JP2023059706A - Milk secretion amount calculation system - Google Patents

Abstract

To provide a milk secretion amount calculation system for calculating a milk secretion amount after a predicted start date on the basis of data before the predicted start date.SOLUTION: The milk secretion amount calculation system includes a memory for storing farm data, an interpolation formula creating part for creating an interpolation formula for interpolating a relationship between the number of days after parturition for a certain period in the farm data prior to the predicted starting date and the actual milk amount, a regression formula creating part for creating a regression formula for calculating a herd estimated milk secretion amount for each of the number of days after parturition, with the interpolated milk amount at the specific number of days after postpartum calculated from the interpolation formula as the objective variable, and with at least one factor parameter selected from the farm data as the explanatory variable, and a control device having a herd estimated milk secretion amount calculation part including a herd regression formula calculation part for calculating an estimated milk secretion amount by substituting the value of the explanatory variable assumed on the predicted date into the regression formula corresponding to the postpartum period on the predicted date.SELECTED DRAWING: Figure 1

Description

The present invention relates to a milk yield calculation system that estimates the milk yield of a dairy cow according to the number of days after parturition based on past data.

For dairy farms, fluctuations in milk production are a major problem that directly affects ranch management. In order to obtain more milk, efforts have been made to improve the composition of feed, improve the breeding environment, and reduce the stress on dairy cows.

On the other hand, such improvements depend largely on individual farms, making comparisons with other farms difficult. Dairy cows are generally sensitive to heat, so milk production is thought to be higher in regions with higher latitudes, but it is not clear to what extent differences in climate affect milk production.

Furthermore, since there are so many factors that can affect milk production, we currently rely on experience to determine which factors have a large impact on milk production in certain cases. be.

Therefore, a system that can estimate the amount of milk produced by inputting conceivable factors will provide a great guideline for dairy farm management.

Patent Literature 1 provides a system for grasping dairy cows in groups by lactation stage or breeding stage using an information terminal.

Moreover, Patent Document 2 discloses that a lactation curve is calculated by a regression equation from the past milk volume for each individual cow.

JP 2020-156359 A Japanese Patent Application Laid-Open No. 2020-020707

Patent Document 1 attempts to grasp the current situation of dairy cows, and Patent Document 2 attempts to estimate future milk production from past milk production. However, it is not possible to investigate the factors for increasing the milk production of dairy cows.

Although the physiological theory is understood that the reduction of oxytocin and the secretion of adrenaline due to high temperature and stress affect milk production, what kind of rearing environment and cow's own condition are comfortable conditions for dairy cows? is difficult for humans to understand. Therefore, it is considered useful to collect many events (information) and analyze factors to increase milk production.

Here, the large amount of information corresponds to the rearing environment, feed composition, and individual information of the dairy cows in as many farms as possible. This information is updated daily. Also, in order to ensure diversity of information, it is desirable to have information on different regions. Therefore, it is preferable to have data from many farms available.

However, it is extremely difficult to regularly collect data from multiple farms with different scales and circumstances. This is because, depending on the ranch, various data may be quantified every day, and data may not be collected unless every few days.

In particular, the so-called lactation curve expresses the relationship between the number of days after parturition and the amount of milk, but it is difficult to imagine a pasture with dairy cows with a one-day difference in the number of days after parturition unless it is very large. Therefore, even data on the amount of lactation that can actually be collected has the problem that it cannot be uniformly analyzed because omissions occur or the range of information (range of days after delivery) is different.

In addition, future prediction of milk production and predicted sales are important for dairy farm management. However, estimation of the future milk yield of multiple dairy cows whose post-partum days change daily has not been done much in the past.

The milk production calculation system according to the present invention has been conceived in view of the above problems, and even if the collected information related to the milk production does not match the same range, it is possible to analyze factors and The present invention provides a system for presenting future predicted values of quantities.

More specifically, the milk production calculation system according to the present invention includes:
Based on the pasture data including the number of days after calving and actual milk volume of each individual cow that constitutes the cattle herd before the prediction start date and climate data, the milk production of the individual cow on the prediction date after the prediction start date is calculated. A milk production calculation system that calculates as a group estimated milk production,
a memory for accumulating the ranch data;
an interpolation formula creation unit that creates an interpolation formula for interpolating the relationship between the number of days after parturition for a certain period in the ranch data prior to the predicted start date and the actual milk yield;
The interpolated milk yield at the specific postpartum calculated from the interpolation formula is used as an objective variable, and at least one factor parameter selected from the ranch data is used as an explanatory variable, and the herd estimated milk yield for each of the postpartum days is used. a regression formula creating unit for creating a regression formula for calculating
In the regression equation corresponding to the number of days postpartum on the predicted date,
A control device having a herd estimated milk production calculation unit including a herd regression formula calculation unit that calculates the herd estimated milk production by substituting the values of the explanatory variables assumed on the prediction date. do.

The milk production calculation system according to the present invention can obtain a certain range of milk production even on a daily basis by interpolating the collected data on milk production, so it is possible to estimate the factors affecting the milk production. give the effect of being useful for

In addition, if the influence of predictable factors such as temperature on milk production is known, it will be possible to predict future milk production and obtain important guidelines for dairy farm management.

It is a figure which shows the structure of the milk production calculation system which concerns on this invention. It is a figure which shows the whole (main) flow of a milk production calculation system. It is a figure which illustrates the output which a milk production calculation system calculates. FIG. 4 is a diagram showing a flow of steps for calculating an estimated lactation amount. It is a figure explaining creation of an interpolation formula. It is a figure which shows the flow which creates an interpolation formula. It is a figure explaining creation of a regression equation. It is a figure which shows the flow of the process of creating a regression equation. It is the figure which expanded the curve which concerns on the estimated milk production of Fig.3 (a). FIG. 5 is a diagram showing the process of factor analysis in step S206 of FIG. 4; FIG. 10 is a diagram showing how the measured milk yield for a certain period of time is compared with the estimated milk yield EY obtained from the regression equation in the factor analysis. It is a figure which shows the flow of a cattle herd regression formula calculation. It is a figure explaining the cow herd estimated total milk production. It is a figure which shows the flow of a cow herd total regression formula calculation. FIG. 10 is a diagram showing a flow for calculating predicted herd sales having an estimated herd total sales calculation unit using an estimated total milk yield of a herd. FIG. 10 is a diagram showing a flow for calculating predicted herd sales having an estimated herd total sales proceeds calculation unit using herd estimated milk production for each individual cow. It is a figure explaining a cow herd dry milk day. FIG. 10 is a diagram showing a flow of herd dry-milk cow determination for comparing the herd estimated lactation amount and the dry-milk reference value for each individual cow. FIG. 10 is a diagram showing a flow of determination of dry-milk cows in a herd by comparing the dry-milk days of the herd and the number of days after parturition for each individual cow. It is a figure explaining the calculation procedure of individual estimated lactation amount. It is a figure explaining an individual estimated total milk production. FIG. 10 is a diagram showing a flow for calculating an individual estimated lactation amount; It is a figure which shows the flow of individual regression formula calculation. It is a figure which shows the flow of an individual total regression formula calculation. FIG. 10 is a diagram showing a flow for calculating estimated individual sales proceeds having an estimated individual total sales proceeds calculation unit using estimated total milk production for individuals. FIG. 10 is a diagram showing a flow for calculating predicted cattle herd sales having an individual estimated total sales revenue calculation unit using an individual estimated milk yield for each individual cow. It is a figure explaining an individual dry-milk day. FIG. 10 is a diagram showing a flow of determination of an individual dry-milk cow, which compares the estimated individual milk yield of each individual cow with the dry-milk reference value. FIG. 10 is a diagram showing the flow of individual dry-milk cow determination for comparing the individual dry-milk day of each individual cow and the number of days after parturition of each individual cow. FIG. 10 is a diagram showing that the milk production calculation system is used in an actual farm, and the estimated milk production can be multiple-regressed using THI and sunshine hours as factor parameters.

DESCRIPTION OF THE PREFERRED EMBODIMENTS A milk production calculation system according to the present invention will be described below with reference to the drawings. In addition, the following description illustrates one embodiment and one example of the present invention, and the present invention is not limited to the following description. The following description can be modified without departing from the spirit of the invention.

FIG. 1 shows the configuration of a milk production calculation system according to the present invention. A milk production calculation system 1 according to the present invention comprises a terminal 10 , a main body 12 and a memory 14 . The terminal 10 itself can be composed of a computer having a CPU (Central Processor Unit), a memory, and a display screen, and can include a mobile communication terminal (so-called smart phone, etc.).

The main body 12 is composed of a CPU (Central Processor Unit). A single CPU may be used, or a plurality of CPUs may be connected. Since the main body 12 is a device that provides services, it may be called a server. A memory 14 is a memory used by the main body 12 . A CPU may also be referred to as a controller. The body 12 is thus a control device. Also, the main body 12 may have an input section 12 a that receives a signal from the terminal 10 . That is, the main body 12 receives commands and numerical values specified by the input section 12a.

The main body 12 and the terminal 10 are communicably connected. Communication may be wired or wireless. Terminal 10 can also be called a client. The terminal 10 is preferably installed in a ranch 16 (ranches 16A, 16B, and 16C are illustrated here) where dairy cows are actually raised. Here, "installation" may mean that the terminal 10 is physically installed on the ranch 16, or that the person in charge or person in charge of the ranch 16 owns the mobile communication terminal. Of course, terminal 10 may be installed at a location other than ranch 16 . Moreover, the ranch 16 only needs to raise dairy cows.

A plurality of farms 16 may be connected to the main body 12 . This is because the milk production calculation system 1 collects a large amount of data relating to the milk production and analyzes them to calculate the milk production, so it is desirable to collect a large amount of data. Also, the main body 12 may be connected to the external information 18 via the Internet. This is because not only data obtained from the ranch 16 but also nationwide weather information can be obtained via the Internet and used.

In this way, the milk production calculation system 1 collects a large amount of data from various locations and analyzes the collected data to calculate the milk production. could be. That is, the milk production calculation system 1 may be configured in the cloud.

Therefore, as a form of cloud for implementing the milk production calculation system, a representative SaaS (Software as a Service) is suitable, but PaaS (Platform as a Service), HaaS (Hardware as a Service) or IaaS (Infrastructure as a Service).

A milk yield calculation system 1 according to the present invention treats a group of a plurality of dairy cows as one cow herd, and predicts the milk yield of the herd. In addition, individual dairy cows belonging to the herd are defined as individual cows (hereinafter also simply referred to as “individuals”), and the milk production of the individual cows is also predicted. Further, from these predicted milk yields, it is also possible to estimate sales revenue, dry days and dry cows. Dairy cows begin to secrete milk after parturition, but the amount of milk produced decreases after a considerable number of days after parturition. Such cows are allowed to rest until the next calving. This is because the dairy cow cannot expect to produce milk after the dry day until the next birth. This is called a "dry cow". A "dry day" is a day on which a dairy cow is treated as a dry cow.

