Fish management system, program, and fish management method

Abstract

Provided is a fish management system comprising: a result acquiring unit for acquiring a scan result obtained by scanning a target fish using a spectrometer scanner; a fish information acquiring unit for acquiring fish information including the freshness of the fish, using the scan result; a processing method acquiring unit for acquiring a recommended processing method for the fish, using the fish information; and an output control unit for performing control to output recommendation information including the recommended processing method for the fish. Also provided is a fish management method to be executed by a computer, the method including: a result acquiring step for acquiring a scan result obtained by scanning a target fish using a spectrometer scanner; a fish information acquiring step for acquiring fish information including the freshness of the fish, using the scan result; a processing method acquiring step for acquiring a recommended processing method for the fish, using the fish information; and an output control step for performing control to output recommendation information including the recommended processing method for the fish.

Description

Fish management system, program, and fish management method

[0001] The present invention relates to a fish management system, a program, and a fish management method.

[0002] Patent Document 1 describes a method using the K value, which is a quantitative evaluation method for the freshness of fish. [Prior art documents] [Patent documents] [Patent document 1] JP 2002-207025 A General disclosure

[0003] According to one embodiment of the present invention, there is provided a fish management system. The fish management system may include a result acquisition unit that acquires scan results obtained by a spectrometer scanner scanning a target fish. The fish management system may include a fish information acquisition unit that uses the scan results to acquire fish information including the freshness of the fish. The fish management system may include a processing method acquisition unit that uses the fish information to acquire a recommended processing method for the fish. The fish management system may include an output control unit that controls the output of recommended information including the recommended processing method for the fish.

[0004] In the fish management system, the fish information acquisition unit may input the scan results acquired by the result acquisition unit into a fish information learning model that takes the scan results obtained by scanning a fish with a spectrometer scanner and GT (Ground Truth) data including fish information such as the freshness of the fish as input and outputs the fish information, and acquire the fish information output from the fish information learning model. The fish management system may include a learning data acquisition unit that acquires a plurality of the GT data, and a learning execution unit that generates the fish information learning model by executing machine learning using the plurality of GT data.

[0005] In any of the fish management systems described above, the fish information may include the umami of the fish. The fish information may include free amino acids contained in the fish. The fish information may include nucleic acids of the fish. The fish information may include the water content of the fish. The fish information may include lipids of the fish. The fish information may include color differences of the fish. The fish information may include microorganisms contained in the fish. The fish information may include fatty acids of the fish. The fish information may include blood content of the fish. The fish information may include texture of the fish.

[0006] In any of the fish management systems, the processing method acquisition unit may input the fish information acquired by the fish information acquisition unit into a fish processing learning model, the fish information being generated by machine learning using GT data including fish information about the fish and a recommended processing method for the fish, and the fish information being output as an output of a recommended processing method, to acquire the recommended processing method output from the fish processing learning model. The fish management system may further include an attribute information acquisition unit that acquires fish attribute information about the target fish, and the processing method acquisition unit may input the fish information acquired by the fish information acquisition unit and the fish attribute information acquired by the attribute information acquisition unit into the fish processing learning model, the fish information being generated by machine learning using the GT data including the fish information about the fish, the fish attribute information about the fish, and a recommended processing method for the fish, to acquire the recommended processing method output from the fish processing learning model. The fish attribute information may include the type of fish. The fish attribute information may include the type of bait eaten by the fish. The fish attribute information may include the place of origin of the fish. The fish attribute information may include a planned delivery period for the fish. The fish attribute information may include a preference for how to eat the fish.

[0007] In any of the fish management systems described above, the recommended method for processing the fish may include a recommended method for killing the fish. The method for killing the fish may include at least one of Tsumoto-shiki, nerve-killing, brain-killing, and iki-jime. The recommended method for processing the fish may include a recommended method for preserving the fish. The recommended method for processing the fish may include a recommended method for freezing the fish. The fish freezing method may include at least one of an air blast method and a liquid method. The recommended method for processing the fish may include a recommended method for transporting the fish. The recommended method for processing the fish may include a recommended way to eat the fish.

[0008] According to one embodiment of the present invention, there is provided a program for causing a computer to function as the fish management system.

[0009] According to one embodiment of the present invention, there is provided a computer-implemented fish management method. The fish management method may include a result acquisition step of acquiring scan results of a target fish scanned by a spectrometer scanner. The fish management method may include a fish information acquisition step of acquiring fish information including the freshness of the fish using the scan results. The fish management method may include a processing method acquisition step of acquiring a recommended processing method for the fish using the fish information. The fish management method may include an output control step of controlling to output recommended information including the recommended processing method for the fish.

