Prawn culture-oriented ecological environment condition dynamic evaluation system

Abstract

The invention discloses a prawn culture-oriented ecological environment condition dynamic evaluation system, and relates to the technical field of culture, prawn metabolism states under different salinity are tested through a test module, the influence of salinity on prawn metabolism can be analyzed, an appropriate salinity range is preliminarily screened out by constructing an influence coefficient Yxxs, and the salinity of prawns can be evaluated according to the influence coefficient Yxxs. According to the method, the defects of traditional empirical judgment are overcome, salinity optimization is more scientific and digitized, and the survival rate and the culture efficiency of the prawns are improved. The survival rate Chz is obtained through secondary screening of the survival analysis module and in combination with survival conditions lasting for the same duration under different salinity, and the salinity in the culture pond is further optimized according to the value, so that the influence of salinity change on prawns can be continuously monitored, the culture environment can be dynamically adjusted, and the survival rate of the prawns is improved. It is ensured that prawns grow under the optimal survival condition, and therefore the death risk caused by environment changes is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of aquaculture, and in particular to a dynamic evaluation system for ecological environment conditions for shrimp aquaculture. Background Art

[0002] In recent years, with the rapid development of the global aquaculture industry, especially in the field of shrimp farming, optimizing environmental parameters to increase production and ensure shrimp health has become an important issue. Salinity regulation and metabolic monitoring in shrimp farming are key factors affecting shrimp growth, survival rate and disease resistance. In the shrimp farming process, salinity optimization and shrimp health status analysis are specific concerns, which directly affect the survival rate, immunity and economic value of shrimp.

[0003] Although the current shrimp farming system has certain automation technology support, it still has deficiencies in salinity optimization and health monitoring. The existing technology may have ignored the research and discovery of shrimp metabolism and survival rate under different salinity conditions, and failed to analyze the profound impact of salinity on shrimp metabolism. In addition, traditional salinity adjustment methods mostly rely on experience and lack dynamic evaluation methods based on scientific analysis, making it difficult to monitor the growth status of shrimp in many aspects. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a dynamic assessment system for the ecological environment status of shrimp farming, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a dynamic evaluation system for the ecological environment status of shrimp farming, including a test module, a survival analysis module, a shrimp health monitoring module, a data processing module, a dynamic evaluation module and a management module; The test module is used to test the metabolic state of shrimps under different salinities in the culture pond, so as to analyze the influence of different salinities on shrimp metabolism, and to construct the influence coefficient Yxxs, and to perform preliminary screening based on the value of the influence coefficient Yxxs; The survival analysis module is used to analyze the survival status of the fish for the same duration under different salinities based on the preliminary screening, and obtain the survival rate Chz under different salinities, and optimize the salinity in the aquaculture pond based on the survival rate Chz value; The shrimp health monitoring module is used to use the salinity optimized in the survival analysis module as the adjustment range of the breeding pond, and randomly select several groups of shrimps for health monitoring to obtain relevant environmental data information and relevant shrimp quality data information; The data processing module is used to pre-process the relevant environmental data information and the relevant shrimp quality data information to generate a data set, and scale the information in the data set using a dimensionless processing technique; The dynamic assessment module extracts features from the information in the data set to obtain dissolved oxygen content Ryhz, breeding density Ymd and shell hardness Jkyd, and constructs enzyme activity factor Mhyz by correlating dissolved oxygen content Ryhz and breeding density Ymd, and fits and obtains health assessment index Jgzs in combination with the trained prediction model; The management module is used to pre-set the evaluation threshold Q, and compare and analyze the health evaluation index Jgzs with the evaluation threshold Q to comprehensively estimate the health status of the shrimp in the current breeding pond.

[0006] Preferably, the test module includes a salinity test unit and a preliminary judgment unit; The salinity test unit is used to test the metabolic state of shrimps under different salinities in the culture pond, so as to analyze the influence of different salinities on shrimp metabolism and construct the influence coefficient Yxxs under different conditions. The specific acquisition method is as follows: ; In the formula, It is expressed as the difference between the inside and outside of the shrimp body when the salinity is i. It is expressed as the excretion of shrimp under the condition of debugging salinity i, It is expressed as the standard deviation of the difference between the inside and outside of the shrimp. Expressed as the standard deviation of excretion, Expressed as and The covariance of Among them, the difference between the inside and outside of the shrimp body when the salinity is adjusted to i Obtained by the following formula: ; In the formula, It is expressed as the salinity of the water outside the shrimp body when the salinity is i. It is expressed as the salinity in the shrimp body when the debugging salinity is i.

[0007] Preferably, the preliminary judgment unit is used to compare and analyze the influence coefficient Yxxs value under different circumstances with the preset balance threshold P to preliminarily screen out the qualified salinity range, and the judgment is specifically performed in the following manner: If the value of the influence coefficient Yxxs does not fall within the balance threshold P, the corresponding salinity will be regarded as unqualified salinity; If the value of the influence coefficient Yxxs falls within the balance threshold P, the corresponding salinity is regarded as the qualified salinity; The values ​​judged as qualified salinity are counted to obtain the qualified range of salinity.

