body components include at least one of muscle, fat, bone, and visceral elements. The estimation system described in claim 1, wherein the estimation unit estimates the fat content in the muscle of the livestock. The estimation system described in claim 1, wherein the estimation unit estimates at least one of the weight of the carcass of the livestock being estimated and the grade of meat from the livestock being estimated. The estimation system described in any one of claims 1 to 5 further comprises a learning model generation unit that generates a learning model by machine learning using learning data including the measurement data obtained by measuring the inside of the livestock and the internal components of the livestock. a learning model storage unit that stores a learning model generated by machine learning using learning data including measurement data obtained by measuring the inside of the livestock and internal components of the livestock;
a measurement data acquisition unit that acquires measurement data obtained by measuring the inside of the livestock that is the subject of estimation;
an estimation unit that estimates the internal components of the livestock to be estimated using the measurement data acquired by the measurement data acquisition unit and the learning model;
and a determination unit that determines whether or not the livestock to be estimated should be slaughtered based on the internal components of the livestock to be estimated. a learning model storage unit that stores a learning model generated by machine learning using learning data including measurement data obtained by measuring the inside of the livestock and internal components of the livestock;
a measurement data acquisition unit that acquires measurement data obtained by measuring the inside of the livestock that is the subject of estimation;
an estimation unit that estimates the internal components of the estimation target livestock using the measurement data acquired by the measurement data acquisition unit and the learning model,
the measurement data acquisition unit acquires the measurement data in time series,
the estimation unit estimates the internal components of the estimation target livestock in a time series by inputting the time series measurement data into the learning model;
The estimation system further comprises a determination unit that determines whether or not a change in a feeding method for the estimation target livestock is necessary based on the internal body components of the time series estimated by the estimation unit. a learning model storage unit that stores a learning model generated by machine learning using learning data including measurement data obtained by measuring the inside of the livestock and internal components of the livestock;
a measurement data acquisition unit that acquires measurement data obtained by measuring the inside of the livestock that is the subject of estimation;
an attribute data acquisition unit that acquires attribute data of the livestock to be estimated;
an estimation unit that estimates the internal components of the estimation target livestock using the measurement data acquired by the measurement data acquisition unit and the learning model,
the learning model storage unit stores the learning model generated by machine learning using learning data including the measurement data and the internal components of the livestock and attribute data of the livestock;
The estimation unit estimates the internal components of the livestock to be estimated by inputting the measurement data acquired by the measurement data acquisition unit and the attribute data acquired by the attribute data acquisition unit into the learning model. a learning data storage unit that stores learning data including measurement data obtained by measuring the inside of the livestock body and the internal components of the livestock body;
a learning model generation unit that generates a learning model by machine learning using the learning data stored in the learning data storage unit, using measurement data that measures the inside of the livestock as an input and outputting the internal components of the livestock;
Equipped with
A generation system in which the measurement data includes at least one of electrical measurement data generated by applying electricity to the body of the livestock and electromagnetic wave measurement data generated by irradiating electromagnetic waves into the body of the livestock. 1. A computer-implemented estimation method comprising:
a measurement data acquisition stage for acquiring measurement data obtained by measuring the inside of the livestock subject to estimation;
a learning model generated by machine learning using learning data including measurement data obtained by measuring the inside of the livestock and the internal components of the livestock, and an estimation step of estimating the internal components of the livestock to be estimated using the measurement data obtained in the measurement data acquisition step,
An estimation method in which the measurement data includes at least one of electrical measurement data generated by applying electricity to the body of the livestock and electromagnetic wave measurement data generated by irradiating the body of the livestock with electromagnetic waves. 1. A computer-implemented estimation method comprising:
a measurement data acquisition stage for acquiring measurement data obtained by measuring the inside of the livestock subject to estimation;
an estimation step of estimating the internal components of the estimation target livestock using a learning model generated by machine learning using learning data including measurement data obtained by measuring the inside of the livestock and the internal components of the livestock, and the measurement data acquired in the measurement data acquisition step;
and a determination step of determining whether or not the livestock to be estimated should be slaughtered based on the internal components of the livestock to be estimated. 1. A computer-implemented estimation method comprising:
a measurement data acquisition stage for acquiring measurement data obtained by measuring the inside of the livestock subject to estimation;
a learning model generated by machine learning using learning data including measurement data obtained by measuring the inside of the livestock and the internal components of the livestock, and an estimation step of estimating the internal components of the livestock to be estimated using the measurement data obtained in the measurement data acquisition step,
the measurement data acquisition step includes a step of acquiring the measurement data in time series,
The estimation step includes a step of estimating the internal components of the estimation target livestock over time by inputting the time-series measurement data into the learning model,
The estimation method further comprises a determination step of determining whether or not a change in the feeding method for the livestock being estimated is necessary based on the internal components of the time series estimated in the estimation step. 1. A computer-implemented estimation method comprising:
a measurement data acquisition stage for acquiring measurement data obtained by measuring the inside of the livestock subject to estimation;
an attribute data acquisition step of acquiring attribute data of the livestock to be estimated;
a learning model generated by machine learning using learning data including measurement data obtained by measuring the inside of the livestock and the internal components of the livestock, and an estimation step of estimating the internal components of the livestock to be estimated using the measurement data obtained in the measurement data acquisition step,
The estimation step includes a step of estimating the internal components of the livestock to be estimated by inputting the measurement data acquired in the measurement data acquisition step and the attribute data acquired in the attribute data acquisition step into the learning model generated by machine learning using learning data including the measurement data and the internal components of the livestock and attribute data of the livestock. A program for causing a computer to execute the estimation method according to any one of claims 11 to 14 . a learning model generation step of generating a learning model that uses the measurement data that measures the inside of the livestock as input and outputs the internal components of the livestock by machine learning using the learning data stored in a learning data storage unit that stores the measurement data that measures the inside of the livestock and the internal components of the livestock,
A generation method in which the measurement data includes at least one of electrical measurement data generated by applying electricity to the body of the livestock and electromagnetic wave measurement data generated by irradiating electromagnetic waves into the body of the livestock. A program for causing a computer to execute the generating method according to claim 16.