Decision device, program, and decision method

Abstract

The present invention provides a determination device comprising: a species setting unit that sets a species indicating the type of organism to be raised in a rearing space; a feed price setting unit that sets the feed price for the organism; and a rearing density determination unit that determines an initial rearing density, which is the rearing density at the start of rearing the organism, based on the species and the feed price, that maximizes the profit, which is the difference between the total sales revenue, which is the sales revenue after the rearing of the plurality of organisms in the rearing space has ended, and the total rearing cost, which is the rearing cost from the start to the end of rearing the plurality of organisms in the rearing space.

Description

[Technical Field]

[0001] The present invention relates to a decision device, a program, and a decision method. [Background technology]

[0002] Patent Document 1 describes an aquaculture simulation device for performing simulations related to the cultivation of fish schools, comprising a feeding calculation unit that calculates feeding information for each individual fish in the school through feeding, and an output unit that outputs the feeding information calculated by the feeding calculation unit. Patent Document 2 describes a technique for land-based aquaculture of aquatic organisms in which environmental data such as illuminance and water quality in a tank, feeding information such as the amount of feed given to aquatic organisms, and aquatic organism data such as the size of aquatic organisms are stored in a database, and the vast amount of stored data is repeatedly analyzed and learned from. [Prior art document] [Patent] [Patent Document 1] Japanese Unexamined Patent Publication No. 2023-015795 [Patent Document 2] Japanese Unexamined Patent Publication No. 2019-170349 [Overview of the project] [Means for solving the problem]

[0003] According to one embodiment of the present invention, a determination device is provided. The determination device may include a species setting unit for setting a species that indicates the type of organism to be raised in a rearing space. The determination device may include a feed price setting unit for setting the feed price of the organism. The determination device may include a rearing density determination unit for determining an initial rearing density, which is the rearing density at the start of rearing the organisms, based on the species and the feed price, that maximizes the profit, which is the difference between the total sales revenue, which is the sales revenue after the rearing of the plurality of organisms in the rearing space, and the total rearing cost, which is the rearing cost from the start to the end of rearing the plurality of organisms in the rearing space.

[0004] In the determination device, the rearing density determination unit may simulate the profit as a function of the initial rearing density and determine the initial rearing density to maximize the profit.

[0005] In any of the above-mentioned determination devices, the stocking density determination unit may use the function configured such that the stocking period, which is the period from the start to the end of stocking of the organism, depends on the initial stocking density.

[0006] In any of the above-mentioned determination devices, the stocking density determination unit may use the function configured such that the total sales revenue depends on the survival rate of the organism, which depends on the initial stocking density.

[0007] In any of the above-mentioned determination devices, the stocking density determination unit may use a function configured such that the total stocking cost depends on the initial cost per unit weight, which is the initial cost per unit weight of the organisms at the start of stocking, and the purchase cost of the multiple organisms at the start of stocking, which depends on the initial stocking density; the feeding cost of the multiple organisms, which depends on the stocking period and the feed price; and the running cost, which depends on the stocking period and the labor and fuel costs of stocking the multiple organisms.

[0008] In any of the above-mentioned determination devices, the stocking density determination unit may determine the initial stocking density using a learning model that takes the initial stocking density, feed price, and parameters related to the organism as input and outputs the profit, which is generated by machine learning using the initial stocking density, feed price, parameters related to the organism, and actual profits from past stocking of the plurality of organisms as learning data. The determination device may further include a learning execution unit that generates the learning model by performing machine learning using the learning data. The parameters related to the organism may include at least one of the following: the species of the organism, the weight unit price at the start of the organism's stocking, the weight unit price at the end of the organism's stocking, the relationship between the elapsed time from the start of the organism's stocking and the average weight, the relationship between the elapsed time and the survival rate of the organism, and the growth rate, which is the ratio of the weight at the start of the organism's stocking to the weight at the end of the stocking.

[0009] In any of the determination devices described above, the stocking density may be the ratio of the size of the area in which the organisms can move freely to the number of organisms in the stocking space at the start of stocking.

[0010] In any of the aforementioned determination devices, the organism may be one that satisfies at least one of the following conditions: the number of deaths during rearing increases as the rearing density increases, and the growth rate decreases as the rearing density increases.

[0011] According to one embodiment of the present invention, a program is provided for a computer to perform the following steps: a species setting step of setting a species that indicates the type of organism to be raised in a rearing space; a feed price setting step of setting the feed price of the organism; and a rearing density determination step of determining an initial rearing density, which is the rearing density at the start of rearing the organisms that maximizes the net profit, which is the difference between the total rearing cost, which is the rearing cost of a plurality of organisms in the rearing space from the start to the end of rearing, and the total sales revenue, which is the sales revenue after the rearing of the plurality of organisms in the rearing space has ended.