[0008] Preferably, the survival analysis module includes a time series analysis unit and an optimization unit; The time series analysis unit is used to analyze the survival status of different salinities within the qualified salinity range for the same duration based on the preliminary screening, and obtain the survival rate Chz under different salinities, which is obtained specifically in the following way: ; In the formula, It is expressed as the survival rate of shrimps when the salinity is adjusted to i for a duration of t. Expressed as total shrimp quantity.

[0009] Preferably, the optimization unit is used to summarize the survival rates Chz under different salinities, and extract the salinity corresponding to the survival rate Chz with the maximum value as the adjustment range of the culture pond.

[0010] Preferably, after determining the adjustment range of the culture pond, the salinity in the culture pond is adjusted and optimized on the spot; the shrimp health monitoring module includes a first monitoring unit and a second monitoring unit; The first monitoring unit is used to randomly select a number of shrimp groups and perform health monitoring and recording on the environment in the current breeding pond to obtain relevant environmental data information, wherein the relevant environmental data information includes the temperature value in the breeding pond. , Stocking density , pH and dissolved oxygen content ; The second monitoring unit is used to monitor and record the health of several groups of shrimps randomly selected to obtain relevant shrimp quality data information, wherein the relevant shrimp quality data information includes the hemocyanin concentration of each shrimp selected and carapace hardness .

[0011] Preferably, the data processing module includes a preprocessing unit and a standardization unit; The preprocessing unit is used to preprocess the relevant environmental data information and the relevant shrimp quality data information to generate a data set, and the preprocessing includes noise removal, missing value filling and data smoothing operations, wherein the missing value filling methods include mean filling, median filling, interpolation filling and regression filling; The standardization unit is used to scale the information in the data set using dimensionless processing technology so that the information range in the data set falls within Inside.

[0012] Preferably, the dynamic evaluation module includes a self-state analysis unit and a comprehensive analysis unit; The self-state analysis unit is used to process the dissolved oxygen content Ryhz and the breeding density Ymd dimensionlessly according to the relevant environmental data information, and map the corresponding data values ​​to the interval To obtain the enzyme activity factor Mhyz, the enzyme activity factor Mhyz is obtained by the following formula: ; In the formula, Expressed as dissolved oxygen content, Expressed as temperature value, Expressed as stocking density, Expressed as pH, , , and are weight values, where 0 < ≤1,0< ≤1,0< ≤1,0< ≤1, and =1, Expressed as the first correction constant.

[0013] Preferably, the comprehensive analysis unit is used to construct a prediction model using convolutional neural network technology, and input relevant shrimp quality data information and enzyme activity factor Mhyz into the prediction model to fit and obtain the health assessment index Jgzs, which is specifically obtained in the following manner: ; In the formula, Expressed as the mean hemocyanin concentration, Expressed as the average carapace hardness, and are weight values, where 0 < ≤1,0< ≤1, and =1, Expressed as the second correction constant.

[0014] Preferably, the management module includes a comparison unit and a feedback unit; The comparison unit is used to pre-set the evaluation threshold Q, and compare and analyze the health evaluation index Jgzs with the evaluation threshold Q. The specific contents are as follows: If the health assessment index Jgzs falls within the assessment threshold Q, it is comprehensively estimated that the shrimp in the current breeding pond are in a healthy state, and no warning instructions will be issued at this time; If the health assessment index Jgzs does not fall within the assessment threshold Q, it is comprehensively estimated that the shrimp in the current breeding pond is not in a healthy state, and an early warning instruction will be issued; The feedback unit is used to visualize the comparison results obtained by the comparison unit, and after receiving the early warning instruction, it will notify the breeding management personnel to conduct on-site inspections of the breeding ponds, observe the actual status of the shrimps, and determine whether manual intervention is needed to increase the opening of the oxygen distribution equipment, adjust the pH value, control the temperature, and adjust the feed.

[0015] The present invention provides a dynamic assessment system for the ecological environment status of shrimp farming, which has the following beneficial effects: (1) The test module tests the metabolic status of shrimp under different salinities, analyzes the effect of salinity on shrimp metabolism, and preliminarily screens out the appropriate salinity range by constructing the influence coefficient Yxxs. This method overcomes the shortcomings of traditional empirical judgment, making salinity optimization more scientific and data-based, and helps to improve shrimp survival rate and breeding efficiency. Through re-screening of the survival analysis module, combined with the survival status of the same duration under different salinities, the survival rate Chz is obtained, and the salinity in the breeding pond is further optimized based on this value. This not only continuously monitors the impact of salinity changes on shrimp, but also dynamically adjusts the breeding environment to ensure that shrimp grow under optimal living conditions, thereby reducing the risk of death caused by environmental changes. The shrimp health monitoring module monitors the health status of shrimp by random sampling. Combined with the salinity range optimized by the survival analysis module, it can not only obtain the health information of individual shrimp, but also collect data related to the environment. The dynamic evaluation module further constructs the enzyme activity factor Mhyz through feature extraction, and fits these data using the trained prediction model to finally obtain the health assessment index Jgzs. This multi-dimensional data combination method not only improves the comprehensiveness and accuracy of health assessment, but also can evaluate the health status of shrimp in real time through comparative analysis with the threshold Q, and take effective management measures in time. The management module not only compares the health assessment index Jgzs with the set assessment threshold Q, but also monitors the health status of shrimp in real time according to the assessment results. This systematic and automated management mode can respond in time when shrimp are in sub-healthy state or adverse environmental changes, thereby reducing the risk of breeding and improving the success rate of breeding. In summary, the system effectively solves the problems of inaccurate salinity optimization and incomplete health monitoring in the traditional shrimp breeding process through data-driven methods, and further improves the scientificity and intelligent level of breeding management.