[0010] The above summary of the invention does not list all of the necessary features of the present invention, and subcombinations of these features may also constitute inventions.

[0011] 1 is a schematic diagram illustrating an example of a fish management system 10. It is an explanatory diagram illustrating each process for a fish 30. It is a schematic diagram illustrating an example of the functional configuration of the fish management device 100. It is a schematic diagram illustrating an example of the hardware configuration of a computer 1200 that functions as the fish management device 100 or the communication terminal 200.

[0012] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention as claimed. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0013] The K value is known as an indicator of fish freshness, but measuring the K value requires specialized equipment and expert knowledge, is time-consuming, and requires destroying the fish for inspection. Furthermore, while the deliciousness of fish is related to both freshness and flavor, no quantitative evaluation of fish flavor exists. The fish management system 10 according to this embodiment contributes to the realization of a technology for measuring the freshness and flavor of fish using a non-destructive, quick, and simple approach that does not impair the quality of the fish. Furthermore, the fish management system 10 contributes to the realization of a technology for providing recommended fish processing methods using the measurement results of the fish.

[0014] 1 schematically illustrates an example of a fish management system 10. The fish management system 10 includes a fish management device 100. The fish management system 10 may further include a spectrometer scanner 102. The fish management system 10 may further include a communication terminal 200 and a spectrometer scanner 202. Note that the fish management system 10 may include only the fish management device 100.

[0015] The fish management device 100 may be a so-called server device. The communication terminal 200 may be a smartphone, a tablet terminal, a PC (Personal Computer), or the like.

[0016] The fish management device 100 and the communication terminal 200 communicate via a network 20. The network 20 may include the Internet. The network 20 may include a local area network (LAN). The network 20 may include a mobile communication network. The mobile communication network may conform to any of the following communication methods: Long Term Evolution (LTE), 5th Generation (5G), 3rd Generation (3G), and 6th Generation (6G) or later.

[0017] The fish management device 100 may be wired to the network 20. The fish management device 100 may be wirelessly connected to the network 20. The fish management device 100 may be connected to the network 20 via a wireless base station. The fish management device 100 may be connected to the network 20 via a Wi-Fi (registered trademark) access point.

[0018] The communication terminal 200 may be connected to the network 20 by wire. The communication terminal 200 may be connected to the network 20 wirelessly. The communication terminal 200 may be connected to the network 20 via a wireless base station. The communication terminal 200 may be connected to the network 20 via a Wi-Fi access point.

[0019] The fish management device 100 acquires the scan results of the spectrometer scanner 102 scanning the fish 30. The fish management device 100 and the spectrometer scanner 102 may be connected by wire. The fish management device 100 and the spectrometer scanner 102 may be connected by wireless. The spectrometer scanner 102 may be built into the fish management device 100.

[0020] The fish management device 100 may use the scan results to estimate fish information, including the freshness of the fish 30. The spectrometer scanner 102 splits light into wavelengths and receives them with a detector to measure the intensity of each wavelength. A characteristic of the spectrometer scanner 102 is that it is known that chemicals absorb specific wavelengths. The scan results of the spectrometer scanner 102 vary depending on the type and amount of chemicals contained in the target fish 30. The spectrometer scanner 102 can measure the wavelengths absorbed by the chemicals contained in the target fish 30, making it possible to estimate the chemicals contained in the target fish 30 from the scan results. Each fish 30 contains different types of chemicals in different amounts, resulting in complex variations in wavelength absorption. However, for example, by performing machine learning using the scan results and the types and amounts of chemicals contained in the fish 30 as training data, a learning model can be generated that inputs the scan results and outputs the types and amounts of chemicals. Using this learning model, the types and amounts of chemicals contained in the fish 30 can be estimated from the scan results, making it possible to indicate indicators of the quality of the fish 30.

[0021] The fish management device 100 may estimate the K value of the fish 30 as an indication of the freshness of the fish 30. The fish information may include the umami of the fish 30. The fish information may include free amino acids contained in the fish 30. Examples of free amino acids estimated by the fish management device 100 include inosinic acid, glutamic acid, and histamine. The fish information may include nucleic acids of the fish 30. The fish information may include the water content of the fish 30. The fish information may include the lipids of the fish 30. The fish information may include the color difference of the fish 30. The fish information may include microorganisms contained in the fish 30. The fish information may include the texture of the fish 30. The fish information may include the fatty acids of the fish 30. The fish information may include the blood content of the fish 30.

