Aquatic product whole industry chain intelligent management platform and data processing method

Abstract

This invention discloses an intelligent management platform and data processing method for the entire aquatic product industry chain, belonging to the field of aquaculture and distribution management technology. The method includes: generating identification codes for batches and uploading them to the blockchain; collecting data on aquaculture water quality and feeding activity; calculating water quality suitability and disease risk indices; collecting processing temperature and time and quality inspection parameters; collecting cold chain temperature and humidity data; constructing temperature history and calculating cumulative quality degradation potential and real-time remaining shelf life; calculating the urgency of intervention based on remaining shelf life and distance, and generating dynamic scheduling decisions; generating a full-chain traceability report including remaining shelf life. This invention breaks down data silos across the entire chain, enabling dynamic quality assessment and collaborative scheduling, and improving management accuracy.

Description

Technical Field

[0001] This invention relates to the field of aquaculture and distribution management technology, and in particular to an intelligent management platform and data processing method for the entire aquatic product industry chain. Background Technology

[0002] With the continuous optimization and upgrading of consumption structure, the proportion of aquatic products in residents' diets is constantly increasing, and consumers are placing higher demands on the quality and safety of aquatic products. The entire industrial chain of aquatic products, from aquaculture water to consumers' tables, includes multiple links such as aquaculture, fishing, processing, storage, transportation, and sales. Significant information transmission barriers and decision-making coordination bottlenecks exist between these links.

[0003] Currently, the following core technical issues exist in the information management of each link in the aquatic product industry chain.

[0004] First, data collection methods at each stage of the industry chain are independent, and there is a lack of unified standards for data formats and sampling frequencies. Water quality sensor data from the aquaculture stage, quality inspection records from the processing stage, temperature monitoring data from the cold chain transportation stage, and inventory data from the sales terminals are stored in different management information systems, creating several information silos. This prevents quality anomalies at any stage from being promptly transmitted to upstream and downstream stages, leading to the propagation and amplification of quality problems throughout the entire industry chain.

[0005] Second, current technologies for assessing the quality of aquatic products generally employ static thresholds or simple rule-based judgments. For example, during cold chain transportation, only whether the temperature exceeds a preset threshold is considered, without taking into account the cumulative effect of temperature fluctuations on the quality of aquatic products; in the sales stage, only fixed shelf-life labels are used to determine whether products are expired, without considering the actual impact of cold chain history on shelf life. This static assessment method cannot reflect the dynamic decay process of aquatic product quality over time, resulting in significant lag and inaccuracy in quality early warning.

[0006] Third, existing technologies lack a supply chain collaborative decision-making mechanism based on real-time quality status. When a quality anomaly is detected at a certain stage, an alarm is usually triggered only within that stage, failing to automatically trigger problem tracing upstream and response adjustments downstream. Each stage's response measures operate independently, lacking a unified, supply chain-wide decision-making and coordination framework.

[0007] Fourth, while existing traceability systems can record product flow information at each stage, there is a lack of coupling between traceability data and quality monitoring data. After scanning the traceability code, consumers can only view static information such as the product's place of origin and date, and cannot obtain the product's current true quality status and remaining shelf life information.

[0008] In summary, existing technologies suffer from four major technical defects: data silos, static quality assessment, passive decision-making response, and superficial traceability information. There is an urgent need for an integrated technical solution that can achieve data connectivity across the entire industry chain, dynamic quality assessment, collaborative decision-making, and enhanced traceability depth. Summary of the Invention

[0009] To achieve the above objectives, this invention provides an intelligent management platform and data processing method for the entire aquatic product industry chain, comprising the following steps:

[0010] Step 1: Generate a batch identification code for the aquaculture batch, which includes the aquaculture entity code, aquaculture water body code, seeding date, aquatic product type code, and batch serial number. Store the batch identification code in the distributed ledger of the blockchain network and assign a digital identity public-private key pair to the aquaculture batch.

[0011] Step 2: Collect dissolved oxygen concentration, aquaculture water temperature, pH, ammonia nitrogen concentration, and nitrite concentration values ​​using a multi-parameter water quality sensor array deployed in the aquaculture water body. Collect the aquatic product population activity index using a camera device deployed above the aquaculture water body. After binding the collected dissolved oxygen concentration, aquaculture water temperature, pH, ammonia nitrogen concentration, nitrite concentration, and aquatic product population activity index with the batch identification code, write them into the distributed ledger of the blockchain network through digital signature.

[0012] Step 3: Calculate the water quality suitability index and disease risk index based on the dissolved oxygen concentration, aquaculture water temperature, pH value, ammonia nitrogen concentration, and nitrite concentration.

[0013] Step 4: Collect the ambient temperature value of the processing workshop, the duration of each processing step, the volatile basic nitrogen content value, the total bacterial count value, and the K value of the processing workshop. After binding the ambient temperature value of the processing workshop, the duration of each processing step, the volatile basic nitrogen content value, the total bacterial count value, and the K value with the batch identification code, write them into the distributed ledger of the blockchain network through digital signature.

[0014] Step 5: Collect the cold chain environment temperature and relative humidity values ​​in the cold chain circulation process, bind the cold chain environment temperature and relative humidity values ​​with the batch identification code, and then write them into the distributed ledger of the blockchain network through digital signature.

[0015] Step 6: Construct a complete temperature history curve from the start of processing to the current time based on the ambient temperature values ​​of the processing workshop and the cold chain environment. Calculate the cumulative quality degradation potential based on the complete temperature history curve, the volatile basic nitrogen content, the total bacterial count, and the K value.

[0016] Step 7: Calculate the real-time remaining shelf life of the aquatic product batch based on the cumulative quality decay potential;

[0017] Step 8: Calculate the intervention urgency based on the real-time remaining shelf life of each batch of aquatic products and the geographical distance between the current location and the target sales terminal. Sort the intervention urgency from largest to smallest to generate an intervention priority sequence and generate dynamic scheduling decisions accordingly.

[0018] Step 9: Respond to the traceability query request, read all data associated with the batch identifier from the distributed ledger of the blockchain network, and generate a full-chain quality traceability report including the real-time remaining shelf life.