More specifically, when the value of the factor parameter P (explanatory variable) assumed for a future prediction date is input from the terminal 10 from the prediction start date, the milk production calculation system 1 calculates the number of days after delivery in the prediction date or the prediction period. A herd estimated milk yield ^N EY (kg) or an individual estimated milk yield ^N DEY (kg) that can be milked from a cow on day N can be obtained. In addition, these are also simply referred to as herd estimated milk yield EY and individual estimated milk yield DEY, omitting the number of days after parturition N. The estimated herd milk yield EY or the individual estimated milk yield DEY is collectively referred to as “estimated herd milk yield ^NEY (kg), etc.” or “estimated herd milk yield EY, etc.”.

The herd estimated milk yield EY is the estimated milk yield of one dairy cow that is referred to as the herd. For the milk production of all individual cows belonging to the herd ("estimated herd total milk production" to be described later), it is necessary to obtain the sum of herd estimated milk production EY in the number of days after calving for each individual cow.

Here, the prediction start date is the date on which the prediction is made. In addition, it is not excluded that the prediction starting date is a week or a month. The normal prediction start date may be the date on which the prediction is made, but it may also be a past day or period. The forecast date is a date in the future from the forecast start date, and is the date on which the estimated cow herd milk yield ^NEY (kg) or the like is to be forecast. Also, the prediction period is a period in the future from the start date of prediction, and is a period in which the estimated cow herd milk yield ^NEY (kg) or the like is to be predicted. Any reference to the forecast date may include the forecast period.

In addition, the factor parameter P is the one that best explains the milk production among the pasture data including climate data, individual data such as the weight of the dairy cow itself, the amount of feed intake, and feed data such as the type of feed that the cow is ingested. It is an item that can be done. This factor parameter P may be data obtained by processing the data of directly measurable items other than directly measurable items. This factor parameter P can be found in the milk production calculation system 1 .

Climate data includes sunrise time, sunset time, temperature, humidity, sunshine duration, amount of solar radiation, wind direction, wind speed, and the like. In addition, the temperature in the barn and the humidity in the barn may be included. Moreover, these processed data, such as THI (Temperature Humidity Index), may be included. In addition, THI is an index represented by (1) Formula as an example.

Also, the climate data may be not only the climate inside and outside the barn, but also the climate of a square kilometer of the ranch, the climate of the region, or climate data from a national weather forecast service.

Individual data is data of the dairy cow itself. Specifically, the registration number, pedigree, number of births, number of days after parturition, milk yield, body weight, medical history, owner, place of breeding, and the like.

The feed data includes the type, composition, number of times, etc., of the feed given in the past.

[Basic data]
In this way, the factor parameter P is a concept that includes data before the prediction start date. The data before the prediction start date used for estimation is called "basic data". "Basic data" is data for creating a regression equation for prediction. It can also be said to be part of the ranch data. The milk production calculation system 1 according to the present invention obtains a regression formula that can explain the milk production of a certain dairy cow group or individual cow as an objective variable based on the factor parameter P before the prediction start date, and predicts based on the regression formula. By applying the factor parameter P (explanatory variable) assumed on the forecast date after the initial calculation date, the estimated milk production amount ^N EY that can be milked from the dairy cow several N days after calving in the forecast date after the forecast initial date or the forecast period. (kg) or the like can be obtained.

A terminal 10 installed in a ranch 16 transmits individual data relating to dairy cows in the ranch, feed data actually ingested, and daily climate data to the main body 12 as ranch data FD. The main body 12 stores these ranch data in the memory 14 . Then, when the predicted starting date for calculation is input from the terminal 10, an equation for calculating the estimated milk yield of the herd and the like is obtained based on the factor parameter P prior to the predicted starting date for calculation. Subsequently, the herd estimated milk production ^NEY corresponding to the number of days after parturition N is calculated and displayed on the terminal 10 according to the factor parameter P assumed in the prediction date or prediction period to be input.

In addition, the factor parameter P (explanatory variable) assumed on the prediction date after the prediction start date input when calculating the estimated milk production ^NEY etc. of the cow herd according to the number of days after calving N is expressed in the above regression formula. It is the value of the input factor parameter P and the value of the explanatory variable of the regression equation. The value of this factor parameter P (explanatory variable) may be not only the value published in the weather forecast, etc., but also the value of the corresponding day or period in the usual year or the past, and some value calculated based on them. .

That is, past values can be used for the factor parameter P, which is an explanatory variable. This is because the climate of each year is not expected to change significantly throughout the four seasons, so the forecast dates and forecast periods after the forecast start date are not significantly different from the days and periods corresponding to the forecast dates of the previous year or earlier.

Note that the main body 12 may acquire climate data from the external information 18 . If it is a closed-type barn, the environment inside the barn is controlled and it is easy to transmit data. However, in the case of an open-type barn, it is difficult to obtain the wind speed inside the barn on that day. In such cases, external climate data can be used as a reference.

Various climate data are provided and can be used effectively. Also, the ranch data FD may be transmitted to the main body 12 by a method other than the terminal 10 . Of course, the terminal 10 that transmits the ranch data FD to the main body 12 and the terminal 10 that inputs the factor parameter P and calculates the milk production may be separate.

FIG. 2 shows the overall (main) flow of the milk production calculation system 1 . It is assumed that each ranch appropriately transmits the ranch data FD to the main body 12 . It is also assumed that dairy cows belonging to a herd that serves as a handling unit are registered in advance.

The milk production calculation system 1 performs a process of calculating an estimated cow herd milk production EY in response to inputs such as calculation conditions and factor parameters P (including explanatory variables) input from a terminal 10 or the like, a process of calculating a cow herd forecast sales E$ determining the herd dry cow DC; computing the individual estimated milk yield DEY; computing the estimated individual sales DE$; and determining the individual dry cow DDC.

Further, there may be a step of calculating the estimated total cow milk production SUM _EY and the estimated total individual milk production SUM _DEY . In addition, the process of calculating the estimated herd sales E$ and the process of calculating the estimated individual sales DE$ include the process of calculating the estimated individual sales of the herd EI$ and the estimated total sales of the herd ΣE$. It can include a step of calculating, a step of calculating individual estimated sales DEI$, a step of calculating individual estimated total sales ΣDE$, and the like.

These results may be returned to terminal 10 . Also, these results may be placed on a specific memory on the net. The terminal 10 can display these results. The process of calculating these can be called the menu of the main flow. That is, the terminal 10 can instruct these calculations.

It should be noted that most of the configuration of the present invention is implemented by software. Therefore, the "process" of processing refers to a group of processes, and it may be considered that the main body 12 has a "unit" that executes the "process". Specifically, the main body 12 (control device) includes a herd estimated milk production calculation unit, a herd forecast sales revenue calculation unit, a herd dry cow determination unit, an individual estimated milk production calculation unit, an individual forecast sales revenue calculation unit, an individual It can be said that there is a dry cow judgment part. In addition, the herd estimated total milk production calculation part, individual estimated total milk production calculation part, herd estimated individual sales proceeds calculation part, herd estimated total sales proceeds calculation part, individual estimated sales proceeds calculation part, individual estimated total sales proceeds calculation part can be said to exist.

In addition, if there is a set of lower processes in these process steps, it may also be called a "part". For example, the herd estimated milk yield calculation unit includes a step of creating an interpolation formula and a step of creating a regression formula, which can be called an "interpolation formula creation unit" and a "regression formula creation unit", respectively. In addition, when the value of the factor parameter P (explanatory variable) is substituted into the obtained regression equation, there is a step (step S210) of specifically calculating the estimated milk yield of the herd. can call In addition, the milk production calculation system 1 only needs to have at least a step (estimated herd milk production calculator) of calculating the estimated cow milk production EY.

<Lactation calculation system>
Referring to FIG. 2, when the milk production calculation system 1 is started (step S100), a termination determination is made (step S102). The end determination may be a termination instruction from the terminal 10 or disconnection of communication between the main body 12 and the terminal 10 . When ending (Y branch of step S102), it ends (step S104). If not completed (N branch of step S102), the process proceeds to the next step.

Next, it is selected whether to calculate the herd estimated milk yield EY or to calculate the individual estimated milk yield DEY (steps S106 and S108). If each option is selected (Y branch), the process proceeds to the corresponding process, and if not selected (N branch), the process proceeds to the next step. If the individual estimated milk yield DEY is not calculated in step S108 (N branch in step S108), the process returns to end determination (step S102).

If the estimated herd milk yield EY is selected (Y branch in step S106), the estimated herd milk yield EY is calculated (step S110). After that, it is selected whether to calculate the herd forecasted sales E$ (step S112) or determine the herd dry cow DC (step S114). When each process is selected (Y branch in step S112 and step S114), the herd forecast sales revenue E$ is calculated and the herd dry cow DC is determined (step S116 and step S118). After that, the processing moves to the selection of the individual estimated milk yield DEY (step S108).

If the estimated individual milk yield DEY is selected (Y branch in step S108), the estimated individual milk yield DEY is calculated (step S120). After that, it is selected whether to calculate the individual predicted sales amount DE$ (step S122) or determine the individual dry cow DDC (step S124). When each process is selected (Y branch in step S122 and step S124), individual predicted sales DE$ is calculated and individual dry cow DDC is determined (step S126 and step S128). After that, the processing moves to end determination (step S102).

FIG. 3 shows respective output examples. FIG. 3(a) is an output example of the herd estimated milk yield EY. The horizontal axis is the number of days after parturition (days), and the vertical axis is the amount of milk (here, the unit is "kg"). Under a certain factor parameter P (eg temperature), the herd estimated milk yield EY can be shown for the number of days after calving. The figure shows the herd estimated lactation curves M when the temperature is T1°C and when the temperature is T2°C. The herd estimated lactation curve M provided by the milk production calculation system 1 of the present invention is at least a set of daily calculated values (herd estimated milk production EY). These calculated values may be connected by straight lines or curves. A herd-estimated lactation curve formed from the herd-estimated milk yield EY is denoted by symbol M. In other words, the estimated herd lactation curve M is obtained by plotting the estimated herd lactation amount EY for each appropriate number of postpartum days N and connecting them with a straight line or a curve.

FIG. 3(b) is an output example of the predicted cattle herd sales E$. The horizontal axis is the forecast date, and the vertical axis is the sales amount (here, the unit is "yen"). Since the estimated milk yield EY of the herd is obtained, it is possible to calculate the estimated sales E$ of the herd on the forecast day by multiplying by the unit price of milk (yen/kg). In addition, in the process of calculating the estimated herd sales E$, the herd estimated individual sales EI$, which is the sales of each individual cow, and the herd estimated total sales, which is the sales of all dairy cows that make up the herd Gold ΣE$ may be obtained.