[0022] The fish management device 100 may use the estimated fish information to identify a recommended processing method for the fish 30. The recommended processing method for the fish 30 may include a recommended method for killing the fish 30. The recommended processing method for the fish 30 may include a recommended method for storing the fish 30. The recommended processing method for the fish 30 may include a recommended method for transporting the fish 30. The recommended processing method for the fish 30 may include a recommended way to eat the fish 30.

[0023] The fish management device 100 may acquire the scan results of the spectrometer scanner 202 scanning the fish 30 from the communication terminal 200. The spectrometer scanner 202 may be similar to the spectrometer scanner 102. The communication terminal 200 and the spectrometer scanner 202 may be connected by wire. The communication terminal 200 and the spectrometer scanner 202 may be connected by wireless. The spectrometer scanner 202 may be built into the communication terminal 200.

[0024] The fish management device 100 may estimate fish information of the fish 30 using the scan results obtained from the communication terminal 200. The fish management device 100 may transmit the estimated fish information to the communication terminal 200.

[0025] The fish management device 100 may use the scan results obtained from the communication terminal 200 to estimate fish information for the fish 30, and may use the fish information to estimate a recommended treatment method for the fish 30. The fish management device 100 may transmit the estimated recommended treatment method for the fish 30 to the communication terminal 200.

[0026] 2 is an explanatory diagram for explaining each treatment of the fish 30. In FIG. 2, examples of treatment of the fish 30 include a method of slaughtering, a processed shape, a period until freezing, a freezing method, a storage temperature, and a freezing period.

[0027] The method of killing the fish 30 may include a method such as the Tsumoto method. The method of killing the fish 30 may include types such as nerve-killing, brain-killing, and live-killing. The method of killing the fish 30 may include other methods.

[0028] The processed form of the fish 30 may include fillets, loins, heat treatments (scalding, roasting, smoking), etc. The processed form of the fish 30 may also include other forms.

[0029] The period until the fish 30 is frozen may be any period. The period until the fish 30 is frozen may be measured in hours or days. In FIG. 2, 12 hours, 2 days, and 5 days are shown as examples, but the period is not limited to these.

[0030] The freezing method for the fish 30 may include an air blast method, a liquid method, etc. The freezing method for the fish 30 may also include other methods.

[0031] The storage temperature of the fish 30 may be any temperature. The storage temperature of the fish 30 may be in increments of 1°C, 5°C, or 10°C, or may be other than these. Although −20°C and −50°C are exemplified in FIG. 2, the storage temperature is not limited to these.

[0032] The fish 30 may be frozen for any period of time. The fish 30 may be frozen for a month, a day, or any other period of time. While FIG. 2 illustrates January and March as examples, the period is not limited to these.

[0033] 3 shows an example of the functional configuration of the fish management device 100. The fish management device 100 includes a memory unit 110, a learning data acquisition unit 112, a learning execution unit 114, a learning model acquisition unit 116, a result acquisition unit 122, a fish information acquisition unit 124, a processing method acquisition unit 126, an attribute information acquisition unit 130, and an output control unit 128. Note that it is not essential for the fish management device 100 to include all of these components.

[0034] The learning data acquisition unit 112 acquires various learning data. The learning data acquisition unit 112 may acquire learning data input to the fish management device 100. The learning data acquisition unit 112 may receive learning data from an external source. The learning data acquisition unit 112 stores the acquired learning data in the memory unit 110.

[0035] The learning execution unit 114 generates a learning model by executing machine learning using the learning data acquired by the learning data acquisition unit 112. The learning execution unit 114 stores the generated learning model in the storage unit 110.

[0036] The learning data acquisition unit 112 may acquire learning data for generating a learning model that estimates fish information, including the freshness of the fish 30. For example, the learning data acquisition unit 112 acquires GT data including the scan results of scanning the fish 30 with a spectrometer scanner and fish information, including the freshness of the fish 30. The learning execution unit 114 may perform machine learning using the multiple GT data acquired by the learning data acquisition unit 112 to generate a fish information learning model that takes the scan results of scanning the fish 30 with the spectrometer scanner as input and outputs the fish information of the fish 30. For example, the learning execution unit 114 generates a fish information NN (Neural Network), which is a neural network that takes the scan results of scanning the fish 30 with the spectrometer scanner as input and outputs the fish information of the fish 30.

[0037] By using the spectrometer scanner, it is possible to obtain various pieces of information about the fish 30. The setting parameters of the spectrometer scanner may be adjusted appropriately depending on the object to be measured.