[0012] According to one embodiment of the present invention, a decision-making method performed by a computer is provided. The determination method may include a species setting step of setting a species that indicates the type of organism to be raised in the rearing space. The determination method may include a feed price setting step of setting the feed price of the organism. The determination method may include a rearing density setting step of determining the initial rearing density, which is the rearing density at the start of rearing the organisms, based on the species and the feed price, that maximizes the net profit, which is the difference between the total rearing cost, which is the rearing cost of multiple organisms in the rearing space from the start to the end of rearing, and the total sales revenue, which is the sales revenue after the rearing of multiple organisms in the rearing space has ended.

[0013] It should be noted that the above summary of the invention does not enumerate all the necessary features of the present invention. Furthermore, subcombinations of these features may also constitute an invention. [Brief explanation of the drawing]

[0014] [Figure 1] An example of the decision device 100 is shown schematically. [Figure 2] A schematic example of a 300-unit fishpond, which is an example of a 200-unit breeding space, is shown. [Figure 3] An example of the functional configuration of the decision device 100 is shown schematically. [Figure 4] A schematic example of the hardware configuration of the computer 1200, which functions as a decision device 100, is shown below. [Modes for carrying out the invention]

[0015] The present invention will be described below through embodiments of the invention, but these embodiments are not intended to limit the invention as defined in the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0016] In recent years, due to the soaring feed prices, the conventional aquaculture methods and feeding methods relying on past experience and intuition have become unprofitable. For example, in the case of aquaculture fish, the profit obtained at the time of landing varies depending on the number of fish stocked per unit volume V of the fishpond. If the stocking density is too low, the number of fish that can be shipped will decrease, and the income may not be expected. However, if the stocking density is too high, the health of the target fish will be damaged, not only the growth rate will slow down, but there is also a possibility that the fish will become sick or die and cannot be used as a commodity, which may instead compress the profitability. In addition, since the amount of dissolved oxygen that can be consumed per fish changes depending on the stocking density, the stocking density is closely related to the appetite and growth of the fish, and the feed efficiency changes depending on the stocking density. Therefore, from the perspective of management, the stocking density has aspects that should depend on factors such as feed prices. However, conventionally, it has not been possible to systematically determine what the optimal stocking density is to maximize the final economic benefit, and it has been necessary to roughly determine the initial stocking density based on past experience and the balance of rising feed costs. Even when performing simulations, the simulation of the feeding amount is mainly carried out, and there is no prior art focusing on the initial stocking density. The determination device 100 according to the present embodiment provides a technology that contributes to solving such problems.

[0017] FIG. 1 schematically shows an example of the determination device 100. The determination device 100 has a function of determining a recommended initial stocking density when a plurality of organisms are stocked in the breeding space 200.

[0018] In the present embodiment, the target organism may be an organism that satisfies at least one of the following conditions: the higher the stocking density, the higher the mortality rate during breeding, and the higher the stocking density, the lower the growth rate. Examples of such organisms include fish, birds, pigs, and cows, but any other organism that satisfies the conditions may be used.

[0019] The breeding space 200 is a space for breeding the target organism. When the target organism is a fish, the breeding space 200 may be an aquarium. When the target organism is a chicken, the breeding space 200 may be a chicken farm. When the target organism is a pig, the breeding space 200 may be a pig farm. When the target organism is a cow, the breeding space 200 may be a ranch.

[0020] The breeding density may be the ratio of the size of the area where the organism can move freely to the number of organisms at the start of breeding in the breeding space 200. The area where the organism can move freely in the breeding space 200 may be the strictly measured part of the breeding space 200 where the organism can move freely, or it may not be. For example, the size of the breeding space 200 may be used as the area where the organism can move freely in the breeding space 200. The size of the breeding space 200 may be the volume of the breeding space 200 or the area of the breeding space 200.

[0021] The recommended initial breeding density may be the initial breeding density for maximizing the profit, which is the difference between the total sales revenue, which is the sales revenue after breeding multiple organisms in the breeding space 200, and the total breeding cost, which is the breeding cost from the start to the end of breeding multiple organisms in the breeding space 200.

[0022] For example, the determination device 100 receives an input of the species of the target organism to be bred in the breeding space 200 and the feed price of the target organism, and determines the recommended initial breeding density. The feed price of the organism can vary due to various factors, but according to the determination device 100, the recommended initial breeding density corresponding to the feed price at that time can be determined.

[0023] As an example, the determination device 100 simulates the profit as a function of the initial breeding density and determines the initial breeding density to maximize the profit.

[0024] As another example, the decision device 100 generates a learning model using machine learning based on past rearing data from rearing in the rearing space 200, and uses this learning model to determine the initial rearing density. For example, the decision device 100 uses the initial rearing density, feed price, parameters related to the target organism, and actual profit from past rearing of multiple organisms in the rearing space 200 as learning data to generate a learning model that takes the initial rearing density, feed price, and parameters related to the target organism as input and outputs the profit. Then, the decision device 100 inputs the parameters related to the target organism whose initial rearing density is to be determined, the feed price, and multiple initial rearing densities into the learning model to determine the initial rearing density that maximizes the profit.

