Low-carbon zero-emission factory recirculating aquaculture system

Abstract

The invention provides a low-carbon zero-emission factory recirculating aquaculture system, which comprises a processor and a memory, and the processor calls and executes a computer program in the memory, so that a management server determines a first aquaculture area and obtains first real-time aquaculture data of the first aquaculture area; evaluating according to the first real-time breeding data to obtain a breeding difficulty level, determining a first number of second breeding areas according to the breeding difficulty level, and controlling the first breeding area and each second breeding area to be networked based on Internet of Things equipment to obtain breeding data of each second breeding area; the first breeding area uses an environment regulation and control model to predict and calculate the first real-time breeding data and the breeding data to obtain a first environment regulation and control parameter set, and multiple environment parameters in the first breeding area are adjusted according to the first environment regulation and control parameter set. According to the invention, which second breeding areas should be networked can be determined according to the actual situation of the first breeding area.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent aquaculture, and more specifically, to a low-carbon zero-emission industrialized recirculating aquaculture system. Background Art

[0002] With the increasingly severe problem of global warming, reducing greenhouse gas emissions and achieving sustainable development have become a global consensus. In the field of aquaculture, traditional aquaculture methods are often accompanied by problems such as high energy consumption, high emissions, and environmental pollution. To address these challenges, low-carbon zero-emission industrialized recirculating aquaculture technology has emerged. This technology integrates modern aquaculture technology, modern industry, and information technology to achieve the recycling and zero-emission of aquaculture water, becoming an important force in promoting the green development of the aquaculture industry.

[0003] A low-carbon zero-emission industrialized recirculating aquaculture system needs to adjust the internal temperature, humidity, etc. in real time to meet the growth requirements of different aquaculture objects at different growth stages. Existing temperature and humidity control methods are all manual or automatic control based on empirical values, with poor pertinence, especially unable to respond promptly and effectively to abnormal growth conditions of aquaculture objects.

[0004] Therefore, how to further improve the aquaculture effect of a low-carbon zero-emission industrialized recirculating aquaculture system is a technical problem that urgently needs to be solved at present. Summary of the Invention

[0005] To solve the technical problems existing in the above background art, the present invention provides a low-carbon zero-emission industrialized recirculating aquaculture system, an electronic device, a computer storage medium, and a computer program product.

[0006] The present invention provides a low-carbon zero-emission industrialized recirculating aquaculture system, the system includes a processor and a memory, and the processor retrieves and executes a computer program in the memory to implement the following steps: The management server determines a first aquaculture area and obtains first real-time aquaculture data of the first aquaculture area; wherein, the first aquaculture area is at least one of several aquaculture areas in the aquaculture factory; Based on the first real-time aquaculture data, an aquaculture difficulty level is evaluated, and based on the aquaculture difficulty level, a first number of second aquaculture areas are determined, and the first aquaculture area and each of the second aquaculture areas are controlled to be networked based on Internet of Things devices to obtain aquaculture data of each of the second aquaculture areas; wherein, each of the second aquaculture areas is an aquaculture area similar to the first aquaculture area; The first breeding area uses an environmental regulation model to perform predictive calculations on the first real-time breeding data and each piece of the breeding data, obtain a first set of environmental regulation parameters, and adjust multiple environmental parameters within the first breeding area according to the first set of environmental regulation parameters.

[0007] Optionally, the management server determines the first breeding area, including: The management server remains connected to each manager's terminal and the management and evaluation systems of each breeding area. If it receives a first poor growth signal sent by the manager's terminal and / or a second poor growth signal from the management and evaluation system, it determines the breeding area corresponding to the manager's terminal and / or the management and evaluation system as the first breeding area.

[0008] Optionally, the breeding difficulty level is evaluated based on the first real-time breeding data, and the first quantity of second breeding areas is determined according to the breeding difficulty level, including: The first real-time breeding data is converted into natural language to obtain a breeding situation description text, and the breeding situation description text is imported into a large language model that has been locally fine-tuned to obtain a preliminary breeding difficulty level predicted by the large language model; Several types of breeding organisms are extracted from the first real-time breeding data to form breeding organism polyculture information, and similarity retrieval is performed in the Internet according to the breeding organism polyculture information to obtain the number of retrieval results; The number of retrieval results is compared with each quantity interval in the first comparison table to determine a difficulty index, and the preliminary breeding difficulty level is corrected to the breeding difficulty level using the difficulty index; The breeding difficulty level is compared with the second comparison table to obtain the first quantity. The remaining breeding areas are subjected to similarity calculations with the first breeding area, and breeding areas with a similarity higher than the similarity threshold are screened out. The first quantity of the second breeding areas is randomly selected from the screened breeding areas.