[0019] Preferably, the batch identification code in step 1 is encoded in the following format: the aquaculture entity code is 6 digits, the aquaculture water body code is 4 digits, the seeding date is 8 digits, the aquatic product type code is 4 digits, and the batch serial number is 4 digits. The aquaculture entity code, aquaculture water body code, seeding date, aquatic product type code, and batch serial number are connected by hyphens.

[0020] The specific process of storing the batch identification code to the distributed ledger of the blockchain network is as follows: the identification registration smart contract in the blockchain network is called. The identification registration smart contract receives the batch identification code and batch metadata as input parameters. The batch metadata includes the aquatic product type name, seeding quantity, seeding specifications and seeding source information. The identification registration smart contract verifies the format of the batch identification code. After the verification is passed, the batch identification code and batch metadata are written into the distributed ledger as a set of key-value pairs. The identification registration smart contract returns the transaction hash value as a storage certificate.

[0021] The public key in the digital identity public-private key pair is bound to the batch identifier code and written into the batch status storage area of ​​the identifier registration smart contract. The private key is kept by the breeding entity. Data generated in each subsequent stage is digitally signed using the private key before being written into the blockchain network. The data recipient verifies the legitimacy of the data source using the public key.

[0022] Preferably, in step 2, the multi-parameter water quality sensor array is deployed at different depths in the aquaculture water body. The multi-parameter water quality sensor array includes a dissolved oxygen sensor, a temperature sensor, a pH sensor, an ammonia nitrogen concentration sensor, and a nitrite concentration sensor. The above sensors collect aquaculture environmental parameters at a fixed sampling interval, which is set to a fixed value within the range of 15 minutes to 30 minutes.

[0023] The dissolved oxygen concentration value collected by the dissolved oxygen sensor is expressed in milligrams per liter and is denoted as . Where t represents the sampling time; the temperature values ​​of the aquaculture water collected by the temperature sensor are in degrees Celsius, denoted as . The pH value collected by the pH sensor is dimensionless and is denoted as . The ammonia nitrogen concentration value collected by the ammonia nitrogen concentration sensor is expressed in milligrams per liter and is denoted as . The nitrite concentration value collected by the nitrite concentration sensor is expressed in milligrams per liter and is denoted as . ;

[0024] The camera device is deployed above the aquaculture water body. Its sampling interval is synchronized with that of the multi-parameter water quality sensor array. It performs target detection and motion analysis on the feeding behavior image sequences, extracting the activity index of the aquatic product group after feeding, denoted as... The aquatic product group activity index is calculated as follows: The movement velocity vectors of individual aquatic products are extracted from each image frame of the feeding behavior image sequence during the 5th to 15th minute after feeding. The mean value of the magnitude of the movement velocity vectors of all aquatic products during this time period is calculated, and this mean value is used as the aquatic product group activity index. .

[0025] Preferably, the formula for calculating the water quality suitability index in step 3 is:

[0026]

[0027] in, Let be the water quality suitability index at time t, with a value ranging from 0 to 1; This represents the minimum tolerable dissolved oxygen concentration for aquatic product species. This is the upper reference limit for dissolved oxygen concentration; The optimal pH value for aquatic products, The pH tolerance range of aquatic product species; This represents the maximum tolerable concentration of ammonia nitrogen for aquatic product species. The maximum tolerable concentration of nitrite for aquatic product species; Let be the weighting coefficient, satisfying Each weighting coefficient is preset based on the sensitivity of aquatic product types to various water quality parameters;

[0028] The formula for calculating the disease risk index is:

[0029]

[0030] in, The disease risk index at time t, with a value ranging from 0 to 1; The optimal growth temperature for aquatic product species; The temperature tolerance range of aquatic product types; This represents the contribution coefficient of temperature deviation to disease risk. This represents the contribution coefficient of water quality suitability to disease risk, and ;

[0031] Water quality suitability index Compared with the preset water quality suitability warning threshold, when When the water quality falls below the warning threshold, an abnormal aquaculture environment warning is generated; the disease risk index is also considered. Compared with the preset disease risk warning threshold, when When the risk level exceeds the disease risk warning threshold, a disease risk warning message is generated. The warning message includes the warning type, the time of the warning, the batch identification code corresponding to the warning, the current aquaculture environment parameter value, and the calculated index value.

[0032] Preferably, the start time of the processing step in step 4 is recorded as follows: The ambient temperature in the processing workshop is recorded in degrees Celsius. The ambient temperature in the processing workshop is collected by temperature sensors deployed in the workshop at the fixed sampling interval described in step 2; the duration of each processing step is in minutes and denoted as... , where i represents the i-th processing step, and the duration of each processing step is recorded by a timing device deployed on the processing equipment;

[0033] The volatile basic nitrogen content value in the quality inspection parameters is expressed in milligrams per 100 grams, denoted as... The total bacterial count is measured in colony-forming units per gram (CFU), and is denoted as CFU / C. The K value is defined as the ratio of the sum of the molar concentrations of hypoxanthine and inosine to the total molar concentration of adenosine triphosphate and its breakdown products. It is dimensionless and denoted as K. ;

[0034] Processing start time Ambient temperature value of the processing workshop Time series data, duration of each processing step Volatile basic nitrogen content value Total bacterial count and K value The data is bound to the batch identifier code, digitally signed using the private key described in step 1, and then transmitted to the data storage smart contract of the blockchain network via a wireless communication network. After receiving the signed data, the data storage smart contract uses the public key to verify the legality of the signature. Once the verification is successful, the data is written into the data storage area of ​​the distributed ledger.

[0035] Preferably, in step 5, the temperature and humidity values ​​in the cold chain circulation process are collected by a cold chain environmental parameter acquisition device deployed inside the cold chain transport container or vehicle. This device includes a temperature sensor and a humidity sensor. The temperature sensor collects the air temperature value inside the cold chain transport container or vehicle at the fixed sampling interval described in step 2, and the value is recorded in degrees Celsius. The humidity sensor collects the relative humidity value of the air inside the cold chain transport container or cold chain transport vehicle at the fixed sampling interval described in step 2, and records it as a percentage. ;

[0036] The start time of the cold chain distribution process is recorded as follows: The end time of the cold chain distribution process is recorded as ;

[0037] Temperature value Time series data, humidity values Time series data, start time of cold chain distribution and termination time The data is bound to the batch identifier code, digitally signed using the private key described in step 1, and then transmitted to the data storage smart contract of the blockchain network via a wireless communication network. After receiving the signed data, the data storage smart contract uses the public key to verify the legality of the signature. Once the verification is successful, the data is written into the data storage area of ​​the distributed ledger.

