Block chain-based recirculating aquaculture traceability management system and method

Abstract

The invention relates to the field of breeding management, and discloses a recirculating aquaculture traceability management system and method based on a block chain, which is used for solving the problem that a risk early warning threshold value is inaccurate during breeding traceability management, and comprises the following steps: collecting breeding key parameters in real time, evaluating according to the breeding key parameters to obtain a risk index, and determining the risk index according to the risk index. The method comprises the following steps: acquiring an initial risk threshold, acquiring threshold influence data in real time, performing evaluation according to the threshold influence data to obtain an adjustment index, performing risk threshold adjustment according to the adjustment index to obtain an actual risk threshold, and judging whether to perform early warning prompt and risk node recording according to the risk index and the actual risk threshold. The key data is encrypted and then stored in the block chain, the key data comprises the breeding key parameters and the early warning data, and the accuracy of the tracing information in breeding tracing management is effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of aquaculture management, and more specifically to a blockchain-based recirculating aquaculture traceability management system and method. Background Art

[0002] With the continuous advancement of blockchain information technology, the aquaculture sector is gradually moving towards digitalization and intelligentization. As an energy-efficient, environmentally friendly, and modern farming model, recirculating aquaculture has been widely adopted in factory farming scenarios due to its advantages such as high water resource utilization, minimal environmental pollution, and strong controllability. Consequently, achieving full lifecycle supervision and traceability of the aquaculture process has become a key focus for improving aquatic product quality and safety, as well as industry transparency.

[0003] In existing technologies, the traceability management system for recirculating aquaculture mainly relies on IoT sensor devices to collect key aquaculture information in real time, and stores and calls it in combination with a database; blockchain technology is introduced to encrypt key data on the chain to ensure the immutability and traceability of the information, and by analyzing key aquaculture information, risk warnings are issued according to risk thresholds.

[0004] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0005] In actual applications, the breeding environment changes dynamically in real time, which may lead to false alarms or missed alarms when issuing risk warnings based on fixed risk thresholds, thereby affecting the accuracy of the warnings and the timeliness of the disposal. It also causes deviations in the records of "risk nodes" in the traceability information, making it difficult to truly reflect the safety status of the breeding process. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a blockchain-based recirculating aquaculture traceability management system and method to solve the problems existing in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A blockchain-based recirculating aquaculture traceability management system, the system comprising: a data acquisition module for real-time collection of key aquaculture parameters, including water quality parameters, feeding records, health status of aquacultured animals, and environmental monitoring data, and transmitting the key parameters to a risk assessment module; a risk assessment module for obtaining a risk index based on the assessment of key aquaculture parameters, and transmitting the risk index to an early warning module; a risk threshold adjustment module for obtaining an initial risk threshold and real-time acquisition of threshold impact data, including environmental change data, biological behavior data, aquaculture operation data, and early warning history data; an adjustment index obtained based on the assessment of the threshold impact data; risk threshold adjustment based on the adjustment index to obtain an actual risk threshold, and transmitting the actual risk threshold to the early warning module; an early warning module for determining whether to issue an early warning prompt and record a risk node based on the risk index and the actual risk threshold; a blockchain evidence storage module for encrypting and storing key data in the blockchain, including key aquaculture parameters and early warning data; and a traceability display module for displaying full life cycle information of aquatic products to users.

[0009] Preferably, the step of obtaining the risk index based on the evaluation of key aquaculture parameters is as follows: obtaining the normal range of each water quality indicator, setting a detection time period, counting the number of times each water quality indicator exceeds the normal range within the detection time period, adding the number of times all water quality indicators exceed the normal range within the detection time period and taking the reciprocal to obtain the water quality quality; obtaining the recommended feeding amount and the actual feeding amount, and calculating the feeding deviation based on the recommended feeding amount and the actual feeding amount; calculating the feeding rationality based on the feeding deviation; obtaining the number of healthy aquacultures and the total number of aquacultures, and calculating the ratio of the number of healthy aquacultures to the total number of aquacultures to obtain the health degree; obtaining the optimal water temperature data and the current water temperature data, and calculating the environmental suitability based on the optimal water temperature data and the current water temperature data; normalizing the water quality quality, feeding rationality, health degree and environmental suitability, and calculating the risk index based on the normalized water quality quality, feeding rationality, health degree and environmental suitability. The specific obtaining steps are as follows: Where RK represents the risk index, sc represents the water quality, th represents the rationality of feeding, jc represents the health level, and hs represents the environmental suitability.

