System and method for digital twin-based intelligent land-based seaweed farming

Abstract

The present invention aims to provide a digital twin-based intelligent land-based seaweed farming system and a digital twin-based intelligent land-based seaweed farming method that can be performed using the same, comprising: a digital twin generation unit that receives marine seaweed farming data collected from a marine seaweed farm and generates a virtual model of a seaweed farm corresponding to the marine seaweed farm based on the marine seaweed farming data; an artificial intelligence model generation unit that generates a seaweed farming artificial intelligence model based on at least one selected from the marine seaweed farming data and the virtual seaweed farming data output from the seaweed farm virtual model; and a control device control unit that controls an environment control device equipped in a land-based seaweed farm based on optimal farming environment data output by the seaweed farming artificial intelligence model.

Description

Technology Field

[0001] The present invention relates to a digital twin-based intelligent land-based seaweed farming system and a digital twin-based intelligent land-based seaweed farming method using the system. More specifically, it relates to a system and method capable of operating a land-based seaweed farm using a digital twin and an artificial intelligence model. Background Technology

[0002] Seaweed farming in Korea began with the introduction of Japanese processing methods in 1907, and recently, with an annual production of 450,000 to 500,000 tons, the annual production of dried seaweed has reached 12 to 13 billion sheets, making Korea the world's number one producer of dried seaweed.

[0003] The laver we consume is a large thallus and is in the gametophyte stage (a hermaphroditic body containing both eggs and sperm). For laver cultivation, the process involves attaching zygospores (fruit spores) or neuter spores produced in artificial seed farms on land to laver nets, followed by cultivation at sea.

[0004] Domestic marine seaweed farming can be classified into the stake method and the floating method. Additionally, the floating method can be further divided into exposed floating and non-exposed floating types. The stake method involves fixing stakes to the seabed of shallow inland bays and installing seaweed nets, a system in which the nets are exposed to the air twice a day depending on the tides. The floating method keeps the nets constantly submerged below the water surface, preventing exposure to the air, and allows for cultivation in offshore fishing grounds rather than just inland bays.

[0005] At this time, the floating method has the advantage of faster growth and higher productivity compared to the stake method because the seaweed nets are always submerged in water and remain in an unexposed state, but it has the disadvantage of being susceptible to seaweed diseases. Recently, an exposure floating method (turning floating method) is also being used, in which styrofoam floats are attached to the floating seaweed nets and the nets are artificially turned over to expose them to the air for a certain period of time.

[0006] Meanwhile, the marine aquaculture environment has a direct impact on laver farming, and recently, laver production has been on a declining trend due to rising seawater temperatures caused by global warming.

[0007] Furthermore, laver is vulnerable not only to water temperature but also to infection by unwanted algae. To address this, acid treatment is applied using various methods, such as the injection of organic acids, which is not beneficial to the marine environment. In addition, due to the specific working conditions of offshore laver farms, farmers are compelled to operate using specially designed vessels, making the work vulnerable to safety risks and labor-intensive.

[0008] In addition, offshore seaweed farming is inefficient in terms of cost due to the repeated annual installation and harvesting of numerous facilities, such as seaweed nets and supports. Above all, the farms are exposed to significant management risks caused by rapidly changing aquaculture environments, including climate change and abnormal high temperatures.

[0009] There is a growing need for land-based seaweed farming methods to overcome the risks associated with such marine cultivation; however, current technologies related to such land-based farming are limited to methods that simply transfer the marine farming environment onto land and install and operate net-shaped seaweed rafts.

[0010] However, this merely amounts to relocating the aquaculture environment from offshore facilities to land, and technology for adjusting and managing the optimal growth environment is required for more efficient land-based seaweed farming. Prior art literature

[0011] Korean Patent Publication No. 10-2084308 (February 26, 2020) The problem to be solved

[0012] Accordingly, the present invention has been devised against the aforementioned background and aims to provide a land-based seaweed farming system configured to create an optimal seaweed farming environment in a land-based seaweed farm by deriving optimal farming environment data that allows for the maximum growth of farmed seaweed while minimizing disease infection through an artificial intelligence model trained on marine seaweed farming data, and controlling the operation of an environmental control device equipped in a land-based seaweed farm based on the derived optimal farming environment data, and a land-based seaweed farming method that can be performed using the same.

[0013] The objectives of the present invention are not limited thereto, and other unmentioned objectives will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0014] To achieve this objective, one embodiment of the present invention provides a digital twin-based intelligent land-based seaweed farming system comprising: a digital twin generation unit that receives marine seaweed farming data collected from a marine seaweed farm and generates a virtual model of a seaweed farm corresponding to the marine seaweed farm based on the marine seaweed farming data; an artificial intelligence model generation unit that generates a seaweed farming artificial intelligence model based on at least one selected from the marine seaweed farming data and the virtual seaweed farming data output from the seaweed farm virtual model; and a control device control unit that controls an environment control device equipped in a land-based seaweed farm based on optimal farming environment data output by the seaweed farming artificial intelligence model.

[0015] Additionally, the present invention provides a digital twin-based intelligent land-based seaweed farming method comprising: receiving marine seaweed farming data collected from a marine seaweed farm; generating a virtual model of a seaweed farm corresponding to the marine seaweed farm based on the marine seaweed farming data; generating a seaweed farming artificial intelligence model based on at least one selected from the marine seaweed farming data and the virtual seaweed farming data output from the seaweed farm virtual model; and controlling an environmental control device equipped in a land-based seaweed farm based on optimal farming environment data output by the seaweed farming artificial intelligence model. Effects of the invention

[0016] According to the present invention, optimal aquaculture environment data is derived through an artificial intelligence model to maximize the growth of cultured seaweed while minimizing disease infection, and the operation of an environmental control device equipped in a land-based seaweed farm is controlled based on the derived optimal aquaculture environment data to create an optimal seaweed farming environment in the land-based seaweed farm. Accordingly, land-based seaweed farming becomes possible continuously regardless of the season and weather conditions, thereby improving the quality of the cultured seaweed harvested through farming and simultaneously increasing the yield of cultured seaweed. Brief explanation of the drawing

[0017] FIG. 1 is a diagram showing the overall configuration of a digital twin-based intelligent land-based seaweed farming system according to exemplary embodiments. FIG. 2 is a block diagram and a perspective view showing the configuration of a marine seaweed farm according to exemplary embodiments. FIG. 3 is a block diagram showing the overall configuration of a land-based seaweed farm according to exemplary embodiments. FIG. 4 is a block diagram showing the detailed configuration of server devices included in a cloud environment according to exemplary embodiments. FIG. 5 is a block diagram showing the detailed configuration of an artificial intelligence model generation unit according to exemplary embodiments. FIGS. 6 and 7 are flowcharts illustrating the process of performing a digital twin-based intelligent land-based seaweed farming method according to exemplary embodiments. Specific details for implementing the invention

[0018] The terms used in the embodiments of this specification have been selected to be as widely used as possible, taking into account the functions of the present invention; however, these terms may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the description section of the relevant embodiments. Therefore, terms used in this specification should be defined not merely by their names, but based on their meanings and the overall content of the present invention.

[0019] Singular expressions may include plural expressions unless the context clearly indicates otherwise. Terms used herein, including technical or scientific terms, may have the same meaning as generally understood by those skilled in the art as described in this specification.

[0020] In the entire invention, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "...part," "...module," etc., as used in this specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software.

[0021] As used herein, the expression “configured to” may be replaced, depending on the context, with, for example, “suitable for,” “having the capacity to,” “designed to,” “adapted to,” “made to,” or “capable of.” The term “configured to” may not necessarily mean only “specifically designed to” in hardware. Instead, in some situations, the expression “system configured to” may mean that the system is “capable of” in conjunction with other devices or components. For example, the phrase “processor configured to perform A, B, and C” may mean a dedicated processor for performing the said operations (e.g., an embedded processor), or a generic-purpose processor (e.g., a CPU or an application processor) capable of performing said operations by executing one or more software programs stored in memory.

[0022] In addition, when a component in the present invention is described as being "connected" or "connected" to another component, it should be understood that the component may be directly connected to or directly connected to the other component, but unless otherwise specifically stated, it may also be connected or connected through another component in between.

[0023] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein.

[0024] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings.

[0025] FIG. 1 is a drawing showing a digital twin-based intelligent land-based seaweed farming system according to exemplary embodiments. FIG. 2 is a block diagram and perspective view showing the configuration of a sea-based seaweed farm according to exemplary embodiments. FIG. 3 is a block diagram showing the overall configuration of a land-based seaweed farm according to exemplary embodiments.

[0026] Referring to FIG. 1, the digital twin-based intelligent land-based seaweed farming system is configured to create an optimal seaweed growth environment that can maximize seaweed production by measuring and collecting seaweed farming data from a seaweed farm (10), generating a seaweed farming virtual model and a seaweed farming artificial intelligence model corresponding to the seaweed farm (10) based on the collected seaweed farming data, and controlling the farming environment of a land-based seaweed farm (20) based on seaweed farming prediction data generated by the seaweed farming artificial intelligence model.

[0027] As illustrated in FIG. 1, this digital twin-based intelligent land-based seaweed farming system may include a sea-based seaweed farm (10), a land-based seaweed farm (20), and a cloud environment (30) including one or more server devices.

[0028] First, as shown in FIG. 2, the offshore seaweed farm (10) can be installed in the sea and equipped to cultivate seaweed, for example, the offshore seaweed farm (10) can be installed in an inland bay or an offshore fishing ground, etc.

[0029] In one embodiment, as shown in (A) of FIG. 2, the offshore seaweed farm (10) may include an offshore seaweed farming facility (110) and an offshore measuring unit (120).

[0030] First, the offshore seaweed farming facility (110) is a facility for cultivating seaweed, and for example, the offshore seaweed farming facility (110) can be equipped as a facility for floating cultivation (non-exposed floating cultivation or exposed floating cultivation) among seaweed farming methods.

[0031] In one embodiment, as shown in (B) of FIG. 2, the seaweed farming facility (110) may include a net-shaped seaweed net (111), a supporting member (113) that supports the seaweed net (111), and a fixing member (115) that fixes a seaweed net installation formed by assembling a plurality of seaweed nets (111) and supporting members (113) to the sea.

[0032] In addition, if the seaweed farming method is an exposed floating type, it may also include a floating body (117) to expose the seaweed raft installation above the sea surface.

[0033] Next, the marine measuring unit (120) may be equipped to measure the aquaculture environment of the marine seaweed farm (10) and collect marine seaweed aquaculture data, which is data on the seaweed aquaculture environment of the marine seaweed farm (10).