[0016] (2) The system uses a data-driven approach to support salinity optimization decisions through quantified impact coefficients Yxxs and standardized equilibrium thresholds P. This data-based decision-making method helps reduce human errors, provides more reliable salinity control solutions, and further improves the success rate and economic benefits of shrimp farming. In summary, the test module improves the accuracy and reliability of salinity optimization as much as possible through scientific salinity impact assessment and standardized qualified range screening, provides strong technical support for shrimp farming, and promotes the modernization of aquaculture environment management.

[0017] (3) The time series analysis unit can accurately calculate the survival rate Chz under different salinity conditions by conducting an in-depth analysis of the survival status of shrimps under different salinity conditions for the same length of time within the acceptable salinity range. This method ensures that the survival status of shrimps under various salinity conditions can be accurately evaluated by calculating the ratio of the survival amount to the total amount, providing a real data basis for subsequent optimization. The optimization unit summarizes the survival rate Chz under different salinity conditions and extracts the salinity value with the highest survival rate as the adjustment range of the breeding pond. This optimization method can ensure that in actual breeding, the salinity with the highest survival rate of shrimp is selected, thereby providing the best growth environment for shrimps, improving the survival rate and reducing the loss caused by inappropriate salinity. This targeted adjustment helps to improve the health level and growth rate of shrimps and enhance the overall benefits of breeding. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a block diagram of a dynamic assessment system for ecological environment conditions for shrimp farming. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example 1

[0020] See also Figure 1 , the present invention provides a dynamic evaluation system for the ecological environment status of shrimp farming, including a test module, a survival analysis module, a shrimp health monitoring module, a data processing module, a dynamic evaluation module and a management module; The test module is used to test the metabolic state of shrimps under different salinities in the culture pond, so as to analyze the influence of different salinities on shrimp metabolism, and to construct the influence coefficient Yxxs, and to perform preliminary screening based on the value of the influence coefficient Yxxs; The survival analysis module is used to analyze the survival status of the fish for the same duration under different salinities based on the preliminary screening, and obtain the survival rate Chz under different salinities, and optimize the salinity in the aquaculture pond based on the survival rate Chz value; The shrimp health monitoring module is used to use the salinity optimized in the survival analysis module as the adjustment range of the breeding pond, and randomly select several groups of shrimps for health monitoring to obtain relevant environmental data information and relevant shrimp quality data information; The data processing module is used to pre-process the relevant environmental data information and the relevant shrimp quality data information to generate a data set, and scale the information in the data set using a dimensionless processing technique; The dynamic assessment module extracts features from the information in the data set to obtain dissolved oxygen content Ryhz, breeding density Ymd and shell hardness Jkyd, and constructs enzyme activity factor Mhyz by correlating dissolved oxygen content Ryhz and breeding density Ymd, and fits and obtains health assessment index Jgzs in combination with the trained prediction model; The management module is used to pre-set the evaluation threshold Q, and compare and analyze the health evaluation index Jgzs with the evaluation threshold Q to comprehensively estimate the health status of the shrimp in the current breeding pond.

[0021] During the operation of this system, firstly, the test module constructs the influence coefficient Yxxs by monitoring and testing the metabolic state of shrimp under different salinity conditions, so that farmers can scientifically identify the degree of influence of salinity on shrimp metabolism and conduct preliminary screening based on the Yxxs value. This step helps to effectively reduce the blindness in environmental regulation and lays the foundation for subsequent salinity optimization. Secondly, the survival analysis module further analyzes the survival rate Chz of shrimp in the same period of time under different salinities, and uses these data to optimize the salinity, so that the environmental conditions in the breeding area can achieve a more accurate regulation state, which not only improves the survival rate of shrimp, but also reduces the risk in the breeding process. Under the optimized salinity conditions, the shrimp health monitoring module randomly selects several groups of shrimp for health monitoring, and combines environmental and shrimp quality data to conduct multi-dimensional health assessment. Through this process, the system can more accurately obtain the health status of shrimp in the actual ecological environment. The data processing module ensures the consistency and accuracy of data processing and analysis by dimensionless processing of the data set, avoids the deviation caused by different data scales, and makes subsequent evaluation and prediction more reliable. In addition, the dynamic evaluation module combines key indicators and constructs the enzyme activity factor Mhyz, which is further combined with the trained prediction model to accurately obtain the health evaluation index Jgzs. This model-driven health evaluation method can dynamically monitor the health status of shrimp during the breeding process. Finally, the management module sets the evaluation threshold Q, automatically compares the health evaluation index Jgzs, and judges in real time whether the shrimp is in a healthy state, and makes timely adjustments or early warning instructions based on the results. This automated management not only improves the efficiency of breeding, but also further reduces the errors in human judgment, ensuring the stability and efficiency of the breeding process. In summary, the system can realize the multi-faceted dynamic evaluation of the shrimp breeding environment and health status, optimize salinity and other key environmental parameters, and improve the breeding efficiency and shrimp health level through data-driven models, effectively solving the problems of inaccurate environmental control and insufficient health monitoring methods in traditional breeding. Example 2