[0025] Figure 2 schematically shows an example of a fish farm 300, which is an example of a rearing space 200. The fish farm 300 is a space for cultivating fish 310. Examples of fish 310 include red sea bream, yellowtail, bluefin tuna, greater amberjack, and horse mackerel, but it is not limited to these; any fish that can be farmed is acceptable.

[0026] The relationship between aquaculture density and profitability includes increased profits due to improved quality per fish and reduced mortality rates at low density, and decreased profits due to a reduction in the number of fish per cage at high density. Generally, it is believed that profits will be higher if aquaculture is carried out at the highest possible density, taking into account the health of the fish. However, the inventor found through experiments that at commonly used densities, the number of fish that become unhealthy or die increases more than generally imagined, and profitability decreases. This is thought to be because higher density increases the probability of fish colliding with each other, and these collisions cause the protective membrane on the fish's body surface to peel off or the fish to be damaged. In addition, it is thought that high aquaculture density also has an effect because the amount of dissolved oxygen that each fish can consume decreases, leading to a decrease in the fish's appetite and slower growth. From this perspective, a lower density is preferable, but if the density is too low, sales volume will decrease, and profits will decline. Therefore, it is thought that there is an optimal initial aquaculture density that is neither too high nor too low. The decision device 100 determines the initial aquaculture density that maximizes profits by, for example, solving an optimization problem of an objective function that includes these factors. Below, an example of the logic by which the decision device 100 determines the initial aquaculture density will be explained step by step.

[0027] The decision-making device 100 models an objective function called Revenue R, taking into account the parameters in Table 1 below, and systematically derives an initial aquaculture density that maximizes R. As mentioned above, it has been experimentally proven that the lower the initial aquaculture density, the better the quality per fish and the fewer fish die.

[0028] [Table 1]

[0029] Here, we define time t=0 as when the farmed fish are introduced into cage 300, and t=T as the time of shipment. That is, T represents the farming period. In this embodiment, we assume that T depends on the initial fish population density and is represented by the following equation 1. The relationship between the initial fish population density and the farming period may be determined, for example, from trends in past farming operations or by simulation.

[0030]

number

[0031] The weight of 310 fish increases over time, so it can be expressed as a function of t, and the total weight of 310 fish per 300 fish tank is ρ W (t)V. The profit R obtained from one fish farm of 300 is ρ W (t)It can be inferred that it is proportional to V and can be expressed by the following equation 2.

[0032]

number

[0033] By the way, it is currently difficult to directly calculate or estimate the weight density of 310 fish in a 300-liter fish tank. Therefore, it is expressed as an estimated quantity based on actual measurements using the following formula 3.

[0034]

number

[0035] Therefore, the profit R can be expressed by the following formula 4.

[0036]

number

[0037] Applying the price per kilogram of fish 310 at the time of shipment to formula 4, it can be expressed as formula 5 below. For the price per kilogram at the time of shipment, for example, the market price may be used. For the price per kilogram at the time of shipment, a value entered by a person may be used, or a value estimated from past history may be used.

[0038]

number

[0039] If the survival rate at the time of shipment for the initial fish population density is expressed by equation 6 below, then equation 5 can be expressed by equation 7 below.

[0040]

number

[0041]

number

[0042] From equation 7, we subtract the costs incurred from purchasing the fry to shipping them. First, the cost of purchasing the fry can be expressed by equation 8 below.

[0043]

number

[0044] Subtracting this from equation 7 results in equation 9 below.

[0045]

number

[0046] Here, T is defined as the condition when the following equation 10 is satisfied, and the growth rate in the following equation 11 is given by the r shown in the table above. fish Assuming these quantities are fixed, equation 9 can be expressed as equation 12 below.

[0047]

number

[0048]

number

[0049]

number

[0050] Next, running costs C, excluding feed costs, such as fuel costs and labor costs. run Subtract this from equation 12. Experiments suggest that T, which depends on the initial fish population density, is likely an increasing function of the initial fish population density. Therefore, the running cost c at time t is run (t) represents the total cost during the farming period, which is given by the following equation 13. C run If the total capacity of the 300 fish tanks is constant, the volume V per fish tank increases, meaning that it decreases as the number of fish tanks decreases, and this can be used as the basis for setting the value. run This can be set based on past records from aquaculture operations.

[0051]

number

[0052] Subtracting equation 13 from the right-hand side of equation 12 yields equation 14 below.

[0053]

number

[0054] Next, calculate the feeding cost and subtract it from the right side of Equation 14 to complete the construction of the objective function. The daily required feeding amount m(t) can be expressed by the following Equation 15 by using the coefficient η(V). The coefficient η(V) may be calculated from, for example, the growth coefficient. The growth coefficient is the amount of feed required to increase the weight of one fish by 1 kg, and in the range handled in the aquaculture industry, it is considered to be a monotonically increasing function of V.