[0034] The marine measurement unit (120) may include one or more measuring devices configured to measure the cultivation environment of the marine seaweed farm (10). For example, each measuring device of the marine measurement unit (120) may be installed on each component forming the aforementioned marine seaweed cultivation facility (110) to measure and collect various environmental data such as water quality and weather conditions required for marine seaweed cultivation, as well as image data of marine seaweed cultivated in the marine seaweed farm (10). For example, the marine seaweed cultivation data collected by the marine measurement unit (120) may include marine water quality data, marine weather data, and marine seaweed photograph data.

[0035] In one embodiment, the marine measurement unit (120) may include a marine water quality measuring device (121), a marine weather measuring device (123), and a marine photographing device (125).

[0036] First, a marine water quality measuring device (121) may be provided to measure the water quality of a marine seaweed farm (10) and collect data regarding the water quality of the marine seaweed farm (10) (hereinafter, marine water quality data).

[0037] For example, the marine water quality measuring device (121) may include a temperature measuring device, such as a temperature sensor, configured to measure the water temperature of the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be configured to measure the temperature of the marine seaweed farm (10) and collect marine water temperature data for the marine seaweed farm (10).

[0038] Additionally, the marine water quality measuring device (121) may include a salinity measuring device, such as a salinity meter, which is equipped to measure the salinity of the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to measure the salinity of the marine seaweed farm (10) and collect marine salinity data for the marine seaweed farm (10).

[0039] Additionally, the marine water quality measuring device (121) may include a hydrogen ion concentration measuring device, such as a pH sensor, configured to measure the hydrogen ion concentration of the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be configured to measure the hydrogen ion concentration of the marine seaweed farm (10) and collect marine hydrogen ion concentration data for the marine seaweed farm (10).

[0040] Additionally, the marine water quality measuring device (121) may include a dissolved oxygen measuring device, such as a dissolved oxygen sensor, which is equipped to measure the dissolved oxygen of the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to measure the amount of dissolved oxygen of the marine seaweed farm (10) and collect marine dissolved oxygen data for the marine seaweed farm (10).

[0041] Additionally, the marine water quality measuring device (121) may include a turbidity measuring device, such as a turbidity meter, which is equipped to measure the turbidity of the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to measure the turbidity of the marine seaweed farm (10) and collect marine turbidity data for the marine seaweed farm (10).

[0042] Additionally, the marine water quality measuring device (121) may include a chlorophyll a measuring device, such as a fluorescent photometer, which is equipped to measure chlorophyll a of the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to collect marine chlorophyll a data for the marine seaweed farm (10) by measuring the concentration of chlorophyll a of the marine seaweed farm (10).

[0043] Additionally, the marine water quality measuring device (121) may include an oil content measuring device, such as an oil content sensor, configured to measure the oil content of the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be configured to measure the concentration of oil content in the marine seaweed farm (10) and collect marine oil content data for the marine seaweed farm (10).

[0044] Additionally, the marine water quality measuring device (121) may include a chemical oxygen demand measuring device, such as a COD analyzer, which is equipped to measure the chemical oxygen demand of the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to measure the chemical oxygen demand of the marine seaweed farm (10) and collect marine chemical oxygen demand data for the marine seaweed farm (10).

[0045] Additionally, the marine water quality measuring device (121) may include a nitrogen measuring device, such as a nitrogen sensor, configured to measure nitrogen in the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be configured to measure the total nitrogen concentration of the marine seaweed farm (10) and collect total marine nitrogen data for the marine seaweed farm (10).

[0046] Additionally, the marine water quality measuring device (121) may include a phosphorus measuring device, such as a phosphorus analyzer, which is equipped to measure phosphorus in the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to measure the total phosphorus concentration of the marine seaweed farm (10) and collect marine total phosphorus data for the marine seaweed farm (10).

[0047] Additionally, the marine water quality measuring device (121) may include a nitrate nitrogen measuring device, such as a nitrate sensor, which is equipped to measure nitrate nitrogen in the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to measure the concentration of nitrate nitrogen in the marine seaweed farm (10) and collect marine nitrate nitrogen data for the marine seaweed farm (10).

[0048] Additionally, the marine water quality measuring device (121) may include an ammonia nitrogen measuring device, such as an ammonia analyzer, which is equipped to measure ammonia nitrogen in the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to measure the concentration of ammonia in the marine seaweed farm (10) and collect marine ammonia nitrogen data for the marine seaweed farm (10).

[0049] Additionally, the marine water quality measuring device (121) may include a phosphate measuring device, such as a phosphate meter, which is equipped to measure phosphate phosphorus in the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to measure the concentration of phosphate phosphorus in the marine seaweed farm (10) and collect marine phosphate phosphorus data for the marine seaweed farm (10).

[0050] Additionally, the marine water quality measuring device (121) may include a silicate measuring device, such as a silicate analyzer, which is equipped to measure silicate in the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to collect marine silicate data for the marine seaweed farm (10) by measuring the concentration of silicate in the marine seaweed farm (10).

[0051] Additionally, the marine water quality measuring device (121) may include a total organic carbon measuring device, such as a TOC analyzer, which is equipped to measure the total organic carbon of the marine seaweed farm (10). Accordingly, the marine water quality measuring device (121) may be equipped to measure the total organic carbon of the marine seaweed farm (10) and collect marine total organic carbon data for the marine seaweed farm (10).

[0052] As described above, the marine water quality measuring device (121) can collect at least one selected data among marine water quality data, marine water temperature data, marine salinity data, marine hydrogen ion concentration data, marine dissolved oxygen data, marine turbidity data, marine oil data, marine chemical oxygen demand data, marine nitrogen data, marine total phosphorus data, marine nitrate nitrogen data, marine ammonia nitrogen data, marine phosphate phosphorus data, marine silicate data and marine total organic carbon data through various measuring devices installed in the marine seaweed farm (10).

[0053] Meanwhile, the marine water quality measuring device (121) can collect marine water quality data according to a preset collection cycle.

[0054] At this time, among the marine water quality data collected by the marine water quality measuring device (121), marine water temperature data, marine salinity data, marine hydrogen ion concentration data, marine dissolved oxygen data, marine turbidity data, and marine oil data are referred to as the first marine water quality data, and among the marine water quality data collected by the marine water quality measuring device (121), marine chemical oxygen demand data, marine nitrogen data, marine total phosphorus data, marine nitrate nitrogen data, marine ammonia nitrogen data, marine phosphate phosphorus data, marine silicate data, and marine total organic carbon data are referred to as the second marine water quality data, and the marine water quality measuring device (121) may have different data collection cycles for the first marine water quality data and the second marine water quality data.

[0055] For example, the marine water quality measuring device (121) can collect first marine water quality data at a first time interval and collect second marine water quality data at a second time interval.

[0056] At this time, the first time may be set to be smaller than the second time, for example, the first time may be set to 5 minutes and the second time to 1 hour. Accordingly, the marine water quality measuring device (121) may collect the first marine water quality data every 5 minutes and the second marine water quality data every 1 hour.

[0057] Next, a marine weather measuring device (123) may be provided to measure the weather of the marine seaweed farm (10) and collect data regarding the weather of the marine seaweed farm (10) (hereinafter, marine weather data).

[0058] For example, the marine weather measuring device (123) may include a solar radiation measuring device, such as a pyranometer, which is equipped to measure the solar radiation of the marine seaweed farm (10). Accordingly, the marine weather measuring device (123) may be equipped to measure the solar radiation of the marine seaweed farm (10) and collect marine solar radiation data for the marine seaweed farm (10).

[0059] Additionally, the marine weather measuring device (123) may include a temperature measuring device, such as a temperature sensor, configured to measure the temperature of the marine seaweed farm (10). Accordingly, the marine weather measuring device (123) may be configured to measure the temperature of the marine seaweed farm (10) and collect marine temperature data for the marine seaweed farm (10).

[0060] Additionally, the marine weather measuring device (123) may include a humidity measuring device, such as a hygrometer, configured to measure the humidity of the marine seaweed farm (10). Accordingly, the marine weather measuring device (123) may be configured to measure the humidity of the marine seaweed farm (10) and collect marine humidity data for the marine seaweed farm (10).

[0061] Additionally, the marine weather measuring device (123) may include a wind speed measuring device, such as an anemometer, configured to measure the wind speed of the marine seaweed farm (10). Accordingly, the marine weather measuring device (123) may be configured to measure the wind speed of the marine seaweed farm (10) and collect marine wind speed data for the marine seaweed farm (10).

[0062] Additionally, the marine weather measuring device (123) may include a wind direction measuring device, such as a wind vane, which is equipped to measure the wind direction of the marine seaweed farm (10). Accordingly, the marine weather measuring device (123) may be equipped to measure the wind direction of the marine seaweed farm (10) and collect marine wind direction data for the marine seaweed farm (10).

[0063] Additionally, the marine weather measuring device (123) may include a precipitation measuring device, such as a rain gauge, equipped to measure the amount of precipitation in the marine seaweed farm (10). Accordingly, the marine weather measuring device (123) may be equipped to measure the amount of precipitation in the marine seaweed farm (10) and collect marine precipitation data for the marine seaweed farm (10).

[0064] Additionally, the marine weather measuring device (123) may include a flow velocity measuring device, such as a flow meter, configured to measure the flow velocity of the marine seaweed farm (10). Accordingly, the marine weather measuring device (123) may be configured to measure the flow velocity of the marine seaweed farm (10) and collect marine flow velocity data for the marine seaweed farm (10).

[0065] As described above, the weather measuring device (123) can collect at least one selected data among sea solar radiation data, sea temperature data, sea humidity data, sea wind speed data, sea wind direction data, sea precipitation data and sea current speed data as sea weather data through various measuring devices installed in the sea seaweed farm (10).

[0066] Meanwhile, the weather measuring device (123) can collect marine weather data according to a preset collection cycle.

[0067] For example, the weather measuring device (123) can collect marine weather data at a third time interval. For example, the third time can be set to 1 hour, and accordingly, the weather measuring device (123) can collect marine weather data every 1 hour.

[0068] At this time, the third time, which is the collection cycle of the weather measuring device (123), can be set to be the same as the second time, which is the second sea water quality data collection cycle of the sea water quality measuring device (121).

[0069] Next, a marine photographing device (125) may be provided to photograph marine-cultivated seaweed being cultivated in a marine seaweed farm (10) and to collect image data (hereinafter, marine seaweed photographing data) of marine-cultivated seaweed being cultivated in a marine seaweed farm (10).

[0070] For example, the marine imaging device (125) may include a camera device, etc., configured to photograph marine-cultivated seaweed grown in a marine seaweed farm (10). Accordingly, the marine imaging device (125) may be configured to photograph marine-cultivated seaweed grown in a marine seaweed farm (10) and collect marine seaweed imaging data regarding marine-cultivated seaweed grown in the sea.