[0010] Preferably, the step of obtaining the adjustment index based on the threshold impact data evaluation is as follows: obtaining environmental change data, the environmental change data including water temperature value and pH value, obtaining the environmental change coefficient by singular value decomposition method based on the environmental change data; obtaining biological behavior data, the biological behavior data being food intake data, obtaining the degree of food intake fluctuation based on the food intake data evaluation, and recording the degree of food intake fluctuation as the biological behavior coefficient; obtaining aquaculture operation data, the aquaculture operation data being aquaculture density value, and obtaining the aquaculture operation coefficient based on the aquaculture operation data evaluation; obtaining early warning history data, the early warning history data being the number of historical early warnings within the detection time period; normalizing the environmental change coefficient, the biological behavior coefficient, the aquaculture operation coefficient, and the number of historical early warnings, and calculating the adjustment index based on the normalized environmental change coefficient, the biological behavior coefficient, the aquaculture operation coefficient, and the number of historical early warnings. The specific acquisition steps are as follows:

[0011] AT = a1×EC+a2×BI+a3×BO+a4×WH; where AT is the adjustment index, EC is the environmental change coefficient, BI is the biological behavior coefficient, BO is the aquaculture operation coefficient, WH is the number of historical warnings, and a1, a2, a3, and a4 are the weight coefficients of the environmental change coefficient, the biological behavior coefficient, the aquaculture operation coefficient, and the historical number of warnings.

[0012] Preferably, the step of obtaining the environmental variation coefficient is: obtaining the water temperature value and pH value at each sampling time point within the detection time period, and constructing an n×2 data matrix X according to the water temperature value and pH value at each time point within the detection time period; centering the matrix X, that is, subtracting the mean of each column to obtain the centralized data matrix X'; performing singular value decomposition on the centralized data matrix to obtain a singular value matrix, obtaining singular values according to the singular value matrix, square-summing all singular values and then calculating the square root to obtain the environmental variation coefficient.

[0013] Preferably, the biological behavior coefficient acquisition step is: obtaining the food intake at each detection time point within the detection time period, calculating the average food intake during the detection time period; and calculating the food intake variance based on the average food intake and the food intake at each detection time point. The specific acquisition steps are: Where sf represents the variance of food intake, n is the number of detection time points, F i It is expressed as the food intake at the i-th detection time point, It is expressed as the average food intake; the root of the variance of food intake is calculated to obtain the degree of fluctuation of food intake.

[0014] Preferably, the step of obtaining the aquaculture operation coefficient is as follows: obtaining the aquaculture density at each detection time point within the detection time period, calculating the standard deviation of the aquaculture density at each detection time point within the detection time period to obtain the aquaculture density standard deviation; calculating the aquaculture density change rate based on the aquaculture density at each detection time point; obtaining the safety reference density, and calculating the trend deviation degree based on the aquaculture density at each detection time point and the safety reference density; normalizing the aquaculture density standard deviation, the aquaculture density change rate, and the trend deviation degree, and calculating the aquaculture operation coefficient based on the normalized aquaculture density standard deviation, the aquaculture density change rate, and the trend deviation degree. The specific obtaining steps are as follows: Where BO is the aquaculture operation coefficient, yc is the standard deviation of aquaculture density, mb is the rate of change of aquaculture density, and qp is the degree of trend deviation.

[0015] Preferably, the step of adjusting the risk threshold according to the adjustment index to obtain the actual risk threshold is: comparing the adjustment index with the adjustment threshold; if the adjustment index is less than the adjustment threshold, it is determined that the initial risk threshold can accurately determine the risk, and no risk threshold adjustment is performed; if the adjustment index is greater than or equal to the adjustment threshold, it is determined that the initial risk threshold cannot accurately determine the risk, and the risk threshold is adjusted according to the adjustment index to obtain the actual risk threshold. The specific acquisition steps are: Where rt 实际 is the actual risk threshold, AT' is the adjusted threshold, AT is the adjusted index, and rt 初始 Denoted as the initial risk threshold.

[0016] Preferably, the step of judging whether to issue an early warning and record a risk node based on the risk index and the actual risk threshold is: comparing the risk index with the actual risk threshold; if the risk index is greater than or equal to the actual risk threshold, it is judged that an early warning is issued and a risk node record is made; if the risk index is less than the actual risk threshold, it is judged that no early warning is issued and no risk node record is made.