[0022] Please refer to Figure 1 ,Specifically: the test module includes a salinity test unit and a preliminary judgment unit; The salinity test unit is used to test the metabolic state of shrimps under different salinities in the culture pond, so as to analyze the influence of different salinities on shrimp metabolism and construct the influence coefficient Yxxs under different conditions. The specific acquisition method is as follows: ; In the formula, It is expressed as the difference between the inside and outside of the shrimp body when the salinity is i. It is expressed as the excretion of shrimp under the condition of debugging salinity i, It is expressed as the standard deviation of the difference between the inside and outside of the shrimp. Expressed as the standard deviation of excretion, Expressed as and The covariance of Among them, the difference between the inside and outside of the shrimp body when the salinity is adjusted to i Obtained by the following formula: ; In the formula, It is expressed as the salinity of the water outside the shrimp body when the salinity is i. It is expressed as the salinity in the shrimp body when the debugging salinity is i.

[0023] The preliminary judgment unit is used to compare and analyze the influence coefficient Yxxs value under different situations with the preset balance threshold P to preliminarily screen out the qualified salinity range, and the judgment is specifically made in the following manner: If the value of the influence coefficient Yxxs does not fall within the balance threshold P, the corresponding salinity will be regarded as unqualified salinity; If the value of the influence coefficient Yxxs falls within the balance threshold P, the corresponding salinity is regarded as the qualified salinity; The values ​​judged as qualified salinity are counted to obtain the qualified range of salinity.

[0024] In this embodiment, the salinity test unit can scientifically analyze the specific impact of salinity on shrimp metabolism by testing the metabolic state of shrimp under different salinities in the culture pond. By calculating the influence coefficient Yxxs under different salinities, the unit can quantify the influence of different salinities on the difference in salinity inside and outside the shrimp and the amount of excretion. This quantification method further avoids subjective judgment and improves the scientificity and accuracy of salinity adjustment. The acquisition method of the influence coefficient Yxxs involves the calculation of the difference in salinity inside and outside the shrimp, as well as the analysis of the standard deviation and covariance of the excretion. These parameters provide the real metabolic state data of shrimp under different salinity conditions, so that the salinity optimization is not only based on experience, but is based on actual data. It also reflects the energy metabolism burden of shrimp in regulating the osmotic pressure in the body under different salinity conditions. Through comparative analysis, the optimal salinity range of shrimp can be accurately identified, thereby optimizing the breeding environment and further improving the growth and survival rate of shrimp. The preliminary judgment unit automatically screens out the qualified salinity range by comparing and analyzing the value of the influence coefficient Yxxs with the preset balance threshold P. This mechanism can effectively exclude unqualified salinities, simplify the work of manual screening, and improve screening efficiency and accuracy. The statistical results of qualified salinity provide clear guidance for the adjustment of salinity in the breeding pond, which helps to maintain the growth of shrimp under optimal environmental conditions. The salinity is judged according to the value of the influence coefficient Yxxs, and the qualified salinity is counted and sorted out to obtain the qualified salinity range, so that the salinity adjustment process has a standardized basis. This standardized method further avoids the breeding risks caused by improper salinity adjustment, thereby effectively improving the management level and production efficiency of shrimp breeding. By dynamically monitoring the impact of salinity on shrimp and comparing it with the preset balance threshold P, the system can adjust the salinity in real time to ensure that the breeding environment always remains within the optimal range for shrimp health. This real-time adjustment function not only improves the growth conditions of shrimp, but also reduces the potential threat of environmental changes to shrimp health. In summary, this test module realizes the scientific evaluation and optimization of shrimp farming salinity through precise salinity testing and automated initial judgment mechanism, providing reliable technical support for improving farming efficiency and shrimp health. Example 3

[0025] Please refer to Figure 1 ,Specifically: the survival analysis module includes a time series analysis unit and an optimization unit; The time series analysis unit is used to analyze the survival status of different salinities within the qualified salinity range for the same duration based on the preliminary screening, and obtain the survival rate Chz under different salinities, which is obtained specifically in the following way: ; In the formula, It is expressed as the survival rate of shrimps when the salinity is adjusted to i for a duration of t. Expressed as total shrimp quantity.