[0071] At this time, the marine imaging device (125) can collect marine seaweed imaging data according to a preset collection cycle.

[0072] For example, the marine imaging device (125) can collect marine seaweed imaging data at four-hour intervals. For example, the four-hour interval can be set to one day, and accordingly, the marine imaging device (125) can collect marine seaweed imaging data every day.

[0073] At this time, the fourth time, which is the collection period of the marine imaging device (125), can be set to be larger than the first time, which is the collection period of the first marine water quality data of the aforementioned marine water quality measuring device (121), the second time, which is the collection period of the second marine water quality data, and the third time, which is the collection period of the weather measuring device (123).

[0074] Next, the land-based seaweed farm (20) can be installed on the ground and equipped to cultivate seaweed, for example, the land-based seaweed farm (20) can be installed on the ground adjacent to the coast, etc.

[0075] In one embodiment, as shown in FIG. 3, the land-based seaweed farm (20) may include a land-based seaweed farming facility (210), a land-based measuring unit (220), and an environmental control device (230).

[0076] First, the land-based seaweed farming facility (210) may be equipped with seaweed farming devices capable of cultivating seaweed in an exposed raft type or a non-exposed raft type.

[0077] For example, the land-based seaweed farming facility (210) may include a farming tank, a seaweed raft, a seaweed raft lifting device, etc.

[0078] Next, the land measuring unit (220) may be equipped to measure the cultivation environment of the land seaweed farm (20) and collect land seaweed cultivation data, which is data on the seaweed cultivation environment of the land seaweed farm (20).

[0079] The land measurement unit (220) may include one or more measurement devices configured to measure the cultivation environment of the land seaweed farm (20). For example, each of the measurement devices of the land measurement unit (220) may be installed on each component forming the aforementioned land seaweed cultivation facility (210) to measure and collect various environmental data such as water quality and weather conditions required for land seaweed cultivation, and image data of the land-cultivated seaweed cultivated in the land seaweed farm (20). For example, the land seaweed cultivation data collected by the land measurement unit (220) may include land water quality data, land weather data, and land seaweed photograph data.

[0080] In one embodiment, as shown in FIG. 3, the land measurement unit (220) may include a land water quality measurement device (221), a land weather measurement device (223), and a land imaging device (225).

[0081] First, a land water quality measuring device (221) may be provided to measure the water quality of a land seaweed farm (20) and collect data regarding the water quality of the land seaweed farm (20) (hereinafter, land water quality data).

[0082] For example, the land water quality measuring device (221) may include a temperature measuring device, such as a temperature sensor, configured to measure the water temperature of the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be configured to measure the temperature of the land seaweed farm (20) and collect land water temperature data for the land seaweed farm (20).

[0083] Additionally, the land water quality measuring device (221) may include a salinity measuring device, such as a salinity meter, which is equipped to measure the salinity of the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the salinity of the land seaweed farm (20) and collect land salinity data for the land seaweed farm (20).

[0084] Additionally, the land water quality measuring device (221) may include a hydrogen ion concentration measuring device, such as a pH sensor, configured to measure the hydrogen ion concentration of the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be configured to measure the hydrogen ion concentration of the land seaweed farm (20) and collect land hydrogen ion concentration data for the land seaweed farm (20).

[0085] Additionally, the land water quality measuring device (221) may include a dissolved oxygen measuring device, such as a dissolved oxygen sensor, which is equipped to measure the dissolved oxygen of the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the amount of dissolved oxygen of the land seaweed farm (20) and collect land dissolved oxygen data for the land seaweed farm (20).

[0086] Additionally, the land water quality measuring device (221) may include a turbidity measuring device, such as a turbidity meter, which is equipped to measure the turbidity of the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the turbidity of the land seaweed farm (20) and collect land turbidity data for the land seaweed farm (20).

[0087] Additionally, the land water quality measuring device (221) may include a chlorophyll a measuring device, such as a fluorescent photometer, equipped to measure chlorophyll a of the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the concentration of chlorophyll a of the land seaweed farm (20) and collect land chlorophyll a data for the land seaweed farm (20).

[0088] Additionally, the land water quality measuring device (221) may include an oil content measuring device, such as an oil content sensor, configured to measure the oil content of the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be configured to measure the concentration of oil content in the land seaweed farm (20) and collect land oil content data for the land seaweed farm (20).

[0089] Additionally, the land water quality measuring device (221) may include a chemical oxygen demand measuring device, such as a COD analyzer, which is equipped to measure the chemical oxygen demand of the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the chemical oxygen demand of the land seaweed farm (20) and collect land chemical oxygen demand data for the land seaweed farm (20).

[0090] Additionally, the land water quality measuring device (221) may include a nitrogen measuring device, such as a nitrogen sensor, configured to measure nitrogen in the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be configured to measure the total nitrogen concentration of the land seaweed farm (20) and collect land total nitrogen data for the land seaweed farm (20).

[0091] Additionally, the land water quality measuring device (221) may include a phosphorus measuring device, such as a phosphorus analyzer, which is equipped to measure phosphorus in the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the total phosphorus concentration in the land seaweed farm (20) and collect land total phosphorus data for the land seaweed farm (20).

[0092] Additionally, the land water quality measuring device (221) may include a nitrate nitrogen measuring device, such as a nitrate sensor, which is equipped to measure nitrate nitrogen in the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the concentration of nitrate nitrogen in the land seaweed farm (20) and collect land nitrate nitrogen data for the land seaweed farm (20).

[0093] Additionally, the land water quality measuring device (221) may include an ammonia nitrogen measuring device, such as an ammonia analyzer, which is equipped to measure ammonia nitrogen in the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the concentration of ammonia in the land seaweed farm (20) and collect land ammonia nitrogen data for the land seaweed farm (20).

[0094] Additionally, the land water quality measuring device (221) may include a phosphate measuring device, such as a phosphate meter, which is equipped to measure phosphate phosphorus in the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the concentration of phosphate phosphorus in the land seaweed farm (20) and collect land phosphate phosphorus data for the land seaweed farm (20).

[0095] Additionally, the land water quality measuring device (221) may include a silicate measuring device, such as a silicate analyzer, which is equipped to measure silicate in the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the concentration of silicate in the land seaweed farm (20) and collect land silicate data for the land seaweed farm (20).

[0096] Additionally, the land water quality measuring device (221) may include a total organic carbon measuring device, such as a TOC analyzer, which is equipped to measure the total organic carbon of the land seaweed farm (20). Accordingly, the land water quality measuring device (221) may be equipped to measure the total organic carbon of the land seaweed farm (20) and collect land total organic carbon data for the land seaweed farm (20).

[0097] As described above, the land water quality measuring device (221) can collect at least one selected data among land water temperature data, land salinity data, land hydrogen ion concentration data, land dissolved oxygen data, land turbidity data, land oil data, land chemical oxygen demand data, land nitrogen data, land total phosphorus data, land nitrate nitrogen data, land ammonia nitrogen data, land phosphate phosphorus data, land silicate data, and land total organic carbon data through various measuring devices installed in the land seaweed farm (20).

[0098] Meanwhile, the land water quality measuring device (221) can collect land water quality data according to a pre-set collection cycle.

[0099] At this time, among the land water quality data collected by the land water quality measuring device (221), land water temperature data, land salinity data, land hydrogen ion concentration data, land dissolved oxygen data, land turbidity data, and land oil data are referred to as the first land water quality data, and among the land water quality data collected by the land water quality measuring device (221), land chemical oxygen demand data, land nitrogen data, land total phosphorus data, land nitrate nitrogen data, land ammonia nitrogen data, land phosphate phosphorus data, land silicate data, and land total organic carbon data are referred to as the second land water quality data, and the land water quality measuring device (221) may have different data collection cycles for the first land water quality data and the second land water quality data.

[0100] For example, the land water quality measuring device (221) can collect the first land water quality data at the fifth time interval and the second land water quality data at the sixth time interval.

[0101] At this time, the fifth time may be set to be smaller than the sixth time, for example, the fifth time may be set to 5 minutes and the sixth time to 1 hour. Accordingly, the land water quality measuring device (221) may collect the first land water quality data every 5 minutes and the second land water quality data every 1 hour.

[0102] Meanwhile, the fifth time, which is the first land water quality data collection cycle of the land water quality measuring device (221), can be set to be the same as the first time, which is the first sea water quality data collection cycle of the aforementioned sea water quality measuring device (121).

[0103] In addition, the 6th time, which is the 2nd land water quality data collection cycle of the land water quality measuring device (221), can be set to be the same as the 2nd time, which is the 2nd sea water quality data collection cycle of the aforementioned sea water quality measuring device (121).

[0104] Next, a land weather measuring device (223) may be provided to measure the weather of the land seaweed farm (20) and collect data regarding the weather of the land seaweed farm (20) (hereinafter, land weather data).

[0105] For example, the land weather measuring device (223) may include a light irradiance measuring device, such as a pyranometer, which is equipped to measure the amount of light irradiance of the land seaweed farm (20). Accordingly, the land weather measuring device (223) may be equipped to measure the amount of solar radiation of the land seaweed farm (20) and collect land light irradiance data for the land seaweed farm (20).

[0106] Additionally, the land weather measuring device (223) may include a temperature measuring device, such as a temperature sensor, configured to measure the temperature of the land seaweed farm (20). Accordingly, the land weather measuring device (223) may be configured to measure the temperature of the land seaweed farm (20) and collect land temperature data for the land seaweed farm (20).

[0107] Additionally, the land weather measuring device (223) may include a humidity measuring device, such as a hygrometer, which is equipped to measure the humidity of the land seaweed farm (20). Accordingly, the land weather measuring device (223) may be equipped to measure the humidity of the land seaweed farm (20) and collect land humidity data for the land seaweed farm (20).

[0108] Additionally, the land weather measuring device (223) may include a wind speed measuring device, such as an anemometer, configured to measure the wind speed of the land seaweed farm (20). Accordingly, the land weather measuring device (223) may be configured to measure the wind speed of the land seaweed farm (20) and collect land wind speed data for the land seaweed farm (20).

[0109] Additionally, the land weather measuring device (223) may include a wind direction measuring device, such as a wind vane, which is equipped to measure the wind direction of the land seaweed farm (20). Accordingly, the land weather measuring device (223) may be equipped to measure the wind direction of the land seaweed farm (20) and collect land wind direction data for the land seaweed farm (20).

[0110] Additionally, the land weather measuring device (223) may include a precipitation measuring device, such as a rain gauge, equipped to measure the amount of precipitation in the land seaweed farm (20). Accordingly, the land weather measuring device (223) may be equipped to measure the amount of precipitation in the land seaweed farm (20) and collect land precipitation data for the land seaweed farm (20). In the case of land precipitation data, if there is an area among each area of ​​the land seaweed farm (20) where rainwater flows in, land precipitation data for that area may be collected.