[0038] Preferably, the complete temperature history curve in step 6 is constructed by: taking the ambient temperature value of the processing workshop... Time series data and cold chain environment temperature values Time series data are spliced ​​together in chronological order to form a sequence starting from the beginning of the processing stage. Up to the current moment Complete temperature history curve ,in For time variables, The range of values ​​is ;

[0039] The formula for calculating the cumulative quality decay potential is:

[0040]

[0041] in, This represents the cumulative quality decay potential up to the current moment. For aquatic product types at reference temperatures The quality decay rate constant under the given conditions, Take 273 Kelvin; The activation energy for quality degradation of aquatic products is expressed in joules per mole; R is the ideal gas constant, taken as 8.314 joules per mole per Kelvin. For a moment The Kelvin temperature value of the environment in which the aquatic products are located is obtained by adding 273.15 to the Celsius temperature value;

[0042] The initial quality correction factor is calculated using the following formula:

[0043]

[0044] in, This provides a reference value for the K-value of aquatic product species under reference conditions. This provides reference values ​​for the volatile basic nitrogen content of aquatic product species under reference conditions. This provides reference values ​​for the total bacterial count of aquatic product species under reference conditions. Let be the weighting coefficient, satisfying Each weighting coefficient is preset based on the contribution of volatile basic nitrogen content, total bacterial count, and K value to the rate of quality degradation of aquatic products.

[0045] For discrete data, the discrete summation form of the cumulative quality decay potential is:

[0046]

[0047] Where N is the total number of sampling periods from the start of processing to the current time. Let Kelvin be the temperature value in the j-th sampling period. This refers to the time length corresponding to the fixed sampling interval mentioned in step 2.

[0048] Preferably, the formula for calculating the real-time remaining shelf life in step 7 is:

[0049]

[0050] in, The remaining shelf life as of the current moment, in hours; This is the critical value for the quality degradation potential of aquatic product species, which is determined by the aquatic product species at a reference temperature. The standard shelf-life experimental data were obtained under the following conditions; The expected storage temperature value for a batch of aquatic products under subsequent standard storage conditions, in Kelvin; For the aforementioned aquatic product types at a reference temperature The constant of the quality decay rate under the given conditions; R is the activation energy for quality degradation of the aforementioned aquatic product species; R is the ideal gas constant. This is the initial quality correction factor.

[0051] Preferably, the calculation method for the urgency of intervention in step 8 is as follows: at any given time, obtain a batch list of all aquatic product batches currently in the cold chain distribution or sales stage; for each aquatic product batch in the batch list, read the real-time remaining shelf life of that aquatic product batch from the distributed ledger of the blockchain network. and current geographical location information;

[0052] The formula for calculating the urgency of intervention is:

[0053]

[0054] in, The urgency of intervention for aquatic product batches; The real-time remaining shelf life of aquatic product batches, in hours; For a less than A positive number; d represents the geographical distance between the current location of the aquatic product batch and the target sales terminal, in kilometers; The average speed of cold chain transport vehicles, expressed in kilometers per hour; This is the distance attenuation coefficient, with a value ranging from 0.1 to 0.5;

[0055] All aquatic product batches are classified according to the urgency of intervention. The values ​​are sorted from largest to smallest to generate an intervention priority sequence;

[0056] Dynamic scheduling decisions are generated based on intervention priority sequences. These decisions include at least one of the following: for batches with intervention urgency greater than a preset high intervention threshold, a priority delivery instruction is generated, including the batch identifier, current location, target sales terminal, and priority level; for batches with intervention urgency between the preset high and medium intervention thresholds, a normal delivery instruction is generated; for batches with intervention urgency less than the preset medium intervention threshold, a delayed delivery instruction is generated; and for batches with real-time remaining shelf life... For batches that are less than the preset safety threshold, generate a price reduction promotion order or a return processing order;

[0057] The generated dynamic scheduling decision is bound to the corresponding batch identifier code and written into the decision record smart contract of the blockchain network. After receiving the dynamic scheduling decision data, the decision record smart contract verifies the data source by signature. After successful verification, the decision data is written into the decision record area of ​​the distributed ledger.

[0058] Preferably, the generation method of the full-chain quality traceability report in step 9 is as follows: in response to the traceability query request initiated by the end user by scanning the traceability code on the outer packaging of aquatic products, all data associated with the batch identification code corresponding to the traceability code is read from the distributed ledger of the blockchain network;

[0059] The data retrieved includes: batch metadata stored in step 1 (including aquatic product species name, number of seedlings, seedling specifications, and seedling source information); and dissolved oxygen concentration values ​​stored in step 2. Aquaculture water temperature value pH value ammonia nitrogen concentration value nitrite concentration value and the activity index of aquatic product groups Time series data; water quality suitability index calculated in step 3 Disease risk index Time series data; ambient temperature values ​​of the processing workshop stored in step 4. Time series data, duration of each processing step Volatile basic nitrogen content value Total bacterial count and K value Step 5: Store the cold chain environment temperature value. Time series data and relative humidity values ​​in cold chain environments Time series data; cumulative quality decay potential calculated in step 6 Step 7 calculates the real-time remaining shelf life. ;

[0060] The time series data of aquaculture environmental parameters and the time series data of water quality suitability index are statistically summarized to generate a quality overview of the aquaculture process. The quality overview of the aquaculture process includes the average, maximum, minimum and standard deviation of dissolved oxygen concentration, aquaculture water temperature, pH, ammonia nitrogen concentration, nitrite concentration and water quality suitability index during the aquaculture cycle.

[0061] Statistical analysis and summarization of time-series data on cold chain environmental parameters are performed to generate a quality overview of the cold chain process, which includes cold chain environmental temperature values. The average, maximum, minimum, and standard deviation of the temperature, as well as the number and cumulative duration of temperature exceedance events. A temperature exceedance event is defined as the temperature value of the cold chain environment. An event that exceeds the preset cold chain temperature limit for a duration exceeding the preset time tolerance;

[0062] All the data and statistical summary results are organized in chronological order into a full-chain quality traceability report. The full-chain quality traceability report includes an overview of the quality of the breeding process, a summary of quality inspection parameters of the processing process, an overview of the quality of the cold chain process, and the current real-time remaining shelf life. The full-chain quality traceability report is returned to the end user's query interface for display.