[0026] The optimization unit is used to summarize the survival rates Chz under different salinities, and extract the salinity corresponding to the survival rate Chz with the maximum value as the adjustment range of the culture pond.

[0027] The survival rate Chc and total shrimp volume mentioned above It can be monitored and acquired through cameras and image processing systems. The activity of shrimps in the water can be monitored by cameras, and combined with image processing algorithms, the amount in the breeding pond can be automatically counted.

[0028] In this embodiment, the time series analysis unit can accurately measure the survival rate Chz under different salinity conditions by analyzing the survival status of shrimps under different salinity conditions within the qualified salinity range. This measurement method effectively reflects the specific impact of different salinities on shrimp survival by calculating the ratio of the shrimp survival amount to the total amount under the adjustment salinity of i for a duration of t, and provides data support for subsequent salinity optimization. The optimization unit summarizes the survival rates Chz under different salinity conditions and extracts the salinity corresponding to the maximum survival rate Chz as the adjustment range of the breeding pond. This method ensures that during the salinity adjustment process, the salinity value with a relatively high shrimp survival rate is selected, thereby providing a better breeding environment and further improving the breeding benefits and the health of the shrimp. By accurately calculating and optimizing the salinity value, the survival analysis module makes the salinity adjustment process more scientific and efficient. This data-based optimization method reduces the error of manual intervention, improves the accuracy and real-time performance of the salinity management of the breeding pond, and makes the breeding management more efficient and reliable. The system provides clear salinity adjustment recommendations through comprehensive analysis and optimization of survival rates, helping farmers make more scientific and reasonable decisions. This data-driven decision support not only reduces the subjectivity of empirical judgments, but also dynamically adjusts the breeding environment based on actual measurement data, further improving the scientific nature and success rate of the breeding process. Example 4

[0029] Please refer to Figure 1 , specifically: after determining the adjustment range of the breeding pond, the salinity in the breeding pond is adjusted and optimized on the spot; the shrimp health monitoring module includes a first monitoring unit and a second monitoring unit; The first monitoring unit is used to randomly select a number of shrimp groups and perform health monitoring and recording on the environment in the current breeding pond to obtain relevant environmental data information, wherein the relevant environmental data information includes the temperature value in the breeding pond. , Stocking density , pH and dissolved oxygen content ; The second monitoring unit is used to monitor and record the health of several groups of shrimps randomly selected to obtain relevant shrimp quality data information, wherein the relevant shrimp quality data information includes the hemocyanin concentration of each shrimp selected and carapace hardness .

[0030] The data processing module includes a preprocessing unit and a standardization unit; The preprocessing unit is used to preprocess the relevant environmental data information and the relevant shrimp quality data information to generate a data set, and the preprocessing includes noise removal, missing value filling and data smoothing operations, wherein the missing value filling methods include mean filling, median filling, interpolation filling and regression filling; The standardization unit is used to scale the information in the data set using dimensionless processing technology so that the information range in the data set falls within Inside.

[0031] In this embodiment, by monitoring the environment in the culture pond in detail, including temperature, culture density, pH and dissolved oxygen content, the ecological environment of the culture pond can be understood in many aspects. The collection of such environmental data helps to assess whether there are environmental factors that affect the health of the shrimp, so as to make timely adjustments. By monitoring the health of several groups of shrimps randomly selected, recording their hemocyanin concentration and shell hardness, the health status of the shrimp can be accurately assessed. This monitoring can effectively reflect the physiological health level of the shrimp and discover potential health problems in a timely manner. The integrity and accuracy of the data set are ensured by removing noise, filling missing values ​​and data smoothing operations. Mean filling, median filling, interpolation filling and regression filling methods can be used to effectively process missing data and reduce interference with the analysis results. The dimensionless processing technology is used to scale the data and standardize the information in the data set so that it falls into the same range. This standardization process can eliminate the dimension differences between different data sources, making the data analysis results more comparable, thereby improving the accuracy of the analysis. Through accurate environmental and health data collection, as well as rigorous data preprocessing and standardization processes, a scientific and reliable data foundation is provided, so that in the subsequent dynamic evaluation and optimization process, more scientific decisions can be made based on high-quality data. This systematic data processing method improves the scientificity and accuracy of environmental management and health assessment in shrimp farming, and promotes scientific farming management and data-driven decision-making. In summary, through detailed environmental and health monitoring, as well as efficient data preprocessing and standardization, the management effect of shrimp farming environment and the assessment accuracy of shrimp health status are further improved, providing reliable data support for farmers and enhancing the scientificity and effectiveness of the farming process. Example 5

[0032] Please refer to Figure 1 ,Specifically: the dynamic evaluation module includes a self-state analysis unit and a comprehensive analysis unit; The self-state analysis unit is used to process the dissolved oxygen content Ryhz and the breeding density Ymd dimensionlessly according to the relevant environmental data information, and map the corresponding data values ​​to the interval To obtain the enzyme activity factor Mhyz, the enzyme activity factor Mhyz is obtained by the following formula: ; In the formula, Expressed as dissolved oxygen content, Expressed as temperature value, Expressed as stocking density, Expressed as pH, , , and are weight values, where 0 < ≤1,0< ≤1,0< ≤1,0< ≤1, and =1, Expressed as the first correction constant.