FIG. 3(c) shows the determination result of the herd dry cow DC. The horizontal axis is the number of days after parturition (days), and the vertical axis is the amount of milk (here, the unit is "kg"). Calculate the herd estimated milk production EY (cow herd estimated milk production curve M) on a certain prediction day η, and determine the dry milk standard value DY _TH or less after the number of days after calving ask for This day is called herd dry day DYday. The cow herd dry-milk day DYday can be said to be the day when the decreasing cow herd estimated milk production reaches the dry-milk reference value.

Therefore, an individual cow whose number of days after calving is greater than the herd dry-milk day DYday is determined to be a herd dry-milk cow DC. In FIG. 3(c), the code DC (black triangle) is a herd dry cow DC because the number of days after parturition is greater than DYday. On the other hand, ^{the NOT} DC (filled circle) is not a herd dry cow DC because the number of days after calving is less than DYday.

FIG. 3(d) is an output example of the individual estimated milk yield DEY. The horizontal axis is the number of days after parturition (days), and the vertical axis is the amount of milk (here, the unit is "kg"). Estimated individual milk yield DEY is determined as a percentage of estimated herd milk yield EY. A curve representing the estimated individual milk yield DEY is defined as an individual estimated milk production curve DM. In FIG. 3(d), there is a curve DM representing the estimated individual milk yield DEY below the estimated herd milk yield curve M representing the estimated herd milk yield EY. This indicates that this specific individual cow is a dairy cow that produces less milk than the estimated milk production of the herd. Therefore, curve DM may be drawn above curve M for other individual cows.

FIG. 3(e) is a graph showing the individual predicted sales amount DE$. The horizontal axis is the forecast date, and the vertical axis is sales revenue (for example, yen). , the individual predicted sales DE$ is also less than the herd predicted sales E$. As for the estimated individual sales DE$, the individual estimated sales DEI$ and the individual estimated total sales ΣDE$, which are the sales for each individual cow, may be calculated.

FIG. 3( f ) is a graph representing individual dry cow DDC. The horizontal axis is the number of days after parturition (days), and the vertical axis is the amount of milk (here, the unit is "kg"). The exemplified individual cow produces less milk than the estimated milk yield EY obtained for the herd, so the individual dry-milk day DDYday is earlier than the herd dry-milk day DYday. In FIG. 3(f), if the number of days after calving of this individual cow is equal to or greater than the individual dry-milk day DDYday on the predicted day η, it is determined to be an individual dry-milk cow DDC. Not determined ( ^NOT DDC). As long as the order number is small, individual cows with low milk yields can also be treated as a herd.

Refer to FIG. 2 again. The overall flow described above may be shared between the main body 12 and the terminal 10 . For example, the selection of each process and the display of the final result are performed on the terminal 10, and each process is performed on the main body 12, and the like. Each step will be described in detail below.

<Estimated cow milk production EY>
FIG. 4 shows the flow of the process of calculating the estimated cow milk yield EY. When the process of calculating the herd estimated milk yield EY starts (step S110), selection of population data and creation conditions are determined (step S200). A large amount of ranch data is stored in the memory 14 shown in FIG. Select the required location (including identification of the individual cattle that make up the herd) and the period of basic data. In addition, the conditions for calculating the herd estimated milk yield EY are also input here.

For example, the location is your farm, the herd is all dairy cows, and the basic data period is the last year. Moreover, the conditions may include all the conditions for calculating the herd estimated milk yield EY. For example, it determines the length of the period in which the ranch data is collected when referring to it. More specifically, the actual milk yield is the daily milk yield, the average milk yield every three days, the weekly average, or the monthly maximum milk yield. is. Along with this, representative values of other variables may also be similarly determined for each fixed period.

Also, enter the forecast start date and forecast date. The start date of prediction calculation is usually "today when the prediction operation is going to be performed", but it may be a day in the past from today. Also, the forecast date is substantially the factor parameter P assumed on the forecast date. As already described, the actual value for the day (or period) corresponding to the past forecast date may be used as the factor parameter P assumed for the forecast date. Therefore, if the factor parameter P is derived from climate data, it is possible to make long-term predictions.

Next, an interpolation formula is created (step S202). The interpolation formula will be explained with reference to FIG. In FIG. 5, the horizontal axis represents the number of days after parturition N (days), and the vertical axis represents the actual milk yield RY (kg). For example, it is data for a certain period (for example, August 1, 2020) of a plurality of dairy cows on a certain ranch. Each point plotted here is a scatter diagram because it is the actual milk amount RY for each individual cow. However, since it is the amount of actual milk, there is also a range that cannot be plotted. This is the case when there are no dairy cows with the corresponding number of days after calving. In FIG. 5, it is represented by a no-data area VR.

In this way, if there is a gap in the ranch data, there will be a shortage of data when creating the regression equation later, and the accuracy of the regression will decrease. Therefore, this scatter diagram is approximated by an appropriate function. A WOOD curve is preferably available. The WOOD curve is a curve represented by the formula (2) and is well known as a curve representing the milk yield Y against the number of days after delivery N. It should be noted that the interpolation of the actual scatter diagram need not be limited to the WOOD curve, and other functions may be used.

Here, A, B, and C are constants, Y is the milk yield, N is the number of days after parturition, and e is the Napier number. The constants A, B, and C can be determined to fit this WOOD curve to the scatterplot using the least squares method. Fitting the relationship between the number of days postpartum N and the milk yield Y in this way with a continuous function is called "creating an interpolation formula". The formula obtained by interpolating the scatter diagram is more generalized and expressed as formula (3).

That is, the interpolation formula of the formula (3) expresses the milk yield Y as a function of the number of days after parturition N. A WOOD curve can be preferably used as the form of the function, but it is not limited to this. The interpolation formula creating step (step S202) in FIG. 4 is a step of determining the interpolation formula (3) from the scatter diagram of the actual milk amount RY as described above.

[Create interpolation formula]
FIG. 6 shows the processing of the step (step S202) of creating the interpolation formula of FIG. When the process of creating an interpolation formula starts (step S202), the data of the number of days after parturition N and the amount of actual milk RY are taken out from the population and conditions determined in step S200 of FIG. 4 (EY calculation flow) (step S230). These can be called real data. You can also draw a scatterplot. Actual data is a set of postpartum days N and actual milk volume RY for each dairy cow.

Next, an interpolation formula that best reflects the actual data of the number of days after delivery N and the amount of milk Y is obtained. For example, the process of determining the constants A, B, and C by applying the method of least squares using the WOOD curve (step S232) (see also FIG. 5). This can be said to obtain a function to be fitted to the actual milk yield RY. Then, the interpolation formula (3) is obtained (step S234). After that, the process returns to the EY calculation routine (FIG. 4) (step S236).

Interpolation formulas can be created for each day. This is because milking is done almost every day. However, if the environment and individual cows do not change significantly, the interpolation formula (3) may be created by regarding the average of the actual data every three days or every week as the actual data.

Alternatively, the time axis may be viewed broadly, and the interpolation formula may be created by regarding the average value of the actual data for one month as the actual data. More specifically, the average monthly milk yield of an individual cow is defined as the actual milk yield RY of the dairy cow. Also, the number of days after parturition of the dairy cow is the average of the month (that is, if N=10 days at the beginning of the month, the number of days after parturition of the month is assumed to be 25 days). These may be determined by the "population data, creation conditions" (step S200) in FIG.

Continuing to refer to FIG. After creating the interpolation formula, it is determined whether or not to perform factor analysis (step S204). This determination can be instructed from the terminal 10 by the user of the milk production calculation system 1 . The factor analysis is a judgment as to whether or not to examine the factor parameter P that can best explain the milk yield Y obtained from the interpolation formula (2) from the ranch data. For example, it is used when the milk production calculation system 1 is used for the first time, or when the population is greatly changed.

When performing factor analysis (Y branch of step S204), the step of factor analysis is performed (step S206). Details of the factor analysis step will be described later. If not (N branch of step S204), the process is shifted to the next step. The factor analysis will be explained in detail in FIG.

Next, a regression equation is created (step S208). The creation of the regression equation will be described with reference to FIG. By the interpolation formula (3) (FIG. 7(a)) shown in FIGS. 5 and 6, for example, the interpolated milk volume of the dairy cow of the number of days after calving N for each month can be calculated. Here, the interpolation formula is represented by the general form Fw( ), and the milk yield Y is the monthly average milk yield. Therefore, Y _{1 month} represents the interpolated milk yield in January, and the formula for obtaining the interpolation formula (3) for a dairy cow with N days after calving is represented as Fw _{1 month} (N).

Here, 50 days postpartum is expressed as _N50 . The interpolated milk yields of dairy cows after 50 days postpartum in each month from January to December are Fw _January (N ₅₀ ), Fw _February (N ₅₀ ), ..., Fw _December (N ₅₀ ). Of course, for Fw _m (N), an interpolation formula is created for each month ("m" represents "month").

A factor parameter P is determined as a factor that can best explain the interpolated milk volume of each month. What kind of factor parameter P is good is known by performing the factor analysis process of step S206. For example, temperature, humidity, hours of sunshine, and the like. If the factor parameter P used to obtain the estimated cow herd milk yield EY has already been determined, it is used. The factor parameter P does not have to be one. In other words, this is to find a regression equation of the interpolated milk volume Y for each month by a least squares method or the like using a factor of 1 or more.

As is well known, the regression equation is expressed as Equation (4).

Here, EY is the herd estimated milk yield, _x1 , _x2 , ..., _xk are factors (factor parameters P), _a1 , _a2 , ..., _ak , c are is a constant.

FIG. 7(c) shows an example of a regression equation with one factor. The interpolation formula (3) shown in FIG. 7(a) is used to calculate the interpolated milk yield _Ym for each month of the dairy cow 50 days after parturition (see FIG. 7(b)). where m represents the month. The interpolated milk volume for each month may be the average of the first three days of the month. Data from only one particular day may be representative of interpolated milk yields for the month.

Next, when these interpolated milk volumes for each month are organized by the factor parameter P (here, for example, the temperature at noon), the graph of FIG. 7(c) can be obtained. Here, the results are shown as an example when the herd's estimated milk yield EY on the 50th day after calving in each month can be well explained by the temperature at noon. A regression formula is represented by (5) Formula.

where _x1 is the temperature at noon and EY is the herd estimated milk yield. Note that such a regression equation is created only for several days after childbirth. That is, assuming that the last day of the postpartum number N is 300 days, it is possible to obtain a regression equation from 1 day to 300 days after delivery (see FIG. 7(e)).

If there are multiple factors, it cannot be described in two dimensions as shown in FIG. can be approximated. The regression equation obtained in this manner is expressed as equation (6) (see FIG. 7(d)).

Here, ^N EY is called the herd estimated milk yield EY when the number of days after calving N is the factor parameter P. Substituting the factor parameter P into the equation (6) and obtaining the result may also be referred to as "calculating the herd's estimated milk yield". The calculated estimated milk yield is the herd estimated milk yield EY. The herd's estimated milk production at the number of days after calving N when the factor parameter is P is expressed as ^NEY (P) (N may be omitted). When expressing the herd estimated milk yield of the i-th individual cow CW _i belonging to the herd, ^N EY [CW _i ] etc. and [ ] (square brackets) are used.