[0038] The scan results of the spectrometer scanner vary depending on the freshness of the fish 30. Therefore, by measuring fish 30 of known freshness with the spectrometer scanner and generating GT data including the scan results and the freshness of the fish 30 for various freshness levels, it is possible to generate a fish information model that can estimate the freshness of the fish 30 from the scan results.

[0039] The scan results of the spectrometer scanner vary depending on the flavor of the fish 30. Therefore, by measuring the fish 30 whose flavor is known with the spectrometer scanner and generating GT data including the scan results and the flavor of the fish 30 for various flavors, it is possible to generate a fish information model that can estimate the flavor of the fish 30 from the scan results.

[0040] The scan results of the spectrometer scanner vary depending on the moisture content of the fish 30. Therefore, by measuring fish 30 with known moisture contents using the spectrometer scanner and generating GT data including the scan results and the moisture content of the fish 30 for various moisture contents, a fish information model can be generated that can estimate the moisture content of the fish 30 from the scan results.

[0041] The scan results of the spectrometer scanner vary depending on the lipid content of the fish 30. Therefore, by measuring the fish 30 whose lipid content is known with the spectrometer scanner and generating GT data including the scan results and the lipid content of the fish 30 for various lipids, it is possible to generate a fish information model that can estimate the lipid content of the fish 30 from the scan results.

[0042] The scan results of the spectrometer scanner vary depending on the color difference of the fish 30. Therefore, by measuring the fish 30 with known color differences using the spectrometer scanner and generating GT data including the scan results and the color differences of the fish 30 for various color differences, it is possible to generate a fish information model that can estimate the color difference of the fish 30 from the scan results.

[0043] The scan results of the spectrometer scanner vary depending on the microorganisms contained in the fish 30. Therefore, by measuring the fish 30 whose contained microorganisms are known with the spectrometer scanner and generating GT data including the scan results and the microorganisms contained in the fish 30 for various contained microorganisms, it is possible to generate a fish information model that can estimate the microorganisms contained in the fish 30 from the scan results.

[0044] The scan results of the spectrometer scanner vary depending on the fatty acids of the fish 30. Therefore, by measuring the fish 30 whose fatty acids are known with the spectrometer scanner and generating GT data including the scan results and the fatty acids of the fish 30 for various fatty acids, it is possible to generate a fish information model that can estimate the fatty acids of the fish 30 from the scan results.

[0045] The scan results of the spectrometer scanner vary depending on the blood content of the fish 30. Therefore, by measuring fish 30 with known blood content using the spectrometer scanner and generating GT data including the scan results and the blood content of the fish 30 for various blood contents, a fish information model can be generated that can estimate the blood content of the fish 30 from the scan results.

[0046] The scan results of the spectrometer scanner vary depending on the texture of the fish 30. Therefore, by measuring the fish 30 with a known texture using the spectrometer scanner and generating GT data including the scan results and the texture of the fish 30 for various textures, a fish information model can be generated that can estimate the texture of the fish 30 from the scan results.

[0047] In addition to the freshness of the fish 30, the fish information may further include at least one of the flavor of the fish 30, the water content of the fish 30, the lipid content of the fish 30, the color difference of the fish 30, the microorganisms contained in the fish 30, the fatty acids of the fish 30, the blood content of the fish 30, and the texture of the fish 30.

[0048] The learning data acquisition unit 112 may acquire learning data for generating a learning model that estimates a recommended processing method for the fish 30. For example, the learning data acquisition unit 112 acquires GT data including fish information about the fish 30 and a recommended processing method for the fish. The learning execution unit 114 may perform machine learning using the multiple GT data acquired by the learning data acquisition unit 112 to generate a fish processing learning model that receives the fish information about the fish 30 as an input and outputs a recommended processing method for the fish 30. For example, the learning execution unit 114 generates a fish processing NN, which is a neural network that receives the fish information about the fish 30 as an input and outputs a recommended processing method for the fish 30.

[0049] The recommended method for processing the fish 30 may include a recommended method for slaughtering the fish 30. The recommended method for processing the fish 30 may include a recommended method for storing the fish 30. The recommended method for processing the fish 30 may include a recommended method for transporting the fish 30. The recommended method for processing the fish 30 may include a recommended method for eating the fish 30.

[0050] The GT data is generated, for example, using a processing method that a so-called professional fish 30 actually uses on the fish 30. For example, when a professional fish 30 processes a fish 30, the processing method used by the professional fish 30 is used as a recommended processing method to generate GT data associated with the fish information of the fish 30. The learning data acquisition unit 112 acquires the GT data. By acquiring a large amount of such GT data, the learning data acquisition unit 112 can generate a fish processing learning model that can make decisions similar to those of a professional fish 30.