[0111] Additionally, the land weather measuring device (223) may include a flow velocity measuring device, such as a flow meter, configured to measure the flow velocity of the land seaweed farm (20). Accordingly, the land weather measuring device (223) may be configured to measure the flow velocity of the land seaweed farm (20) and collect land flow velocity data for the land seaweed farm (20).

[0112] As described above, the weather measuring device (223) can collect at least one selected data among land weather data, land light irradiation data, land temperature data, land humidity data, land wind speed data, land wind direction data, land precipitation data, and land flow velocity data through various measuring devices installed in the land seaweed farm (20).

[0113] Meanwhile, the weather measuring device (223) can collect land weather data according to a pre-set collection cycle.

[0114] For example, the weather measuring device (223) can collect land weather data at a seven-hour interval. For example, the seven-hour interval can be set to one hour, and accordingly, the weather measuring device (223) can collect land weather data every hour.

[0115] At this time, the 7th time, which is the collection cycle of the weather measuring device (223), can be set to be the same as the 6th time, which is the 2nd land water quality data collection cycle of the land water quality measuring device (221).

[0116] Meanwhile, the 7th time, which is the land weather data collection cycle of the land weather measuring device (223), can be set to be the same as the 3rd time, which is the sea weather data collection cycle of the aforementioned sea weather measuring device (123).

[0117] Next, a land-based photographing device (225) may be provided to photograph land-based cultivated seaweed being cultivated in a land-based seaweed farm (20) and to collect image data (hereinafter, land-based seaweed photographing data) of land-based cultivated seaweed being cultivated in a land-based seaweed farm (20).

[0118] For example, the land-based photographing device (225) may include a camera device, etc., configured to photograph land-based cultivated seaweed grown in a land-based seaweed farm (20). Accordingly, the land-based photographing device (225) may be configured to photograph land-based cultivated seaweed grown in a land-based seaweed farm (20) and collect land-based seaweed photographing data regarding land-based cultivated seaweed grown on land.

[0119] At this time, the land-based photographing device (225) can collect land-based seaweed photographing data according to a preset collection cycle.

[0120] For example, the land imaging device (225) can collect land seaweed imaging data at the eighth hour interval. For example, the eighth hour can be set to one day, and accordingly, the land imaging device (225) can collect land seaweed imaging data every day.

[0121] At this time, the 8th time, which is the collection period of the land-based imaging device (225), can be set to be larger than the 5th time, which is the collection period of the 1st land-based water quality data of the aforementioned land-based water quality measuring device (221), the 6th time, which is the collection period of the 2nd land-based water quality data, and the 7th time, which is the collection period of the weather measuring device (223).

[0122] Meanwhile, the 8th time, which is the data collection cycle for land-based seaweed photography of the land-based photography device (225), can be set to be the same as the 4th time, which is the data collection cycle for sea-based seaweed photography of the aforementioned sea-based photography device (125).

[0123] Next, the environmental control device (230) may be provided to control the aquaculture environment of the land-based seaweed farm (20).

[0124] The environmental control device (230) may include one or more control devices configured to control the aquaculture environment of the land-based seaweed farm (20). For example, each control device of the environmental control device (230) may be installed in each area of ​​the land-based seaweed farm (20) to control the water temperature, salinity, air temperature, light irradiation amount, etc. of the land-based seaweed farm (20). For example, the land-based aquaculture environment controlled by the environmental control device (230) may include a land-based water quality environment and a land-based weather environment.

[0125] Here, the operation of the environment control device (230) can be controlled in real time according to a control command received from the environment control server (330) described later.

[0126] In one embodiment, as shown in FIG. 3, the environmental control device (230) may include a land water quality control device (231) and a land weather control device (233).

[0127] First, a land-based water quality control device (231) can be provided to control the water quality environment of a land-based seaweed farm (20).

[0128] For example, the land-based water quality control device (231) may include a heating device or a cooling device configured to control the water temperature of the land-based seaweed farm (20). Accordingly, the land-based water quality control device (231) may be configured to control the water temperature of the land-based seaweed farm (20) to a preset target water temperature.

[0129] Additionally, the land water quality control device (231) may include a salinity control device configured to control the salinity of the land seaweed farm (20). Accordingly, the land water quality control device (231) may be configured to control the salinity of the land seaweed farm (20) to a preset target salinity.

[0130] Additionally, the land-based water quality control device (231) may include a hydrogen ion concentration control device, such as a pH regulator, which is provided to control the hydrogen ion concentration of the land-based seaweed farm (20). Accordingly, the land-based water quality control device (231) may be provided to control the hydrogen ion concentration of the land-based seaweed farm (20) to a preset target hydrogen ion concentration.

[0131] Additionally, the land water quality control device (231) may include a dissolved oxygen control device, such as an oxygen generator, which is provided to control the amount of dissolved oxygen in the land seaweed farm (20). Accordingly, the land water quality control device (231) may be provided to control the amount of dissolved oxygen in the land seaweed farm (20) to a predetermined target amount of dissolved oxygen.

[0132] Additionally, the land water quality control device (231) may include a turbidity control device configured to control the turbidity of the land seaweed farm (20). Accordingly, the land water quality control device (231) may be configured to control the turbidity of the land seaweed farm (20) to a preset target turbidity.

[0133] Additionally, the land water quality control device (231) may include an oil content control device configured to control the oil content of the land seaweed farm (20). Accordingly, the land water quality control device (231) may be configured to control the oil content of the land seaweed farm (20) to a preset target oil content.

[0134] Additionally, the land-based water quality control device (231) may include a chemical oxygen demand control device configured to control the chemical oxygen demand of the land-based seaweed farm (20). Accordingly, the land-based water quality control device (231) may be configured to control the chemical oxygen demand of the land-based seaweed farm (20) to a predetermined target chemical oxygen demand.

[0135] Additionally, the land water quality control device (231) may include a nitrogen control device configured to control the total nitrogen amount of the land seaweed farm (20). Accordingly, the land water quality control device (231) may be configured to control the total nitrogen amount of the land seaweed farm (20) to a preset target total nitrogen amount.

[0136] Additionally, the land water quality control device (231) may include a phosphorus control device configured to control the total phosphorus amount of the land seaweed farm (20). Accordingly, the land water quality control device (231) may be configured to control the total phosphorus amount of the land seaweed farm (20) to a preset target total phosphorus amount.

[0137] Additionally, the land water quality control device (231) may include a nitrate nitrogen control device configured to control the amount of nitrate nitrogen in the land seaweed farm (20). Accordingly, the land water quality control device (231) may be configured to control the amount of nitrate nitrogen in the land seaweed farm (20) to a preset target amount of nitrate nitrogen.

[0138] Additionally, the land-based water quality control device (231) may include an ammonia nitrogen control device configured to control the amount of ammonia nitrogen in the land-based seaweed farm (20). Accordingly, the land-based water quality control device (231) may be configured to control the amount of ammonia nitrogen in the land-based seaweed farm (20) to a predetermined target amount of ammonia nitrogen.

[0139] Additionally, the land water quality control device (231) may include a phosphate control device configured to control the amount of phosphate in the land seaweed farm (20). Accordingly, the land water quality control device (231) may be configured to control the amount of phosphate in the land seaweed farm (20) to a preset target amount of phosphate.

[0140] Additionally, the land water quality control device (231) may include a silicate control device configured to control the silicate amount of the land seaweed farm (20). Accordingly, the land water quality control device (231) may be configured to control the silicate amount of the land seaweed farm (20) to a preset target silicate amount.

[0141] Additionally, the land water quality control device (231) may include an organic carbon control device configured to control the total organic carbon amount of the land seaweed farm (20). Accordingly, the land water quality control device (231) may be configured to control the total organic carbon amount of the land seaweed farm (20) to a predetermined target total organic carbon amount.

[0142] Next, the land weather control device (233) may be equipped to control the weather environment of the land seaweed farm (20).

[0143] For example, the land weather control device (233) may include a light irradiation device configured to control the amount of light irradiation of the land seaweed farm (20). Accordingly, the land weather control device (233) may be configured to control the amount of light irradiation of the land seaweed farm (20) to a preset target amount of light irradiation.

[0144] Additionally, the land weather control device (233) may include a temperature control device, such as a cooling / heat air conditioning device, which is provided to control the temperature of the land seaweed farm (20). Accordingly, the land weather control device (233) may be provided to control the temperature of the land seaweed farm (20) to a preset target temperature.

[0145] Additionally, the land weather control device (233) may include a humidity control device configured to control the humidity of the land seaweed farm (20). Accordingly, the land weather control device (233) may be configured to control the humidity of the land seaweed farm (20) to a preset target humidity.

[0146] Additionally, the land weather control device (233) may include a blower device configured to control the wind speed and wind direction of the land seaweed farm (20). Accordingly, the land weather control device (233) may be configured to control the wind speed and wind direction of the land seaweed farm (20) to a preset target wind speed and target wind direction.

[0147] Additionally, the land weather control device (233) may include a flow rate control device configured to control the flow rate of the land seaweed farm (20). Accordingly, the land weather control device (233) may be configured to control the flow rate to a preset flow rate while causing flow in the aquaculture tank of the land seaweed farm (20).

[0148] Next, the cloud environment (30) may be provided to support hardware and software resources for data collection and data processing for operating a digital twin-based intelligent land-based seaweed farming system according to the present invention.

[0149] The cloud environment (30) may include one or more server devices configured to perform data collection and data processing for operating a digital twin-based intelligent land-based seaweed farming system according to the present invention.

[0150] In one embodiment, server devices provided based on a cloud environment (30) may be configured to receive seaweed farming data obtained by measuring the farming environment of a seaweed farm (10), and to generate a seaweed farming virtual model corresponding to the seaweed farm (10) based on the received seaweed farming data.

[0151] Additionally, server devices provided based on a cloud environment (30) may be configured to generate a seaweed farming artificial intelligence model based on seaweed farming virtual data generated by the generated seaweed farming virtual model, and to control the operation of an environment control device (230) installed in a land-based seaweed farming facility (20) based on optimal farming environment data generated by the seaweed farming artificial intelligence model.

[0152] Such server devices may be provided as computing devices including one or more processors and memory, as an example.

[0153] For example, the processor can execute one or more instructions or program code stored in memory and perform functions or operations corresponding to the instructions or program code. By executing one or more instructions or program code stored in memory, the processor can control the overall operation of the server device.