[0009] Optionally, the first breeding area uses an environmental regulation model to perform predictive calculations on the first real-time breeding data and each piece of the breeding data, obtain a first set of environmental regulation parameters, including: The first breeding area first uses a pre-convolutional network to extract features from the first real-time breeding data and each piece of the breeding data, respectively obtaining a first feature and a second feature; The first breeding area then uses the environmental regulation model to simultaneously process the first feature and the second feature, predict and output the first set of environmental regulation parameters.

[0010] Optionally, the breeding data includes second real-time breeding data and historical breeding data; wherein, the historical breeding data includes the historical yields of various corresponding types of breeding organisms in the corresponding second breeding area, and the second real-time breeding data includes the set of second environmental regulation parameters currently executed in the corresponding second breeding area; Wherein, the second quantity of the historical breeding data is determined according to the number of types of breeding organisms in the breeding organism polyculture information.

[0011] An embodiment of the present invention further provides an electronic device, which is applied to a low-carbon zero-emission factory recirculating aquaculture system as described in any one of the preceding items; including: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory.

[0012] An embodiment of the present invention further provides a computer storage medium, which is applied to a low-carbon zero-emission factory recirculating aquaculture system as described in any one of the preceding items; a computer program is stored on the storage medium.

[0013] An embodiment of the present invention further provides a computer program product, which is applied to a low-carbon zero-emission factory recirculating aquaculture system as described in any one of the preceding items; the computer program product contains a computer program stored in a computer storage medium.

[0014] The above solution of the present invention can determine which second breeding areas should be networked according to the actual situation of the first breeding area itself, and then obtain the breeding data of these second breeding areas, and can further analyze and obtain a set of first environmental regulation parameters applicable to the first breeding area based on these breeding data, so as to optimize the breeding environment in the first breeding area and improve the growth and yield of the breeding organisms. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0016] Figure 1 It is a schematic diagram of the steps implemented by the processor in a low-carbon zero-emission factory recirculating aquaculture system disclosed in an embodiment of the present invention.

[0017] Figure 2 It is a schematic diagram of obtaining a set of first environmental regulation parameters disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Generally, the components of the embodiments of the present invention described and illustrated in the drawings here can be arranged and designed in various different configurations.

[0019] Please refer to Figure 1 , an industrialized circulating water aquaculture system with low carbon and zero emissions is disclosed in the embodiments of the present invention. The system includes a processor and a memory. The processor retrieves and executes a computer program in the memory to implement the following steps: The management server determines a first aquaculture area and obtains first real-time aquaculture data of the first aquaculture area; wherein, the first aquaculture area is at least one of several aquaculture areas in the aquaculture farm. An aquaculture difficulty level is evaluated based on the first real-time aquaculture data, a first number of second aquaculture areas are determined according to the aquaculture difficulty level, and the first aquaculture area is controlled to be networked with each of the second aquaculture areas based on Internet of Things devices to obtain aquaculture data of each of the second aquaculture areas; wherein, each of the second aquaculture areas is an aquaculture area similar to the first aquaculture area. The first aquaculture area uses an environmental regulation model to perform predictive calculations on the first real-time aquaculture data and each aquaculture data to obtain a first set of environmental regulation parameters, and adjusts a plurality of environmental parameters in the first aquaculture area according to the first set of environmental regulation parameters.

[0020] In the above solution, multiple aquaculture areas are built in the aquaculture farm. The management server screens out a first aquaculture area that needs to be networked with other aquaculture areas in the aquaculture area according to a preset rule, and then further obtains the first real-time aquaculture data of the first aquaculture area. Based on this, the aquaculture difficulty level of the first aquaculture area is analyzed, and a first number of second aquaculture areas similar to the first aquaculture area are determined according to the aquaculture difficulty level. Then, the first aquaculture area and the Internet of Things devices deployed in these second aquaculture areas can perform local Internet of Things on their own to construct a local area network. The first aquaculture area can request the aquaculture data of each second aquaculture area through this local area network. Finally, the first aquaculture area uses a pre-constructed environmental regulation model to perform predictive calculations on the first real-time aquaculture data and aquaculture data to obtain a first set of environmental regulation parameters, and adjusts a plurality of environmental parameters in the first aquaculture area according to the first set of environmental regulation parameters. Among them, both the first set of environmental regulation parameters and the subsequent second set of environmental regulation parameters include multiple environmental regulation parameters such as temperature, humidity, and light duration, which will not be elaborated here.