[0051] The GT data may be generated by conducting a sensory test. For example, a certain fish 30 is processed using a certain processing method, and an experimenter eats the processed fish 30 and ranks it. The fish information of the fish 30, the processing method, and the rank are recorded in association with each other. For example, GT data is generated that associates the fish information associated with the highest rank with the processing method. The learning data acquisition unit 112 acquires the GT data. By acquiring a large amount of such GT data, the learning data acquisition unit 112 can generate a fish processing learning model that can provide a processing method that enables the fish 30 to acquire the highest rank.

[0052] The learning data acquisition unit 112 may acquire learning data for generating a learning model that estimates a recommended processing method suitable for the fish attribute information of the fish 30. For example, the learning data acquisition unit 112 acquires GT data including fish information of the fish 30, fish attribute information of the fish 30, and a recommended processing method for the fish 30. The learning execution unit 114 may perform machine learning using the multiple GT data acquired by the learning data acquisition unit 112 to generate a fish processing learning model that receives the fish information and fish attribute information of the fish 30 as input and outputs a recommended processing method for the fish 30. For example, the learning execution unit 114 generates a fish processing NN, which is a neural network that receives the fish information and fish attribute information of the fish 30 as input and outputs a recommended processing method for the fish 30.

[0053] The GT data is generated, for example, using a processing method that a so-called professional fish 30 actually uses on the fish 30. For example, when a professional fish 30 processes the fish 30, the processing method used by the professional fish 30 is used as a recommended processing method, and GT data is generated that corresponds to the fish information and fish attribute information of the fish 30. The learning data acquisition unit 112 acquires the GT data. By acquiring a large amount of such GT data, the learning data acquisition unit 112 can generate a fish processing learning model that can make judgments similar to those of the professional fish 30.

[0054] The GT data may be generated by conducting a sensory test. For example, a certain fish 30 is processed using a certain processing method, and an experimenter eats the processed fish 30 and ranks it. The fish information and fish attribute information of the fish 30 are recorded in association with the processing method and rank. For example, GT data is generated in association with the fish information, fish attribute information, and processing method associated with the highest rank. The learning data acquisition unit 112 acquires the GT data. By acquiring a large amount of such GT data, the learning data acquisition unit 112 can generate a fish processing learning model that can provide a processing method that enables the fish 30 to acquire the highest rank.

[0055] The learning model acquisition unit 116 acquires a learning model. The learning model acquisition unit 116 may externally receive a learning model generated by an external device. The learning model acquisition unit 116 stores the acquired learning model in the memory unit 110. The learning model acquisition unit 116, for example, inputs a scan result of scanning a fish 30 with a spectrometer scanner and acquires a fish information learning model that outputs fish information about the fish 30. The learning model acquisition unit 116, for example, inputs fish information about the fish 30 and acquires a fish processing NN, which is a neural network that outputs a recommended processing method for the fish 30. The learning model acquisition unit 116, for example, inputs fish information and fish attribute information about the fish 30 and acquires a fish processing learning model that outputs a recommended processing method for the fish 30.

[0056] The result acquisition unit 122 acquires the scan results of the spectrometer scanner scanning the target fish 30. The result acquisition unit 122 receives the scan results from, for example, the spectrometer scanner 102. The result acquisition unit 122 receives the scan results from, for example, the spectrometer scanner 202.

[0057] The fish information acquisition unit 124 acquires fish information of the target fish 30 using the scan results acquired by the result acquisition unit 122. The fish information acquisition unit 124 may input the scan results acquired by the result acquisition unit 122 into a fish information learning model stored in the memory unit 110, and acquire the fish information output from the fish information learning model.

[0058] The processing method acquisition unit 126 uses the fish information acquired by the fish information acquisition unit 124 to identify a recommended processing method for the target fish 30. The processing method acquisition unit 126 may input the fish information acquired by the fish information acquisition unit 124 into a fish processing learning model stored in the memory unit 110, and acquire the recommended processing method output from the fish processing learning model.

[0059] The output control unit 128 controls the output of recommended information including the recommended method for processing the fish 30 acquired by the processing method acquisition unit 126. For example, the output control unit 128 controls the display of the recommended information on the display provided in the fish management device 100. For example, the output control unit 128 controls the transmission of the recommended information to the communication terminal 200.