[0055]

Number

[0056] Here, in a common-size fish cage 300, since the required amount of feed may increase as the volume V increases, the coefficient η(V) is assumed to be proportional to V. However, there may be cases where the required amount of feed does not increase as the volume V increases. In such cases, the coefficient may not be proportional to V and may be a value independent of V.

[0057] The feed cost during the cultivation period can be expressed by the following Equation 16.

[0058]

Number

[0059] To calculate this directly, the time-series data of ρ # (t) and μ fish (t)ρ # (t) are required. In the decision-making device 100, these time-series data may be acquired by using the monitoring system of the fish 310. The decision-making device 100 may substitute the right side of the following Equation 17 on the premise that no fish 310 dies during the cultivation period.

[0060]

Number

[0061] From the above, the profit R can be expressed by the following Equation 18.

[0062]

number

[0063] The first term in parentheses corresponds to the sales profit at the time of shipment, the second term in parentheses corresponds to the cost of purchasing juvenile fish, the third term in parentheses corresponds to the cost of feed for aquaculture, and the integral outside the parentheses corresponds to costs other than feed, such as labor costs and fuel costs. As mentioned above, the third term in parentheses is an approximate formula using a theoretical upper limit, but in the case of a fish farm 300 with a fish monitoring system 310, time-series data from the monitoring system may be used.

[0064] In a fish farm 300 where no monitoring system exists, if an attempt is made to improve accuracy, the decision device 100 may replace the third term in parentheses with the following formula 19 by assuming that the number of fish 310 that die is constant and the growth rate is linear over time.

[0065]

number

[0066] The determination device 100 may determine the initial fish density that maximizes the profit R by using equation 18. Conventionally, the optimal initial density in fish farming 310 was determined by intuition and experience, but with the determination device 100, the theoretically optimal initial density can be determined, which can contribute to improving the efficiency of fish farming 310.

[0067] Figure 3 schematically shows an example of the functional configuration of the decision device 100. The decision device 100 comprises a storage unit 110, a setting unit 120, a rearing density determination unit 140, a learning execution unit 142, and an output control unit 144. It is not necessarily required that the decision device 100 comprises all of these components.

[0068] The setting unit 120 performs various settings. The setting unit 120 may accept settings from the user via the user interface. The setting unit 120 stores the set information in the storage unit 110.

[0069] The setting unit 120 may have a rearing space setting unit 121. The rearing space setting unit 121 sets information related to the target rearing space 200. For example, the rearing space setting unit 121 sets the size of the rearing space 200. If the rearing space 200 is a fish pen, the rearing space setting unit 121 may set the volume of the space inside the pen. If the rearing space 200 is a poultry farm, the rearing space setting unit 121 may set the area of ​​the poultry farm. If the rearing space 200 is a pig farm, the rearing space setting unit 121 may set the area of ​​the pig farm. If the rearing space 200 is a pasture, the rearing space setting unit 121 may set the area of ​​the pasture.

[0070] The setting unit 120 may include a feed price setting unit 122. The feed price setting unit 122 sets the price of feed for the target organism. The feed price setting unit 122 may set a weight-based price, which is the price per unit weight of feed. The unit weight may be, for example, in kilograms.

[0071] The setting unit 120 may include an average weight setting unit 123. The average weight setting unit 123 may set the average weight of the target organism. The average weight setting unit 123 may set the average weight for each elapsed time since the start of rearing the target organism. Based on the measured weight for each elapsed time since the start of rearing the organism, the average weight setting unit 123 may identify the relationship between time and weight and generate and use at least one of a function, statistical table, and learning model to estimate the average weight for each elapsed time since the start of rearing.

[0072] The setting unit 120 may have an initial weight unit price setting unit 124. The initial weight unit price setting unit 124 may set a weight unit price, which is the price per unit weight at the start of rearing the target organism. The unit weight may be, for example, in kilograms. If the target organism is a fish, the initial weight unit price setting unit 124 may set the weight unit price for a juvenile fish. If the target organism is a bird, the initial weight unit price setting unit 124 may set the weight unit price for a chick. If the target organism is a pig, the initial weight unit price setting unit 124 may set the weight unit price for a piglet. If the target organism is a cow, the initial weight unit price setting unit 124 may set the weight unit price for a calf.

[0073] The setting unit 120 may include a unit price setting unit 125 at the end of the breeding period. The unit price setting unit 125 may set a unit price, which is the price per unit weight at the end of the breeding period for the target organism. The unit weight may be, for example, in kilograms. The end of the breeding period may be when the weight of the target organism reaches the target weight.

