Information processing device, information processing method, and information processing program

Abstract

To optimize feeding by a feeding device.SOLUTION: An information processing device of the present invention includes: an acquisition unit for acquiring sound information on a sound from a microphone that collects a sound in a fish culturing environment; an estimation unit for determining whether or not feed intake activity of the fish is high on the basis of the sound information; and a feeding control unit for generating control information indicating a timing at which a feeding action by a feeding device is stopped when the feed intake activity of the fish is determined to be low by the estimation unit.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there are known technologies related to feeding devices that are installed in fish farms, such as fish ponds, to feed fish in water. For example, there is known a technology in which artificial intelligence (AI) analyzes live video captured by a network camera to determine whether the activity of farmed fish is high during the feeding time from the automatic feeder, and adjusts and controls the feeding from the automatic feeder based on the result of the determination. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-78278 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned conventional technology only determines whether the activity of farmed fish is high during the feeding time from the automatic feeder based on images taken by a network camera installed on the sea surface aquaculture raft, so it is not necessarily possible to optimize feeding by the feeding device. [Means for solving the problem]

[0005] The information processing device according to the embodiment includes an acquisition unit that acquires sound information regarding the sounds from a microphone that collects sounds in a fish farming environment, an estimation unit that determines whether the feeding activity of the fish is high or not based on the sound information, and a feeding control unit that generates control information indicating the timing to stop the feeding operation of the feeding device when the estimation unit determines that the feeding activity of the fish is low.

[0006] The information processing device according to the embodiment includes an acquisition unit that acquires stomach information indicating the size of the stomachs of fish in a fish pen and water temperature information indicating the water temperature of the fish pen, and a feeding control unit that generates control information for controlling a feeding operation of a feeding device for the fish in the fish pen based on the stomach information and the water temperature information. The information processing device according to the embodiment also includes an estimation unit that estimates the time when the fish in the fish pen will become hungry. The acquisition unit acquires digestion information indicating the digestion rate of the feed fed by the feeding device by the fish in the fish pen, the estimation unit estimates the time when the fish in the fish pen will become hungry using a first machine learning model that has been trained to output information indicating the time when the fish in the fish pen will become hungry in response to input of the stomach information, the water temperature information, and input information based on the digestion information, and the feeding control unit generates the control information indicating the start timing of the feeding operation based on the information indicating the time when the fish in the fish pen will become hungry.

[0007] The information processing device according to the embodiment further includes an estimation unit that estimates an amount of feed to be fed to the fish in the fish pen. The acquisition unit acquires fish count information regarding the number of fish in the fish pen and feed information regarding the size and type of feed to be fed by the feeding device. The estimation unit estimates the amount of feed using a second machine learning model that has been trained to output information indicating the amount of feed in response to input information based on the stomach information, the water temperature information, the fish count information, and the feed information. The feeding control unit generates the control information indicating the amount of feed to be fed by the feeding device based on the information indicating the amount of feed. [Effects of the Invention]

[0008] According to one aspect of the embodiment, it is possible to achieve an effect of optimizing feeding by the feeding device. [Brief explanation of the drawings]

[0009] [Figure 1]FIG. 1 is a diagram illustrating an example of the configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 3] FIG. 3 is a flowchart illustrating an example of information processing by the information processing device according to the embodiment. [Figure 4] FIG. 4 is a flowchart showing an example of information processing by the information processing device according to the first modified example. [Figure 5] FIG. 5 is a diagram showing an example of a spectrogram of sounds collected during feeding according to the second modified example. [Figure 6] FIG. 6 is a flowchart showing an example of information processing by the information processing device according to the second modified example. [Figure 7] FIG. 7 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0011] (Embodiment) 1. Introduction Conventionally, an automatic feeder (hereinafter also referred to as a feeding device) installed in an aquaculture facility such as a fish pen determines whether fish are biting well (the degree of biting is high) during feeding time from images captured by a camera installed around the feeder. A known technology then automatically stops feeding by the feeder if it is determined that the fish are not biting well (the degree of biting is low). Note that a good bite (high degree of biting) of fish during feeding time can be rephrased as a high level of activity of the fish during feeding time, i.e., a high level of feeding activity of the fish. Furthermore, a poor bite (low degree of biting) of fish during feeding time can be rephrased as a low level of activity of the fish during feeding time, i.e., a low level of feeding activity of the fish.