[0060] The attribute information acquisition unit 130 acquires fish attribute information of the target fish 30. The attribute information acquisition unit 130 may acquire fish attribute information that is separately input when the result acquisition unit 122 acquires the scan results of the target fish 30. The fish attribute information may include at least one of the type of fish 30, the type of food eaten by the fish 30, the place of origin of the fish 30, the expected delivery period of the fish 30, and a desired way of eating the fish 30. The desired way of eating the fish 30 may differ depending on the type of fish 30. Examples of ways of eating the fish 30 include, but are not limited to, sashimi, grilled, steamed, boiled, etc.

[0061] The processing method acquisition unit 126 may acquire a recommended processing method for the target fish 30 using the fish attribute information of the target fish 30 acquired by the attribute information acquisition unit 130 in addition to the fish information of the target fish 30 acquired by the fish information acquisition unit 124. The processing method acquisition unit 126 may input the fish information of the target fish 30 and the fish attribute information of the target fish 30 into a fish processing learning model stored in the memory unit 110, and acquire a recommended processing method output from the fish processing learning model.

[0062] As a specific example, the learning data acquisition unit 112 acquires multiple GT data sets including fish information about the fish 30, the type of the fish 30, and a recommended processing method for the fish 30, and the learning execution unit 114 generates a fish processing learning model that receives the fish information about the fish 30 and the type of the fish 30 as input and outputs a recommended processing method for the fish 30. The result acquisition unit 122 acquires scan results for the target fish 30, and the fish information acquisition unit 124 acquires fish information about the fish 30 using the scan results. The attribute information acquisition unit 130 acquires the type of the target fish 30. The processing method acquisition unit 126 inputs the fish information acquired by the fish information acquisition unit 124 and the type of fish 30 acquired by the attribute information acquisition unit 130 into the fish processing learning model generated by the learning execution unit 114, and acquires the recommended processing method for the fish 30 output from the fish processing learning model. This makes it possible to provide recommended processing appropriate for the type and freshness of the target fish 30.

[0063] As a specific example, the learning data acquisition unit 112 acquires multiple pieces of GT data including fish information about the fish 30, the type of bait eaten by the fish 30, and a recommended processing method for the fish 30, and the learning execution unit 114 receives the fish information about the fish 30 and the type of bait eaten by the fish 30 as input and generates a fish processing learning model that outputs a recommended processing method for the fish 30. The result acquisition unit 122 acquires scan results for the target fish 30, and the fish information acquisition unit 124 acquires fish information about the fish 30 using the scan results. The attribute information acquisition unit 130 acquires the type of bait eaten by the target fish 30. The processing method acquisition unit 126 inputs the fish information acquired by the fish information acquisition unit 124 and the type of bait acquired by the attribute information acquisition unit 130 into the fish processing learning model generated by the learning execution unit 114, and acquires the recommended processing method for the fish 30 output from the fish processing learning model. This makes it possible to provide recommended treatments that are suited to the freshness of the target fish 30 and the type of food it has eaten.

[0064] As a specific example, the learning data acquisition unit 112 acquires multiple GT data sets including fish information about the fish 30, the origin of the fish 30, and a recommended processing method for the fish 30, and the learning execution unit 114 generates a fish processing learning model that receives the fish information about the fish 30 and the origin of the fish 30 as input and outputs a recommended processing method for the fish 30. The result acquisition unit 122 acquires scan results for the target fish 30, and the fish information acquisition unit 124 acquires the fish information about the fish 30 using the scan results. The attribute information acquisition unit 130 acquires the origin of the target fish 30. The processing method acquisition unit 126 inputs the fish information acquired by the fish information acquisition unit 124 and the origin of the fish 30 acquired by the attribute information acquisition unit 130 into the fish processing learning model generated by the learning execution unit 114, and acquires the recommended processing method for the fish 30 output from the fish processing learning model. This makes it possible to provide recommended processing suited to the freshness and origin of the target fish 30.

[0065] As a specific example, the learning data acquisition unit 112 acquires multiple pieces of GT data including fish information about the fish 30, a planned delivery period for the fish 30, and a recommended processing method for the fish 30. The learning execution unit 114 receives the fish information about the fish 30 and the planned delivery period for the fish 30 as input and generates a fish processing learning model that outputs a recommended processing method for the fish 30. The result acquisition unit 122 acquires scan results for the target fish 30, and the fish information acquisition unit 124 acquires the fish information about the fish 30 using the scan results. The attribute information acquisition unit 130 acquires the planned delivery period for the target fish 30. The processing method acquisition unit 126 inputs the fish information acquired by the fish information acquisition unit 124 and the planned delivery period acquired by the attribute information acquisition unit 130 into the fish processing learning model generated by the learning execution unit 114, and acquires the recommended processing method for the fish 30 output from the fish processing learning model. This makes it possible to provide recommended processing appropriate for the freshness, etc., of the target fish 30 and the planned delivery period.