[0017] Preferably, the blockchain-based recirculating aquaculture traceability management method includes the following steps: Step 1: Real-time collection of key aquaculture parameters, which include water quality parameters, feeding records, health status of aquacultured animals, and environmental monitoring data; Step 2: Obtaining a risk index based on the evaluation of key aquaculture parameters; Step 3: Obtaining an initial risk threshold, obtaining threshold impact data in real time, which includes environmental change data, biological behavior data, aquaculture operation data, and early warning history data, obtaining an adjustment index based on the evaluation of the threshold impact data, adjusting the risk threshold based on the adjustment index, and obtaining an actual risk threshold; Step 4: Judging whether to issue an early warning prompt and record a risk node based on the risk index and the actual risk threshold; Step 5: Encrypting the key data and storing it in the blockchain, which includes key aquaculture parameters and early warning data; Step 6: Displaying the full life cycle information of aquatic products to users.

[0018] The technical effects and advantages of the present invention are as follows:

[0019] Collect key aquaculture parameters in real time, evaluate the key aquaculture parameters to obtain a risk index, obtain the initial risk threshold, obtain the threshold impact data in real time, evaluate the threshold impact data to obtain an adjustment index, adjust the risk threshold according to the adjustment index, and obtain the actual risk threshold. Based on the risk index and the actual risk threshold, determine whether to issue an early warning prompt and record the risk node. Encrypt the key data and store it in the blockchain. The key data includes key aquaculture parameters and early warning data, which effectively improves the accuracy of traceability information in aquaculture traceability management. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 Structural diagram of the blockchain-based recirculating aquaculture traceability management system provided in an embodiment of the present application.

[0021] Figure 2 Flowchart of the blockchain-based recirculating aquaculture traceability management method provided in the embodiment of this application. DETAILED DESCRIPTION

[0022] The technical solutions of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures described in the following embodiments are merely examples. The blockchain-based recirculating aquaculture traceability management system and method involved in the present invention are not limited to the various structures described in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0023] The present invention provides a blockchain-based recirculating aquaculture traceability management system, such as Figure 1 As shown, the system includes:

[0024] The data acquisition module is used to collect key aquaculture parameters in real time, including water quality parameters, feeding records, animal health status, and environmental monitoring data, and transmit these key parameters to the risk assessment module;

[0025] The risk assessment module is used to obtain a risk index based on key farming parameters and transmit the risk index to the early warning module;

[0026] In this embodiment, it should be specifically explained that the steps for obtaining the risk index based on the key breeding parameters are as follows:

[0027] Obtain the normal range of each water quality indicator, including dissolved oxygen, pH value, water temperature and other data. For example, the normal range of dissolved oxygen is [5,8] mg / L. Set a detection time period, count the number of times each water quality indicator exceeds the normal range during the detection period, add up the number of times all water quality indicators exceed the normal range during the detection period, and take the reciprocal to obtain the degree of water quality.

[0028] Obtain the recommended feeding amount and the actual feeding amount, and calculate the feeding deviation based on the recommended feeding amount and the actual feeding amount. The specific steps for obtaining the deviation are as follows:

[0029]

[0030] In the formula, D represents the feeding deviation, P represents the recommended feeding amount, and A represents the actual feeding amount;

[0031] The reasonableness of feeding is calculated based on the feeding deviation. The specific steps are as follows:

[0032] th=e -D ;

[0033] In the formula, th represents the rationality of feeding, and D represents the feeding deviation;

[0034] Obtain the number of healthy cultured animals and the total number of cultured animals, calculate the ratio of the number of healthy cultured animals to the total number of cultured animals, and obtain the health level;

[0035] Obtain the optimal water temperature data and the current water temperature data, and calculate the environmental suitability based on the optimal water temperature data and the current water temperature data. The specific acquisition steps are as follows:

[0036]

[0037] In the formula, hs represents the environmental suitability, T represents the current water temperature data, and T' represents the optimal water temperature data;

[0038] The water quality, feeding rationality, health and environmental suitability are normalized, and the risk index is calculated based on the normalized water quality, feeding rationality, health and environmental suitability. The specific steps for obtaining the risk index are as follows:

[0039]