[0021] The above solution of the present invention can determine which second breeding areas should be networked according to the actual situation of the first breeding area itself, and then obtain the breeding data of these second breeding areas. It can further analyze these breeding data to obtain a set of first environmental regulation parameters applicable to the first breeding area, so as to optimize the breeding environment in the first breeding area and improve the growth and yield of the breeding objects.

[0022] Optionally, the management server determines the first breeding area, including: The management server is connected to each manager's terminal and the management and evaluation systems of each breeding area. If it receives the first poor growth signal sent by the manager's terminal and / or the second poor growth signal of the management and evaluation system, it determines the breeding area corresponding to the manager's terminal and / or the management and evaluation system as the first breeding area.

[0023] In this embodiment, the breeding factory itself is provided with a management server, each breeding area is equipped with its own management and evaluation system, and managers and their associated manager terminals are also configured for each breeding area. When the manager discovers that the growth of the breeding objects in a certain breeding area is in poor condition (such as the weight is less than expected, the mortality rate is high, etc.), the first poor growth signal can be reported to the management server through the manager's terminal. In addition, the management and evaluation system can collect the breeding object growth data collected by each monitoring sensor in the corresponding breeding area in real time, and use a preset evaluation method to evaluate its growth. If it is found that the growth of the breeding objects in this breeding area is in poor condition, the second poor growth signal can be automatically reported to the management server. The management server can then know which breeding areas have the need for collaborative management, that is, need to be networked with other breeding areas, and thus determine them as the first breeding areas.

[0024] Optionally, the breeding difficulty level is evaluated based on the first real-time breeding data, and the first number of second breeding areas is determined according to the breeding difficulty level, including: Convert the first real-time breeding data into natural language to obtain a breeding situation description text, and import the breeding situation description text into a large language model that has been fine-tuned locally to obtain a preliminary breeding difficulty level predicted by the large language model; Extract several breeding object types from the first real-time breeding data to form breeding object polyculture information, and perform similar retrieval in the Internet according to the breeding object polyculture information to obtain the number of retrieval results; Compare the number of retrieval results with each quantity interval in the first comparison table to determine a difficulty index, and use the difficulty index to correct the preliminary breeding difficulty level to the breeding difficulty level; Compare with the second comparison table according to the breeding difficulty level, and obtain the first quantity through the comparison. Perform similarity calculation on the remaining breeding areas and the first breeding area, screen out the breeding areas with a similarity higher than the similarity threshold, and randomly select the first quantity of the second breeding areas from the screened breeding areas.

[0025] In this embodiment, the present invention uses a large language model trained with local fine-tuning to evaluate the breeding difficulty level of the first breeding area. First, a training data set is composed of a relatively small number of historical data, and the existing large language model (such as GPT large model, BERT large model) is trained using this training data set. The historical data includes the overall yield of various polyculture aquaculture species and the yield during single culture. The large language model can determine through comparative analysis whether the yield during polyculture of aquaculture species increases or decreases compared to the unit yield during single culture. If the corresponding unit yield during polyculture increases, it indicates that the preliminary breeding difficulty level is lower, and if the corresponding unit yield during polyculture decreases, it indicates that the preliminary breeding difficulty level is higher.

[0026] Among them, first convert the first real-time breeding data into a natural language description text, which is conducive to the understanding and analysis of the large language model.

[0027] At the same time, the polyculture techniques of some aquaculture species may be relatively mature, but the polyculture techniques of some new ones are just developed and not yet mature. Therefore, it is necessary to obtain a difficulty index based on the maturity of these polyculture techniques, and then use the difficulty index to appropriately correct the preliminary breeding difficulty level obtained above to make it closer to the actual situation. Specifically, several aquaculture species types are obtained from the first real-time breeding data, that is, which aquaculture species are polycultured in the first breeding area. Similarity retrieval is performed on the Internet according to this aquaculture species polyculture information to obtain the number of retrieval results, that is, analyze how much relevant information there is on the Internet about this polyculture method. The more the number of relevant information, the more mature the polyculture technique, and vice versa, indicating that it is a new technique that is not yet mature. Thus, by comparing the number of retrieval results with each quantity interval in the comparison table, the difficulty index can be determined. The larger the number of retrieval results here, the lower the corresponding difficulty index, such as the difficulty index being 0.9, 1.0; the smaller the number of retrieval results, the higher the corresponding difficulty index, such as the difficulty index being 1.2, 1.3.