[0033] The dissolved oxygen content mentioned above The oxygen content in water can be monitored in real time using a dissolved oxygen sensor such as polarographic or optical.

[0034] Temperature value Monitor and obtain through temperature sensor; Stocking density Acoustic monitors can be used. Utilizing acoustic principles, sensors can monitor the density of organisms in the water and estimate the breeding density based on the size of the organisms. Alternatively, cameras and data analysis systems can be used. High-resolution cameras combined with artificial intelligence or image recognition algorithms can analyze the number of shrimp in the water and estimate the breeding density.

[0035] pH It can be monitored and obtained through a pH sensor. The pH sensor is used to monitor the acidity and alkalinity of the water body. It reflects the concentration of hydrogen ions in the water through the potential change of the electrode and detects the pH value of the aquaculture environment in real time.

[0036] In this embodiment, by mapping the data values ​​to a unified interval range, this processing method effectively eliminates the data inconsistency caused by different dimensions, making the data analysis more accurate and reliable. The enzyme activity factor Mhyz combines key environmental factors such as dissolved oxygen content, temperature value, breeding density and pH, and provides a comprehensive assessment of the environmental state through weighted synthesis of weight values. This multi-factor comprehensive analysis method can fully reflect the comprehensive impact of the environment on the health of shrimp. By adjusting the weight values ​​of different environmental factors, the degree of attention to each factor can be flexibly adjusted according to actual conditions, so that the environmental state assessment is more in line with actual needs. This helps to more accurately identify environmental factors that have a greater impact on shrimp health, thereby optimizing the breeding environment. The system can monitor environmental data in real time and perform dynamic evaluation based on the calculated enzyme activity factor Mhyz. This real-time monitoring and dynamic evaluation capability enables breeding managers to understand and adjust environmental conditions in a timely manner to maintain a relatively good breeding state. Through accurate environmental state analysis, the system can identify environmental problems that may affect the health of shrimp in advance, thereby providing early warnings and helping breeders take timely adjustment measures to further reduce potential risks. Combined with the comprehensive analysis results of various environmental factors, it provides scientific data support for farmers to help make more accurate environmental adjustment decisions. This data-driven approach enhances the scientificity and effectiveness of aquaculture management. In summary, the system effectively improves the dynamic assessment capability of shrimp aquaculture environment through accurate environmental data processing and comprehensive analysis, provides scientific data support, optimizes environmental adjustment and management decisions, and enhances the scientificity and stability of the aquaculture process. Example 6

[0037] Please refer to Figure 1 Specifically: the comprehensive analysis unit is used to construct a prediction model using convolutional neural network technology, and input relevant shrimp quality data information and enzyme activity factor Mhyz into the prediction model to fit and obtain the health assessment index Jgzs, which is specifically obtained in the following manner: ; In the formula, Expressed as the mean hemocyanin concentration, Expressed as the average carapace hardness, and are weight values, where 0 < ≤1,0< ≤1, and =1, Expressed as the second correction constant.

[0038] The average hemocyanin concentration mentioned above It refers to the average hemocyanin concentration of several groups of shrimps randomly selected, which is obtained by monitoring with a blood analyzer. The hemocyanin concentration is determined by the blood samples taken from the shrimps.

[0039] Average carapace hardness It refers to the average shell hardness of several groups of shrimp randomly selected. The physical compressive strength of the shrimp shell is usually measured by mechanical or piezoelectric sensors.

[0040] The management module includes a comparison unit and a feedback unit; The comparison unit is used to pre-set the evaluation threshold Q, and compare and analyze the health evaluation index Jgzs with the evaluation threshold Q. The specific contents are as follows: If the health assessment index Jgzs falls within the assessment threshold Q, it is comprehensively estimated that the shrimp in the current breeding pond are in a healthy state, and no warning instructions will be issued at this time; If the health assessment index Jgzs does not fall within the assessment threshold Q, it is comprehensively estimated that the shrimp in the current breeding pond is not in a healthy state, and an early warning instruction will be issued; The feedback unit is used to visualize the comparison results obtained by the comparison unit, and after receiving the early warning instruction, it will notify the breeding management personnel to conduct on-site inspections of the breeding pond, observe the actual state of the shrimp, and determine whether manual intervention is needed to increase the opening of the oxygen distribution equipment, adjust the pH value, control the temperature, and adjust the feed; specifically, the opening of the oxygen distribution equipment: increase the dissolved oxygen concentration in the water body to prevent the shrimp from causing health problems due to lack of oxygen. The adjustment of salinity ensures that the osmotic pressure of the water body is suitable for the physiological needs of the shrimp. Feed adjustment: adjust the feed ingredients according to the health assessment of the shrimp. For example, increase the content of protein, vitamins and minerals to enhance the immunity of the shrimp. Feeding frequency adjustment: change the feeding frequency or time of the feed to avoid excessive or insufficient feeding causing health problems for the shrimp. Water quality filtration equipment startup: if the water quality pollution exceeds the standard, the water quality filtration equipment can be turned on to filter harmful substances such as ammonia nitrogen, nitrite, etc. Replace the water body: when the water quality deteriorates seriously, partially or completely replace the pool water to ensure the cleanliness of the breeding water quality.