[0012] However, the method of determining the level of feeding activity of fish using images from cameras installed around the feeding device may not be highly accurate. For example, water from aquaculture farms such as fish pens may splash onto the camera lens. In this case, water droplets on the lens may blur the camera image, making it difficult to properly determine the level of feeding activity of the fish. Furthermore, when recognizing fish shadows from camera images, depending on the angle of sunlight, fish may not be visible at all, and shadows on waves may be mistaken for fish, resulting in continued feeding even though the fish are not eating.

[0013] In contrast, an information processing device according to an embodiment acquires stomach information indicating the size of the stomachs of the fish in the fish tank, water temperature information indicating the water temperature in the fish tank, and digestion information indicating the digestion rate of the feed provided by the feeding device to the fish in the fish tank. The information processing device also estimates the time when the fish in the fish tank will become hungry using a first machine learning model trained to output information indicating the time when the fish in the fish tank will become hungry, in response to input information based on the stomach information, water temperature information, and digestion information. The information processing device also generates control information indicating the start timing of the feeding operation, based on the information indicating the time when the fish in the fish tank will become hungry.

[0014] Here, it is estimated that the water temperature in the fish tank correlates with, for example, the activity of digestive enzymes contained in the fish's gastric juice. That is, it is estimated that the water temperature in the fish tank correlates with, for example, the digestibility of the feed. This allows the information processing device according to the embodiment to appropriately estimate the time when the fish in the tank will become hungry based on the size of the fish's stomach, the water temperature in the tank, and the digestibility of the feed. Furthermore, since the information processing device can appropriately estimate the time when the fish in the tank will become hungry, it can appropriately determine the timing to start the feeding operation of the feeding device based on the time when the fish in the tank will become hungry. Therefore, the information processing device can optimize feeding by the feeding device.

[0015] [2. Information Processing System Configuration] Fig. 1 is a diagram showing an example of the configuration of an information processing system 1 according to an embodiment. As shown in Fig. 1, information processing system 1 includes a feeding apparatus 10 and an information processing device 100. Feeding apparatus 10 and information processing device 100 are connected to each other via a network N, either wired or wirelessly, so that they can communicate with each other. Note that information processing system 1 shown in Fig. 1 may include multiple feeding apparatuses 10 and multiple information processing devices 100.

[0016] Feeding device 10 is installed in a fish pen (an example of an aquaculture facility) and feeds the fish raised in the pen. Feeding device 10 is installed, for example, above the water surface of the pen, at a predetermined distance from the water surface. Feeding device 10 receives control information from information processing device 100 and feeds the fish in accordance with the received control information.

[0017] Information processing device 100 acquires stomach information indicating the size of the stomachs of the fish in the fish tank and water temperature information indicating the water temperature in the tank. Based on the stomach information and water temperature information, information processing device 10 generates control information for controlling the feeding operation of feeding device 10 for the fish in the fish tank. When information processing device 100 generates the control information, it transmits the generated control information to feeding device 10.

[0018] 3. Configuration of Information Processing Device 2 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in FIG. 2, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit .

[0019] (Communication unit 110) Communication unit 110 is realized by, for example, a network interface card (NIC), etc. Communication unit 110 is connected to feeding apparatus 10 via network N, either wired or wirelessly, and is a communication interface that controls the communication of information between communication unit 110 and feeding apparatus 10.

[0020] (Storage unit 120) The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 stores a program (an example of an information processing program) executed by the control unit 130 or data processed by the control unit 130.

[0021] (control unit 130) The control unit 130 is a controller, and is realized by, for example, a central processing unit (CPU), a micro processing unit (MPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or the like, by executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 100 using a storage area such as a RAM as a work area. In the example shown in FIG. 2, the control unit 130 has an acquisition unit 131, an estimation unit 132, and a feeding control unit 133. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 2, and may be other configurations as long as they perform the information processing described below. Furthermore, each functional unit indicates a function of the control unit 130 and does not necessarily have to be physically distinct.