[Create regression equation]
FIG. 8 shows the flow of the process of creating a regression equation. When the step of creating a regression equation (step S208) is started in the EY calculation flow shown in FIG. 4, the process jumps to FIG. 8, where the factor parameter P is input (step S250). A factor parameter P can be input from the terminal 10 . That is, the user of the milk production calculation system 1 inputs. Assume here that the factor parameter P is p ₁ (temperature).

Next, the estimated milk yield Ym for each number of days after parturition N is obtained by the interpolation formula (3) for each fixed period m (this is determined in step S200) specified for the factor parameter _p1 (step S252). That is, the interpolated milk quantity Ym in FIG. 7(b) is obtained. As a result, the scatter diagram of FIG. 7(c) can be drawn.

Next, a regression equation is obtained using the factor parameter _p1 as an explanatory variable and the interpolated milk yield Ym as a target variable (step S254). That is, with regard to the time factor parameter _p1 , it is possible to obtain the relationship (6) (FIG. 7(d)) of the amount of milk when the postpartum days N are the same. A known method may be used to obtain the regression equation.

Thus, in the present invention, when calculating the herd estimated milk production using the factor parameter P, instead of directly using the actual milk amount RY, the interpolated milk amount calculated from the interpolation formula for interpolating the actual milk amount RY use quantity. Therefore, even if there is a missing data in the actual milk yield RY, a reasonable value can be calculated as the average milk yield.

The formula (6) can generate a number from 1 to the last day (here, the last day means the longest day after parturition) for the number of days after parturition N (see FIG. 7(e)). Regression formula (6) summarizes FIG. 7(e). After obtaining the regression equation, the process returns to the routine for obtaining the estimated cow herd milk yield EY in FIG. 4 (step S256).

Referring to FIG. 4 again, once the regression equation (6) for obtaining the estimated herd milk yield EY is obtained, the estimated herd milk yield EY can be obtained by inputting the factor parameter P into the regression equation (6) ( step S210).

[Cattle herd regression equation calculation EYI]
FIG. 12 shows a flow for actually calculating the regression equation (6) and obtaining the herd estimated milk yield EY. This is the herd regression equation calculation (EYI) step. When the herd regression equation calculation is started (step S210), the number of days after delivery N and the factor parameter P are input (step S280). Next, using the inputted number of days after parturition N, factor parameter P, and equation (6), the herd estimated milk yield ^NEY at the number of days after parturition N when factor parameter P is used is calculated (step S282). It may be displayed after calculation.

Next, re-input is confirmed (step S284). If it is desired to re-input and obtain the herd's estimated milk yield ^NEY for another number of days after calving N or factor parameter P (Y branch of step S284), return to the input (step S280). Otherwise, return to the EY routine (step S286).

Regression formula (6) corresponding to the number of days after parturition N is input with the factor parameter P (explanatory variable) to calculate the herd estimated milk yield EY. Therefore, by sequentially inputting the value of the same factor parameter P into the regression equation (6) representing each number of days after parturition N, the data of the number of days after parturition N and the estimated milk yield EY of the herd at the same value of the factor parameter P you can get a set. The curve related to the estimated herd milk production in FIG. are connected by straight lines.

FIG. 9 shows an enlarged view of the estimated herd lactation curve M in which the estimated herd milk yield EY of FIG. 3(a) is plotted. It plots the herd's estimated milk yield EY for each number of days after parturition. A factor parameter P indicates a case where a multiple regression equation is obtained with two factors _p1 and _p2 . Therefore, explanatory variables are also two factor parameters P _{, p1} and _p2 . The number of days postpartum N was obtained in discrete values (10 days, 20 days, 30 days, 50 days, 80 days, 100 days, 150 days, 200 days, 250 days), but it can also be obtained in units of 1 day. . Each herd's estimated milk yield EY is obtained from separate regression equations represented by equation (6) (differences in postpartum days; see FIG. 7(e)). That is, the constants of these equations (for example, _a1 and c in equation (5)) are different.

In step S210 (see FIG. 4) of calculating the herd regression equation, the client side inputs the value of the factor parameter P (explanatory variable) assumed on the prediction date from the terminal 10 and the desired number of postpartum days N. returns the herd estimated milk yield EY. If the client side returns at least one herd estimated milk yield EY, it satisfies the requirements of the milk yield calculation system 1 according to the present invention. The herd estimated milk yield EY may be obtained for a plurality of postpartum days N and graphed as shown in FIG.

Next, the herd total regression equation calculation EYS is executed to obtain the herd estimated total milk yield SUM _EY (step S212). FIG. 13 shows a conceptual diagram of calculation of the herd estimated total milk yield SUM _EY . The horizontal axis is the number of days after parturition (days), and the vertical axis is the herd's estimated milk yield (kg). Since the herd estimated milk yield EY is obtained, the herd estimated milk production curve M can be drawn. Specifically, by substituting the factor parameter P assumed on the prediction date into all the regression equations of the equation (6), the herd estimated milk yield EY can be plotted for all the days after parturition N. Assume that the herd consists of nine dairy cows.

Assume that the factor parameter P (explanatory variable) of the predicted date is p1, and the postpartum days of each dairy cow on the predicted date are N1, N2, N3, N4, and N5 days. It is also assumed that the number of dairy cows at each postpartum day is 1, 2, 4, 1, and 1, respectively. In FIG. 13, the number of animals is shown in parentheses on the number of days after parturition on the horizontal axis.

Then, the herd estimated total milk yield SUM _EY is obtained as the sum of the herd estimated total milk yield EY obtained from each number of days after calving N of each dairy cow.

That is, in general, the estimated total milk yield SUM _EY of the herd is expressed by the formula (7), assuming that there are Ck dairy cows that are several k days after parturition.

In addition, the herd estimated milk production ^NEY is obtained from the number of days after calving N of each dairy cow, and the herd estimated milk production ^NEY is taken as the milk volume of the dairy cow, and all the cows are added to the herd estimated total milk production SUM. _EY may be used. The result is the same as the expression (7).

If the herd estimated milk yield EY is obtained in units of a certain period (for example, one week, one month, etc.), the formula (7) may be further multiplied by the period (days).

[Total herd regression calculation]
FIG. 14 shows a flow for obtaining the estimated total milk production of the herd. This is the herd total regression calculation step. When the cattle herd total regression formula calculation is started (step S212), initial setting is performed (step S300). As an initial setting, the herd estimated total milk yield SUM _EY and the identification index i of the individual cow are initialized, and the final value (END) of the identification index is set to n+1. Here, n is the number of individual cows belonging to the herd.

Next, the number of days after parturition Ni of the i-th individual cow CW _i is acquired (step S302). Then, the herd estimated milk yield ^Ni EY is calculated using the regression equation (6) and added to the herd estimated total milk yield SUM _EY (step S304). As the factor parameter P (explanatory variable), the value used in step S210 (cow herd regression formula calculation step: see FIG. 12) may be used, or before and after initial setting (step S300). You may inquire.

It is determined whether or not the calculations for all individual cows have been completed (step S306), and if there are still remaining (N branch of step S306), the identification index i is incremented (step S310), and the number of days after calving of the individual cow CW _i is calculated. The process returns to the step of acquiring Ni (step S302). When the sum of herd estimated lactation amounts for all individual cows is completed (Y branch of step S306), the result is displayed (step S308), and the process returns to the EY routine (step S312).

Referring to FIG. 4 again, when the herd regression equation calculation or the herd total regression equation calculation is repeated (Y branch of step S214), step S210 is performed again. When the repetition is not performed (N branch of step S214), end determination is performed (step S216). When finished (Y branch of step S216), the process returns to the main routine (step S218). If not completed (N branch of step S216), the process returns to step S200 to re-execute the EY calculation process.

[Factor analysis]
FIG. 10 shows the process of factor analysis in step S206 of FIG. The process of factor analysis is the same as the process of creating a regression equation (step S208) up to the middle. Specifically, steps S250, S252, and S254 shown in FIG. 8 are the same as in FIG. Therefore, the same step numbers are used.

Therefore, the factor parameter P is input (step S250), and the milk yield Ym for each postpartum period N is calculated by the interpolation formula (3 ) (step S252), and a regression equation is obtained (step S254) using the factor parameter P as an explanatory variable and the milk yield Ym as a target variable.

In the factor analysis, the actual milk yield RY of the milk yield for a given period m is compared with the herd estimated milk yield EY obtained from the regression equation (step S260). FIG. 11 illustrates this situation. A case is shown in which two factors, _p1 and _p2, are selected as factor parameters. For example, temperature and wind speed. The constant period is shown for four different days. For example, it may be a representative day of spring, summer, autumn, and winter. Specifically, it is m1 n1, m2 n2, m3 n3, and m4 n4. The specific factor parameters p ₁ , p ₂ for these days remain on record. The selection of factor parameters may be carried out separately by principal factor analysis, or may be selected by trial and error. By inputting the factor parameters p ₁ and p ₂ , it is possible to calculate the herd estimated milk yield EY from the regression equation (6).

The postpartum days N can be obtained from 1 to the maximum day, and here, the obtained conditions for four types of days 30, 50, 100, and 150 are shown. These values are taken as the absolute value ERR of the difference from the actual milk amount RY of each date and time. In addition, ³⁰ RY in FIG. 11 is the actual milk amount of a dairy cow with a postpartum period of 30 days. ³⁰ ERR indicates the absolute value of the difference between the herd's estimated milk yield EY and actual milk yield RY when the postpartum period is 30 days. This ERR is also calculated when the postpartum days are 50 days, 100 days, and 150 days. In the examples described later, an example was shown in which the herd's estimated milk yield EY and actual milk yield RY were compared in the case of 50 days after parturition.

The sum of the absolute values ERR of the difference between the herd estimated milk yield EY and the actual milk yield RY for four days is expressed as a total error TΣ. Thus, in step S260, the herd estimated milk yield EY and the actual milk yield RY are compared.

Referring to FIG. 10 again, after comparing the herd estimated milk yield EY and the actual milk yield RY, the end determination is made (step S262). The termination determination is made by determining whether or not the absolute value ERR of the difference between the herd estimated milk yield EY and the actual milk yield RY of the factor parameter P input in step S250 is appropriate. Whether or not the ERR is appropriate may be determined in advance or determined by the user. Also, a program (which may include a so-called "AI") may be set to select the optimum value. Further, although the difference between the herd estimated milk yield EY and the actual milk yield RY has been described as an absolute value, a square value may be used.

When ending (Y branch of step S262), it returns to the EY calculation flow (step S264). When continuing (N branch of step S262), the process returns to step S250 and the factor parameter P is input again.