[0040] In the formula, RK represents the risk index, sc represents the water quality, th represents the appropriateness of feeding, jc represents the health level, and hs represents the environmental suitability. This formula, based on the Euclidean norm, comprehensively reflects the overall health level of various indicators. When any indicator is low, its contribution to the denominator decreases, significantly improving the risk index and enabling sensitive identification of local anomalies. This formula exhibits both continuity and nonlinear amplification. The Euclidean norm is a classic method for measuring vector length in vector space, derived from the concept of distance in Euclidean geometry. The core idea is to calculate the "true" geometric length of a vector by taking the square root of the sum of its squares. This norm embodies the generalization of the Pythagorean theorem to multidimensional space, emphasizing the balanced accumulation of the squares of its components and exhibiting rotational invariance. It is widely used in fields such as physics, engineering, and machine learning as a fundamental tool for measuring error, distance, or similarity.

[0041] The risk threshold adjustment module is used to obtain the initial risk threshold and the threshold impact data in real time. The threshold impact data includes environmental change data, biological behavior data, breeding operation data, and early warning history data. The adjustment index is obtained based on the threshold impact data evaluation. The risk threshold is adjusted based on the adjustment index to obtain the actual risk threshold, and the actual risk threshold is transmitted to the early warning module.

[0042] In this embodiment, it should be specifically explained that the steps of obtaining the adjustment index based on the threshold impact data evaluation are:

[0043] Obtain environmental change data, which includes water temperature and pH values. The environmental change coefficient is obtained by evaluating the environmental change data through the singular value decomposition method. The singular value decomposition method is a commonly used matrix decomposition technology that can decompose the original multidimensional data matrix into a set of orthogonal basis vectors and corresponding singular values, revealing the intensity of data changes in the direction of each principal component. In the environmental change assessment, the collected environmental parameters such as water temperature and pH are constructed into a data matrix according to time. The singular value decomposition method can be used to extract singular values reflecting the main fluctuation trends, and then the combination of singular values can be quantified as the environmental change coefficient. It can comprehensively measure the joint change amplitude of multiple parameters, avoid the one-sidedness of the fluctuation judgment of a single indicator, and improve the accuracy and robustness of the assessment of the degree of environmental disturbance;

[0044] Obtaining biological behavior data, which is food intake data, and evaluating the degree of food intake fluctuation based on the food intake data, and recording the degree of food intake fluctuation as a biological behavior coefficient;

[0045] Acquire aquaculture operation data, which is aquaculture density value, and obtain aquaculture operation coefficient based on the aquaculture operation data;

[0046] Obtain historical warning data, which is the number of historical warnings within the detection period;

[0047] The environmental variation coefficient, biological behavior coefficient, aquaculture operation coefficient, and historical warning times are normalized. The purpose of normalization is to unify indicators with different dimensions and value ranges into the same numerical range, thereby eliminating the calculation deviation caused by different scales between parameters. Through normalization, the various factors can be made comparable and fair in the subsequent calculation of the adjustment index, avoiding the unreasonable dominant effect of a high-valued parameter on the results, improving the stability, accuracy, and interpretability of the overall model, and facilitating function design and system implementation. The adjustment index is calculated based on the normalized environmental variation coefficient, biological behavior coefficient, aquaculture operation coefficient, and historical warning times. The specific steps for obtaining it are:

[0048] AT=a1×EC+a2×BI+a3×BO+a4×WH;