[0028] Next, compare the aquaculture difficulty level with the second comparison table to obtain the matching first quantity, and select the first quantity of second aquaculture areas from the remaining aquaculture areas with high similarity to the first aquaculture area. In the second comparison table, the higher the aquaculture difficulty level, the larger the first quantity, and vice versa, so that the data volume of the aquaculture data can be adjusted. The similarity calculation between the first aquaculture area and other aquaculture areas is based on the above-mentioned first real-time aquaculture data and aquaculture data, mainly determining its similarity based on the type of aquaculture, and secondly based on the growth stage of the aquaculture.

[0029] Optionally, the first aquaculture area uses an environmental regulation model to perform predictive calculations on the first real-time aquaculture data and each aquaculture data to obtain a first set of environmental regulation parameters, including: The first aquaculture area first uses a pre-convolutional network to extract features from the first real-time aquaculture data and each aquaculture data, and respectively obtains a first feature and a second feature; The first aquaculture area then uses the environmental regulation model to simultaneously process the first feature and the second feature, predict and obtain the first set of environmental regulation parameters, and output them.

[0030] In this embodiment, as Figure 2 shown, the first aquaculture area can retrieve the pre-convolutional network and the environmental regulation model from the management server. The pre-convolutional network first performs convolutional processing on the above-mentioned feature data to respectively extract the first feature and the second feature. Then, the first feature and the second feature are input into the environmental regulation model together, and the model predicts and processes them to obtain the first set of environmental regulation parameters.

[0031] Therefore, the present invention evaluates and obtains a first set of environmental regulation parameters suitable for the current actual aquaculture situation of the first aquaculture area by referring to the aquaculture data of similar aquaculture areas, so that the output of the first aquaculture area can reach a better level.

[0032] Optionally, the aquaculture data includes second real-time aquaculture data and historical aquaculture data; among them, the historical aquaculture data includes the historical yields of each corresponding type of aquaculture in the corresponding second aquaculture area, and the second real-time aquaculture data includes the second set of environmental regulation parameters currently implemented in the corresponding second aquaculture area; Among them, the second quantity of the historical aquaculture data is determined according to the number of types of aquaculture in the aquaculture mixed culture information.

[0033] In this embodiment, the aquaculture data requested from the second aquaculture area includes two types of data, namely, the second set of environmental regulation parameters currently being executed in each second aquaculture area, i.e., the second real-time aquaculture data; and also includes the historical yields of various corresponding types of aquaculture in the corresponding second aquaculture area, and the total yield of the second aquaculture area when the same type of mixed culture was carried out in the past. These data constitute the historical aquaculture data.

[0034] In addition, the above historical yields are used to determine the weighted weights of the second set of environmental regulation parameters. The larger the average value of the above historical yields, the larger the weighted weight is set; conversely, the smaller the weighted weight is set. Then, calculate the weighted average value of the same environmental regulation parameters in the second set of environmental regulation parameters corresponding to each second aquaculture area to obtain the final first set of environmental regulation parameters.

[0035] Moreover, the second quantity of the historical aquaculture data is determined according to the number of aquaculture types in the aquaculture mixed culture information in the first aquaculture area. Generally speaking, the second quantity is positively correlated with the number of aquaculture types, that is, the more aquaculture species are mixed in the first aquaculture area, the more historical aquaculture data of the second aquaculture area is set to be obtained, so that the accuracy of the above-derived weighted weights is higher.

[0036] An embodiment of the present invention also provides an electronic device, which is applied to a low-carbon zero-emission factory recirculating aquaculture system as described in any one of the preceding items; including: a memory storing executable program codes; a processor coupled to the memory; the processor calls the executable program codes stored in the memory.

[0037] An embodiment of the present invention also provides a computer storage medium, which is applied to a low-carbon zero-emission factory recirculating aquaculture system as described in any one of the preceding items; a computer program is stored on the storage medium.

[0038] An embodiment of the present invention also provides a computer program product, which is applied to a low-carbon zero-emission factory recirculating aquaculture system as described in any one of the preceding items; the computer program product includes a computer program stored in a computer storage medium.