[0022] (Acquisition part 131) The acquisition unit 131 acquires stomach information indicating the size of the stomachs of fish present in the fish pen. Specifically, the size of a fish's stomach varies depending on the fish species. Furthermore, the size of a fish's stomach varies depending on the tail length (an example of fish size). The stomach size is the stomach volume and may be measured in milliliters. Therefore, the storage unit 120 stores stomach dictionary information in which stomach information indicating the size of the stomach of fish for each fish species and tail length is associated with the fish species and tail length. Furthermore, it is assumed that the fish species and tail lengths (e.g., average tail lengths) of fish present in the target fish pen are known. The acquisition unit 131 refers to the stomach dictionary information in the storage unit 120 to acquire stomach information indicating the size of the stomach of fish corresponding to the fish species and tail lengths of the fish present in the target fish pen.

[0023] The acquisition unit 131 also acquires water temperature information indicating the water temperature of the cage. Specifically, the acquisition unit 131 acquires water temperature information indicating the water temperature of the cage from a temperature sensor installed in the water of the cage. Here, it is estimated that the water temperature of the cage is correlated with the movement amount (e.g., feeding activity) of the fish. For example, it is estimated that the lower the water temperature of the cage, the lower the movement amount (e.g., feeding activity) of the fish, and that the higher the water temperature of the cage, the higher the movement amount (e.g., feeding activity) of the fish. In other words, it is estimated that the fish will eat more food in a given time when the water temperature of the cage is higher than when the water temperature of the cage is low. It is also estimated that the water temperature of the cage is correlated with the activity level of digestive enzymes contained in the gastric juice of the fish. For example, it is estimated that the lower the water temperature in the fish pen, the lower the activity of the digestive enzymes contained in the fish's gastric juice, and the higher the water temperature in the fish pen, the higher the activity of the digestive enzymes contained in the fish's gastric juice. In other words, it is estimated that fish with a higher water temperature in the fish pen have a higher ability to digest food than when the water temperature in the fish pen is low. In other words, it is estimated that fish become hungry in a shorter time when the water temperature in the fish pen is high than when the water temperature in the fish pen is low.

[0024] The acquisition unit 131 also acquires digestion information indicating the digestibility of the feed provided by the feeding device 10 to the fish in the fish preserve. Specifically, the digestibility of the feed varies depending on the type of digestive enzymes contained in the fish's gastric juice and the type of feed. The digestibility of the feed may be the amount of feed digested per unit time. Therefore, the memory unit 120 stores digestion dictionary information that associates digestion information indicating the digestibility of the feed for each type of digestive enzyme contained in the fish's gastric juice and each type of feed with the type of digestive enzymes contained in the fish's gastric juice and each type of feed. It is also assumed that the types of digestive enzymes contained in the gastric juice of the fish in the target fish preserve and the type of feed provided by the feeding device 10 are known. The acquisition unit 131 references the digestion dictionary information in the memory unit 120 to acquire digestion information indicating the digestibility of the feed corresponding to the type of digestive enzymes contained in the gastric juice of the fish in the target fish preserve and the type of feed provided by the feeding device 10.

[0025] (Estimation part 132) The estimation unit 132 estimates the time when the fish in the fish tank will become hungry. Specifically, the estimation unit 132 trains a first machine learning model using a set of stomach information, water temperature information, digestion information, and information indicating the time when the fish in the fish tank will become hungry (e.g., two hours after the start time of the first feeding operation by the feeding device 10) as correct answer data. More specifically, the estimation unit 132 trains the first machine learning model to output information indicating the time when the fish in the fish tank will become hungry as output information in response to input information based on the stomach information, water temperature information, and digestion information. Next, the estimation unit 132 inputs the stomach information, water temperature information, and digestion information acquired by the acquisition unit 131 into the trained first machine learning model and obtains the time when the fish in the fish tank will become hungry as an estimation result output from the trained first machine learning model.

[0026] (Feeding control unit 133) Based on the information indicating the time when the fish in the fish tank will become hungry, estimated by the estimation unit 132, the feeding control unit 133 generates control information indicating the timing for starting the feeding operation by the feeding apparatus 10. For example, assume that the time when the fish in the tank will become hungry, estimated by the estimation unit 132, is two hours after the start of the first feeding operation by the feeding apparatus 10. In this case, the feeding control unit 133 generates control information indicating the start of the feeding operation, instructing the feeding apparatus 10 to start the second feeding operation two hours after the start of the first feeding operation by the feeding apparatus 10. When the feeding control unit 133 generates the control information, it transmits the generated control information to the feeding apparatus 10.