[0066] As a specific example, the learning data acquisition unit 112 acquires multiple GT data sets including fish information about the fish 30, a desired way of eating the fish 30, and a recommended processing method for the fish 30, and the learning execution unit 114 receives the fish information about the fish 30 and the desired way of eating the fish 30 as input and generates a fish processing learning model that outputs a recommended processing method for the fish 30. The result acquisition unit 122 acquires scan results for the target fish 30, and the fish information acquisition unit 124 acquires the fish information about the fish 30 using the scan results. The attribute information acquisition unit 130 acquires the desired way of eating the target fish 30. The processing method acquisition unit 126 inputs the fish information acquired by the fish information acquisition unit 124 and the desired way of eating acquired by the attribute information acquisition unit 130 into the fish processing learning model generated by the learning execution unit 114, and acquires the recommended processing method for the fish 30 output from the fish processing learning model. This makes it possible to provide recommended processing that is suited to the freshness, etc., of the target fish 30 and the desired way of eating it.

[0067] As described above, the fish management device 100 according to this embodiment can provide a recommended processing method for the fish 30 according to fish information such as the freshness and flavor of the fish 30. Furthermore, the fish management device 100 can provide a recommended processing method for the fish 30 according to the fish information such as the freshness and flavor of the fish 30, the type of fish 30, the type of bait, etc.

[0068] For example, in Japan, a cap on overtime work for truck drivers will come into effect on April 1, 2024. This will increase transportation costs and significantly restrict the transportation of raw fish, making transportation methods that can maintain fish quality as much as possible more important. Such transportation methods are important not only in Japan but around the world. In response to this, the fish management system 10 according to this embodiment can provide an environment in which fish 30 can be scanned with a spectrometer scanner to learn recommended processing methods suitable for the fish 30. This enables many people to realize transportation methods that can maintain fish quality as much as possible. Furthermore, the fish management system 10 can contribute to producing frozen fish that is more delicious than raw fish by guaranteeing the quality of the fish 30 during freezing, thereby making a significant contribution to the fishing industry.

[0069] 4 shows a schematic diagram of an example of the hardware configuration of a computer 1200 that functions as the fish management device 100. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of an apparatus according to the present embodiment, or to perform one or more operations or "parts" associated with an apparatus according to the present embodiment, and / or to perform a process or steps of a process according to the present embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to perform specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0070] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communications interface 1222, a storage device 1224, a DVD drive, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid-state drive, or the like. The computer 1200 also includes a ROM 1230 and a legacy input / output unit such as a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0071] The CPU 1212 operates according to programs stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into the graphics controller 1216 itself, and causes the image data to be displayed on the display device 1218.

[0072] 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.

[0073] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or programs that depend on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0074] The programs are provided by a computer-readable storage medium such as a DVD-ROM or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, RAM 1214, or ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or a method may be configured by implementing operations or processing of information in accordance with the use of the computer 1200.

[0075] For example, when communication is performed between computer 1200 and an external device, CPU 1212 may execute a communication program loaded into RAM 1214 and instruct communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of CPU 1212, communication interface 1222 reads transmission data stored in a transmission buffer area provided in RAM 1214, storage device 1224, a DVD-ROM, or a recording medium such as an IC card, and transmits the read transmission data to a network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

[0076] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, a DVD drive (DVD-ROM), an IC card, etc. to be read into the RAM 1214, and may perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

[0077] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. The CPU 1212 may perform various types of processing on data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequences of the programs, and write the results back to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. on the recording medium. For example, if multiple entries, each having an attribute value of a first attribute associated with an attribute value of a second attribute, are stored on the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0078] The above-described programs or software modules may be stored in a computer-readable storage medium on or near the computer 1200. A recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can also be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0079] The blocks in the flowcharts and block diagrams in the present embodiments may represent stages of a process in which an operation is performed or "parts" of a device responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and / or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as field programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0080] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by an appropriate device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture, including instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media may include electronic, magnetic, optical, electromagnetic, and semiconductor storage media. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disc read-only memories (CD-ROMs), digital versatile discs (DVDs), Blu-ray discs, memory sticks, integrated circuit cards, and the like.