Please refer to FIG. 4 again. After exiting the factor analysis (step S206), the process proceeds to the process of calculating the cattle herd regression formula (step S210). After passing through the factor analysis step (step S206), it is considered that the regression equation and the suitable factor parameter P have been found, so the herd regression equation calculation step (step S210) for calculating the herd estimated milk yield EY is performed. This is because it is thought that they may go. In the step of calculating the cattle herd regression formula (step S210), as already described, the regression formula of formula (6) is calculated from the value of the factor parameter P (explanatory variable) assumed on the expected date and the desired number of days after parturition N. is used to calculate and obtain the herd's estimated milk yield EY. Subsequent steps are as described above.

[Regression formula construction step]
In addition, in the milk production calculation system 1 according to the present invention, the step of obtaining the regression equation (6) is used in any menu. Therefore, steps S200, S202, S204, S206, and S208 are collectively referred to as step S290. Step S290 may be called a regression formula construction step.

Calculation of the estimated herd milk yield EY (step S110) calculates the estimated herd milk yield EY when the value of the factor parameter P (explanatory variable) is input. Unless otherwise specified, herd estimated milk yield EY is calculated for all postpartum days. Of course, it may be calculated only for specific postpartum days. The value of the factor parameter P in this case is the factor parameter P assumed on the forecast date. The factor parameter P assumed on the forecast date may be input when setting the population data creation condition (step S200). Alternatively, it may be input in step S210, which is the step of calculating the herd estimated milk yield EY. Also, when re-inputting the factor parameter P (when returning to step S210 at the Y branch of step S214), it may be input again.

As described above, the herd estimated milk yield calculation returns a value obtained by estimating the average milk yield of dairy cows belonging to the herd when the factor parameter P has a certain value for a specific population. In other words, the herd estimated milk yield value is the predicted milk yield that can be expected from dairy cows belonging to the population when the factor parameter P has a certain value.

<Forecast sales of cattle E$>
Refer to FIG. 2 again. When the herd estimated milk yield EY has been calculated (step S110), the estimated cow herd sales E$ can be obtained therefrom. If calculation of the predicted herd sales E$ is selected (Y branch of step S112), the step of calculating the predicted sales E$ of the herd is performed (step S116). In the step of calculating the estimated herd sales E$, the estimated individual herd sales EI$ and the estimated total herd sales ΣE$ can be calculated. The herd estimated individual sales revenue EI$ is the estimated sales revenue of an individual cow calculated based on the cow herd estimated milk yield EY. Also, the estimated total sales of the herd ΣE$ is the total sales of all individual cows belonging to the herd calculated based on the estimated milk yield EY of the herd.

The herd estimated individual sales income EI$ can be obtained by calculating the herd estimated milk production EY [CW _i ] of a specific individual cow CW _i from the formula (6) and multiplying it by the milk unit price q (yen/kg). can. In addition, the estimated total herd sales ΣE$ is obtained by adding the estimated herd milk production EY [CW _i ] of the individual cow CW _i for all individual cows, or by adding the estimated total herd milk production SUM _EY to the milk unit price q (yen/ kg). Although the unit price of milk q is an amount assumed on the forecast date, it does not require any particular basis, and may be based on past performance for each season.

[Cattle forecast sales calculation 1]
FIG. 15 shows a flow for obtaining the estimated total sales of the herd ΣE$ by multiplying the estimated total milk production SUM _EY of the herd by the unit price of milk q (yen/kg).

When the process of the estimated herd sales E$ starts (step S116A), whether to calculate the estimated individual herd sales EI$ (step S330) or to calculate the estimated total sales ΣE$ (step S330) S332) is selected.

When calculating the estimated individual cow sales EI$ (Y branch of step S330), the number of days after parturition Ni of a specific individual cow CW _i and the factor parameter P (explanatory variable) are input, and the herd estimated milk yield is calculated. ^Ni EY is calculated and multiplied by the milk unit price q (yen/kg) to calculate an estimated individual sales income EI$ (step S340). Results may be displayed.

If it is to be repeated (Y branch of step S342), step S340 is repeated again. If not (N branch of step S342), the process proceeds to the step of calculating the estimated total sales ΣE$ of the cattle herd (step S332).

When calculating the estimated total sales of the herd ΣE$ (Y branch of step S332), first, the estimated total milk yield SUM _EY of the herd is calculated (step S212). In the step of calculating the estimated herd milk yield EY (step S110: see FIG. 2), if the estimated total herd milk yield SUM _EY has already been calculated and that value is used, this step can be skipped. good.

Next, the herd estimated total milk production SUM _EY is multiplied by the milk unit price q (yen/kg) to calculate the herd estimated total sales revenue ΣE$ (step S350). Results may be displayed.

When repeating (Y branch of step S352), the process returns to step S212. Otherwise (N branch of step S352), the process returns to the cattle herd forecast sales revenue E$ (step S354).

Through the above steps, the herd estimated total sales ΣE$ obtained by multiplying the herd estimated total milk production SUM _EY , which is the sum of the herd estimated milk production EY of the individual cows belonging to the herd on the prediction date, by the milk unit price q can be calculated.

[Cattle forecast sales calculation 2]
FIG. 16 shows the flow for obtaining the estimated total herd sales ΣE$ by multiplying the herd estimated milk yield EY [CW _i ] of an individual cow CW _i by the unit price of milk q and adding it for all individual cows. indicates

When the process of the estimated herd sales E$ starts (step S116B), whether to calculate the estimated individual herd sales EI$ (step S330) or to calculate the estimated total sales ΣE$ (step S330) S334) is selected.

The calculation of the estimated cow herd individual sales income EI$ (Y branch of step S330) is the same as in FIG. 15, and is therefore omitted. When calculating the estimated total sales of the herd ΣE$ (Y branch of step S334), the estimated total sales of the herd ΣE$ and the identification index i of the individual cow are initialized, and the last value of the identification index (END) is set to n+1 (step S360). Here, n is the number of individual cows belonging to the herd. Also, the value of the factor parameter P (explanatory variable) of the prediction date is acquired. This may be input separately, or may be the value used when the herd's estimated milk production was determined (step S110).

Next, the number of days after parturition Ni of the i-th individual cow CW _i on the predicted date is obtained (step S362). This can be obtained by adding the number of days until the predicted date to the number of days after delivery at the predicted starting date.

Then, the herd estimated milk production ^Ni EY of the individual cow is calculated, multiplied by the milk unit price q (yen/kg), and added to the herd estimated total sales ΣE$ (step S364). That is, the estimated individual herd sales EI$ of the individual cow CW _i is obtained and added to the estimated total herd sales ΣE$.

If addition for all individual cows has not been completed (N branch of step S366), increment the identification index i (step S370), and obtain the number of days after delivery Ni of the individual cow CWi on the predicted date (step S362 ).

When the addition is completed for all individual cows (Y branch of step S366), the result is displayed and re-input is requested (step S368). If you want to change the value of the factor parameter P (change the forecast date), re-input (Y branch of step S368) and return to the initial setting (step S360). If not repeated (N branch of step S368), return to the cattle herd forecast sales E$ (step S372).

Through the above steps, the estimated herd total sales revenue ΣE$ is calculated as the sum of the herd estimated individual sales revenues EI$ obtained by multiplying the estimated herd milk yield EY of the individual cows belonging to the herd on the forecast date by the milk unit price q. can be calculated.

Both A and B of steps S116 can be used as a step (step S116) of calculating the predicted cattle herd sales in FIG.

<Determination of cow herd dry cow DC>
Please refer to FIG. When the herd estimated milk yield EY is calculated (step S110), the herd dry cow DC can be determined. Determination of the herd dry cow DC will be described with reference to FIG. 17 . In FIG. 17, the horizontal axis is the number of days after parturition (days), and the vertical axis is the herd estimated milk yield EY (kg). Since the herd estimated milk yield EY is calculated, the herd estimated milk production curve M can be drawn.

A herd dry cow DC can be determined by applying a dry milk reference value DY _TH that can be determined as a dry cow candidate to the cow herd estimated lactation curve M. The dry-milk reference value DY _TH is the amount of milk for judging a dairy cow after a certain period of days after calving to be a dry-milk candidate. In FIG. 17 , the individual cow with the number of days after calving N5 can be determined as a candidate for the herd dry milk cow DC because the herd estimated milk yield EY is lower than the dry milk reference value DY _TH . On the other hand, a dairy cow whose number of days after calving is less than N4 cannot be a candidate for a herd dry cow DC because the herd estimated milk yield EY is higher than the dry milk reference value DY _TH ( ^NOT DC).

The day of intersection between the herd estimated lactation curve M and the dry milk reference value DY _TH is the herd dry milk day DYday. Also, the dry milk reference value DY _TH is obtained empirically, and is input in step S200 in FIG. 4, for example. In addition, individual cows with low milk production immediately after giving birth are excluded from the candidates for dry cows.

[Dry cow judgment 1]
FIG. 18 shows a flow for directly comparing the herd estimated milk yield EY and the dry milk reference value DY _TH to display candidates for the herd dry cow DC. When the process of determining the DC of the herd dry dairy cattle is started (step S118A), initial setting is performed (step S400). As initial settings, the individual identification index i is initialized (i=1), and the final value (END) of the identification index is set to n+1. where n is the number of cows belonging to the herd.

Next, the number of days after parturition Ni on the predicted date of the i-th individual cow CW _i is obtained (step S402). This is obtained by adding the number of days until the predicted date to the number of days after the sorting of the individual cow CW _i on the predicted start date. Then, the herd's estimated milk yield ^Ni EY at the number of days after parturition Ni is obtained and compared with the dry milk reference value DY _TH (step S404).

If the herd milk yield ^Ni EY is less than the dry milk reference value DY _TH (Y branch of step S404), the individual cow CW _i is displayed as a candidate for the dry milk cow DC of the herd (step S406), and whether the CW _i is the last individual cow is displayed. It is determined whether or not (step S408). If the herd estimated milk yield ^Ni EY is not less than the dry milk reference value DY _TH (N branch of step S404), step S406 is skipped.

If CW _i is not the last individual cow (N branch of step S408), the identification index i is incremented (step S410), and the step of obtaining the number of days after parturition Ni of the i-th individual cow CW _i on the predicted date (step S402 ). When the determination is completed up to the last individual cow (Y branch of step S408), the process returns to the DC determination (step S412).

Through the above steps, it is possible to display individual cows whose herd estimated milk yield EY on the prediction date is lower than the dry milk reference value DY _TH as candidates for dry milk cows in the herd.

[Dry cow judgment 2]
The herd dry-milk cows can also be determined by determining the herd dry-milk day DYday in the herd estimated lactation curve M on the predicted date and displaying individual cows whose postpartum days are equal to or greater than the herd dry-milk day DYday. It can also be obtained by displaying the individual cows whose herd estimated milk yield on the prediction date for all individual cows belonging to the herd is less than the dry milk reference value DY _TH .

FIG. 19 shows a flow for determining a herd dry-milk cow DC from a herd dry-milk date. When the herd dry cow DC determination is executed (step S118B), the number of days after parturition N is set to a day (step S430). Day a includes the day after the estimated cow herd milk production EY exceeds the dry milk reference value DY _TH for the first time (DC ₀ : see FIG. 17). Usually, 30 to 50 days should be set for the a day. "a days" are referred to as early days.