[0063] The beneficial effects of this invention are:

[0064] 1. By establishing a unified batch digital identity and aggregating data from the entire process of breeding, processing, and cold chain distribution to a blockchain distributed ledger, information silos in each link of the industrial chain are completely eliminated, ensuring that the data source is verifiable and the content is tamper-proof, thus solving the problems of data fragmentation and low credibility in existing technologies.

[0065] 2. A dynamic quality assessment system is constructed based on the complete temperature history curve and the cumulative quality decay potential. The degree of quality decay is calculated cumulatively in the form of integrals and the remaining shelf life is updated in real time, which overcomes the lag and inaccuracy of the existing technology that uses static thresholds or fixed shelf life to assess quality.

[0066] 3. By comprehensively calculating the urgency of intervention based on real-time remaining shelf life and spatial distance, and generating dynamic scheduling decisions, the response measures of each link are automatically coordinated, achieving precise matching between distribution resources and actual product quality requirements. This solves the problem of existing technologies making decisions independently and lacking a unified coordination framework. Attached Figure Description

[0067] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0068] Figure 1 This is a flowchart of the steps of the method of the present invention. Detailed Implementation

[0069] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0070] Please see Figure 1This invention provides an intelligent management platform and data processing method for the entire aquatic product industry chain. The method constructs a digital identity identification and data collection system that runs through the entire process of breeding, processing, cold chain circulation and sales. It dynamically and quantitatively assesses the quality status of aquatic products based on the cumulative quality decay potential, and generates a collaborative scheduling decision for the entire chain based on the urgency of intervention. Finally, the quality assessment results are deeply embedded into the traceability information chain to achieve intelligent management of the entire aquatic product industry chain from water to table.

[0071] The overall process of this invention comprises nine steps: Step 1, establishing a digital identity for each aquatic product batch across the entire industry chain; Step 2, collecting aquaculture environment parameters and aquatic product growth parameters during the aquaculture stage; Step 3, calculating the water quality suitability index and disease risk index during the aquaculture stage based on the aquaculture environment parameters; Step 4, collecting processing parameters and quality inspection parameters during the processing stage; Step 5, collecting cold chain environment parameters during the cold chain distribution stage; Step 6, calculating the cumulative quality decay potential of each aquatic product batch; Step 7, calculating the real-time remaining shelf life of each aquatic product batch based on the cumulative quality decay potential; Step 8, calculating the intervention urgency for each aquatic product batch and generating dynamic scheduling decisions; Step 9, generating a quality traceability report for the entire industry chain. These nine steps are interconnected and data is integrated; the output data of each step forms the input basis for subsequent steps, creating a complete closed-loop management chain.

[0072] Step 1: Establish digital identity identification for aquatic product batches across the entire industry chain.

[0073] When aquaculture batches are established, a unique batch identification code is generated for each batch. The batch identification code includes the following fields: aquaculture entity code, aquaculture water body code, stocking date, aquatic product type code, and batch serial number. The encoding format of the batch identification code is as follows: aquaculture entity code is 6 digits, aquaculture water body code is 4 digits, stocking date is 8 digits, aquatic product type code is 4 digits, and batch serial number is 4 digits, with each field connected by a hyphen. For example, a complete batch identification code would be in the form of "320501-P008-20240315-V001-0023". This encoding format ensures that each aquaculture batch has a globally unique, traceable digital identity containing key business information across the entire industry chain.

[0074] The specific process of storing batch identification codes in the distributed ledger of the blockchain network is as follows: The identification registration smart contract deployed in the blockchain network is invoked. The identification registration smart contract receives the batch identification code and batch metadata as input parameters. The batch metadata includes the aquatic product type name, seeding quantity, seeding specifications, and seeding source information. The identification registration smart contract first validates the format of the batch identification code, including whether the length of each field meets the requirements, whether fields are connected by hyphens, and whether all field contents are numbers. After successful validation, the identification registration smart contract writes the batch identification code and batch metadata as a key-value pair to the designated storage area of ​​the distributed ledger and returns a transaction hash value as a storage certificate. The transaction hash value can be used for subsequent querying and verification.

[0075] A digital identity public-private key pair is assigned to each aquatic product farming batch. After the public key is bound to the batch identifier code, it is written to the batch status storage area through the batch status update interface of the identifier-registered smart contract. The private key is stored in encrypted form by the farming entity in an offline hardware encryption device. Any data generated in subsequent stages is written to the blockchain network using this private key and a digital signature generated according to the elliptic curve digital signature algorithm. The data recipient queries the corresponding public key from the blockchain network using the batch identifier code and uses this public key to verify the legality of the data source and the integrity of the data content. This mechanism ensures the non-repudiation and tamper-proof nature of data uploaded at all stages of the entire industry chain.

[0076] Step 2: Collect aquaculture environment parameters and aquatic product growth parameters during the aquaculture stage.

[0077] A multi-parameter water quality sensor array is deployed at different depths in the aquaculture water body. The array includes dissolved oxygen, temperature, pH, ammonia nitrogen, and nitrite concentration sensors. All sensors synchronously collect aquaculture environmental parameters at fixed sampling intervals, set to a fixed value within the range of 15 to 30 minutes, for example, 15 minutes.

[0078] Dissolved oxygen sensors collect dissolved oxygen concentration values ​​in aquaculture water, measured in milligrams per liter (mg / L), denoted as . Where t represents the sampling time. The temperature sensor collects the temperature value of the aquaculture water, in degrees Celsius, denoted as . The pH sensor collects the pH value of the aquaculture water; it is dimensionless and denoted as pH. The ammonia nitrogen concentration sensor collects the ammonia nitrogen concentration value in the aquaculture water, in milligrams per liter, denoted as . The nitrite concentration sensor collects the nitrite concentration value in the aquaculture water, in milligrams per liter, denoted as . .