[0049] In the formula, AT represents the adjustment index, EC represents the environmental change coefficient, the more unstable the environment, the lower the system's tolerance for potential risks should be, and by increasing the adjustment index, the risk assessment model is prompted to intervene more actively and to warn of possible problems in advance. This proportional relationship helps to build a more robust and adaptable risk warning system to ensure that hidden dangers can be discovered and intervention measures can be taken in a timely manner when environmental pressure increases, thereby ensuring the safety and continuity of the breeding process. BI represents the biological behavior coefficient. When abnormal fluctuations occur in biological behavior and the biological behavior coefficient increases, it means that the potential risk is increasing. The system needs to increase the adjustment index accordingly to achieve more advanced and accurate intelligent warnings and dynamically correct the risk threshold. BO represents the breeding operation coefficient. When the breeding operation changes frequently or with greater intensity, the breeding operation coefficient increases, which means that the stability of the system may be disturbed, and the adjustment index needs to be increased to dynamically correct the risk threshold. WH represents the historical warning When warning events are frequent and the historical warning coefficient increases, it indicates that the system is in an unstable or high-risk state in the near term. In this case, the adjustment index should be increased accordingly, and the risk threshold should be dynamically tightened to enhance the ability to identify and prevent potential problems. a1, a2, a3, and a4 represent the weight coefficients for the environmental change coefficient, the biological behavior coefficient, the aquaculture operation coefficient, and the number of historical warnings. a1 + a2 + a3 + a4 = 1. a1, a2, a3, and a4 are obtained using the Analytic Hierarchy Process (AHP). The AHP is a multi-criteria decision-making method that decomposes complex decision-making problems into multiple levels and factors and calculates the relative importance of each factor through pairwise comparisons based on expert judgment. When calculating the adjustment index, the AHP can be used to scientifically determine the impact of each factor on the risk threshold adjustment. By constructing a judgment matrix, comparing each factor pairwise, and combining consistency tests, the weight coefficients for each factor are ultimately determined. This ensures that the weight assignment is logical, interpretable, and supported by expert knowledge, providing a reliable basis for the weighted summation calculation.

[0050] In this embodiment, it should be specifically explained that the steps for obtaining the environmental variation coefficient are:

[0051] Obtain the water temperature and pH value at each sampling time point during the detection period, and construct an n×2 data matrix X based on the water temperature and pH value at each time point during the detection period, specifically:

[0052]

[0053] Where n is the number of sampling time points, T n is the water temperature at the nth sampling time point, PH n is the pH value at the nth sampling time point;

[0054] In order to eliminate the absolute dimension influence of the original data, it is necessary to center the matrix X, that is, to subtract the mean of each column to obtain the centered data matrix X', specifically:

[0055]

[0056] Where, Expressed as the average water temperature, Expressed as the average pH value;

[0057] The centered data matrix is subjected to singular value decomposition (SVD), resulting in a singular value matrix. Singular values are then extracted from this SV matrix. The square root of the squared sum of all singular values is calculated to yield the environmental variation coefficient. By considering the overall trend of water temperature and pH over the testing period, this method not only reflects the individual fluctuations of each parameter but also their joint variations in multidimensional space. Compared to simple range or standard deviation, SVD extracts the "energy of variation" in the principal direction. Therefore, the environmental variation coefficient can more accurately and comprehensively reflect the degree of system disturbance.

[0058] In this embodiment, it should be specifically explained that the steps for obtaining the biological behavior coefficient are:

[0059] Obtain the food intake at each testing time point during the testing period, and calculate the average food intake during the testing period;

[0060] The food intake variance is calculated based on the average food intake and the food intake at each detection time point. The specific steps for obtaining the variance are as follows:

[0061]

[0062] Where sf represents the variance of food intake, n is the number of detection time points, F i It is represented as the food intake at the i-th detection time point, and F is represented as the average food intake;

[0063] The variance of food intake was calculated to obtain the degree of food intake fluctuation.

[0064] In this embodiment, it should be specifically explained that the steps for obtaining the aquaculture operation coefficient are:

[0065] Obtaining the stocking density at each detection time point within the detection time period, calculating the standard deviation of the stocking density at each detection time point within the detection time period, and obtaining the stocking density standard deviation;

[0066] The stocking density change rate is calculated based on the stocking density at each detection time point. The specific steps for obtaining the rate are as follows:

[0067]

[0068] In the formula, mb represents the rate of change of stocking density, n is the number of detection time points, D i It is expressed as the breeding density at the i-th detection time point, D i+1 It is expressed as the stocking density at the i+1th detection time point;

[0069] Obtain the safety reference density and calculate the trend deviation degree based on the breeding density and safety reference density at each detection time point. The specific steps are as follows:

[0070]

[0071] Where qp represents the degree of trend deviation, n is the number of detection time points, and D i It is expressed as the breeding density at the i-th detection time point, D ref Expressed as safety reference density;

[0072] The standard deviation of stocking density, the rate of change of stocking density and the degree of trend deviation are normalized, and the stocking operation coefficient is calculated based on the normalized standard deviation of stocking density, the rate of change of stocking density and the degree of trend deviation. The specific steps for obtaining the coefficient are as follows:

[0073]