[0041] In this embodiment, by using convolutional neural network technology to build a prediction model, the relevant shrimp quality data information and enzyme activity factor Mhyz are input into the model, and the health assessment index Jgzs can be accurately fitted. The weight value and the second correction constant included in the formula adjust the influence of different factors to ensure the accuracy and reliability of the health assessment index. This technology improves the recognition accuracy of the health status of shrimp and supports more scientific breeding management decisions. The evaluation threshold Q is preset and the health assessment index Jgzs is compared with it, which can monitor the health status of shrimp in the breeding pond in real time. If the health assessment index Jgzs is within the threshold range, the system will maintain the status quo; if Jgzs exceeds the threshold, an early warning is triggered and an alarm is issued in time. This mechanism can effectively prevent the deterioration of health problems and take measures at the early stage of the problem to reduce losses. The comparison results are visualized for managers to quickly understand and respond. At the same time, according to the early warning instructions, the system can automatically recommend or directly execute a series of optimization measures, including oxygen addition equipment, salinity adjustment, pH adjustment, temperature control, feed adjustment, feeding frequency adjustment, water quality filtration equipment startup, and water body replacement. These measures can effectively intervene in the detected health problems, ensure that shrimp grow under optimal environmental conditions, and improve the farming efficiency. Through automated early warning and visual display, managers can quickly obtain real-time health data in the breeding pond, reducing the time and cost of manual inspection. The system's intelligent intervention suggestions reduce the reliance on manual intervention and ensure timely and effective handling of problems. The early warning system based on the health assessment index can identify potential disease risks in a timely manner. Measures recommended or automatically executed by the system, such as adjusting salinity, pH value, temperature, etc., can effectively prevent and control the outbreak of shrimp diseases and reduce farming losses. In summary, this system improves the level of refined management of shrimp farming by combining the health assessment and intelligent management functions of convolutional neural network technology. Its accurate health assessment, dynamic early warning system and intelligent intervention measures not only improve farming efficiency, but also effectively reduce health problems and disease risks, ensuring the sustainable development of shrimp farming.

[0042] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic assessment system for the ecological environment status of shrimp farming, characterized by: It includes test module, survival analysis module, shrimp health monitoring module, data processing module, dynamic evaluation module and management module; The test module is used to test the metabolic state of shrimps under different salinities in the culture pond, so as to analyze the influence of different salinities on shrimp metabolism, and to construct the influence coefficient Yxxs, and to perform preliminary screening based on the value of the influence coefficient Yxxs; The survival analysis module is used to analyze the survival status of the fish for the same duration under different salinities based on the preliminary screening, and obtain the survival rate Chz under different salinities, and optimize the salinity in the aquaculture pond based on the survival rate Chz value; The shrimp health monitoring module is used to use the salinity optimized in the survival analysis module as the adjustment range of the breeding pond, and randomly select several groups of shrimps for health monitoring to obtain relevant environmental data information and relevant shrimp quality data information; The data processing module is used to pre-process the relevant environmental data information and the relevant shrimp quality data information to generate a data set, and scale the information in the data set using a dimensionless processing technique; The dynamic assessment module extracts features from the information in the data set to obtain dissolved oxygen content Ryhz, breeding density Ymd and shell hardness Jkyd, and constructs enzyme activity factor Mhyz by correlating dissolved oxygen content Ryhz and breeding density Ymd, and fits and obtains health assessment index Jgzs in combination with the trained prediction model; The management module is used to pre-set the evaluation threshold Q, and compare and analyze the health evaluation index Jgzs with the evaluation threshold Q to comprehensively estimate the health status of the shrimp in the current breeding pond.

2. The dynamic evaluation system for ecological environment status of shrimp farming according to claim 1 is characterized by: The test module includes a salinity test unit and a preliminary judgment unit; The salinity test unit is used to test the metabolic state of shrimps under different salinities in the culture pond, so as to analyze the influence of different salinities on shrimp metabolism and construct the influence coefficient Yxxs under different conditions. The specific acquisition method is as follows: ； In the formula, It is expressed as the difference between the inside and outside of the shrimp body when the salinity is i. It is expressed as the excretion of shrimp under the condition of debugging salinity i, It is expressed as the standard deviation of the difference between the inside and outside of the shrimp. Expressed as the standard deviation of excretion, Expressed as and The covariance of Among them, the difference between the inside and outside of the shrimp body when the salinity is adjusted to i Obtained by the following formula: ； In the formula, It is expressed as the salinity of the water outside the shrimp body when the salinity is i. It is expressed as the salinity in the shrimp body when the debugging salinity is i.