[0079] Image sequences of feeding behavior of aquatic product groups were collected using cameras deployed above the aquaculture water body. The sampling interval of the cameras was synchronized with the sampling interval of a multi-parameter water quality sensor array. Target detection and motion analysis were performed on the feeding behavior image sequences to extract the activity index of the aquatic product group after feeding, denoted as [missing information]. The aquatic product group activity index is calculated as follows: The movement velocity vectors of individual aquatic products are extracted from each image frame of the feeding behavior image sequence during the 5th to 15th minute after feeding. The mean value of the magnitude of the movement velocity vectors of all aquatic products during this time period is calculated, and this mean value is used as the aquatic product group activity index. This index reflects the vitality level of aquatic product populations during feeding and is an important auxiliary indicator for assessing the growth and health status of aquatic products.

[0080] The collected dissolved oxygen concentration values Aquaculture water temperature value pH value ammonia nitrogen concentration value nitrite concentration value and the activity index of aquatic product groups All data is bound to the batch identifier code described in step 1. The private key described in step 1 is used to digitally sign the data. The signed data is then transmitted via a wireless communication network to the data storage smart contract on the blockchain network. Upon receiving the signed data, the data storage smart contract verifies the signature's validity using the corresponding public key. If verification is successful, the data is written to the distributed ledger's data storage area using the batch identifier code as an index. Through this method, all environmental and growth data during the breeding stage is securely and reliably recorded in the blockchain network, providing a data foundation for subsequent quality assessment and traceability.

[0081] Step 3: Calculate the water quality suitability index and disease risk index for the aquaculture stage based on aquaculture environment parameters.

[0082] Based on the dissolved oxygen concentration value collected in step 2 Aquaculture water temperature value pH value ammonia nitrogen concentration value and nitrite concentration value Calculate the water quality suitability index of the aquaculture water body. The formula for calculating the water quality suitability index is:

[0083]

[0084] in, The water quality suitability index at time t ranges from 0 to 1. The larger the value, the more suitable the water quality is for the growth of aquatic products. This refers to the minimum tolerable dissolved oxygen concentration for the aquatic product species being farmed. This is the upper limit of the dissolved oxygen concentration (generally taken as the saturation value of dissolved oxygen concentration in aquaculture water under fully oxygenated conditions). The optimal pH value for the aquatic products being cultured. The pH tolerance range of the aquatic products being farmed; and These are the maximum tolerable concentrations of ammonia nitrogen and nitrite for the aquatic product species being farmed; Let be the weighting coefficient, satisfying Each weighting coefficient is preset based on the sensitivity of the aquatic product species to various water quality parameters. The water quality suitability index comprehensively reflects the overall suitability of multiple key indicators of the aquaculture water body for the growth of aquatic products, overcoming the one-sidedness of judging by single indicator thresholds.

[0085] The formula for calculating the disease risk index is:

[0086]

[0087] in, The disease risk index is at time t, and its value ranges from 0 to 1. The larger the value, the higher the risk of disease occurrence. The optimal growth temperature for the aquatic products being farmed; The temperature tolerance range of the aquatic products being farmed; This represents the contribution coefficient of temperature deviation to disease risk. This represents the contribution coefficient of water quality suitability to disease risk, and The disease risk index takes into account both the degree to which the temperature deviates from the optimal growth range and the degree of decline in the overall suitability of water quality, thus more accurately reflecting the potential disease threats faced by farmed aquatic products.

[0088] The calculated water quality suitability index The water quality suitability warning threshold is compared with a preset threshold. The water quality suitability warning threshold can be preset based on the tolerance characteristics of the aquatic species and aquaculture management experience (e.g., for Litopenaeus vannamei, it can be preset to 0.60). When the water quality falls below the warning threshold for suitability, an abnormal aquaculture environment warning is generated. The calculated disease risk index is then used to... Compare with a preset disease risk warning threshold (e.g., 0.50). When When the levels exceed the disease risk warning threshold, a disease risk warning message is generated. The warning message includes the warning type, the time of occurrence, the batch identifier corresponding to the warning, the current aquaculture environment parameter values, and the calculated index value. The warning message is pushed to the aquaculture management personnel's terminal via a preset communication method, enabling timely intervention measures such as oxygenation, water changes, or medication.

[0089] Step 4: Collect processing parameters and quality inspection parameters for the processing stage.

[0090] When aquatic product farmed batches are harvested and enter the processing stage, record the start time of processing, denoted as . After the processing begins, temperature sensors deployed in the processing workshop collect ambient temperature values ​​at the fixed sampling intervals described in step 2. The arithmetic mean of the temperature values ​​collected simultaneously by temperature sensors at multiple locations within the processing workshop is taken as the ambient temperature value of the processing workshop at that moment, expressed in degrees Celsius and denoted as . The duration of each processing step is recorded in minutes by timing devices deployed on each processing equipment. , where i represents the i-th processing step.

[0091] At the quality inspection stage of processing, the processed aquatic product samples undergo quality inspection. Quality inspection parameters include the volatile basic nitrogen content, total bacterial count, and K value of the aquatic product samples. The unit for volatile basic nitrogen content is milligrams per 100 grams, denoted as mg / 100g. The unit for total colony count is colony forming units per gram, denoted as . The K value is defined as the ratio of the sum of the molar concentrations of hypoxanthine and inosine to the total molar concentration of adenosine triphosphate and its breakdown products. It is dimensionless and denoted as K. The K value reflects the degree of adenosine triphosphate (ATP) breakdown in aquatic products and is an important biochemical indicator for evaluating the freshness of aquatic products. The determination of the above three quality inspection parameters was carried out in accordance with relevant national food safety standards.

[0092] Processing start time Ambient temperature value of the processing workshop Time series data, duration of each processing step Volatile basic nitrogen content value Total bacterial count and K value The data is then bound to the batch identifier code described in step 1. After digitally signing the data using the private key described in step 1, it is transmitted to the data storage smart contract on the blockchain network via a wireless communication network. Upon receiving the signed data, the data storage smart contract verifies the signature's validity using the corresponding public key. If the verification is successful, the data is written into the data storage area of ​​the distributed ledger.

[0093] Step 5: Collect cold chain environmental parameters during the cold chain distribution process.