[0074] In the formula, BO represents the aquaculture operation coefficient, yc represents the standard deviation of stocking density, and the standard deviation of stocking density is smoothed and amplified. The more dramatic the fluctuation, the faster the increase, avoiding linear imbalance caused by excessively large standard deviation values. mb represents the rate of change of stocking density, and qp represents the degree of trend deviation. A larger trend deviation increases the square of the operation coefficient, further emphasizing the risk of "long-term deviation from the standard." This formula constructs a continuous, monotonically increasing aquaculture operation coefficient calculation model by introducing logarithmic, square root, and square functions to the standard deviation, rate of change, and trend deviation of stocking density, respectively. This model comprehensively reflects the impact of operational behavior on system stability. In the formula, the greater the density fluctuation, the more frequent the operation, or the greater the long-term deviation from the reference density, the larger the operation coefficient, effectively expressing the logical relationship that "stronger intervention, greater disturbance."

[0075] In this embodiment, it should be specifically explained that the steps for adjusting the risk threshold according to the adjustment index to obtain the actual risk threshold are:

[0076] The adjustment index is compared with the adjustment threshold. The adjustment threshold is obtained through the empirical method. The empirical method refers to the qualitative and quantitative analysis of key environmental factors that affect the accuracy of risk judgment based on the long-term practical experience of experts in the field of aquaculture, industry standards and historical aquaculture data, to determine their sensitivity to the interference of the risk threshold, and accordingly set an empirical threshold range for determining whether the risk threshold needs to be adjusted. The empirical threshold can be appropriately adjusted according to different fish species, aquaculture stages and environmental conditions to ensure the scientific nature and adaptability of system risk identification. If the adjustment index is less than the adjustment threshold, it is judged that the initial risk threshold can accurately judge the risk and no risk threshold adjustment is performed; if the adjustment index is greater than or equal to the adjustment threshold, it is judged that the initial risk threshold cannot accurately judge the risk, and the risk threshold is adjusted according to the adjustment index to obtain the actual risk threshold. The specific acquisition steps are as follows:

[0077]

[0078] Where rt 实际 is the actual risk threshold, AT' is the adjusted threshold, AT is the adjusted index, and rt 初始 This is represented as the initial risk threshold, dynamically generating the actual risk threshold to implement an adaptive tightening mechanism based on risk dynamics. When the adjustment index is greater than the adjustment threshold, it indicates that the system is currently experiencing instability or a potential increase in risk due to the combined influence of multiple factors. At this time, by reducing the ratio magnification factor to less than 1, the original risk threshold is lowered, making it easier for the system to identify and respond to subtle abnormal fluctuations, improving early warning sensitivity, and effectively enhancing the system's risk identification capabilities under complex and changing conditions. This avoids risk omissions caused by excessively high thresholds, thereby achieving more precise and proactive risk management.

[0079] The early warning module is used to determine whether to issue early warning prompts and record risk nodes based on the risk index and actual risk threshold;

[0080] In this embodiment, it should be specifically explained that the steps for determining whether to issue an early warning prompt and record a risk node based on the risk index and the actual risk threshold are as follows:

[0081] Compare the risk index with the actual risk threshold. If the risk index is greater than or equal to the actual risk threshold, an early warning will be issued and a risk node record will be made; if the risk index is less than the actual risk threshold, no early warning will be issued and no risk node record will be made.

[0082] The blockchain evidence storage module encrypts key data and stores it on the blockchain. Key data includes key farming parameters and early warning data.

[0083] Key data is encrypted and stored on the blockchain. The blockchain's decentralized, tamper-proof, and timestamped nature ensures the authenticity and integrity of data during transmission and storage. This effectively prevents data from being tampered with or deleted, providing a reliable data foundation for subsequent risk tracing, responsibility definition, and quality control, thereby enhancing the transparency and credibility of the entire aquaculture traceability system.

[0084] The traceability display module displays the entire life cycle information of aquatic products to consumers or regulatory authorities.

[0085] By visualizing key data from the entire aquaculture process, the platform provides consumers and regulators with intuitive information about the entire life cycle of aquatic products. This helps enhance product transparency and consumer trust, strengthens brand value, and facilitates accurate traceability and accountability for regulators, thereby improving food safety regulatory efficiency and market responsiveness.