[0027] In this way, based on the stomach information and water temperature information acquired by acquisition unit 131, feeding control unit 133 generates control information for controlling the feeding operation of feeding device 10 on the fish in the fish preserve.

[0028] [4. Processing Procedure] FIG. 3 is a flowchart illustrating an example of information processing by information processing device 100 according to an embodiment. In the example illustrated in FIG. 3, acquisition unit 131 acquires stomach information, water temperature information, and digestion information (step S101). Using the first machine learning model, estimation unit 132 estimates the time at which the fish in the fish tank will become hungry from the stomach information, water temperature information, and digestion information acquired by acquisition unit 131 (step S102). Based on the information indicating the time at which the fish in the fish tank will become hungry estimated by estimation unit 132, feeding control unit 133 generates control information indicating the start timing of the feeding operation by feeding apparatus 10 (step S103). Subsequently, when generating control information, feeding control unit 133 transmits the generated control information to feeding apparatus 10 (step S104).

[0029] [5. Modifications] The above-described embodiment is merely an example, and various modifications and applications are possible. Modifications of the embodiment will now be described.

[0030] [5-1. First Modified Example] In the above-described embodiment, a case has been described in which the information processing device 100 estimates the time when the fish in the fish tank will become hungry from the stomach information, water temperature information, and digestion information, and generates control information indicating the timing to start the feeding operation by the feeding device 10 based on the time when the fish in the fish tank will become hungry. In the first modified example, a case will be described in which the information processing device 100 estimates the amount of feed to be fed to the fish in the fish tank from the stomach information, water temperature information, fish number information, and feed information, and generates control information indicating the amount of feed based on the amount of feed to be fed to the fish in the fish tank.

[0031] Here, it is estimated that the water temperature in the fish tank correlates with, for example, the flexibility of the fish's stomachs. That is, it is estimated that the water temperature in the fish tank correlates with, for example, the amount of food that the fish can digest at one time. Furthermore, the maximum amount of food that the fish in the tank can consume is calculated by multiplying the size of the fish's stomachs by the number of fish in the tank. Furthermore, feeding more than the maximum amount of food is considered to be wasted. Thus, in the first modified example, the information processing device 100 can appropriately estimate the maximum amount of food that the fish in the tank can consume based on the size of the fish's stomachs, the water temperature in the tank, the number of fish in the tank, and the amount and type of food fed by the feeding device 10. Furthermore, since information processing device 100 can appropriately estimate the maximum amount of food that fish in the fish preserve can consume, for example, by setting the amount of food dispensed by feeding device 10 to an amount less than the maximum amount, information processing device 100 can appropriately estimate the amount of food dispensed by feeding device 10. Therefore, information processing device 100 can optimize feeding by feeding device 10.

[0032] Specifically, the acquisition unit 131 acquires fish count information regarding the number of fish present in the fish pen. For example, the acquisition unit 131 acquires an image from a camera installed underwater in the fish pen. Next, the acquisition unit 131 estimates the number of fish captured in the image by analyzing the camera image using known image recognition technology. The acquisition unit 131 also estimates the number of fish present in the fish pen based on the number of fish captured in the image. Alternatively, the number of fish present in the fish pen is known. The memory unit 120 stores the fish count information regarding the number of fish present in the fish pen in association with information that can identify the fish pen. The acquisition unit 131 refers to the memory unit 120 to acquire the fish count information regarding the number of fish present in the target fish pen. In this way, the acquisition unit 131 acquires the fish count information regarding the number of fish present in the fish pen.

[0033] Acquisition unit 131 also acquires bait information regarding the size and type of bait fed by feeding device 10. Memory unit 120 stores bait information regarding the size and type of bait fed to fish in a fish preserve in association with information that can identify the preserve. It is also assumed that the size and type of bait fed to the target fish preserve are known. Acquisition unit 131 references the bait information in memory unit 120 to acquire bait information regarding the size and type of bait fed by feeding device 10 to fish in the target fish preserve.