[0154] A processor may refer to a data processing unit embedded in hardware that has physically structured circuits to perform functions expressed by instructions or program code. For example, a processor may include, but is not limited to, a Central Processing Unit, a microprocessor, a Graphic Processing Unit, an Application Processor (AP), Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), and Field Programmable Gate Arrays (FPGAs).

[0155] Memory can store instructions and program code that can be read by a processor. For example, memory may include flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), Mask ROM, Flash ROM, etc.), hard disk drive (HDD), or solid state drive (SSD).

[0156] Instructions or program code stored in memory can be implemented in programming or scripting languages ​​such as C, C++, Java, and assembler.

[0157] Memory may store at least one software module containing instructions or program code. Each software module is executed by a processor to enable the server device to perform a specific operation or function.

[0158] Meanwhile, it goes without saying that the server device may include, in addition to the processor and memory, an input device for data input, an output device for data output, and a communication device for data transmission and reception.

[0159] Meanwhile, the configuration and operation of each server device included in the cloud environment (30) will be explained in more detail below with reference to FIG. 4.

[0160] Next, FIG. 4 is a block diagram showing the detailed configuration of server devices included in a cloud environment according to exemplary embodiments.

[0161] Referring to FIG. 4, the cloud environment (30) may include a data collection server (310), a model creation server (320), and an environment control server (330).

[0162] First, the data collection server (310) can receive seaweed farming data collected from the sea measurement unit (120) of the seaweed farm (10).

[0163] In one embodiment, the data collection server (310) may include a data transmission and reception unit (311) and a storage unit (313).

[0164] The data transmission and reception unit (311) may include a wireless communication device or a wired communication device. The data transmission and reception unit (311) may communicate with the marine measurement unit (120) through at least one network using a wireless communication device or a wired communication device. For example, the wireless communication device may include a cellular communication device, a short-range wireless communication device, or a GNSS (global navigation satellite system) communication device. The wired communication device may include a LAN (local area network) communication device or a power line communication device.

[0165] In one embodiment, the data transmission and reception unit (311) can receive seaweed farming data from the sea measurement unit (120) of the seaweed farm (10).

[0166] For example, the data transmission and reception unit (311) can receive marine water quality data from the marine measurement unit (120). That is, the data transmission and reception unit (311) can receive at least one selected data from the marine measurement unit (120) among marine water temperature data, marine salinity data, marine hydrogen ion concentration data, marine dissolved oxygen data, marine turbidity data, marine oil data, marine chemical oxygen demand data, marine nitrogen data, marine total phosphorus data, marine nitrate nitrogen data, marine ammonia nitrogen data, marine phosphate phosphorus data, marine silicate data, and marine total organic carbon data.

[0167] Additionally, the data transmission and reception unit (311) can receive marine weather data from the marine measurement unit (120). That is, the data transmission and reception unit (311) can receive at least one selected data from the marine measurement unit (120), including marine solar radiation data, marine temperature data, marine humidity data, marine wind speed data, marine wind direction data, marine precipitation data, and marine current speed data.

[0168] In addition, the data transmission and reception unit (311) can receive sea seaweed shooting data from the sea measurement unit (120).

[0169] Additionally, the data transmission and reception unit (311) can receive land water quality data from the land measurement unit (220). That is, the data transmission and reception unit (311) can receive at least one selected data from the land measurement unit (220) among land water temperature data, land salinity data, land hydrogen ion concentration data, land dissolved oxygen data, land turbidity data, land oil content data, land chemical oxygen demand data, land nitrogen data, land total phosphorus data, land nitrate nitrogen data, land ammonia nitrogen data, land phosphate phosphorus data, land silicate data, and land total organic carbon data.

[0170] Additionally, the data transmission and reception unit (311) can receive land weather data from the land measurement unit (220). That is, the data transmission and reception unit (311) can receive at least one selected data from the land measurement unit (220), among land solar radiation data, land temperature data, land humidity data, land wind speed data, land wind direction data, land precipitation data, and land flow velocity data.

[0171] Additionally, the data transmission and reception unit (311) can receive land seaweed shooting data from the land measurement unit (220).

[0172] Next, the storage unit (313) can store seaweed farming data received from the sea measurement unit (120) by the data transmission and reception unit (311).

[0173] That is, the storage unit (313) can store the marine water quality data, marine weather data, and marine seaweed photograph data received by the data transmission and reception unit (311) from the marine measurement unit (120), respectively.

[0174] Additionally, the storage unit (313) can store land seaweed farming data received from the land measurement unit (220) by the data transmission and reception unit (311).

[0175] That is, the storage unit (313) can store land water quality data, land weather data, and land seaweed photography data received by the data transmission and reception unit (311) from the land measurement unit (220), respectively.

[0176] For example, the storage unit (313) can store sea seaweed farming data and land seaweed farming data in the form of a CSV file or a TXT file.

[0177] In addition, as described above, the marine measurement unit (120) can collect each marine seaweed farming data according to different data collection cycles, and the storage unit (313) can sequentially store the marine seaweed farming data according to the collected time series order.

[0178] Additionally, the land measurement unit (220) can collect each of the land seaweed farming data according to different data collection cycles, and the storage unit (313) can sequentially store the land seaweed farming data according to the collected time series order.

[0179] Next, the model generation server (320) may be configured to receive seaweed farming data collected from the seaweed farm (10), generate a seaweed farm virtual model (322) corresponding to the seaweed farm (10) based on the seaweed farming data, and generate a seaweed farming artificial intelligence model (324) based on the seaweed farming virtual data output from the seaweed farm virtual model (322).

[0180] In one embodiment, the model generation server (320) may include a digital twin generation unit (321) and an artificial intelligence model generation unit (323).

[0181] First, the digital twin generation unit (321) receives seaweed farming data collected from the seaweed farm (10) and can generate a seaweed farm virtual model (322) corresponding to the seaweed farm (10) based on the seaweed farming data.

[0182] At this time, the digital twin generation unit (321) can receive marine seaweed farming data collected from the marine seaweed farm (10) from the aforementioned data collection server (310).

[0183] In one embodiment, the digital twin generation unit (321) can receive marine water quality data from the data collection server (310). For example, the digital twin generation unit (321) can receive at least one selected data from the data collection server (310), including marine water temperature data, marine salinity data, marine hydrogen ion concentration data, marine dissolved oxygen data, marine turbidity data, marine oil data, marine chemical oxygen demand data, marine nitrogen data, marine total phosphorus data, marine nitrate nitrogen data, marine ammonia nitrogen data, marine phosphate phosphorus data, marine silicate data, and marine total organic carbon data.

[0184] Additionally, the digital twin generation unit (321) can receive marine weather data from the data collection server (310). For example, the digital twin generation unit (321) can receive at least one selected data from the data collection server (310), including marine solar radiation data, marine temperature data, marine humidity data, marine wind speed data, marine wind direction data, marine precipitation data, and marine current speed data.

[0185] In addition, the digital twin generation unit (321) can receive sea seaweed shooting data from the data collection server (310).

[0186] Here, the digital twin generation unit (321) can generate a virtual model (322) of a seaweed farm corresponding to a seaweed farm (10) based on seaweed farming data received from the data collection server (310).

[0187] In one embodiment, the digital twin generation unit (321) can generate virtual models corresponding to each of the seaweed cultivation facility (110) of the seaweed farm (10), the seaweed cultivation seawater environment, the seaweed cultivation atmospheric environment, and the seaweed cultivated in the seaweed cultivation facility (110), based on seaweed cultivation data received from the data collection server (310).

[0188] Here, when generating a virtual model corresponding to a seaweed farming facility (110), the digital twin generation unit (321) may additionally receive design data for the seaweed farming facility (110) in addition to the seaweed farming data and generate a virtual model corresponding to the seaweed farming facility (110) based thereon.

[0189] For example, the digital twin generation unit (321) can be generated as a 3D model that can visually represent a virtual model corresponding to each of the seaweed farming facility (110) of the seaweed farm (10), the seawater environment, the atmospheric environment, and the seaweed grown in the seaweed farming facility (110), and can be generated as a simulation model built to perform a simulation (e.g., physical simulation) for a specific input and output a specific simulation result by setting a simulation environment.

[0190] At this time, the digital twin generation unit (321) can synchronize the seaweed farming data collected from the data collection server (310) by reflecting it in real time in the seaweed farming virtual model (322).

[0191] In one embodiment, the virtual model (322) of a seaweed farm generated by the digital twin generation unit (321) may include a virtual offshore seaweed farming facility model, a virtual seaweed farming seawater model, a virtual seaweed farming waiting model, and a virtual farming seaweed model.

[0192] Here, the virtual offshore seaweed farming facility model may be a virtual model generated based on design data for the seaweed farming facility (110). Additionally, the virtual seaweed farming seawater model may be a virtual model generated based on offshore water quality data. Additionally, the virtual seaweed farming atmosphere model may be a virtual model generated based on offshore weather data. Additionally, the virtual farming seaweed model may be a virtual model generated based on offshore seaweed photography data.

[0193] Meanwhile, the seaweed farm virtual model (322) can output virtual seaweed farming data.

[0194] Here, virtual seaweed farming data may refer to a simulation result value derived by the virtual seaweed farming model (322) performing a simulation when a specific input value is input into the virtual seaweed farming model (322).

[0195] In one embodiment, the virtual seaweed farming data output by the seaweed farming virtual model (322) may include virtual water quality data, virtual weather data, and virtual farmed seaweed image data.

[0196] For example, virtual water quality data can be derived by a virtual seaweed farming seawater model, and the virtual water quality data output by the virtual seaweed farming seawater model may include at least one selected from virtual water temperature data, virtual salinity data, virtual hydrogen ion concentration data, virtual dissolved oxygen data, virtual turbidity data, virtual oil content data, virtual chemical oxygen demand data, virtual nitrogen data, virtual total phosphorus data, virtual nitrate nitrogen data, virtual ammonia nitrogen data, virtual phosphate phosphorus data, virtual silicate data, and virtual total organic carbon data.

[0197] Additionally, virtual weather data can be derived by a virtual seaweed farming atmosphere model, and the virtual weather data output by the virtual seaweed farming atmosphere model may include at least one selected from virtual solar radiation data, virtual temperature data, virtual humidity data, virtual wind speed data, virtual wind direction data, virtual precipitation data, and virtual flow velocity data.

[0198] In addition, virtual culture seaweed image data can be derived by a virtual culture seaweed model.

[0199] For example, if “size of cultivated seaweed after 6 months when the water temperature of the seaweed farm is 10℃” is input as an input to the seaweed farm virtual model (322), the seaweed farm virtual model (322) can perform a simulation according to the condition when the water temperature of the seaweed farm is maintained at 10℃ and derive the size of cultivated seaweed after 6 months as a simulation result in the form of virtual cultivated seaweed image data.