Next, it is determined whether or not the postpartum number N is the final day (step S432). If it is the last day (Y branch of step S432), it is determined that "there is no DC" (step S442), and the process returns to the DC determination step (S118B) (step S444).

If the number of days after parturition N is not the final day (N branch of step S432), it is determined whether or not the herd's estimated milk production ^NEY when the number of days after parturition is N is equal to or less than the dry milk reference value DY _TH ( step S434).

If the herd estimated milk production ^N EY when the number of days after parturition is N is equal to or less than the dry milk reference value DY _TH (Y branch of step S434), the herd dry milk day DYday is set to N (step S436), and the herd dry milk An individual cow i whose postpartum number Ni is greater than day DYday is displayed as a herd dry cow DC candidate (step S438). After that, the process returns to the DC calculation step (S118) (step S444).

If the herd estimated milk production ^NEY when the number of days after parturition is N is not equal to or less than the dry milk reference value DY _TH (N branch of step S434), the number of days after parturition N is incremented (step S440), and step S432. Return processing to .

Through the above steps, individual cows whose number of days after parturition is greater than the herd dry milk day DYday on which the herd estimated milk production EY on the prediction date is the dry milk reference value DY _TH can be displayed as herd dry cow DC candidates.

Both A and B of the above step S118 can be set as the step of determining the dry cow in the herd of FIG. 2 (step S118).

<Individual estimated milk production DEY>
Refer to FIG. 2 again. Next, the individual estimated lactation amount DEY will be described. The herd yield estimate EY assumes that all cows follow the same herd yield estimate EY. However, the individual estimated milk yield DEY estimates the milk yield for each individual cow. The estimated individual milk yield DEY is obtained by multiplying the herd estimated milk yield EY by the milk yield coefficient calculated for each individual cow.

FIG. 20 shows how the individual estimated lactation amount DEY is obtained. Let the i-th individual cow in the herd be an individual cow CW _i . The day for calculating the degree of milk yield coefficient of an individual cow CW _i with respect to the herd estimated milk yield EY is called an “individual specific date”. The individual specific date may be any date before the prediction starting date, and may be the latest date on which the actual milk volume RY[CW _i ] of the individual cow CW _i is determined. RY[CW _i ] is the actual milk yield of the individual cow CW _i .

FIG. 20(a) shows the estimated milk yield EY of the herd on the individual specific day (the factor parameter for this day is p ₁ ). The estimated herd milk yield EY is represented by an estimated herd lactation curve M. The horizontal axis is the number of days after parturition, and the vertical axis is the herd's estimated milk yield EY. Assume that the individual cow CW _i on the individual specific day has a postpartum number of days Nr and an actual milk yield of RY[CW _i ]. The milk yield of an individual cow CW _i with postpartum period Nr is expressed as ^Nr RY[CW _i ]. In addition, the herd's estimated milk production at the number of days after parturition, Nr, is represented by ^Nr EY.

Here, it is assumed that the actual milk yield ^Nr RY[CW _i ] of the individual cow CW _i is greater than the herd estimated milk yield ^Nr EY. Of course, the opposite is also possible. Then, the milk volume coefficient α _i of the individual cow CW _i is calculated as shown in Equation (8). Such a step can be said to be a milk yield coefficient calculation step.

α _i is a value determined for each individual cow. An individual cow CW _i for which α _i is to be calculated is also called a specific individual cow. Incidentally, both the actual milk yield ^Nr RY[CW _i ] and the herd estimated milk yield ^Nr EY may be average values for a certain period of time as the milk yield coefficient α _i . Alternatively, the milk yield coefficients for a continuous period of time may be averaged. For example, in the three months immediately preceding the date of drafting the forecast, the monthly milk yield coefficient α _i is obtained from the monthly actual milk yield ^Nr RY [CW _i ] and the herd estimated milk yield ^Nr EY. For example, the milk yield coefficient α _i is obtained by averaging the milk yield coefficients of the minutes. Note that the predicted start date can include not only the current day but also a certain period before the predicted start date, so even if such calculation is performed, the milk quantity coefficient αi can be said to be the value at the predicted start date.

Next, with reference to FIG. 20(b), the estimated cow herd milk yield EY on the prediction day (the factor parameter for this day is p _k ) is calculated. In FIG. 20(b), it is represented as a cow herd estimated lactation curve M. The herd estimated lactation curve M in FIG. 20(a) and the herd estimated lactation curve M in FIG. 20(b) are different curves if the factor parameter P has a different value. The individual estimated milk yield DEY[CW _i ] of an individual cow CW _i is obtained by multiplying the herd estimated milk yield EY by α _i .

The herd estimated milk yield EY is represented by the regression equation (6). Therefore, the step of obtaining the estimated individual milk yield DEY can be said to be the step of calculating the individual regression equation obtained by multiplying the regression equation of the equation (6) by _αi . The individual estimated lactation amount DEY[CW _i ] can also be drawn as an individual estimated lactation curve DM. Therefore, the estimated individual lactation curve DM is α _i times the herd estimated lactation curve M (see FIG. 20(b)).

Next, the number of days after parturition Nr+X of the individual cow CW _i on the predicted date is calculated. This can be obtained from the number of days after parturition of the individual cow CW _i on the predicted date. Here, X is the number of days from the individual identification date to the prediction date. Then, the individual estimated milk production ^Nr+X DEY[CW _i ] is obtained. This is equivalent to finding α _i ( ^Nr+X EY). ^Nr+X DEY[CW _i ] is the estimated individual milk yield of an individual cow CW _i with a postpartum period of Nr+X (days). In addition, ^Nr+X EY is the herd's estimated lactation amount of Nr+X (days) after parturition.

In other words, the individual estimated milk yield DEY on the prediction date is α _i times the milk yield EY of the herd whose number of days after calving is Nr+X (days) on the prediction date. This step is a step of calculating an estimated individual milk yield.

The individual estimated total milk yield SUM _DEY will be described with reference to FIG. The individual estimated lactation amount DEY was determined as shown in FIG. Therefore, the individual estimated milk yield DEY is obtained individually for all dairy cows belonging to the herd. The sum of the individual estimated total milk yield DEY on the prediction date is the individual estimated total milk yield SUM _DEY .

In FIG. 21, the horizontal axis is the number of days after parturition (days), and the vertical axis is the amount of milk (kg). For the sake of simple explanation, it is assumed that the current cow herd consists of an individual cow A and an individual cow B. The graph shows the estimated herd milk yield EY (estimated herd lactation curve M) and the individual estimated milk yields ^NADEY [A] and ^NB DEY [B] of individual cow A and individual cow B on the prediction date. NA and NB are the number of days after parturition of individual cow A and individual cow B on the predicted date. The individual estimated lactation amounts DEY[A] and DEY[B] were expressed as individual estimated lactation curves _DMA and _DMB . Also, the milk yield coefficients of individual cow A and individual cow B were set to α _A and α _B , respectively.

The individual estimated milk yield DEY[A] of the individual cow A is greater than the herd estimated milk yield EY, and the individual estimated milk yield DEY[B] of the individual cow B is less than the herd estimated milk yield EY. The number of days after parturition on the predicted date of individual cow A and individual cow B was set to NA (day) and NB (day) on the predicted date, respectively.

The individual estimated total milk production SUM _DEY is the sum of the estimated individual milk production ^NADEY [A] at the number of days postpartum NA of individual cow A and the estimated individual milk production ^NB DEY [B] at the number of days postpartum NB of individual cow B. can be obtained as This step is a step of calculating an estimated individual milk yield.

FIG. 22 shows the flow for calculating the individual estimated lactation amount DEY. When the step of calculating the individual estimated milk yield DEY in FIG. 2 is started (step S120), the step of constructing the regression equation for the individual specific date is performed (step S500). This involves executing step S290 in FIG. 4 to obtain the regression equation of formula (6) on the individual specific day (the day on which the milk volume coefficient α is determined). It can be said that the cow herd milk yield EY on the individual specific day is obtained.

Next, the process of individual regression equation calculation DEYI is performed (step S502). Since the regression equation (6) is obtained in step S500, the milk yield coefficient α can be determined by using the actual milk yield RY on the individual specific day. As a result, the individual estimated milk yield DEY of the individual cow CW _i on the prediction date can be calculated. The step of the individual regression equation calculation DEYI results in the calculation of the individual estimated milk yield DEY for CW _i .

Next, the step of the individual total regression equation calculation DEYS (step S504) is performed. Since the individual estimated milk yield DEY on the prediction date can be calculated, the individual estimated total milk yield SUM _DEY is obtained by adding the individual estimated milk yields DEY for all individual cows belonging to the herd. The step of the individual total regression equation calculation DEYS results in the calculation of the individual estimated total milk yield SUM _DEY .

Then, it asks whether or not there is a re-input (step S506). When re-inputting (Y branch of step S506), the process returns to the step of constructing the regression equation for the individual identification date (step S500), and the processing can be repeated by changing the individual identification date. If re-input is not performed (N branch of step S506), the process returns to the DEY calculation step (step S120) (step S508).

[Individual regression calculation]
FIG. 23 shows the flow of the individual regression equation calculation process. When the individual regression formula calculation flow starts (step S502), the number of days after parturition Nr (days) of the individual cow CW _i on the individual specific date and the actual milk amount ^Nr RY[CW _i ] on the individual specific date are obtained (step S520). ). This is recorded in the basic data.

Next, the herd estimated milk production ^Nr EY on the individual specific day is calculated (step S522). Specifically, the formula (6) is obtained. For this, the result obtained in step S500 of FIG. 22 may be used as it is.

Next, the milk yield coefficient α _i is calculated from the actual milk yield ^Nr RY[CW _i ] and the herd estimated milk yield EY based on the equation (8) (step S524). Then, the herd estimated milk production ^Nr+XEY on the prediction date is calculated (step S526), and by multiplying it by _αi , the individual estimated milk production DEY is obtained (step S528). X is the number of days from the individual identification date to the prediction date. After that, the process returns to the individual regression equation calculation step (step S530). In step S528, the calculation of equation (9) is performed.

In addition, the individual estimated lactation DEY obtained here is expressed as ^Nr+X DEY[CW _i ]. This means the estimated milk yield of the i-th individual cow CW _i in the herd when the number of days after calving is Nr+X (days). The calculated individual estimated milk yield DEY can be displayed on a terminal or the like. Nr (day) is the number of days after parturition of the individual cow CW _i on the individual specific date, and X (day) is the number of days from the individual specific date to the prediction date.

[Individual total regression calculation]
FIG. 24 shows the flow of the individual total regression equation calculation process. When the individual total regression formula calculation process starts (step S504), initial setting is first performed (step S540). Initial settings are identification index i, initialization of individual estimated total milk yield _{SUM_DEY} (i=1, _{SUM_DEY} =0), and setting of the final value (END) of the number of individuals. The final value (END) is set to n+1, where "n" is the number of cows in the herd.