[0074] The setting unit 120 may include a survival rate setting unit 126. The survival rate setting unit 126 may set the survival rate for each elapsed time since the start of rearing the target organism. Based on the measured values ​​of the survival rate for each elapsed time when the target organism is actually reared, the survival rate setting unit 126 may identify the relationship between the passage of time and the survival rate, and generate and use at least one of a function, statistical table, and learning model for estimating the survival rate for each elapsed time since the start of rearing the target organism. The survival rate setting unit 126 may also set a constant value as the survival rate.

[0075] The setting unit 120 may include a growth rate setting unit 127. The growth rate setting unit 127 may set the growth rate of the target organism. The growth rate may be, for example, the value obtained by dividing the weight at the end of rearing by the weight at the start of rearing. The growth rate setting unit 127 may generate and use at least one of a function, statistical table, and learning model for estimating the growth rate based on the measured weight at each elapsed time when the target organism was actually reared. The growth rate setting unit 127 may also set a constant value as the growth rate.

[0076] The setting unit 120 may include a running cost setting unit 128. The running cost setting unit 128 may set the running costs for each elapsed time since the start of raising the target organism. The running cost setting unit 128 sets the running costs by, for example, multiplying the labor costs per unit hour, fuel costs per unit hour, and miscellaneous expenses per unit hour by the total time and adding them up. The running cost setting unit 128 may generate and use at least one of a function, statistical table, and learning model for estimating the running costs for each elapsed time based on the total labor costs, total fuel costs, and total miscellaneous expenses for each elapsed time when the target organism is actually raised.

[0077] The setting unit 120 includes a species setting unit 130. The species setting unit 130 sets the species that indicates the type of organism to be raised in the rearing space 200. The species setting unit 130 may set the species that has been entered by a user requesting the recommended initial rearing density of the target organism via the user interface.

[0078] The stocking density determination unit 140 determines the recommended initial stocking density for the target organism. The stocking density determination unit 140 determines the initial stocking density that maximizes the profit, which is the difference between the total sales revenue, which is the sales profit after the completion of the stocking of multiple organisms in the stocking space 200, and the total stocking costs, which is the stocking costs from the start to the end of the stocking of multiple organisms in the stocking space 200.

[0079] The stocking density determination unit 140 may determine the initial stocking density based on the species set by the species setting unit 130 and the feed price for the target organism set by the feed price setting unit 122.

[0080] For example, the stocking density determination unit 140 simulates profit as a function of the initial stocking density and determines the initial stocking density to maximize profit.

[0081] The stocking density determination unit 140 may use a function configured such that the stocking period, which is the period from the start to the end of stocking of the target organism, depends on the initial stocking density. The stocking density determination unit 140 may use a function configured such that the relationship between the stocking period and the initial stocking density is such that the higher the initial stocking density, the longer the stocking period. The lower the initial stocking density, the less interference between organisms there is, the faster their growth tends to be, and the shorter the stocking period tends to be. The higher the initial stocking density, the more interference between organisms there is, and the more organisms collide, causing damage to the organisms, or damage to the mucous membranes, skin, hair, etc. that protect the body surface, resulting in slower growth and a longer stocking period. By using a function configured such that the higher the initial stocking density, the longer the stocking period becomes, the stocking density determination unit 140 can determine an initial stocking density that reflects this relationship.

[0082] The stocking density determination unit 140 may use a function configured such that total sales revenue depends on the survival rate of organisms, which depends on the initial stocking density. The stocking density determination unit 140 may use a function configured such that the relationship between initial stocking density and survival rate is such that the higher the initial stocking density, the lower the survival rate. The lower the initial stocking density, the less interference between organisms there is, and the higher the survival rate tends to be. The higher the initial stocking density, the more interference between organisms there is, and the more organisms collide, causing damage to the organisms, or damage to protective mucous membranes, skin, hair, etc., which tends to be, and the lower the survival rate tends to be. By using a function configured such that the growth rate is lower as the initial stocking density increases, the stocking density determination unit 140 can determine an initial stocking density that reflects this relationship.

[0083] The stocking density determination unit 140 may use a function configured such that the total stocking cost depends on the initial cost per unit weight, which is the unit price of the organisms at the start of stocking, the purchase cost of the multiple organisms at the start of stocking, which depends on the initial stocking density, the feeding cost of the multiple organisms, which depends on the stocking period and feed prices, and the running cost, which depends on the stocking period and the labor and fuel costs of stocking the multiple organisms.

[0084] The purchase cost may be calculated by multiplying the initial stocking density by the volume of the stocking space (200 units) and then multiplying that by the initial price per unit weight.