[0200] Next, the artificial intelligence model generation unit (323) can generate a seaweed farming artificial intelligence model (324) based on at least one selected from the marine seaweed farming data received from the data collection server (310), the virtual seaweed farming data output from the seaweed farming virtual model (322), and the land seaweed farming data received from the land measurement unit (220) of the land seaweed farming site (20).

[0201] In one embodiment, as illustrated in FIG. 5, the artificial intelligence model generation unit (323) may include a data preprocessing unit (323-1), a training data construction unit (323-2), a model training unit (323-3), and a model verification unit (323-4).

[0202] First, the data preprocessing unit (323-1) can receive marine seaweed farming data from the data collection server (310), receive virtual seaweed farming data from the seaweed farm virtual model (322), or receive land-based seaweed farming data from the data collection server (310).

[0203] The data preprocessing unit (323-1) can receive at least one selected from marine seaweed farming data, virtual seaweed farming data, and land seaweed farming data.

[0204] At this time, the data preprocessing unit (323-1) can perform data refinement on the input sea seaweed farming data, virtual seaweed farming data, and land seaweed farming data.

[0205] For example, the data cleaning performed by the data preprocessing unit (323-1) may include processing missing values, processing outliers, removing duplicate data, and removing noise data for marine seaweed farming data, virtual seaweed farming data, and land seaweed farming data.

[0206] In addition, the data preprocessing unit (323-1) can perform data conversion on the input sea seaweed farming data, virtual seaweed farming data, and land seaweed farming data.

[0207] For example, the data transformation performed by the data preprocessing unit (323-1) may include categorical data encoding (One-Hot Encoding, Label Encoding, etc.) for marine seaweed farming data, virtual seaweed farming data, and land seaweed farming data, data scaling (normalization, standardization, etc.), resampling for data synchronization (e.g., unifying data collected at different intervals into a specific interval), and time data processing (e.g., separating dates into days of the week, months, etc. to create new features).

[0208] The data preprocessing unit (323-1) can perform data refinement and data conversion as described above on the input sea seaweed farming data, virtual seaweed farming data, and land seaweed farming data. Since each of the sea seaweed farming data, virtual seaweed farming data, and land seaweed farming data includes numerical data and image data, the data preprocessing unit (323-1) can perform data refinement and data conversion suitable for each of the numerical data and image data.

[0209] Meanwhile, the data preprocessing unit (323-1) can perform data refinement and data conversion on land-based seaweed farming data in the same manner as the data refinement and data conversion performed on the sea-based seaweed farming data and virtual seaweed farming data when land-based seaweed farming data is additionally collected after sea-based seaweed farming data and virtual seaweed farming data are first collected and data refinement and data conversion are performed on the sea-based seaweed farming data and virtual seaweed farming data.

[0210] Next, the learning data construction unit (323-2) can construct a dataset to build the marine seaweed farming data, virtual seaweed farming data, and land seaweed farming data refined and converted by the data preprocessing unit (323-1) as training data for model training.

[0211] In one embodiment, the dataset construction performed by the training data construction unit (323-2) may include data labeling, data integration, dataset splitting, etc.

[0212] For example, the learning data construction unit (323-2) can perform labeling work on image data included in marine seaweed farming data, virtual seaweed farming data, and land seaweed farming data.

[0213] As described above, in the case of marine seaweed farming data, it may include marine seaweed photograph data, which is image data, and the learning data construction unit (323-2) may perform object detection, attribute labeling, etc. as a labeling task for the marine seaweed photograph data.

[0214] For example, the learning data construction unit (323-2) can identify the location of sea-farmed seaweed in an image based on sea-farmed seaweed photography data and assign a label to the location of the sea-farmed seaweed.

[0215] In addition, the learning data construction unit (323-2) can assign attribute labels for the distribution, number, area increase, color, etc. of sea-cultivated seaweed in images based on sea-sea seaweed photography data.

[0216] The training data construction unit (323-2) can perform labeling tasks such as object detection and attribute labeling on virtual seaweed image data included in virtual seaweed farming data and land seaweed photograph data included in land seaweed farming data, respectively.

[0217] Next, the learning data construction unit (323-2) can perform a data integration operation that merges marine seaweed farming data, virtual seaweed farming data, and land-based seaweed farming data.

[0218] In one embodiment, the learning data construction unit (323-2) can perform a data integration operation that merges marine water quality data, marine weather data, and marine seaweed photography data included in marine seaweed farming data.

[0219] For example, the learning data construction unit (323-2) can merge marine water quality data and marine weather data using time as a key value. Additionally, the learning data construction unit (323-2) can merge marine seaweed image data, for which labeling work has been performed, into a dataset for the merged marine water quality data and marine weather data using time as a key value.

[0220] At this time, since the marine water quality data, marine weather data, and marine seaweed image data are synchronized with respect to the time axis through the aforementioned data preprocessing unit (323-1), the learning data construction unit (323-2) can merge the marine water quality data, marine weather data, and marine seaweed image data using time as the key value.

[0221] In this way, the learning data construction unit (323-2) can construct a dataset by merging marine weather data, marine seaweed photography data and marine seaweed photography data, and the constructed dataset can be used as training data for a multimodal model (hereinafter, the first training data).

[0222] Meanwhile, the learning data construction unit (323-2) can perform a data integration operation that merges virtual water quality data, virtual weather data, and virtual farmed seaweed image data included in the virtual seaweed farming data.

[0223] For example, the training data construction unit (323-2) can merge virtual water quality data and virtual weather data using time as the key value. Additionally, the training data construction unit (323-2) can merge virtual farmed seaweed image data, for which labeling work has been performed, into a dataset for the merged virtual water quality data and virtual weather data using time as the key value.

[0224] At this time, since the virtual water quality data, virtual weather data, and virtual farmed seaweed image data are synchronized with respect to the time axis through the aforementioned data preprocessing unit (323-1), the learning data construction unit (323-2) can merge the virtual water quality data, virtual weather data, and virtual farmed seaweed image data using time as the key value.

[0225] In this way, the learning data construction unit (323-2) can construct a dataset by merging virtual weather data, virtual seaweed photography data, and virtual seaweed photography data, and the constructed dataset can be used as learning data for multimodal model training (hereinafter, second learning data).

[0226] Meanwhile, the learning data construction unit (323-2) can perform a data integration operation that merges land water quality data, land weather data, and land seaweed photography data included in the land seaweed farming data.

[0227] For example, the training data construction unit (323-2) can merge land water quality data and land weather data using time as the key value. Additionally, the training data construction unit (323-2) can merge land seaweed image data, for which labeling has been performed, into a dataset of land water quality data and land weather data merged using time as the key value.

[0228] At this time, since the land water quality data, land weather data, and land seaweed image data are synchronized with respect to the time axis through the aforementioned data preprocessing unit (323-1), the learning data construction unit (323-2) can merge the land water quality data, land weather data, and land seaweed image data using time as the key value.

[0229] In this way, the learning data construction unit (323-2) can construct a dataset by merging land weather data, land seaweed photography data, and land seaweed photography data, and the constructed dataset can be used as training data for multimodal model training (hereinafter, third training data).

[0230] Next, the learning data construction unit (323-2) can perform data splitting operations for each of the first learning data, the second learning data, and the third learning data.

[0231] In one embodiment, the learning data construction unit (323-2) can perform the task of dividing the dataset into a learning dataset, a verification dataset, and a test dataset for each of the first learning data, the second learning data, and the third learning data.

[0232] For example, the training data construction unit (323-2) can perform the task of dividing the first training data into a training dataset, a verification dataset, and a test dataset.

[0233] In addition, the training data construction unit (323-2) can perform the task of dividing the second training data into a training dataset, a verification dataset, and a test dataset.

[0234] In addition, the training data construction unit (323-2) can perform the task of dividing the third training data into a training dataset, a verification dataset, and a test dataset.

[0235] At this time, the training data construction unit (323-2) can divide the training dataset so that it is allocated at a ratio of 70~80% to the total dataset, divide the verification dataset so that it is allocated at a ratio of 10~15% to the total dataset, and divide the test dataset so that it is allocated at a ratio of 10~15% to the total dataset.

[0236] The learning data construction unit (323-2) can perform data labeling, data integration, and dataset splitting for land-based seaweed farming data in the same way as the data labeling, data integration, and dataset splitting performed for the sea-based seaweed farming data and virtual seaweed farming data, after the sea-based seaweed farming data and virtual seaweed farming data are collected first.

[0237] Next, the model learning unit (323-3) can take water quality data and weather data for the seaweed farm as input and perform model learning to create an artificial intelligence model (324) for seaweed farming that outputs optimal farming environment data that can grow the seaweed to its maximum size while minimizing disease infection of the farmed seaweed for a set period.

[0238] For example, the model learning unit (323-3) can train an initial model using a learning algorithm including error back-propagation or gradient descent, and the model learning unit (323-3) can also train an initial model through supervised learning, unsupervised learning, or reinforcement learning.

[0239] In one embodiment, the model learning unit (323-3) can train an initial model using at least one selected from the first learning data, second learning data, and third learning data generated by the aforementioned learning data building unit (323-2) as the learning data.

[0240] For example, the model learning unit (323-3) can perform model learning using only the first learning data as input.

[0241] Here, as described above, the first training data may include numerical data such as marine water quality data and marine weather data, and image data such as marine seaweed capture data.

[0242] For example, the model learning unit (323-3) can extract features of marine water quality data and marine weather data using a Fully Connected Layer. Additionally, the model learning unit (323-3) can extract size information and color information (for determining disease infection status) of marine farmed seaweed from marine seaweed image data using a Convolutional Neural Network (CNN).

[0243] At this time, the model learning unit (323-3) can perform multimodal model learning by merging feature vectors extracted from water quality data and marine weather data and feature vectors extracted from marine seaweed photography data, and inputting the merged feature vectors into the model for learning.

[0244] As another example, the model learning unit (323-3) may perform the same model learning as the model learning described above using the first learning data as input, using only the second learning data as input.

[0245] As another example, the model learning unit (323-3) can perform the same model learning as the model learning with the first learning data described above as input, using the first learning data and the second learning data as input.

[0246] When performing model training using integrated training data including first training data and second training data as input, the ratio of the first training data and the ratio of the second training data constituting the integrated training data can be configured to be different from each other.

[0247] In this way, when model training is performed using integrated training data including first training data and second training data as input, it becomes possible to train the model using training data with increased quantity and diversity of data.

[0248] Next, the model verification unit (323-4) inputs a test dataset into the trained model and evaluates the performance of the trained model by comparing the optimal aquaculture environment data (which may include optimal water quality data and optimal weather data) and the predicted aquaculture seaweed growth data output by the trained model with the land water quality data, land weather data, and land seaweed photographic data actually collected at the land seaweed farm (20).