[0086] In this embodiment, it is necessary to specifically explain that the traceability management method for circulating aquaculture based on blockchain, such as Figure 2 As shown, the following steps are included:

[0087] Step 1: Real-time collection of key aquaculture parameters, including water quality parameters, feeding records, animal health status, and environmental monitoring data;

[0088] Step 2: Obtain risk index based on key farming parameters assessment;

[0089] Step 3: Obtain the initial risk threshold and acquire the threshold impact data in real time. The threshold impact data includes environmental change data, biological behavior data, farming operation data, and historical warning data. The adjustment index is obtained based on the threshold impact data evaluation. The risk threshold is adjusted based on the adjustment index to obtain the actual risk threshold.

[0090] Step 4: Determine whether to issue an early warning and record risk nodes based on the risk index and actual risk threshold;

[0091] Step 5: Encrypt key data and store it on the blockchain. The key data includes key farming parameters and early warning data.

[0092] Step 6: Display the full life cycle information of aquatic products to consumers or regulatory authorities.

[0093] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0094] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. The blockchain-based recirculating aquaculture traceability management system is characterized by: The system comprises: The data acquisition module is used to collect key aquaculture parameters in real time, including water quality parameters, feeding records, animal health status, and environmental monitoring data, and transmit these key parameters to the risk assessment module; The risk assessment module is used to obtain a risk index based on key farming parameters and transmit the risk index to the early warning module; The risk threshold adjustment module is used to obtain the initial risk threshold and the threshold impact data in real time. The threshold impact data includes environmental change data, biological behavior data, breeding operation data, and early warning history data. The adjustment index is obtained based on the threshold impact data evaluation. The risk threshold is adjusted based on the adjustment index to obtain the actual risk threshold, and the actual risk threshold is transmitted to the early warning module. The early warning module is used to determine whether to issue early warning prompts and record risk nodes based on the risk index and actual risk threshold; The blockchain evidence storage module encrypts key data and stores it on the blockchain. Key data includes key farming parameters and early warning data. The traceability display module shows users the full life cycle information of aquatic products.

2. The blockchain-based recirculating aquaculture traceability management system according to claim 1, characterized in that: The steps for obtaining the risk index based on the key parameters of aquaculture are as follows: Obtain the normal range of each water quality indicator, set a detection time period, count the number of times each water quality indicator exceeds the normal range during the detection time period, add up the number of times all water quality indicators exceed the normal range during the detection time period and take the reciprocal to obtain the degree of water quality; Obtain the recommended feeding amount and the actual feeding amount, and calculate the feeding deviation based on the recommended feeding amount and the actual feeding amount; The rationality of feeding is calculated based on the feeding deviation; Obtain the number of healthy cultured animals and the total number of cultured animals, calculate the ratio of the number of healthy cultured animals to the total number of cultured animals, and obtain the health level; Obtain optimal water temperature data and current water temperature data, and calculate the environmental suitability based on the optimal water temperature data and current water temperature data; The water quality, feeding rationality, health and environmental suitability are normalized, and the risk index is calculated based on the normalized water quality, feeding rationality, health and environmental suitability. The specific steps for obtaining the risk index are as follows: Where RK represents the risk index, sc represents the water quality, th represents the rationality of feeding, jc represents the health level, and hs represents the environmental suitability.

3. The blockchain-based recirculating aquaculture traceability management system according to claim 1 is characterized in that: The step of obtaining the adjustment index based on the threshold impact data evaluation is as follows: Obtain environmental change data, including water temperature and pH value, and obtain environmental change coefficients through singular value decomposition method based on the environmental change data; Obtaining biological behavior data, which is food intake data, and evaluating the degree of food intake fluctuation based on the food intake data, and recording the degree of food intake fluctuation as a biological behavior coefficient; Acquire aquaculture operation data, which is aquaculture density value, and obtain aquaculture operation coefficient based on the aquaculture operation data; Obtain historical warning data, which is the number of historical warnings within the detection period; The environmental change coefficient, biological behavior coefficient, aquaculture operation coefficient and historical warning times are normalized, and the adjustment index is calculated based on the normalized environmental change coefficient, biological behavior coefficient, aquaculture operation coefficient and historical warning times. The specific steps for obtaining the index are as follows: AT=a1×EC+a2×BI+a3×BO+a4×WH; Where AT is the adjustment index, EC is the environmental change coefficient, BI is the biological behavior coefficient, BO is the aquaculture operation coefficient, WH is the number of historical warnings, a1, a2, a3, and a4 are the weight coefficients of the environmental change coefficient, the biological behavior coefficient, the aquaculture operation coefficient, and the historical warning number.