[0081] The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0082] The computer-readable instructions may be provided to a general-purpose computer, a special-purpose computer, or another programmable data processing device processor or programmable circuit, either locally or via a local area network (LAN), a wide area network (WAN) such as the Internet, so that the processor or programmable circuit of the programmable data processing device, such as a computer, executes the computer-readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Here, the computer may be a personal computer (PC), a tablet computer, a smartphone, a workstation, a server computer, a general-purpose computer, a special-purpose computer, or the like, or may be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system, and is a broad definition of computer. In a distributed computing system, multiple computers collectively execute a program by each executing a portion of the program and passing data between the computers as needed during program execution.

[0083] Examples of processors include computer processors, central processing units, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc. A computer may have one processor or multiple processors. In a multiprocessor system with multiple processors, each processor executes a portion of a program and passes data between processors as needed during program execution, allowing the multiple processors to collectively execute the program. For example, in multitasking, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at each time slice. In this case, which portion of a program each processor executes changes dynamically. Which portion of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

[0084] Although the present invention has been described above using the 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 and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

[0085] It should be noted that the execution order of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and that the processes can be performed in any order unless the output of a previous process is used in a subsequent process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, this does not mean that the processes must be performed in this order.

[0086] 10 Fish management system, 20 Network, 30 Fish, 100 Fish management device, 102 Spectrometer scanner, 110 Memory unit, 112 Learning data acquisition unit, 114 Learning execution unit, 116 Learning model acquisition unit, 122 Result acquisition unit, 124 Fish information acquisition unit, 126 Processing method acquisition unit, 128 Output control unit, 130 Attribute information acquisition unit, 200 Communication terminal, 202 Spectrometer scanner, 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 fish management system comprising: a result acquisition unit that acquires scan results obtained by a spectrometer scanner scanning a target fish; a fish information acquisition unit that uses the scan results to acquire fish information including the freshness of the fish; a processing method acquisition unit that uses the fish information to acquire a recommended processing method for the fish; and an output control unit that controls the output of recommended information including the recommended processing method for the fish.

2. The fish management system of claim 1, wherein the fish information acquisition unit inputs the scan results acquired by the result acquisition unit into a fish information learning model that takes the scan results obtained by scanning a fish with a spectrometer scanner and GT (Ground Truth) data including fish information including the freshness of the fish as input and outputs the fish information, generated by machine learning using the GT data, and acquires the fish information output from the fish information learning model.

3. A fish management system as described in claim 2, comprising: a learning data acquisition unit that acquires a plurality of the GT data; and a learning execution unit that generates the fish information learning model by performing machine learning using the plurality of the GT data.

4. A fish management system as described in any one of claims 1 to 3, wherein the fish information further includes at least one of the flavor of the fish, the water content of the fish, the lipid content of the fish, the color difference of the fish, microorganisms contained in the fish, fatty acids of the fish, the blood content of the fish, and the texture of the fish.

5. A fish management system as described in any one of claims 1 to 4, wherein the processing method acquisition unit inputs the fish information acquired by the fish information acquisition unit into a fish processing learning model that takes fish information as input and outputs a recommended processing method, the fish information being generated by machine learning using GT data including fish information of the fish and a recommended processing method for the fish, and acquires the recommended processing method output from the fish processing learning model.

6. A fish management system as described in claim 5, further comprising an attribute information acquisition unit that acquires fish attribute information of the target fish, wherein the processing method acquisition unit inputs the fish information acquired by the fish information acquisition unit and the fish attribute information acquired by the attribute information acquisition unit into the fish processing learning model generated by machine learning using the GT data including fish information of the fish, the fish attribute information of the fish, and a recommended processing method for the fish, and acquires the recommended processing method output from the fish processing learning model.

7. A fish management system as described in claim 6, wherein the fish attribute information includes at least one of the type of fish, the type of food eaten by the fish, the place of origin of the fish, the expected delivery period of the fish, and the desired way of eating the fish.

8. A fish management system as claimed in any one of claims 1 to 7, wherein the recommended method for processing the fish includes at least one of a recommended method for killing the fish, a recommended method for storing the fish, a recommended method for transporting the fish, and a recommended method for eating the fish.

9. A program for causing a computer to function as a fish management system according to any one of claims 1 to 8.

10. A fish management method executed by a computer, comprising: a result acquisition step of acquiring scan results of a target fish scanned by a spectrometer scanner; a fish information acquisition step of acquiring fish information including the freshness of the fish using the scan results; a processing method acquisition step of acquiring a recommended processing method for the fish using the fish information; and an output control step of controlling the output of recommended information including the recommended processing method for the fish.

Images