[0039] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementation in the process Figure 1One process or multiple processes and / or boxes Figure 1 Apparatus for the functions specified in one box or multiple boxes.

[0040] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the process Figure 1 One process or multiple processes and / or boxes Figure 1 The functions specified in one box or multiple boxes.

[0041] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Therefore, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the process Figure 1 One process or multiple processes and / or boxes Figure 1 The functions specified in one box or multiple boxes.

[0042] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A low-carbon zero-emission factory-scale circulating aquaculture system, characterized by: The system includes a processor and a memory, and the processor retrieves and executes a computer program in the memory to implement the following steps: The management server determines a first breeding area, and obtains first real-time breeding data of the first breeding area; wherein the first breeding area is at least one of several breeding areas in the breeding factory; Determine a farming difficulty level based on the first real-time farming data, determine a first number of second farming areas based on the farming difficulty level, and control the first farming area to be connected to each of the second farming areas based on an Internet of Things device to obtain farming data of each of the second farming areas; wherein each of the second farming areas is a farming area similar to the first farming area; The first breeding area uses an environmental control model to predict and calculate the first real-time breeding data and each breeding data to obtain a first environmental control parameter set, and adjusts multiple environmental parameters in the first breeding area according to the first environmental control parameter set.

2. A low-carbon zero-emission factory-scale circulating aquaculture system according to claim 1, characterized in that: The management server determines the first breeding area, including: The management server maintains communication with each manager terminal and the management and evaluation system of each breeding area. If a first poor growth signal sent by the manager terminal and / or a second poor growth signal of the management and evaluation system is received, the breeding area corresponding to the manager terminal and / or the management and evaluation system is determined as the first breeding area.

3. A low-carbon zero-emission factory-scale circulating aquaculture system according to claim 2, characterized in that: The step of evaluating the breeding difficulty level according to the first real-time breeding data and determining a first number of second breeding areas according to the breeding difficulty level includes: The first real-time breeding data is converted into natural language to obtain a breeding situation description text, and the breeding situation description text is imported into a large language model that has been fine-tuned locally to obtain a preliminary breeding difficulty level predicted by the large language model; Extracting a number of farmed animal types from the first real-time farmed animal data to form farmed animal polyculture information, and performing a similar search on the Internet based on the farmed animal polyculture information to obtain a number of search results; Comparing the number of the search results with each number interval in the first comparison table to determine a difficulty index, and using the difficulty index to correct the preliminary breeding difficulty level to the breeding difficulty level; The breeding difficulty level is compared with the second comparison table to obtain the first number, and the remaining breeding areas are similarly calculated with the first breeding area to screen out breeding areas with a similarity higher than a similarity threshold, and the second breeding areas of the first number are randomly selected from the screened breeding areas.

4. A low-carbon zero-emission factory-scale circulating aquaculture system according to claim 3, characterized in that: The first breeding area uses an environmental control model to predict and calculate the first real-time breeding data and each of the breeding data to obtain a first environmental control parameter set, including: The first breeding area first uses a pre-convolutional network to extract features from the first real-time breeding data and each of the breeding data to obtain a first feature and a second feature respectively; The first breeding area then uses the environmental control model to simultaneously process the first feature and the second feature, predicts the first environmental control parameter set, and outputs it.

5. A low-carbon zero-emission factory-scale circulating aquaculture system according to claim 4, characterized in that: The breeding data includes second real-time breeding data and historical breeding data; wherein the historical breeding data includes the historical production of each corresponding type of breeding in the corresponding second breeding area, and the second real-time breeding data includes the second environmental control parameter set currently executed in the corresponding second breeding area; The second quantity of the historical breeding data is determined according to the number of breeding types in the breeding mixed breeding information.

6. An electronic device, characterized in that: A low-carbon, zero-emission factory-scale recirculating aquaculture system applied to any one of claims 1-5; comprising: a memory storing executable program code; a processor coupled to the memory; the processor calling the executable program code stored in the memory.

7. A computer storage medium, characterized in that: Applicable to a low-carbon, zero-emission factory-scale recirculating aquaculture system as described in any one of claims 1 to 5; a computer program is stored on the storage medium.

8. A computer program product, characterized in that: Applied to a low-carbon, zero-emission factory-scale recirculating aquaculture system as described in any one of claims 1 to 5; the computer program product includes a computer program stored in a computer storage medium.

Images