Next, the individual estimated lactation amount DEY (more precisely, " ^Nr+X DEY[CW _i ]") on the predicted day is calculated (step S542). Nr (day) is the number of days after parturition on the individual specific day, and Nr+X (days) is the number of days after parturition on the predicted day. Then, the individual estimated total milk production DEY and the individual estimated total milk production SUM _DEY are added to obtain a new individual estimated total milk production SUM _DEY (step S544).

It is determined whether addition of all individual cows has ended (step S546). If not (N branch of step S546), the identification index i is incremented (step S548), and the process returns to step S542. If completed (Y branch of step S546), the process is returned to the individual total regression equation calculation step (step S550).

The individual estimated total milk production SUM _DEY obtained here is the total sum of individual estimated total milk production on the prediction date. The calculated individual estimated total milk yield SUM _DEY can be displayed on a terminal or the like.

<Individual predicted sales DE$>
With reference to FIG. 2, once the estimated individual milk yield DEY is obtained, the estimated individual sales DE$ can be calculated. If calculation of predicted individual sales DE$ is selected (Y branch at step S122), predicted individual sales DE$ is calculated (step S126). For the individual estimated sales DE$, it is possible to obtain the estimated individual sales DEI$, which is the estimated sales of each individual cow, and the estimated individual total sales ΣDE$, which is the estimated sales of all individual cows belonging to the herd. can.

The individual estimated sales amount DEI$ can be obtained by multiplying the individual estimated milk yield DEY obtained in step S120 (see FIG. 2) by the unit price of milk q (yen/kg). On the other hand, the individual estimated total sales revenue ΣDE$ is calculated by multiplying the individual estimated milk production DEY by the milk unit price q to calculate the individual estimated sales revenue for each individual cow, and calculating the total _. is multiplied by the unit price of milk q. Either process may be used to obtain the individual estimated total sales ΣDE$.

The respective flows are illustrated in FIGS. 25 and 26 below. These are called steps S126A and S126B, respectively. Any process can be made into step S126 of FIG.

[Individual estimated gross sales calculation 1]
FIG. 25 shows the flow of the individual predicted sales amount DE$ calculation process. This flow uses the individual estimated total milk production SUM - - _DEY to obtain the individual estimated total sales ΣDE$. When the step of calculating the estimated individual sales DE$ is started (step S126A), the calculation of the individual estimated sales DEI$ or the individual estimated total sales ΣDE$ is selected (steps S560, 562). When not selecting each, the processing is moved to the next. That is, in the N branch of step S560, the process proceeds to step S562, and in the N branch of step S562, the process returns to the individual predicted sales amount DE$ calculation step.

When the individual estimated sales DEI$ is selected (Y branch of step S560), the individual estimated milk production of the individual cow CWi on the prediction date is calculated and multiplied by the milk unit price q to obtain the individual estimated milk production DEI$ (step S570). . It is assumed that which individual cow is entered at the beginning of this step. Next, confirmation of re-input is performed (step S572), and if re-input is performed (Y branch of step S572), the individual cow is changed, etc., and step S570 is executed again. If re-input is not performed (N branch of step S572), the process moves to the next step (step S562).

When individual estimated total sales ΣDE$ is selected (Y branch of step S562), first. An individual estimated total milk yield SUM _DEY is calculated (step S504). This is obtained by executing step S504 in FIG. However, if individual estimated total milk yield SUM _DEY has already been calculated, that value may be used.

Then, the individual estimated total milk production SUM _DEY is multiplied by the milk unit price q to obtain the individual estimated total sales revenue ΣDE$ (step S580). The calculated individual estimated total sales ΣDE$ may be displayed on the terminal or the like.

Next, confirmation of re-input is performed (step S582), and if re-input is performed (Y branch of step S582), the predicted date and the like are changed, and step S504 is executed again. If re-input is not performed (N branch of step S582), the process is returned to the individual predicted sales amount DE$ step (step S584).

Through the above steps, the individual estimated total milk production SUM _DEY , which is the sum of the individual estimated milk production DEY of all individual cows belonging to the herd on the scheduled date, multiplied by the milk unit price q is calculated as the individual estimated total sales revenue ΣDE$. can do.

[Individual estimated gross sales calculation 2]
FIG. 26 shows the flow of the method of obtaining the individual estimated total sales revenue ΣDE$ as the sum of the estimated sales revenues of individual cows. When the step of calculating the estimated individual sales DE$ is started (step S126B), the calculation of the individual estimated sales DEI$ or the individual estimated total sales ΣDE$ is selected (steps S560, 564). When not selecting each, the processing is moved to the next. That is, in the N branch of step S560, the process proceeds to step S564, and in the N branch of step S564, the process returns to the individual predicted sales amount DE$ calculation step (step S600).

The flow for calculating the individual estimated sales amount DEI$ is the same as in the case of FIG. 25, so it will be omitted. If the calculation of individual estimated total sales ΣDE$ is selected (Y branch of step S564), initial setting is performed (step S590). The initial settings are the identification index i, the initialization of the individual estimated total sales ΣDE$ (i=1, ΣDE$=0), and the setting of the final value (END) of the number of individuals. The final value END is set to n+1, where "n" is the number of cows in the herd.

Next, the individual's estimated milk production amount DEY on the prediction date is calculated, multiplied by the milk unit price q, and added to the individual's estimated total sales revenue ΣDE$ to obtain a new individual's estimated total sales revenue ΣDE$ (step S592). It is checked whether addition up to the last individual cow has been completed (step S594), and if not completed (N branch of step S594), the identification index i is incremented (step S598), and the individual estimated total sales ΣDE$ is calculated. Addition (step S592) is repeated.

When the calculation is completed up to the last individual cow (Y branch of step S594), it is confirmed whether or not there is a re-input (step S596). At this time, the obtained individual estimated total sales ΣDE$ may be displayed on the terminal or the like. When re-inputting (Y branch of step S596), the predicted date and the like are changed, and the process is repeated from the initialization step (step S590). If not re-entered (N branch of step S596), the process is returned to individual predicted sales amount DE$ (step S600).

Through the above steps, for all individual cows in the herd, the individual estimated milk production is multiplied by the milk unit price q to calculate the sales for each individual, and the sum of these is calculated as the individual estimated total sales DE$. be able to.

Both A and B of steps S126 described above can be a step (step S126) of calculating the predicted individual sales amount DE$ in FIG.

<Determination of individual dry cow DDC>
Please refer to FIG. Once the individual estimated milk yield DEY has been calculated (step S120), the individual dry cow DDC can also be determined. Determination of the individual dry cow DDC will be described with reference to FIG. In FIG. 27, the horizontal axis is the number of days after parturition (days), and the vertical axis is the individual estimated lactation amount DEY (kg). The herd estimated milk yield EY is also drawn as a cow herd estimated lactation curve M.

The individual dry cow DDC can be obtained by applying a dry milk reference value DY _TH that can be judged as a dry cow to the estimated individual lactation curve DM. FIG. 27 shows that if the number of days after calving of this individual cow on the predicted date is greater than N6, then this individual cow is a candidate for an individual dry cow DDC. If the number of days after calving is less than N6, the individual cow is not an individual dry cow ( ^NOT DDC). The day (N6) of the intersection of the estimated individual lactation curve DM and the dry milk reference value DY _TH is the individual dry milk day DDYday.

In addition, the dry milk reference value DY _TH is obtained empirically, and when executing step S200 in FIG. 4 or step S500 in FIG. input.

There are two possible methods for distinguishing individual dried cows. A method of calculating the individual estimated milk yield DEY for each individual cow and comparing it with the dry milk standard value DY _TH , and the individual estimated milk yield DEY and the dry milk standard value DY _TH for each individual cow to determine the individual dry milk day DDYday and compare the number of days after parturition of the individual on the predicted date with the individual's dry milk date DDYday. Either method can serve as the individual dry cow discrimination step (step S128) in FIG.

[Individual Dry Cow Judgment 1]
FIG. 28 shows the flow of the method of calculating the individual estimated milk yield DEY for each individual cow and comparing it with the dry milk reference value DY _TH . When the process of determining individual dry cows is started (step S128A), initial setting is performed (step S610). The initial setting is the initialization of the identification index i and the setting of the final value (END) of the number of individuals. The identification index i is set to i=1 and the final value (END) is set to n+1. "n" is the number of dairy cows in the herd.

Next, the number of days after parturition Nr+X of the i-th individual cow CW _i on the predicted date is acquired (step S612). Here, Nr is the number of days after parturition on the individual specific date, and X is the number of days from the individual specific date to the predicted date.

Then, it is determined whether or not the number of days after parturition Nr+X on the predicted date is less than or equal to the individual early days Da (step S614). The individual early days Da is the day corresponding to the early days a, which is the day when the herd estimated milk yield EY first exceeds the dry milk reference value DY _TH (DC ₀ : see FIG. 13). The day on which the milk yield DEY first exceeds the dry milk threshold DY _TH . Normally, 30 to 50 days should be set.

If the number of days after parturition Nr+X is equal to or less than the individual early days Da, the process of incrementing the identification index i and obtaining the number of days after parturition Nr+X with another individual cow is repeated (step S612). This is because individual cows that have just given birth are not considered dry cows.

Then, it is determined whether or not the individual estimated milk yield DEY of the individual cow CW _i is equal to or less than the dry milk reference value DY _TH (step S616). If the individual estimated milk yield DEY of the individual cow CW _i is equal to or less than the dry milk reference value DY _TH (Y branch of step S616), the individual cow CW _i is displayed as a candidate for the individual dry milk cow (step S618), and all the individuals A determination is made as to whether or not the cow determination has been completed (step S620). If the individual estimated milk yield DEY of the individual cow CW _i is not equal to or less than the dry milk reference value DY _TH (N branch of step S616), step S618 is skipped and the process proceeds to step S620.

If the determination has not been completed up to the last individual cow (N branch of step S620), the step of incrementing the identification index i and acquiring the number Nr+X after parturition of the i-th individual cow CW _i on the prediction date (step S612) Back to If the determination has been completed up to the last individual cow (Y branch of step S620), the process returns to the step of determining the individual dry cow (step S624).

Through the above steps, an individual cow whose estimated individual milk yield DEY on the prediction date is lower than the dry milk reference value DY _TH can be displayed as a dry milk cow candidate.

[Individual Dry Cow Judgment 2]
FIG. 29 shows a flow for judging an individual dry cow using the individual dry milk day DDYday. When the process of determining individual dry cows is started (step S128B), initial setting is performed (step S640). The initial setting is the initialization of the identification index i and the setting of the final value (END) of the number of individuals. The identification index i is set to i=1 and the final value (END) is set to n+1. "n" is the number of dairy cows in the herd.

Next, the number of days after parturition N is set to the individual early days Da (step S642). Then, it is determined whether or not determination has been completed for all individual cows belonging to the herd (step S644). When finished (Y branch of step S644), the process is returned to the individual dry cow judgment step (step S660). If there are still individual cows to be judged (N branch of step S644), the process is shifted to the next step.