[0094] After the aquatic products have completed processing and entered the cold chain distribution process, a cold chain environmental parameter acquisition device is deployed on the cold chain transport containers or vehicles carrying that batch of aquatic products. The cold chain environmental parameter acquisition device includes a temperature sensor and a humidity sensor. The temperature sensor collects the air temperature value inside the cold chain transport container or vehicle at the fixed sampling interval described in step 2, expressed in degrees Celsius and denoted as . The humidity sensor collects the relative humidity value of the air inside the cold chain transport container or cold chain transport vehicle at the fixed sampling interval described in step 2, and records it as a percentage. When multiple cold chain environmental parameter acquisition devices are deployed at different locations inside a cold chain transport vehicle, the arithmetic mean of the temperature values ​​collected by each device at the same time is taken as the cold chain environmental temperature value at that time, and the arithmetic mean of the relative humidity values ​​collected by each device at the same time is taken as the cold chain environmental relative humidity value at that time.

[0095] Throughout the entire cold chain distribution process, temperature values ​​are continuously recorded using cold chain environmental parameter acquisition devices. and humidity value Time series data. The start time of the cold chain distribution process is denoted as... The end time of the cold chain distribution process is recorded as .

[0096] Temperature value Time series data, humidity values Time series data, start time of cold chain distribution and termination time The data is bound to the batch identifier code described in step 1. After digitally signing using the private key described in step 1, the data is transmitted to the data storage smart contract on the blockchain network via a wireless communication network. Upon receiving the signed data, the data storage smart contract verifies the signature's validity using the corresponding public key. If the verification is successful, the data is written to the data storage area of ​​the distributed ledger.

[0097] Step 6: Calculate the cumulative quality decay potential of the aquatic product batch.

[0098] Based on the ambient temperature value of the processing workshop collected in step 4 Time series data and cold chain environmental temperature values ​​collected in step 5 Time series data were used to construct the timeline of this batch of aquatic products from the start of the processing stage. Up to the current moment Complete temperature history curve ,in It is a time variable, and its value range is... The complete temperature history curve is constructed by: taking the ambient temperature values ​​of the processing workshop... Time series data and cold chain environment temperature values The time-series data are concatenated sequentially, ensuring that timestamps are continuous and without overlap or gaps. If time gaps exist, linear interpolation is used to fill in the temperature values ​​within those gaps.

[0099] Based on the complete temperature history curve of this batch of aquatic products Calculate the cumulative quality decay potential of this batch of aquatic products from the start of processing to the current time. The formula for calculating the cumulative quality decay potential is:

[0100]

[0101] in, This represents the cumulative quality decay potential up to the current moment. For the types of aquatic products involved, at the reference temperature The quality decay rate constant under the given conditions, The usual value is 273 Kelvin (i.e., 0 degrees Celsius). The activation energy for quality degradation of the aquatic product types involved is expressed in joules per mole; R is the ideal gas constant, taken as 8.314 joules per mole per Kelvin. For a moment The Kelvin temperature value of the environment in which the aquatic products are located is obtained by adding 273.15 to the Celsius temperature value; This is the initial quality correction factor, which is calculated based on the quality inspection parameters collected in step 4.

[0102] Initial quality correction factor The calculation formula is:

[0103]

[0104] in, The K-values ​​are reference values ​​for the aquatic product types under reference conditions. The reference values ​​for the volatile basic nitrogen content of the relevant aquatic product types under reference conditions are provided. The total bacterial count is a reference value for the types of aquatic products involved under reference conditions. Let be the weighting coefficient, satisfying Each weighting coefficient is preset based on the contribution of volatile basic nitrogen content, total bacterial count, and K value to the quality degradation rate of the aquatic product species involved. The initial quality correction factor reflects the deviation of the initial quality state of the aquatic product at the end of the processing stage from the reference state. A correction factor greater than 1 indicates poor initial quality, and the subsequent quality degradation rate will be accelerated accordingly.

[0105] For the actual collected discrete temperature data, the integral form of the calculation formula is converted into a discrete summation form:

[0106]

[0107] Where N is the total number of sampling periods from the start of processing to the current time. Let Kelvin be the temperature value in the j-th sampling period. This refers to the time length corresponding to the fixed sampling interval described in step 2. Through discrete accumulation, the cumulative quality decay potential can be accurately calculated based on the actually acquired temperature time series data.

[0108] The core technological significance of the cumulative quality decay potential lies in its ability to transform the temperature impact on aquatic products at every moment from the start of processing into a quality decay rate using the Arrhenius equation, and then integrate and accumulate this rate over time. This allows for a continuous, dynamic, and quantitative description of the degree of quality decay in aquatic products. Unlike existing technologies that simply judge based on whether the current temperature exceeds a threshold, the cumulative quality decay potential fully considers the cumulative effect of temperature history on quality.

[0109] Step 7: Calculate the real-time remaining shelf life of the seafood batch based on the cumulative quality decay potential.

[0110] Based on the cumulative quality decay potential calculated in step 6 Calculate the real-time remaining shelf life of this batch of aquatic products. The formula for calculating the real-time remaining shelf life is:

[0111]

[0112] in, The remaining shelf life as of the current moment, in hours; This is the critical value for the quality degradation potential of the aquatic product category. When the cumulative quality degradation potential reaches this critical value, the aquatic product is determined to be inedible or does not meet the sales standards. Based on the types of aquatic products involved and the reference temperature The standard shelf-life test data were obtained by calibration, specifically by placing freshly processed aquatic product samples at a reference temperature. During storage, key freshness indicators are measured daily until they exceed acceptable limits. The total storage time is recorded, and this total storage time is multiplied by the quality degradation rate constant. That is, get . This is the expected storage temperature value for this batch of aquatic products under subsequent standard storage conditions, in Kelvin.

[0113] Real-time remaining shelf life directly reflects the expected length of time that the batch of aquatic products can maintain acceptable quality under subsequent standard storage conditions. Since the cumulative quality decay potential has fully accounted for the cumulative impact of the entire temperature history experienced by the aquatic products from the processing stage to the present moment on quality, the real-time remaining shelf life calculated based on the cumulative quality decay potential can truly reflect the current quality status of aquatic products, and its accuracy is far higher than that of shelf life calculated solely based on a fixed production date.

[0114] Step 8: Calculate the intervention urgency for each batch of aquatic products and generate dynamic scheduling decisions.