[0034] The estimation unit 132 also estimates the amount of food to be fed to the fish in the fish pen. Specifically, the estimation unit 132 trains a second machine learning model using a set of stomach information, water temperature information, fish number information, and food information, and information indicating the amount of food to be fed to the fish in the fish pen (for example, the maximum amount of food to be fed to the fish in the fish pen at one time) as correct answer data. More specifically, the estimation unit 132 trains the second machine learning model to output information indicating the amount of food as output information in response to input information based on the stomach information, water temperature information, fish number information, and food information. Next, the estimation unit 132 inputs the stomach information, water temperature information, fish number information, and food information acquired by the acquisition unit 131 into the trained second machine learning model, and obtains information indicating the amount of food output from the trained second machine learning model as an estimation result.

[0035] Furthermore, based on the information indicating the amount of feed estimated by the estimation unit 132, the feeding control unit 133 generates control information indicating the amount of feed to be fed by the feeding apparatus 10. For example, assume that the amount of feed estimated by the estimation unit 132 is the maximum amount of feed to be fed at one time to the fish in the fish pen. In this case, the feeding control unit 133 generates control information indicating the amount of feed to be fed by the feeding apparatus 10, instructing the feeding apparatus 10 to feed an amount of feed less than the estimated maximum amount (e.g., 80% of the maximum amount). Note that if the fish in the fish pen are growing slowly and it is desired to make the fish grow faster, the feeding control unit 133 may also generate control information indicating the amount of feed to be fed by the feeding apparatus 10, instructing the feeding apparatus 10 to feed an amount of feed more than the estimated maximum amount (e.g., 120% of the maximum amount). When the feeding control unit 133 generates the control information, it transmits the generated control information to the feeding apparatus 10.

[0036] FIG. 4 is a flowchart showing an example of information processing by information processing device 100 according to the first modification. In the example shown in FIG. 4, acquisition unit 131 acquires stomach information, water temperature information, fish number information, and food information (step S201). Using the second machine learning model, estimation unit 132 estimates the amount of food to be fed to the fish in the fish pen from the stomach information, water temperature information, fish number information, and food information acquired by acquisition unit 131 (step S202). Based on the information indicating the amount of food estimated by estimation unit 132, feeding control unit 133 generates control information indicating the amount of food to be fed by feeding apparatus 10 (step S203). Subsequently, when generating control information, feeding control unit 133 transmits the generated control information to feeding apparatus 10 (step S204).

[0037] [5-2. Second Modified Example] In the above-described embodiment, the information processing device 100 estimates the time when the fish in the fish tank will become hungry based on stomach information, water temperature information, and digestion information, and generates control information indicating the timing to start feeding operation by the feeding device 10 based on the time when the fish in the fish tank will become hungry. In the second modification, the information processing device 100 determines whether the feeding activity of the fish is high based on sound information about sounds in the fish farming environment. Furthermore, the information processing device 100 generates control information indicating the timing to stop the feeding operation by the feeding device 10 when it determines that the feeding activity of the fish is low.

[0038] As a result, in the second modification, the information processing device 100 can appropriately determine whether the feeding activity of the fish is high or low based on the sounds in the fish culture environment. Furthermore, because the information processing device 100 can appropriately determine whether the feeding activity of the fish is high or low, it can, for example, prevent overfeeding by stopping the feeding operation of the feeding device 10 during times when the feeding activity of the fish is low (i.e., when the fish are hardly eating any food). Therefore, the information processing device 100 can optimize feeding by the feeding device 10.

[0039] Specifically, the acquisition unit 131 acquires sound information related to sounds from a microphone that collects sounds in the fish farming environment. For example, the acquisition unit 131 acquires sound information related to sounds collected by a microphone installed around or in the fish pen. For example, the acquisition unit 131 acquires sound information related to sounds collected by a microphone installed at a position within a predetermined range from the feeding device 10 installed in the fish pen.

[0040] Furthermore, the estimation unit 132 determines whether the feeding activity of the fish is high based on the sound information. Specifically, the estimation unit 132 processes the sound information acquired by the acquisition unit 131 into three-dimensional data indicating frequency, sound intensity (also referred to as amplitude), and changes in frequency and sound intensity over time. For example, the estimation unit 132 generates a spectrogram as shown in FIG. 5 from the sound information acquired by the acquisition unit 131 using a short-time Fourier transform (STFT). FIG. 5 is a diagram showing an example of a spectrogram of sound collected during feeding according to the second modification. In the graph shown in FIG. 5, the vertical axis represents frequency, the horizontal axis represents time, and the color intensity represents sound intensity. In FIG. 5, the darker the color, the greater the sound intensity (i.e., amplitude). Furthermore, time periods T1 to T8 shown in FIG. 5 are time periods during which fish are biting and making splashing sounds on the water surface. In other words, each of the time periods T1 to T8 shown in FIG. 5 indicates a time period during which the feeding activity of the fish is high.