[0249] At this time, if the evaluation indicator of the learned model calculated by the model verification unit (323-4) satisfies a pre-set standard value, the corresponding learned model can be extracted and generated as a seaweed farming artificial intelligence model (324).

[0250] In addition, if the evaluation indicator of the learned model calculated by the model verification unit (323-4) does not satisfy the pre-set standard value, the model learning can be performed again by the model learning unit (323-3) by adjusting the variables (parameters, etc.) regarding model learning or by additionally configuring the learning data.

[0251] Meanwhile, the generated artificial intelligence model for seaweed farming (324) can output optimal farming environment data that allows the seaweed to grow to its maximum size while minimizing disease infection of the farmed seaweed for a set period when water quality data and weather data for the seaweed farm are input.

[0252] For example, when land water quality data and land weather data for a land seaweed farm (20) are input into the seaweed farming artificial intelligence model (324), the seaweed farming artificial intelligence model (324) can output optimal farming environment data that allows the farmed seaweed to grow to a maximum size while minimizing disease infection of the farmed seaweed for a pre-set period.

[0253] In one embodiment, the optimal aquaculture environment data output by the seaweed aquaculture artificial intelligence model (324) may include optimal water quality data, optimal weather data, and optimal growth seaweed data.

[0254] For example, optimal water quality data may include at least one selected from optimal water temperature data, optimal salinity data, optimal hydrogen ion concentration data, optimal dissolved oxygen data, optimal turbidity data, optimal oil content data, optimal chemical oxygen demand data, optimal nitrogen data, optimal total phosphorus data, optimal nitrate nitrogen data, optimal ammonia nitrogen data, optimal phosphate phosphorus data, optimal silicate data, and optimal total organic carbon data.

[0255] In addition, the optimal weather data may include at least one selected from optimal solar radiation data, optimal temperature data, optimal humidity data, optimal wind speed data, optimal wind direction data, optimal precipitation data, and optimal flow velocity data.

[0256] In addition, the optimal growth data for seaweed may include data representing the maximum growth amount of cultivated seaweed predicted according to the optimal farming environment. For example, the optimal growth data for seaweed may be numerical data representing the size and area of ​​the cultivated seaweed that has grown to its maximum size according to the optimal farming environment, or image data representing the shape of the cultivated seaweed that has grown to its maximum size according to the optimal farming environment.

[0257] Meanwhile, the aforementioned model learning unit (323-3) can perform additional model learning using the third learning data.

[0258] That is, the model learning unit (323-3) can additionally train a model that has been previously trained using the first learning data or the second learning data by using the land water quality data, land weather data, and land seaweed photograph data collected from the land seaweed farm (20) as learning data.

[0259] Since the actual cultivation environments of the seaweed farm (10) and the land-based seaweed farm (20) are different from each other, even if the optimal cultivation environment data output by the seaweed cultivation artificial intelligence model (324) trained by the first training data or the second training data is applied to the land-based seaweed farm (20), there may be a difference between the predicted growth degree of the land-based seaweed and the actual growth degree of the land-based seaweed.

[0260] To compensate for such problems, the model learning unit (323-3) can improve the performance of the learning model by using land water quality data, land weather data, and land seaweed photographic data collected from the land seaweed farm (20) as learning data, and by additionally training the model that was previously trained using marine aquaculture data and virtual aquaculture data.

[0261] Meanwhile, the model verification unit (323-4) performs a performance evaluation of the additionally trained model in the same manner as described above, and if the evaluation indicator of the calculated trained model satisfies a preset standard value, the additionally trained model can be extracted and generated as a seaweed farming artificial intelligence model (324).

[0262] Meanwhile, the aforementioned model learning unit (323-3) can perform k-means model learning using at least one selected from the first learning data, the second learning data, and the third learning data.

[0263] For example, the model learning unit (323-3) can determine the number of clusters by performing k-means clustering during the model learning process and identify the centroid of each cluster to derive representative environmental conditions of the seaweed farm (water quality condition, air condition, size of farmed seaweed, etc.), and further derive the optimal cluster among the derived multiple clusters.

[0264] In this way, the seaweed farming artificial intelligence model (324) generated by k-means model learning can output optimal farming environment data based on each derived cluster.

[0265] For example, when land water quality data, land weather data, and land seaweed photography data according to the current state of the land seaweed farm (20) are input into the seaweed farming artificial intelligence model (324), the seaweed farming artificial intelligence model (324) can select a specific cluster that is most similar to the input land water quality data, land weather data, and land seaweed photography data among the derived multiple clusters, and output optimal farming environment data based on the selected specific cluster.

[0266] As another example, the seaweed farming artificial intelligence model (324) may output optimal farming environment data based on an optimal cluster as a fixed output, in response to inputs of land water quality data, land weather data, and land seaweed photograph data according to the current state of the land seaweed farm (20).

[0267] As described above, since the actual cultivation environments of the seaweed farm (10) and the land-based seaweed farm (20) are different from each other, even if the optimal cultivation environment data output by the seaweed cultivation artificial intelligence model (324) is applied to the land-based seaweed farm (20), there may be a difference between the predicted growth degree of the land-based seaweed and the actual growth degree of the land-based seaweed. However, since the seaweed cultivation artificial intelligence model (324) generated by k-means model learning as described above outputs optimal cultivation environment data based on the cluster that best matches the input, the prediction error caused by the difference between the actual cultivation environments of the seaweed farm (10) and the land-based seaweed farm (20) can be reduced.

[0268] Next, the environment control server (330) may be configured to control the environment control device (230) provided in the land-based seaweed farm (20) based on the optimal farming environment data output by the aforementioned seaweed farming artificial intelligence model (324).

[0269] In one embodiment, the environment control server (330) may include a control device control unit (331) and a data transmission and reception unit (333).

[0270] First, the control unit (331) can generate a control command to control the operation of an environment control device (230) provided in a land-based seaweed farm (20) based on optimal farming environment data output by the seaweed farming artificial intelligence model (324).

[0271] In one embodiment, the control unit (331) can generate a water quality control command to control the operation of a land-based water quality control device (231) provided in a land-based seaweed farm (20) based on optimal water quality data.

[0272] For example, the control unit (331) can generate a water quality control command to control the operation of at least one selected from a water temperature control device, a salinity control device, a hydrogen ion concentration control device, a dissolved oxygen control device, a turbidity control device, an oil control device, a chemical oxygen demand control device, a nitrogen control device, a phosphorus control device, a nitrate nitrogen control device, an ammonia nitrogen control device, a phosphate phosphorus control device, a silicate control device, and an organic carbon control device equipped in a land-based seaweed farm (20) based on optimal water quality data.

[0273] Additionally, the control unit (331) can generate a weather control control command to control the operation of a land weather control device (233) provided in a land seaweed farm (20) based on optimal weather data.

[0274] For example, the control unit (331) can generate a weather control control command to control the operation of at least one selected from a light irradiation device, a cooling / heat air conditioning device, a humidity control device, a blower device, and a flow rate control device equipped in a land-based seaweed farm (20) based on optimal weather data.

[0275] Next, the data transmission and reception unit (333) may include a wireless communication device or a wired communication device. The data transmission and reception unit (333) may communicate with an environment control device (230) provided in an onshore seaweed farm (20) through at least one network using a wireless communication device or a wired communication device. For example, the wireless communication device may include a cellular communication device, a short-range wireless communication device, or a GNSS (global navigation satellite system) communication device. The wired communication device may include a LAN (local area network) communication device or a power line communication device.

[0276] Such a data transmission and reception unit (333) can transmit a control command generated by the control device control unit (331) to an environment control device (230) provided in the land-based seaweed farm (20).

[0277] Of course, the functions performed by the data collection server (310), model creation server (320), and environment control server (330) described above can be performed by a single integrated server device or by server devices consisting of three or more.

[0278] Meanwhile, the environment control device (230) provided in the land-based seaweed farm (20) can receive control commands from the environment control server (330), and its operation can be controlled according to the received control commands.

[0279] In one embodiment, the operation of the land-based water quality control device (231) provided in the land-based seaweed farm (20) can be controlled according to a water quality control command received from the environment control server (330).

[0280] For example, a water temperature control device provided in a land-based seaweed farm (20) can operate to form the water temperature of the land-based seaweed farm (20) into an optimal water temperature derived according to optimal water temperature data, in accordance with a water temperature control command received from an environment control server (330).

[0281] At this time, the control unit of the water temperature control device can determine whether the water temperature of the land-based seaweed farm (20) has been formed to the target optimal water temperature based on the water temperature value measured by the land-based measuring unit (220) provided in the land-based seaweed farm (20), and can operate to form the water temperature of the land-based seaweed farm (20) to the target optimal water temperature.

[0282] Additionally, the land weather control device (233) provided in the land seaweed farming facility (210) can be controlled to operate according to a weather control control command received from the environment control server (330).

[0283] For example, a cooling / heat air conditioning device provided in an onshore seaweed farm (20) can operate to set the temperature of the onshore seaweed farm (20) to an optimal temperature derived according to optimal temperature data, in accordance with a temperature control command received from an environment control server (330).

[0284] At this time, the control unit of the cooling / heat air conditioning device can determine whether the temperature of the land-based seaweed farm (20) has been formed to a target optimal temperature based on the temperature value measured by the land-based measuring unit (220) provided in the land-based seaweed farm (20), and can operate to form the water temperature of the land-based seaweed farm (20) to a target optimal temperature.

[0285] Meanwhile, the land-based seaweed farm (20) may be equipped with an automatic harvesting device to automatically harvest land-based seaweed that has completed growth, and the land-based seaweed that has completed growth in the land-based seaweed farm (20) may be harvested according to the automatic harvesting device.

[0286] Next, the process of performing a digital twin-based intelligent land-based seaweed farming method using the aforementioned digital twin-based intelligent land-based seaweed farming system (hereinafter, intelligent land-based seaweed farming system) will be explained.

[0287] FIGS. 6 and 7 are flowcharts illustrating the process of performing a digital twin-based intelligent land-based seaweed farming method in exemplary embodiments.

[0288] Referring to FIGS. 1 to 7, an intelligent land-based seaweed farming system can collect seaweed farming data including seawater quality data, land-based seaweed farming data, and seaweed photography data from a sea-based seaweed farm (10) (S100).

[0289] As described above, the intelligent land-based seaweed farming system can collect sea-sea seaweed farming data through a sea-sea measuring unit (120) provided in a sea-sea seaweed farm (10).

[0290] In addition, seaweed farming data collected through the sea measurement unit (120) can be transmitted to the data collection server (310) and stored in the data storage unit (313) of the data collection server (310).