[0115] At any given moment, obtain a batch list of all aquatic product batches currently in the cold chain distribution or sales stage. For each aquatic product batch in the batch list, retrieve the real-time remaining shelf life of that batch from the distributed ledger of the blockchain network. And the current geographical location information. Geographical location information can be obtained through the on-board positioning device of the cold chain transport vehicle or the inbound records of the warehouse management system.

[0116] For each batch of aquatic products, the intervention urgency is calculated. The formula for calculating intervention urgency is:

[0117]

[0118] in, The urgency of intervention for this batch of aquatic products; This represents the real-time remaining shelf life of this batch of aquatic products, in hours. For a less than The positive number is used to prevent abnormal values ​​where the denominator is zero when the real-time remaining shelf life approaches zero; d is the geographical distance between the current location of the aquatic product batch and the target sales terminal, in kilometers; The average speed of cold chain transport vehicles, expressed in kilometers per hour; This is the distance attenuation coefficient, with a value ranging from 0.1 to 0.5.

[0119] The formula for calculating the urgency of intervention has a clear technical meaning: the first item This reflects the urgency of the situation; the shorter the real-time remaining shelf life, the higher this value, indicating that the batch requires immediate intervention; the second item... This reflects the amplifying effect of spatial barriers on the urgency of intervention. The greater the distance and the longer the transportation time, the larger this value, indicating that for the same remaining shelf life, batches that are farther apart need to be intervened in advance. The two factors are combined through a product, allowing the intervention urgency to be comprehensively quantified into the relative intensity of the demand for scheduling resources for each batch.

[0120] All aquatic product batches are classified according to the urgency of intervention. The values ​​are sorted from largest to smallest to generate an intervention priority sequence. The intervention priority sequence clarifies the processing priority of each batch at the current moment.

[0121] Based on the intervention priority sequence, a dynamic scheduling decision is generated. The dynamic scheduling decision includes at least one of the following: for batches with an intervention urgency greater than a preset high intervention threshold, a priority delivery instruction is generated, which includes the batch identifier, current location, target sales terminal, and priority level; for batches with an intervention urgency between the preset high intervention threshold and the preset medium intervention threshold, a normal delivery instruction is generated; for batches with an intervention urgency less than the preset medium intervention threshold, a delayed delivery instruction is generated; and for batches with real-time remaining shelf life… For batches below the preset safety threshold, a price reduction promotion order or a return processing order will be generated. The specific values ​​of the high intervention threshold, medium intervention threshold, and safety threshold can be preset according to the company's operating strategy and product characteristics (for example, the high intervention threshold can be set to 0.030, the medium intervention threshold can be set to 0.010, and the safety threshold can be set to 24 hours).

[0122] The generated dynamic scheduling decisions are bound to the corresponding batch identifiers and written to the decision record smart contract on the blockchain network. Upon receiving the dynamic scheduling decision data, the decision record smart contract verifies the data source with a signature. Once verified, the decision data is written to the decision record area of ​​the distributed ledger. The decision records are immutably stored in the blockchain network, providing a basis for subsequent decision tracing and accountability.

[0123] Step 9: Generate a full supply chain quality traceability report.

[0124] In response to traceability query requests initiated by end users by scanning the traceability code on the outer packaging of aquatic products, the system retrieves all data associated with the batch identification code corresponding to the traceability code from the distributed ledger of the blockchain network. The traceability code is a graphic code generated by encoding and converting the batch identification code; scanning the traceability code allows the batch identification code to be obtained.

[0125] The data retrieved includes: batch metadata stored in step 1 (including aquatic product species name, number of seedlings, seedling specifications, and seedling source information); and dissolved oxygen concentration values ​​stored in step 2. Aquaculture water temperature value pH value ammonia nitrogen concentration value nitrite concentration value and the activity index of aquatic product groups Time series data; water quality suitability index calculated in step 3 Disease risk index Time series data; ambient temperature values ​​of the processing workshop stored in step 4. Time series data, duration of each processing step Volatile basic nitrogen content value Total bacterial count and K value Step 5: Store the cold chain environment temperature value. Time series data and relative humidity values ​​in cold chain environments Time series data; cumulative quality decay potential calculated in step 6 Step 7 calculates the real-time remaining shelf life. .

[0126] The time-series data of the aquaculture environment parameters and the water quality suitability index were statistically summarized to generate a quality overview of the aquaculture process. This quality overview includes the average, maximum, minimum, and standard deviation of dissolved oxygen concentration, aquaculture water temperature, pH, ammonia nitrogen concentration, nitrite concentration, and water quality suitability index over the aquaculture cycle.

[0127] The time-series data of the read cold chain environmental parameters are statistically summarized to generate a quality overview of the cold chain process. This quality overview includes cold chain environmental temperature values. The average, maximum, minimum, and standard deviation of the temperature, as well as the number and cumulative duration of temperature exceedance events. A temperature exceedance event is defined as a temperature value in the cold chain environment. An event that exceeds the preset upper limit of cold chain temperature for a duration exceeding the preset time tolerance. The upper limit of cold chain temperature is set according to the cold chain storage requirements of the type of aquatic product (e.g., -15.0 degrees Celsius for frozen aquatic products), and the time tolerance can be set to, for example, 30 minutes.

[0128] The data and statistical summaries collected above are organized into a full-chain quality traceability report according to the time sequence of the aquaculture, processing, cold chain distribution, and quality assessment results. The full-chain quality traceability report is structured as follows: Part 1: Basic product information, including batch identification code, aquatic product type name, seeding date, and harvest date; Part 2: Quality overview of the aquaculture stage, showing the changing trends of key indicators such as water quality suitability index during the aquaculture cycle in tabular or chart form; Part 3: Summary of quality inspection parameters in the processing stage, listing the test results of volatile basic nitrogen content, total bacterial count, and K value; Part 4: Quality overview of the cold chain distribution stage, showing the change curves and statistical indicators of cold chain environmental temperature values; Part 5: Current quality status, prominently displaying the real-time remaining shelf life value.

[0129] The entire supply chain quality traceability report is displayed on the end-user's query interface. End-users can not only obtain static traceability information such as the origin, variety, and date of aquatic products, but also intuitively understand the true quality history of the batch of aquatic products from farming to the present moment and the current remaining shelf life, realizing a deep leap from superficial traceability information to substantive quality information.