[0085] Feeding costs may be calculated by multiplying the daily required amount of feed by the rearing period. The daily required amount of feed depends on the total weight of organisms in the rearing space 200. The rearing density determination unit 140 may calculate the daily required amount of feed by multiplying the total weight of organisms in the rearing space 200 by a coefficient that shows the relationship between the weight of an organism and the amount of feed that an organism of that weight consumes per day. The coefficient that shows the relationship between the weight of an organism and the amount of feed that an organism of that weight consumes per day may be determined by the relationship between the weight and the amount of feed when organisms are actually reared. In some cases, depending on the rearing space 200, the amount of feed required may increase as the volume of the rearing space 200 increases. In such cases, the coefficient may be configured to depend on the volume of the rearing space 200.

[0086] Running costs may be calculated by multiplying the daily labor and fuel costs by the breeding period. Daily labor and fuel costs may be set based on the actual labor and fuel costs at that time in the breeding space 200. Daily labor and fuel costs may also be set based on the history of past labor and fuel costs in the breeding space 200. Running costs may include miscellaneous expenses incurred in addition to labor costs, fuel costs, and feed costs.

[0087] The rearing density determination unit 140 may use formula 18. The rearing density determination unit 140 may also use formula 19 by replacing the third term in parentheses in formula 18.

[0088] The learning execution unit 142 performs machine learning to generate a learning model used to determine the recommended initial stocking density when the target organism is stocked in the target stocking space 200. The stocking density determination unit 140 may determine the initial stocking density using the learning model generated by the learning execution unit 142.

[0089] For example, the learning execution unit 142 uses machine learning, with initial stocking density, feed price, parameters related to the organism, and actual profits from past breeding operations of multiple target organisms as training data, to generate a learning model that takes initial stocking density, feed price, and parameters related to the organism as input and outputs profit.

[0090] The parameters related to the organism may include the species of the organism in question. This allows for the determination of a recommended initial stocking density for each species, in response to changes in feed prices. Feed prices can fluctuate due to various factors. When feed prices change significantly, it is necessary to adjust the initial stocking density accordingly, but it is difficult for a person to make such a judgment. A person with sufficient experience may be able to make an appropriate judgment, but it is difficult to assign a person with sufficient experience to every stocking space 200. According to the determination device 100 of this embodiment, it is possible to determine an initial stocking density that maximizes profits in accordance with feed prices, thereby contributing to the efficiency of aquaculture.

[0091] The parameters related to the organism may include the weight cost per unit of weight of the target organism at the start of rearing. This allows for the determination of a recommended initial rearing density that corresponds to changes in the weight cost per unit of weight of the organism at the start of rearing, in addition to the feed price of the organism. The weight cost per unit of weight of an organism at the start of rearing, which is equivalent to the weight cost per unit of weight of juvenile fish, can fluctuate due to various factors. If the weight cost per unit of weight at the start of rearing changes significantly, it is necessary to adjust the initial rearing density accordingly, but it is difficult for a person to make that judgment. A person with sufficient experience may be able to make an appropriate judgment, but it is difficult to assign a person with sufficient experience to every rearing space 200. According to the determination device 100 of this embodiment, it is possible to determine an initial rearing density that maximizes profit according to the weight cost per unit of weight of the organism at the start of rearing, and this can contribute to the efficiency of aquaculture.

[0092] The parameters related to the organism may include the unit price per weight of the organism at the end of its rearing period. This allows for the determination of a recommended initial rearing density that corresponds to changes in the unit price per weight of the organism at the end of its rearing period, in addition to the feed price of the organism. The unit price per weight of the organism at the end of its rearing period may be, for example, the market selling price per weight of an organism that has reached its target weight and is sold on the market. The unit price per weight of the organism at the end of its rearing period can fluctuate due to various factors. If the unit price per weight at the end of its rearing period changes significantly, it is necessary to adjust the initial rearing density accordingly, but it is difficult for a person to make that judgment. A person with sufficient experience may be able to make an appropriate judgment, but it is difficult to assign a person with sufficient experience to all rearing spaces 200. According to the determination device 100 of this embodiment, it is possible to determine an initial rearing density that maximizes profit according to the unit price per weight of the organism at the end of its rearing period, and this can contribute to the efficiency of aquaculture.

[0093] The parameters related to the organism may include the relationship between the elapsed time since the start of rearing and the average weight of the organism. This allows for the determination of a recommended initial stocking density that corresponds to the relationship between the elapsed time since the start of rearing and the average weight of the organism, in addition to the feed price of the organism. The change in average weight with respect to the elapsed time since the start of rearing can vary greatly depending on the species of organism. By using this relationship, it becomes possible to estimate how the total weight of multiple organisms changes over time, and the accuracy of the initial stocking density that maximizes profit can be improved.

[0094] The parameters related to the organism may include the relationship between the organism's elapsed time and its survival rate. This allows for the determination of a recommended initial stocking density that corresponds to the relationship between the organism's elapsed time and its survival rate, in addition to the organism's feed price. Since the survival rate relative to elapsed time depends on the organism's species and also on the initial stocking density, using these in the learning process can improve the accuracy of the initial stocking density that maximizes profits.