[0041] For example, the estimation unit 132 determines whether the feeding activity of the fish is high based on whether the volume (also referred to as sound intensity or sound amplitude) of sound in a first frequency band, which is used as sound information, is equal to or greater than a first threshold value for a first period of time or longer. For example, if the estimation unit 132 determines that the volume (also referred to as sound intensity or sound amplitude) of sound in a first frequency band (e.g., a frequency band of 0 to 2 kHz) is equal to or greater than a first threshold value for a first period of time or longer, the estimation unit 132 determines that the feeding activity of the fish is high. On the other hand, if the estimation unit 132 determines that the volume (also referred to as sound intensity or sound amplitude) of sound in a first frequency band (e.g., a frequency band of 0 to 2 kHz) is not equal to or greater than the first threshold value for a first period of time or longer, the estimation unit 132 determines that the feeding activity of the fish is low.

[0042] Furthermore, when estimation unit 132 determines that the feeding activity of the fish is low, feeding control unit 133 generates control information indicating the timing to stop the feeding operation by feeding apparatus 10. When generating the control information, feeding control unit 133 transmits the generated control information to feeding apparatus 10.

[0043] Furthermore, the estimation unit 132 determines whether the feeding activity of the fish is high based on a comparison between the shape of the envelope of the waveform of the frequency spectrum of the sound as sound information and the shape of the envelope of the waveform of the frequency spectrum of the sound when the feeding activity of the fish is high. More specifically, the estimation unit 132 trains a third machine learning model using information indicating the shape of the envelope of the waveform of the frequency spectrum of the sound when the feeding activity of the fish is high (or low) and information indicating that the feeding activity of the fish is high (or low) as correct answer data. For example, the estimation unit 132 trains the third machine learning model to output information indicating that the feeding activity of the fish is high (or low) in response to input information based on the shape of the envelope of the waveform of the frequency spectrum of the sound when the feeding activity of the fish is high (or low). Next, the estimation unit 132 inputs information indicating the envelope of the waveform of the frequency spectrum of the sound generated from the sound information acquired by the acquisition unit 131 into the trained third machine learning model, and obtains the output result output from the trained third machine learning model as an estimation result. For example, based on the output results output from the trained third machine learning model, the estimation unit 132 determines that the feeding activity of the fish is high if information indicating that the feeding activity of the fish is high is output continuously for at least a first hour. On the other hand, the estimation unit 132 determines that the feeding activity of the fish is low if information indicating that the feeding activity of the fish is high is not output continuously for at least a first hour. Alternatively, the estimation unit 132 determines that the feeding activity of the fish is low if information indicating that the feeding activity of the fish is low is output continuously for at least a second hour.

[0044] Fig. 6 is a flowchart showing an example of information processing by an information processing device according to a second modification. In the example shown in Fig. 6, acquisition unit 131 acquires sound information related to sounds collected in a fish tank (step S301). Furthermore, estimation unit 132 determines whether the feeding activity of the fish is high or not based on the sound information acquired by acquisition unit 131 (step S302). Furthermore, if estimation unit 132 determines that the feeding activity of the fish is low, feeding control unit 133 generates control information indicating the timing to stop the feeding operation of feeding apparatus 10 (step S303). Subsequently, if feeding control unit 133 generates control information, it transmits the generated control information to feeding apparatus 10 (step S304).

[0045] [6. Hardware Configuration] The information processing device 100 according to the above-described embodiment or modification is realized by, for example, a computer 1000 configured as shown in Fig. 7. Fig. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0046] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0047] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a predetermined communication network and sends it to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined communication network.