[0291] Next, the intelligent land-based seaweed farming system can generate a virtual model (322) of a seaweed farm corresponding to a seaweed farm (10) based on sea-based seaweed farming data (S200).

[0292] The model generation server (320) of the intelligent land-based seaweed farming system receives seaweed farming data collected from the seaweed farm (10) as described above from the data collection server (310), and can generate a seaweed farm virtual model (322) corresponding to the seaweed farm (10) based on the seaweed farming data.

[0293] In one embodiment, the model generation server (320) of the intelligent land-based seaweed farming system can generate virtual models corresponding to each of the seaweed farming facility (110) of the seaweed farm (10), the seaweed farming seawater environment, the seaweed farming atmospheric environment, and the seaweed being farmed in the seaweed farming facility (110), based on seaweed farming data received from the data collection server (310).

[0294] In one embodiment, a virtual model (322) of a seaweed farm generated by a model generation server (320) of an intelligent land-based seaweed farming system may include a virtual offshore seaweed farming facility model, a virtual seaweed farming seawater model, a virtual seaweed farming waiting model, and a virtual farming seaweed model.

[0295] Next, the intelligent land-based seaweed farming system can build the seaweed farming data and the virtual seaweed farming data output from the seaweed farm virtual model as training data, and generate a seaweed farming artificial intelligence model (324) through model training using the built training data (S300).

[0296] The model generation server (320) of the intelligent land-based seaweed farming system can generate a seaweed farming artificial intelligence model (324) based on at least one selected from the sea-based seaweed farming data received from the data collection server (310) as described above, the virtual seaweed farming data output from the seaweed farm virtual model (322), and the land-based seaweed farming data received from the land-based measurement unit (220) of the land-based seaweed farm (20).

[0297] Next, the intelligent land-based seaweed farming system can derive optimal farming environment data through the generated seaweed farming artificial intelligence model (324) (S400).

[0298] The generated artificial intelligence model for seaweed farming (324) can output optimal farming environment data that allows the seaweed to grow to a maximum size while minimizing disease infection of the farmed seaweed for a set period, when water quality data and weather data for the seaweed farm are input as described above.

[0299] For example, when land water quality data and land weather data for a land seaweed farm (20) are input into the seaweed farming artificial intelligence model (324), the seaweed farming artificial intelligence model (324) can output optimal farming environment data that allows the farmed seaweed to grow to a maximum size while minimizing disease infection of the farmed seaweed for a pre-set period.

[0300] In one embodiment, the optimal aquaculture environment data output by the seaweed aquaculture artificial intelligence model (324) may include optimal water quality data, optimal weather data, and optimal growth seaweed data.

[0301] Next, the intelligent land-based seaweed farming system can control an environment control device (230) equipped in a land-based seaweed farm (20) based on the derived optimal farming environment data (S500).

[0302] The environment control server (330) of the intelligent land-based seaweed farming system can control the environment control device (230) provided in the land-based seaweed farm (20) based on the optimal farming environment data output by the seaweed farming artificial intelligence model (324) as described above.

[0303] The environment control server (330) of the intelligent land-based seaweed farming system can generate control commands to control the operation of the environment control device (230) provided in the land-based seaweed farm (20) based on the optimal farming environment data output by the seaweed farming artificial intelligence model (324).

[0304] In one embodiment, the environment control server (330) of the intelligent land-based seaweed farming system can generate a water quality control command to control the operation of a land-based water quality control device (231) provided in a land-based seaweed farm (20) based on optimal water quality data.

[0305] Additionally, the environment control server (330) of the intelligent land-based seaweed farming system can generate a weather control control command to control the operation of a land-based weather control device (233) equipped in a land-based seaweed farm (20) based on optimal weather data.

[0306] In addition, the environment control server (330) of the intelligent land-based seaweed farming system can transmit the generated control command to the environment control device (230) provided in the land-based seaweed farm (20).

[0307] Next, the intelligent land-based seaweed farming system can collect land-based seaweed farming data including land-based water quality data, land-based seaweed farming data, and land-based seaweed photographic data from the land-based seaweed farm (20) (S600).

[0308] As described above, the intelligent land-based seaweed farming system can collect land-based seaweed farming data through a land-based measuring unit (220) provided in the land-based seaweed farm (20).

[0309] Additionally, land-based seaweed farming data collected through the land-based measuring unit (220) can be transmitted to the data collection server (310) and stored in the data storage unit (313) of the data collection server (310).

[0310] Next, the intelligent land-based seaweed farming system evaluates the performance of the seaweed farming artificial intelligence model (324) based on land-based seaweed farming data, and if the evaluation indicator does not satisfy a preset standard value, the model can be retrained (S700).

[0311] The intelligent land-based seaweed farming system model generation server (320) inputs a test dataset into the trained model and evaluates the performance of the trained model by comparing the optimal farming environment data and predicted farming seaweed growth data output by the trained model with land-based water quality data, land-based weather data, and land-based seaweed photography data actually collected at the land-based seaweed farm (20).

[0312] At this time, if the evaluation indicators calculated for the trained model do not satisfy the previously set criteria, the model training for the trained model may be performed again by adjusting the variables (parameters, etc.) related to model training or by configuring additional training data.

[0313] Next, the intelligent land-based seaweed farming system can build land-based seaweed farming data as additional training data and improve the seaweed farming artificial intelligence model (324) through model training using the additional training data (S800).

[0314] The intelligent land-based seaweed farming system model generation server (320) can additionally train a model that has been previously trained using sea-based seaweed farming data or virtual seaweed farming data by using land-based water quality data, land-based weather data, and land-based seaweed photograph data collected from the land-based seaweed farm (20) as described above.

[0315] Next, the intelligent land-based seaweed farming system can check the growth amount of the farmed seaweed and harvest the farmed seaweed once growth is complete (S900).

[0316] As described above, the land-based seaweed farm (20) may be equipped with an automatic harvesting device to automatically harvest land-based seaweed that has completed growth, and the land-based seaweed that has completed growth in the land-based seaweed farm (20) may be harvested according to the automatic harvesting device.

[0317] As explained above, according to the present invention, optimal aquaculture environment data that can maximize the growth of cultured seaweed while minimizing disease infection is derived through an artificial intelligence model, and by controlling the operation of an environmental control device equipped in a land-based seaweed farm based on the derived optimal aquaculture environment data, an optimal seaweed farming environment can be created in the land-based seaweed farm. Accordingly, land-based seaweed farming can be continuously carried out regardless of the season and weather conditions, thereby improving the quality of cultured seaweed harvested through farming and simultaneously increasing the yield of cultured seaweed.

[0318] Although it has been described above that all components constituting an embodiment of the present invention are combined or operate as a single unit, the present invention is not necessarily limited to such an embodiment. That is, within the scope of the purpose of the present invention, all components may be selectively combined in one or more ways to operate.

[0319] The foregoing description is merely an illustrative explanation of the technical concept of the present invention, and those skilled in the art to which the present invention pertains will be able to make various modifications and variations within the scope of the essential characteristics of the present invention. Accordingly, the embodiments disclosed in the present invention are intended to explain, not limit, the technical concept of the present invention, and the scope of the technical concept of the present invention is not limited by these embodiments. The scope of protection of the present invention shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the present invention. Explanation of the symbols

[0320] 10 : Offshore seaweed farm 110: Offshore seaweed farming facilities 120 : Marine measurement unit 20: Land-based seaweed farm 210: Land-based seaweed farming facilities 220 : Land measurement unit 230 : Environmental Control Autonomy 30: Cloud environment 310: Data collection server 320 : Model creation server 330: Environment Control Server

Claims

Claim 1 A digital twin generation unit that receives marine seaweed farming data collected from a marine seaweed farm and generates a virtual model of a seaweed farm corresponding to the marine seaweed farm based on the marine seaweed farming data; and an artificial intelligence model generation unit that generates a seaweed farming artificial intelligence model based on the marine seaweed farming data and virtual seaweed farming data output from the virtual model of the seaweed farm. and a control device control unit that controls an environmental control device provided in a land-based seaweed farm based on optimal farming environment data output by the seaweed farming AI model; wherein the AI ​​model generation unit generates first training data based on the marine seaweed farming data - the marine seaweed farming data includes marine water quality data, marine weather data, and marine seaweed photography data collected from the marine seaweed farm - and generates second training data based on the virtual seaweed farming data, and performs model training for an initial model using integrated training data including the first training data and the second training data as input, wherein the ratio of the first training data and the ratio of the second training data are configured to be different from each other, and the AI ​​model generation unit receives land-based seaweed farming data collected from the land-based seaweed farm, generates third training data based on the land-based seaweed farming data, and performs additional model training for the seaweed farming AI model using the third training data as input, and the AI ​​model generation unit performs the model training including k-means clustering using at least one selected from the first training data, the second training data, and the third training data. A digital twin-based intelligent land-based seaweed farming system that performs. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 In claim 1, the above-ground seaweed farming data comprises a digital twin-based intelligent land-based seaweed farming system including land-based water quality data, land-based weather data, and land-based seaweed photographic data collected from the above-ground seaweed farm. Claim 6 A digital twin generation unit receives marine seaweed farming data collected from a marine seaweed farm; the digital twin generation unit generates a virtual model of a seaweed farm corresponding to the marine seaweed farm based on the marine seaweed farming data; and an artificial intelligence model generation unit generates a seaweed farming artificial intelligence model based on the marine seaweed farming data and virtual seaweed farming data output from the seaweed farm virtual model. And the control device control unit controls an environment control device equipped in a land-based seaweed farm based on optimal farming environment data output by the seaweed farming AI model, and the AI ​​model generation unit generating the seaweed farming AI model includes generating first training data based on the marine seaweed farming data - the marine seaweed farming data includes marine water quality data, marine weather data, and marine seaweed photography data collected from the marine seaweed farm - generating second training data based on the virtual seaweed farming data, and performing model training for an initial model using integrated training data including the first training data and the second training data as input, wherein the ratio of the first training data and the ratio of the second training data are configured to be different from each other, and the AI ​​model generation unit generating the seaweed farming AI model receives land-based seaweed farming data collected from the land-based seaweed farm, generates third training data based on the land-based seaweed farming data, and performs additional model training for the seaweed farming AI model using the third training data as input, and the AI ​​model generation unit generating the seaweed farming AI model includes the first training data, the second training data, and the A digital twin-based intelligent land-based seaweed farming method comprising performing model training including k-means clustering using at least one selected from third training data. Claim 7 delete Claim 8 delete Claim 9 delete Claim 10 In claim 6, the above-ground seaweed farming data comprises land water quality data, land weather data, and land seaweed photographic data collected from the above-ground seaweed farm, in a digital twin-based intelligent land seaweed farming method.

Images