3. The dynamic evaluation system for ecological environment status of shrimp farming according to claim 2 is characterized in that: The preliminary judgment unit is used to compare and analyze the influence coefficient Yxxs value under different situations with the preset balance threshold P to preliminarily screen out the qualified salinity range, and the judgment is specifically made in the following manner: If the value of the influence coefficient Yxxs does not fall within the balance threshold P, the corresponding salinity will be regarded as unqualified salinity; If the value of the influence coefficient Yxxs falls within the balance threshold P, the corresponding salinity is regarded as the qualified salinity; The values ​​judged as qualified salinity are counted to obtain the qualified salinity range.

4. The dynamic evaluation system for ecological environment status of shrimp farming according to claim 3 is characterized by: The survival analysis module includes a time series analysis unit and an optimization unit; The time series analysis unit is used to analyze the survival status of different salinities within the qualified salinity range for the same duration based on the preliminary screening, and obtain the survival rate Chz under different salinities, which is obtained specifically in the following way: ； In the formula, It is expressed as the survival rate of shrimps when the salinity is adjusted to i for a duration of t. Expressed as total shrimp quantity.

5. The dynamic evaluation system for ecological environment status of shrimp farming according to claim 4 is characterized in that: The optimization unit is used to summarize the survival rates Chz under different salinities, and extract the salinity corresponding to the survival rate Chz with the maximum value as the adjustment range of the culture pond.

6. The dynamic evaluation system for ecological environment status of shrimp farming according to claim 5 is characterized by: After determining the adjustment range of the culture pond, the salinity in the culture pond is adjusted and optimized on the spot; the shrimp health monitoring module includes a first monitoring unit and a second monitoring unit; The first monitoring unit is used to randomly select a number of shrimp groups and perform health monitoring and recording on the environment in the current breeding pond to obtain relevant environmental data information, wherein the relevant environmental data information includes the temperature value in the breeding pond. , Stocking density , pH and dissolved oxygen content ; The second monitoring unit is used to monitor and record the health of several groups of shrimps randomly selected to obtain relevant shrimp quality data information, wherein the relevant shrimp quality data information includes the hemocyanin concentration of each shrimp selected and carapace hardness .

7. The dynamic evaluation system for ecological environment status of shrimp farming according to claim 1 is characterized by: The data processing module includes a preprocessing unit and a standardization unit; The preprocessing unit is used to preprocess the relevant environmental data information and the relevant shrimp quality data information to generate a data set, and the preprocessing includes noise removal, missing value filling and data smoothing operations, wherein the missing value filling methods include mean filling, median filling, interpolation filling and regression filling; The standardization unit is used to scale the information in the data set using dimensionless processing technology so that the information range in the data set falls within Inside.

8. The dynamic evaluation system for ecological environment status of shrimp farming according to claim 6 is characterized by: The dynamic evaluation module includes a self-state analysis unit and a comprehensive analysis unit; The self-state analysis unit is used to process the dissolved oxygen content Ryhz and the breeding density Ymd dimensionlessly according to the relevant environmental data information, and map the corresponding data values ​​to the interval To obtain the enzyme activity factor Mhyz, the enzyme activity factor Mhyz is obtained by the following formula: ； In the formula, Expressed as dissolved oxygen content, Expressed as temperature value, Expressed as stocking density, Expressed as pH, , , and are weight values, Expressed as the first correction constant.

9. The dynamic evaluation system for ecological environment status of shrimp farming according to claim 8, characterized in that: The comprehensive analysis unit is used to construct a prediction model using convolutional neural network technology, and input relevant shrimp quality data information and enzyme activity factor Mhyz into the prediction model to fit and obtain the health assessment index Jgzs, which is specifically obtained in the following manner: ； In the formula, Expressed as the mean hemocyanin concentration, Expressed as the average carapace hardness, and are weight values, Expressed as the second correction constant.

10. The dynamic evaluation system of ecological environment status for shrimp farming according to claim 1, characterized in that: The management module includes a comparison unit and a feedback unit; The comparison unit is used to pre-set the evaluation threshold Q, and compare and analyze the health evaluation index Jgzs with the evaluation threshold Q. The specific contents are as follows: If the health assessment index Jgzs falls within the assessment threshold Q, it is comprehensively estimated that the shrimp in the current breeding pond are in a healthy state, and no warning instructions will be issued at this time; If the health assessment index Jgzs does not fall within the assessment threshold Q, it is comprehensively estimated that the shrimp in the current breeding pond is not in a healthy state, and an early warning instruction will be issued; The feedback unit is used to visualize the comparison results obtained by the comparison unit, and after receiving the early warning instruction, it will notify the breeding management personnel to conduct on-site inspections of the breeding ponds, observe the actual status of the shrimps, and determine whether manual intervention is needed to increase the opening of the oxygen distribution equipment, adjust the pH value, control the temperature, and adjust the feed.

Images