[0095] The parameters related to the organism may include the growth rate, which is the ratio of the organism's weight at the start of rearing to its weight at the end of rearing. This allows for the determination of a recommended initial rearing density that corresponds to the organism's growth rate, in addition to the cost of the organism's feed. Since the organism's growth rate depends on the species, using the organism's growth rate in the learning process can help determine a recommended initial rearing density that reflects the impact of the growth rate on the rearing period.

[0096] Figure 4 schematically shows an example of the hardware configuration of a computer 1200 that functions as a decision device 100. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the apparatus according to this embodiment, or to cause the computer 1200 to execute operations associated with the apparatus according to this embodiment or such one or more "parts", and / or to cause the computer 1200 to execute a process or a stage of such process according to this embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0097] The computer 1200 according to this embodiment includes a CPU 1212, RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive may be a DVD-ROM drive and a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive and a solid-state drive, etc. The computer 1200 also includes legacy input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0098] The CPU 1212 operates according to the programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires the image data generated by the CPU 1212 and stores it in the frame buffer provided in RAM 1214 or within itself, so that the image data is displayed on the display device 1218.

[0099] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive reads programs or data from a DVD-ROM or the like and provides them to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0100] The ROM 1230 stores boot programs and / or hardware-dependent programs of the computer 1200, which are executed by the computer 1200 upon activation. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0101] The program is provided on a computer-readable storage medium such as a DVD-ROM or IC card. The program is read from the computer-readable storage medium and installed on a storage device 1224, RAM 1214, or ROM 1230, which are examples of computer-readable storage media, and executed by the CPU 1212. The information processing described within these programs is read by the computer 1200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the operation or processing of information in accordance with the use of the computer 1200.

[0102] For example, when communication is performed between a computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into RAM 1214 and, based on the processing described in the communication program, instruct the communication interface 1222 to perform communication processing. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in a recording medium such as RAM 1214, storage device 1224, DVD-ROM, or IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area provided on the recording medium.

[0103] Furthermore, the CPU 1212 may read all or necessary parts of a file or database stored on an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), or an IC card into the RAM 1214, and perform various types of processing on the data in the RAM 1214. The CPU 1212 may then write the processed data back to the external recording medium.

[0104] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 1212 may perform various types of processing on the data read from RAM 1214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to RAM 1214. The CPU 1212 may also retrieve information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 1212 may search among the multiple entries for an entry that matches the specified condition for the attribute value of the first attribute, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies the predetermined condition.

[0105] The program or software module described above may be stored on or near the computer 1200 in a computer-readable storage medium. Alternatively, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the program to the computer 1200 via the network.

[0106] In this embodiment, blocks in the flowchart and block diagram may represent a stage in a process in which an operation is performed or a "part" of a device that has the role of performing an operation. A particular stage and "part" may be implemented by a dedicated circuit, a programmable circuit supplied with computer-readable instructions stored on a computer-readable storage medium, and / or a processor supplied with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuit may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuit may include reconfigurable hardware circuits, such as field-programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), which include logical AND, logical OR, exclusive OR, negated AND, negated OR, and other logical operations, flip-flops, registers, and memory elements.

[0107] A computer-readable storage medium may include any tangible device capable of storing instructions that can be executed by a suitable device, and as a result, a computer-readable storage medium having instructions stored therein will comprise a product that includes instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital multipurpose disc (DVD), Blu-ray® disc, memory stick, integrated circuit card, etc.

[0108] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and traditional procedural programming languages ​​such as the C programming language or similar programming languages.

[0109] Computer-readable instructions may be provided locally or via a wide area network (WAN) such as a local area network (LAN) or the internet to a processor or programmable circuit of a general-purpose computer, special-purpose computer, or other programmable data processing device, so that the processor or programmable circuit of the programmable data processing device, such as a computer, can execute the instructions to generate means for performing operations specified in a flowchart or block diagram. Here, the computer may be a PC (personal computer), tablet computer, smartphone, workstation, server computer, general-purpose computer, or special-purpose computer, and may also be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system and is a computer in a broad sense. In a distributed computing system, multiple computers execute a program collectively by each computer executing a part of the program and passing data during program execution between computers as needed.

[0110] Examples of processors include computer processors, central processing units, processing units, microprocessors, digital signal processors, controllers, and microcontrollers. A computer may have one or more processors. In a multiprocessor system with multiple processors, each processor executes a portion of the program, and the processors collectively execute the program by passing program execution data between them as needed. For example, in the execution of multitasks, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at each time slice. In this case, which part of a program each processor executes changes dynamically. Which part of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

[0111] By using the invention according to this embodiment, it is possible to make the rearing of organisms more efficient and contribute to achieving at least one of the Sustainable Development Goals (SDGs) Goal 11, "Make cities and human settlements inclusive, safe, resilient and sustainable," and Goal 14, "Protect the oceans, seas and marine resources."