4. The blockchain-based recirculating aquaculture traceability management system according to claim 3 is characterized in that: The steps for obtaining the environmental variation coefficient are as follows: Obtain the water temperature and pH value at each sampling time point within the detection period, and construct an n×2 data matrix X based on the water temperature and pH value at each time point within the detection period; Perform centralization on the matrix X, that is, subtract the mean of each column to obtain the centralized data matrix X'; Perform singular value decomposition on the data matrix after centralization to obtain a singular value matrix. Obtain singular values according to the singular value matrix, calculate the square root of the square sum of all singular values, and obtain the environmental variation coefficient.

5. The blockchain-based recirculating aquaculture traceability management system according to claim 3 is characterized by: The steps for obtaining the biological behavior coefficient are: Obtain the food intake at each testing time point during the testing period, and calculate the average food intake during the testing period; The food intake variance is calculated based on the average food intake and the food intake at each detection time point. The specific steps for obtaining the variance are as follows: Where sf represents the variance of food intake, n is the number of detection time points, F i It is expressed as the food intake at the i-th detection time point, Expressed as mean food intake; The root of the variance of food intake was calculated to obtain the degree of food intake fluctuation.

6. The blockchain-based recirculating aquaculture traceability management system according to claim 3 is characterized by: The steps for obtaining the breeding operation coefficient are as follows: Obtaining the stocking density at each detection time point within the detection time period, calculating the standard deviation of the stocking density at each detection time point within the detection time period, and obtaining the stocking density standard deviation; The stocking density change rate was calculated based on the stocking density at each detection time point; Obtain the safety reference density and calculate the trend deviation degree based on the stocking density and the safety reference density at each detection time point; The standard deviation of stocking density, the rate of change of stocking density and the degree of trend deviation are normalized, and the stocking operation coefficient is calculated based on the normalized standard deviation of stocking density, the rate of change of stocking density and the degree of trend deviation. The specific steps for obtaining the coefficient are as follows: Where BO is the aquaculture operation coefficient, yc is the standard deviation of aquaculture density, mb is the rate of change of aquaculture density, and qp is the degree of trend deviation.

7. The blockchain-based recirculating aquaculture traceability management system according to claim 1, characterized in that: The steps of adjusting the risk threshold according to the adjustment index to obtain the actual risk threshold are as follows: Compare the adjustment index with the adjustment threshold. If the adjustment index is less than the adjustment threshold, it is determined that the initial risk threshold can accurately determine the risk and no risk threshold adjustment is performed. If the adjustment index is greater than or equal to the adjustment threshold, and the initial risk threshold cannot accurately determine the risk, the risk threshold is adjusted according to the adjustment index to obtain the actual risk threshold. The specific steps for obtaining the actual risk threshold are as follows: Where rt 实际 is the actual risk threshold, AT' is the adjusted threshold, AT is the adjusted index, and rt 初始 Denoted as the initial risk threshold.

8. The blockchain-based recirculating aquaculture traceability management system according to claim 1, characterized in that: The steps of determining whether to issue an early warning and record a risk node based on the risk index and the actual risk threshold are as follows: Compare the risk index with the actual risk threshold. If the risk index is greater than or equal to the actual risk threshold, an early warning will be issued and the risk node will be recorded. If the risk index is less than the actual risk threshold, no warning will be issued and no risk node record will be made.

9. A blockchain-based recirculating aquaculture traceability management method, for implementing the blockchain-based recirculating aquaculture traceability management system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: Real-time collection of key aquaculture parameters, including water quality parameters, feeding records, animal health status, and environmental monitoring data; Step 2: Obtain risk index based on key farming parameters assessment; Step 3: Obtain the initial risk threshold and acquire the threshold impact data in real time. The threshold impact data includes environmental change data, biological behavior data, farming operation data, and historical warning data. The adjustment index is obtained based on the threshold impact data evaluation. The risk threshold is adjusted based on the adjustment index to obtain the actual risk threshold. Step 4: Determine whether to issue an early warning and record risk nodes based on the risk index and actual risk threshold; Step 5: Encrypt key data and store it on the blockchain. The key data includes key farming parameters and early warning data. Step 6: Display the full life cycle information of aquatic products to users.

Images