In the next process, it is determined whether or not the postpartum number N is the last (step S646). Assume that the final value of the postpartum number N is set in advance. Usually, it is set as the number of days after 260 days. If N is not the final value (N branch of step S646), the process proceeds to the next process (step S648), and if N is the final value (Y branch of step S646), the identification index i is incremented. (Step S658), the process returns to the step of setting the number of days postpartum N (Step S642).

If N is not the final value (N branch of step S646), the estimated individual milk production DEY on the predicted date of the i-th individual is the dry milk reference value DY _TH when the number of days after delivery is N. It is determined whether or not (step S648). This can be obtained from the individual regression equation on the predicted date of the individual cow CW _i . The individual regression formula for the predicted date of the individual cow CW _i is obtained by multiplying the formula (6) by the milk volume coefficient α _i of the individual cow CW _i . is.

If the estimated individual milk yield DEY does not fall below the dry milk reference value DY _TH (N branch of step S648), N is incremented (step S656), and the process returns to determine whether or not N is the last day (step S646). When the estimated individual milk yield DEY becomes equal to or less than the dry milk standard value DY _TH , the number N of days after sorting is determined as the individual dry milk day DDYday for this individual cow (step S650).

Then, it is determined whether the number of days after parturition of the individual cow CW _i on the predicted date is greater than the individual dry milk day DDYday (step S652). Nr[CW _i ] is the number of days after parturition of the individual cow CW _i on the individual specific date, and X is the number of days from the individual specific date to the predicted date. If the number of days after parturition of the individual cow CW _i on the predicted date is greater than the individual dry milk day DDYday (Y branch of step S652), the individual cow CWi is displayed as the individual dry milk cow DDC (step S654).

If the number of days after calving of the individual cow CW _i on the predicted date is not greater than the individual dry milk day DDYday (N branch of step S652), the identification index i is incremented and the process returns to the step of setting the number of days after calving N (step S642). In this way, for all individual cows belonging to the herd, the individual dry-milk day DDYday is obtained and compared with the number of days after calving of the individual cow on the predicted date to determine whether it is an individual dry-milk cow DDC. can be done.

By the above steps, it is possible to display an individual cow for which the number of days after parturition Nr+X (days) is greater than the individual dry milk day DDYday on which the estimated individual milk yield DEY on the prediction date is the dry milk reference value DY _TH , as an individual dry milk cow candidate. can.

Both A and B of steps S128 described above can be used as the step of determining the individual dry cow in FIG. 2 (step S128).

As described above, the milk yield calculation system according to the present invention predicts future milk yield based on past basic data. If we can predict future milk production, we can predict sales based on that quantity.

In addition, if the sales can be predicted, it becomes possible to compare with the cost of feed (this is the cost), and to estimate the productivity. For example, by inputting the feed cost by the user, it is possible to compare with the predicted sales and display that the feed cost is 30% of the predicted sales. As a result, it is possible to study feed loss and efficient feed formulation. In particular, it is possible to examine the formulation of concentrated feed.

In addition, milk components representing the content of fat, protein, and the like may also be predicted and displayed in the same manner. When the unit price of milk is increased when the concentration is equal to or higher than the predetermined concentration, and the unit price of milk is decreased when the concentration is less than the predetermined concentration, the sales proceeds may be displayed in consideration of the increase or decrease in the unit price of milk according to the predetermined concentration.

A milk production calculation system according to the present invention was implemented using data obtained from farms in Japan. This ranch is a multiple ranch in a certain region, and the number of dairy cows is about 5000 data. The population is monthly data for 2019. Factor parameters P are THI and hours of sunshine. THI uses the monthly average temperature and average humidity values. Sunshine hours are monthly totals. The results are shown in FIG.

FIG. 30( a ) shows values of THI and hours of sunshine for five months in February, May, August, and November of 2019. FIG. Approximate the average actual milk production (kg / day) and the number of days after parturition N of the target farm with a WOOD curve, and use the values obtained from it to estimate the estimated milk production EY as a factor parameter P. Simple regression using only THI The obtained result is shown in FIG. 30(b). FIG. 30(c) shows the result of obtaining the estimated milk yield EY by multiple regression using THI and the sunshine duration (monthly total) as the factor parameter P. In both cases, the postpartum postpartum period is 50 days.

When THI alone was used as the factor parameter P, the standard error varied considerably with 0.65. However, when THI and sunshine duration are used as the factor parameter P, the standard error is 0.17
As a result, it was found that the amount of actual milk could be estimated considerably.

The fact that milk production can be estimated from THI and sunshine hours has not been known until now, and will have a great impact on responses to future increases in milk production.

INDUSTRIAL APPLICABILITY The present invention can be suitably used for computerization of dairy farming.

1 milk production calculation system 10 terminal 12 main body
14 memory 16 ranch 18 external information

Claims (16)

Based on the pasture data including the number of days after calving and actual milk volume of each individual cow that constitutes the cattle herd before the prediction start date and climate data, the milk production of the individual cow on the prediction date after the prediction start date is calculated. A milk production calculation system that calculates as a group estimated milk production,
a memory for accumulating the ranch data;
an interpolation formula creation unit that creates an interpolation formula for interpolating the relationship between the number of days after parturition for a certain period in the ranch data prior to the predicted start date and the actual milk yield;
The interpolated milk yield at the specific postpartum calculated from the interpolation formula is used as an objective variable, and at least one factor parameter selected from the ranch data is used as an explanatory variable, and the herd estimated milk yield for each of the postpartum days is used. a regression formula creating unit for creating a regression formula for calculating
In the regression equation corresponding to the number of days postpartum on the predicted date,
A milk production calculation system having a control device having a herd estimated milk production calculation unit including a herd regression formula calculator for calculating the herd estimated milk production by substituting the explanatory variable values assumed on the prediction date. . 2. The milk production calculation system according to claim 1, further comprising a herd forecast sales calculation unit for calculating sales based on the estimated cow herd milk production and the unit price of milk assumed on the forecast date. The estimated herd sales proceeds calculation unit has an estimated individual herd sales proceeds calculation unit that calculates estimated individual herd sales proceeds obtained by multiplying the estimated milk production of the herd on the forecast day by the unit price of milk. The milk production calculation system according to claim 2. The herd forecast sales calculation unit calculates the herd estimated total milk production obtained by multiplying the herd estimated total milk production, which is the sum of the herd estimated milk production of individual cows belonging to the herd on the prediction date, by the milk unit price. 4. The milk production calculation system according to claim 2 or 3, further comprising a cow herd estimated total sales proceeds calculation unit for calculating the sales proceeds. The estimated herd sales revenue calculation unit calculates the sum of the estimated herd individual sales revenues obtained by multiplying the estimated milk yield of the individual cows belonging to the herd on the prediction date by the unit price of milk. 4. A milk production calculation system according to claim 2 or 3, further comprising a herd estimated total sales proceeds calculation unit for calculating sales proceeds. The milk production amount according to claim 1, further comprising a herd dry cow determination unit that indicates dry cow candidates among the dairy cows belonging to the herd on the prediction date based on the herd estimated milk production and the dry milk reference value. calculation system. 7. The milk production amount according to claim 6, wherein the herd dry milk cow determination unit displays the individual cows whose estimated herd milk production amount on the prediction date is lower than the dry milk reference value as candidates for the herd dry milk cow candidates. calculation system. The herd dry-milk cow determination unit displays the individual cows for which the number of days after parturition is greater than the herd dry-milk date on which the herd estimated milk production on the prediction date is the dry-milk reference value is displayed as the herd dry-milk cow candidate. The milk production calculation system according to claim 6. The estimated milk production of the individual cow on the forecast date after the forecast start date based on the pasture data including the number of days after calving and actual milk volume of each individual cow that constitutes the cattle herd before the forecast start date, and the climate data. A milk production calculation system that calculates as an individual estimated milk production,
a memory for accumulating the ranch data;
an interpolation formula creation unit that creates an interpolation formula for interpolating the relationship between the number of days after parturition for a certain period in the ranch data prior to the predicted start date and the actual milk yield;
Using the interpolated milk volume at the specific postpartum calculated from the interpolation formula as the objective variable and at least one factor parameter selected from the ranch data as the explanatory variable, the herd estimated milk yield is calculated for each postpartum postpartum. a regression formula creating unit for creating a regression formula to be calculated;
In the regression equation corresponding to the number of days after parturition of the individual cow on the predicted start date,
a herd regression formula calculator that calculates the herd estimated milk yield by substituting the values of the explanatory variables assumed on the prediction start date;
A milk yield coefficient calculation unit that calculates, as a milk yield coefficient, a ratio of the specific individual cow to the regression equation based on the herd estimated milk yield on the prediction start date and the actual milk yield of the specific individual cow on the prediction start date. and,
In the regression equation corresponding to the number of days after parturition of the specific individual cow on the prediction date,
Estimated individual milk production calculation including an individual regression equation calculation unit that calculates an estimated individual milk production by substituting the values of the explanatory variables assumed on the prediction date and multiplying the obtained result by the milk production coefficient. A milk production system having a controller with a unit. 10. The milk production calculation system according to claim 9, further comprising an estimated individual sales revenue calculation unit that calculates sales based on the estimated individual milk production volume and the unit price of milk assumed on the prediction date. 10. The estimated individual sales proceeds calculation unit further comprises an estimated individual sales proceeds calculation unit that calculates the estimated individual sales proceeds of the specific individual cow on the prediction date by multiplying the estimated individual milk production amount by the unit price of milk. The milk production calculation system described in . The individual estimated sales revenue calculation unit multiplies the individual estimated total milk production, which is the sum of the individual estimated milk production of all the individual cows belonging to the cow herd on the scheduled date, by the milk unit price, and calculates the estimated individual sales. 12. The milk production calculation system according to claim 10 or 11, further comprising an individual estimated total sales proceeds calculation unit for calculating as money. The estimated individual sales revenue calculation unit calculates the sales revenue for each individual by multiplying the estimated individual milk yield by the unit price of milk for all the individual cows in the herd, 12. The milk production calculation system according to claim 10 or 11, further comprising an individual estimated total sales amount calculation unit for calculating the total sales amount. 10. The milk production amount according to claim 9, further comprising an individual dry cow determination unit that indicates dry cow candidates among dairy cows belonging to the herd on the prediction date based on the estimated individual milk production amount and the dry milk reference value. calculation system. 15. The lactating cow according to claim 14, wherein the individual dry cow determination unit displays the individual cow for which the estimated individual milk yield on the prediction date is lower than the dry milk reference value as the dry cow candidate. quantity calculation system. The individual dry dairy cow determination unit displays the individual cows for which the number of days after parturition is greater than the individual dry milk date on which the individual estimated milk production on the prediction date is the dry milk reference value is displayed as an individual dry dairy cow candidate. 15. A milk production calculation system according to claim 14.

Images