[0112] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0113] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before" or "prior to," and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," and "next," for convenience, this does not mean that it is essential to perform the operations in that order. [Explanation of Symbols]

[0114] 100 Decision device, 110 Memory unit, 120 Setting unit, 121 Rearing space setting unit, 122 Feed price setting unit, 123 Average weight setting unit, 124 Starting weight unit price setting unit, 125 Ending weight unit price setting unit, 126 Survival rate setting unit, 127 Growth rate setting unit, 128 Running cost setting unit, 130 Species setting unit, 140 Rearing density determination unit, 142 Learning execution unit, 144 Output control unit, 200 Rearing space, 300 Fish pond, 310 Fish, 1200 Computer, 1210 Host controller, 1212 CPU, 1214 RAM, 1216 Graphics controller, 1218 Display device, 1220 Input / Output controller, 1222 Communication interface, 1224 Storage device, 1230 ROM, 1240 Input / Output chip

Claims

1. A species setting unit that sets the species of organism to be kept in the breeding space, A feed price setting unit that sets the feed price for the aforementioned organism, A rearing density determination unit determines the initial rearing density, which is the rearing density at the start of rearing the organisms, based on the species of organisms and the feed price, which maximizes the profit, which is the difference between the total sales revenue, which is the sales revenue after the rearing of multiple organisms in the rearing space has ended, and the total rearing costs, which is the rearing costs from the start to the end of rearing of multiple organisms in the rearing space. A decision-making device equipped with the following features.

2. The determination device according to claim 1, wherein the stocking density determination unit simulates the profit as a function of the initial stocking density and determines the initial stocking density to maximize the profit.

3. The determination device according to claim 2, wherein the stocking density determination unit uses the function configured such that the stocking period, which is the period from the start to the end of stocking of the organism, depends on the initial stocking density.

4. The determination device according to claim 3, wherein the stocking density determination unit uses the function configured such that the total sales revenue depends on the survival rate of the organisms which depend on the initial stocking density.

5. The aforementioned rearing density determination unit determines that the total rearing cost is The initial unit price, which is the unit price by weight at the start of rearing the organisms, and the purchase cost of the multiple organisms at the start of rearing, which depends on the initial rearing density, The feeding costs of the multiple organisms, which depend on the aforementioned rearing period and the aforementioned feed price, Running costs depend on the aforementioned breeding period and the labor and fuel costs of breeding the aforementioned multiple organisms. The determination device according to claim 3, which uses the function configured to depend on the function.

6. The determination device according to claim 1, wherein the stocking density determination unit determines the initial stocking density using a learning model that takes the initial stocking density, feed price, parameters related to organisms, and actual profits from previous stocking of the plurality of organisms as input and outputs profits, generated by machine learning using the initial stocking density, feed price, parameters related to organisms, and actual profits from previous stocking of the plurality of organisms as learning data.

7. A learning execution unit that generates the learning model by performing machine learning using the aforementioned learning data. The determination device according to claim 6, further comprising the following:

8. The determination device according to claim 6, wherein the parameters related to the organism include at least one of the species of the organism, the unit weight cost of the organism at the start of rearing, the unit weight cost of the organism at the end of rearing, the relationship between the elapsed time from the start of rearing and the average weight of the organism, the relationship between the elapsed time and the survival rate of the organism, and the growth rate, which is the ratio of the weight of the organism at the start of rearing to the weight at the end of rearing.

9. The determination device according to any one of claims 1 to 8, wherein the stocking density is the ratio of the size of the area in which the organisms can move freely to the number of organisms in the stocking space at the start of stocking.

10. The determination device according to any one of claims 1 to 8, wherein the organism is an organism that satisfies at least one of the following conditions: the number of deaths during rearing increases with increasing rearing density, and the growth rate decreases with increasing rearing density.

11. On the computer, The species selection stage involves defining the species of organisms to be kept in the breeding space, and A feed price setting stage in which the feed price of the aforementioned organism is set, A stocking density determination step in which, based on the species of organism and the feed price, the stocking density at the start of stocking the organism is determined to maximize the net profit, which is the difference between the total stocking cost, which is the cost of stocking multiple organisms in the stocking space from the start to the end of stocking, and the total sales revenue, which is the sales revenue after the end of stocking multiple organisms in the stocking space. A program to execute.

12. A decision-making method performed by a computer, The species selection stage involves defining the species of organisms to be kept in the breeding space, and A feed price setting stage in which the feed price of the aforementioned organism is set, A stocking density determination step in which, based on the species of organism and the feed price, the stocking density at the start of stocking the organism is determined to maximize the net profit, which is the difference between the total stocking cost, which is the cost of stocking multiple organisms in the stocking space from the start to the end of stocking, and the total sales revenue, which is the sales revenue after the end of stocking multiple organisms in the stocking space. A decision-making method comprising the following features.

Images