[0048] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0049] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. Recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0050] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 130. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0051] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0052] [7. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0053] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0054] For example, the information processing device 100 described above may be realized by a plurality of server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0055] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0056] [8. Effects] As described above, the information processing device 100 according to the embodiment includes an acquisition unit 131 and a feeding control unit 133. The acquisition unit 131 acquires stomach information indicating the size of the stomachs of the fish in the fish tank and water temperature information indicating the water temperature in the fish tank. The feeding control unit 133 generates control information for controlling the feeding operation of the feeding device 10 for the fish in the fish tank based on the stomach information and the water temperature information.

[0057] This allows the information processing device 100 to appropriately estimate, for example, the time when the fish in the fish tank will become hungry and the amount of food to feed the fish in the tank based on the size of the fish's stomach and the water temperature of the tank. Therefore, the information processing device 100 can optimize feeding by the feeding device 10. Furthermore, because the information processing device 100 can optimize feeding by the feeding device 10, it can contribute to achieving Goal 14 of the Sustainable Development Goals (SDGs), "Conserve and sustainably use the water below sea level." Furthermore, because the information processing device 100 can optimize feeding by the feeding device 10, it can contribute to achieving Goal 9 of the Sustainable Development Goals (SDGs), "Build resilience and promote inclusive and sustainable industrialization."

[0058] The information processing device 100 further includes an estimation unit 132 that estimates the time when the fish in the fish tank will become hungry. The acquisition unit 131 acquires digestion information indicating the digestion rate of the feed provided by the feeding device 10 by the fish in the fish tank. The estimation unit 132 estimates the time when the fish in the fish tank will become hungry using a first machine learning model that has been trained to output information indicating the time when the fish in the fish tank will become hungry in response to input information based on stomach information, water temperature information, and the digestion information. The feeding control unit 133 generates control information indicating the start timing of the feeding operation based on the information indicating the time when the fish in the fish tank will become hungry.

[0059] Here, it is estimated that the water temperature in the fish pen is correlated with, for example, the activity of digestive enzymes contained in the fish's gastric juice. That is, it is estimated that the water temperature in the fish pen is correlated with, for example, the digestibility of the feed. This allows the information processing device 100 to appropriately estimate the time when the fish in the pen will become hungry based on the size of the fish's stomach, the water temperature in the pen, and the digestibility of the feed. Furthermore, since the information processing device 100 can appropriately determine the time when the fish in the pen will become hungry, it can appropriately determine the timing to start the feeding operation by the feeding device 10 based on the time when the fish in the pen will become hungry. Therefore, the information processing device 100 can optimize feeding by the feeding device 10.

[0060] The information processing device 100 further includes an estimation unit 132 that estimates the amount of food to be fed to the fish in the fish pen. The acquisition unit 131 acquires fish count information regarding the number of fish in the fish pen, as well as food information regarding the size and type of food to be fed by the feeding device 10. The estimation unit 132 estimates the amount of food using a second machine learning model that has been trained to output information indicating the amount of food in response to input information based on stomach information, water temperature information, fish count information, and food information. The feeding control unit 133 generates control information indicating the amount of food to be fed by the feeding device 10 based on the information indicating the amount of food.

[0061] Here, it is estimated that the water temperature in the fish tank correlates with, for example, the flexibility of the fish's stomach. That is, it is estimated that the water temperature in the fish tank correlates with, for example, the amount of food that the fish can digest at one time. Furthermore, the maximum amount of food that the fish in the tank can consume is calculated by multiplying the size of the fish's stomach by the number of fish in the tank. Furthermore, feeding more than the maximum amount of food is considered to be wasted. In this way, the information processing device 100 can appropriately estimate the maximum amount of food that the fish in the tank can consume based on the size of the fish's stomach, the water temperature in the tank, the number of fish in the tank, and the type and amount of food fed by the feeding device 10. Furthermore, since information processing device 100 can appropriately estimate the maximum amount of food that fish in the fish preserve can consume, for example, by setting the amount of food dispensed by feeding device 10 to an amount less than the maximum amount, information processing device 100 can appropriately estimate the amount of food dispensed by feeding device 10. Therefore, information processing device 100 can optimize feeding by feeding device 10.

[0062] Acquisition unit 131 also acquires sound information from a microphone that collects sounds in the fish farming environment. Estimation unit 132 determines whether the feeding activity of the fish is high or low based on the sound information. If estimation unit 132 determines that the feeding activity of the fish is low, feeding control unit 133 generates control information indicating when to stop the feeding operation of feeding device 10.

[0063] This allows the information processing device 100 to appropriately determine whether the feeding activity of the fish is high or low based on the sounds in the fish culture environment. Furthermore, since the information processing device 100 can appropriately determine whether the feeding activity of the fish is high or low, it can, for example, prevent overfeeding by stopping the feeding operation of the feeding device 10 during times when the feeding activity of the fish is low (i.e., when the fish are hardly eating any food). Therefore, the information processing device 100 can optimize feeding by the feeding device 10.

[0064] Furthermore, the estimation unit 132 determines whether the feeding activity of the fish is high based on whether the volume of the sound in the first frequency band, as sound information, remains at or above a first threshold for a first period of time or more.

[0065] As a result, the information processing device 100 can determine that the feeding activity of the fish is low when, for example, the sound produced when the feeding activity of the fish is high does not continue for a predetermined period of time or longer.

[0066] In addition, the estimation unit 132 determines whether the feeding activity of the fish is high based on a comparison of the shape of the envelope of the waveform of the frequency spectrum of the sound as sound information with the shape of the envelope of the waveform of the frequency spectrum of the sound when the feeding activity of the fish is high.

[0067] As a result, the information processing device 100 can determine that the feeding activity of the fish is high if the shape of the envelope of the waveform of the frequency spectrum of the sound is similar to the shape of the envelope of the waveform of the frequency spectrum of the sound when the feeding activity of the fish is high. [Explanation of symbols]

[0068] 1. Information Processing Systems 10 Feeding Device 100 Information processing device 110 Communications Department 120 Storage section 130 control section 131 Acquisition Department 132 Estimation Department 133 Feeding control unit

Claims

1. an acquisition unit that acquires sound information related to the sounds from a microphone that collects sounds in a fish farming environment; an estimation unit that inputs information indicating the envelope of the waveform of the frequency spectrum of the sound generated from the sound information to a machine learning model that has been trained to output information indicating that the feeding activity of the fish is high in response to input information based on the shape of the envelope of the waveform of the frequency spectrum of the sound when the feeding activity of the fish is high, based on the sound information, and determines whether the feeding activity of the fish is high based on the output result output from the machine learning model; a feeding control unit that generates control information indicating a timing to stop the feeding operation of the feeding device when the estimation unit determines that the feeding activity of the fish is low; and Equipped with The estimation unit If the machine learning model does not output information indicating that the feeding activity of the fish is high for a first hour or more, the feeding activity of the fish is determined to be low. Information processing device.

2. An information processing method realized by a program executed by an information processing device, an acquisition step of acquiring sound information relating to the sounds from a microphone that collects sounds in a fish farming environment; an estimation process for inputting information indicating the envelope of the waveform of the frequency spectrum of the sound generated from the sound information into a machine learning model that has been trained to output information indicating that the feeding activity of the fish is high in response to input information based on the shape of the envelope of the waveform of the frequency spectrum of the sound when the feeding activity of the fish is high, based on the sound information, and determining whether the feeding activity of the fish is high based on the output result output from the machine learning model; a feeding control step of generating control information indicating a timing to stop the feeding operation of the feeding device when the feeding activity of the fish is determined to be low by the estimation step; Including, The estimation step includes: If the machine learning model does not output information indicating that the feeding activity of the fish is high for a first hour or more, the feeding activity of the fish is determined to be low. Information processing methods.

3. an acquisition step of acquiring sound information relating to the sounds from a microphone that collects sounds in a fish farming environment; an estimation procedure for inputting information indicating the envelope of the waveform of the frequency spectrum of the sound generated from the sound information into a machine learning model that has been trained to output information indicating that the feeding activity of the fish is high in response to input information based on the shape of the envelope of the waveform of the frequency spectrum of the sound when the feeding activity of the fish is high, based on the sound information, and determining whether the feeding activity of the fish is high based on the output result output from the machine learning model; a feeding control procedure for generating control information indicating a timing for stopping the feeding operation of the feeding device when the feeding activity of the fish is determined to be low by the estimation procedure; on the computer, The estimation procedure comprises: If the machine learning model does not output information indicating that the feeding activity of the fish is high for a first hour or more, the feeding activity of the fish is determined to be low. Information processing program.

Images