[0130] Through the coordinated implementation of steps 1 to 9 above, the method of this invention organically integrates data collection, quality assessment, decision-making scheduling, and traceability disclosure across all stages of the aquatic product industry chain into a closed-loop system. Water quality monitoring and early warning in the aquaculture stage ensure quality at the source; quality inspection parameters in the processing stage provide an initial benchmark for subsequent quality degradation calculations; continuous temperature monitoring in the cold chain provides data support for calculating the cumulative quality degradation potential; the cumulative quality degradation potential and real-time remaining shelf life provide a scientific basis for dynamic scheduling decisions; dynamic scheduling decisions guide the optimal allocation of distribution resources; and the final traceability report presents the key information from each stage to end users. The data flow and logical progression between each step collectively achieve intelligent management of the entire aquatic product industry chain.

[0131] Example 1

[0132] This embodiment uses the entire supply chain management process of Litopenaeus vannamei, from farming, processing, cold chain transportation to sales, as an example to illustrate the complete implementation process of the method of the present invention. All data involved in this embodiment are exemplary data collected in a real production environment or reasonably configured, used to demonstrate the feasibility and technical effects of the technical solution.

[0133] Step 1: Establish digital identity identification for aquatic product batches across the entire industry chain.

[0134] When establishing a Litopenaeus vannamei farming batch, a unique batch identification code is generated for that batch. The farming entity code is "320501", representing a farming enterprise in Suzhou City, Jiangsu Province; the farming water body code is "P008", representing the 8th farming pond of that enterprise; the stocking date is "20240315", representing stocking on March 15, 2024; the aquatic product type code is "V001", representing Litopenaeus vannamei; and the batch serial number is "0023", representing the 23rd farming batch of that year. By concatenating the above codes in the format "farming entity code - farming water body code - stocking date - aquatic product type code - batch serial number", the complete batch identification code is "320501-P008-20240315-V001-0023".

[0135] The system invokes a smart contract for identifier registration already deployed in the blockchain network. The contract address of this smart contract is 0x7A2B3C4D5E6F7A8B9C0D1E2F3A4B5C6D7E8F9A0B. The identifier registration smart contract receives the batch identifier code "320501-P008-20240315-V001-0023" and batch metadata as input parameters. The batch metadata includes: the aquatic product type name is "Litopenaeus vannamei," the stocking quantity is "50,000," the stocking specification is "body length 1.2 cm," and the stocking source information is "SPF shrimp larvae from a certain hatchery in Hainan." The identifier registration smart contract first validates the format of the batch identifier code. The validation rules are: each field length must conform to the requirements of 6, 4, 8, 4, and 4 digits, fields must be connected by hyphens, and the content of each field must be numeric. After successful verification, the identifier registration smart contract uses the batch identifier code as the key and the batch metadata as the value to form a key-value pair, which is then written to the batch registration area of ​​the distributed ledger. Upon successful writing, the identifier registration smart contract returns the transaction hash value 0x8F3A2B1C6D5E4F7A9B8C0D1E2F3A4B5C6D7E8F9A0B1C2D3E4F5A6B7C8D9E0F as a storage credential.

[0136] A digital identity public-private key pair is assigned to this Litopenaeus vannamei farming batch. The public key is a 256-character hexadecimal string, and the private key is a 512-character hexadecimal string. After the public key is bound to the batch identifier "320501-P008-20240315-V001-0023", it is written to the batch status storage area through the batch status update interface of the identifier-registered smart contract. The private key is stored as an encrypted file by the farming entity in an offline hardware encryption device. In all subsequent stages, before any data is written to the blockchain network, a digital signature must be generated using this private key according to the elliptic curve digital signature algorithm. The data recipient queries the corresponding public key from the blockchain network using the batch identifier and uses this public key to verify the legality of the digital signature.

[0137] Step 2: Collect aquaculture environment parameters and aquatic product growth parameters during the aquaculture stage.

[0138] In aquaculture pond numbered P008, a multi-parameter water quality sensor array was deployed at three different depths: 0.5 meters, 1.2 meters, and 1.8 meters. Each array included one dissolved oxygen sensor, one temperature sensor, one pH sensor, one ammonia nitrogen concentration sensor, and one nitrite concentration sensor. All sensors were set to a fixed sampling interval of 15 minutes, resulting in 96 data sets collected daily.

[0139] Dissolved oxygen sensors collect dissolved oxygen concentration values ​​in aquaculture water, measured in milligrams per liter (mg / L), denoted as . , where t represents the sampling time. At 8:00 AM on April 10, 2024, the dissolved oxygen concentration collected by the dissolved oxygen sensor at a water depth of 1.2 meters was 6.8 mg / L.

[0140] Temperature sensors collect water temperature values ​​in aquaculture, expressed in degrees Celsius, and denoted as . The temperature of the aquaculture water sampled at the same depth at the same time was 25.3 degrees Celsius.

[0141] pH sensors collect the pH value of aquaculture water, which is dimensionless and denoted as . The pH value collected at the same time and depth was 7.8.

[0142] The ammonia nitrogen concentration sensor collects the ammonia nitrogen concentration value in the aquaculture water, in milligrams per liter, denoted as . The ammonia nitrogen concentration collected at the same time and depth was 0.25 mg / L.

[0143] The nitrite concentration sensor collects the nitrite concentration value in the aquaculture water, in milligrams per liter, denoted as . The nitrite concentration collected at the same time and depth was 0.03 mg / L.

[0144] A camera device was deployed 3.5 meters directly above the aquaculture pond, covering 85% of the pond's surface area. The camera's sampling interval was strictly synchronized with the sampling interval of the multi-parameter water quality sensor array, both being 15 minutes. Feeding was conducted twice daily, at 8:30 AM and 4:30 PM. After each feeding, the camera continuously captured a sequence of 40 frames of images depicting feeding behavior from the 5th to the 15th minute following feeding.

[0145] The specific process of target detection and motion analysis for the feeding behavior image sequence is as follows: First, a shrimp detection model based on a deep convolutional neural network is used to identify and locate individual Litopenaeus vannamei in each frame of the image, obtaining the bounding box coordinates of each Litopenaeus vannamei in the image coordinate system. Then, the displacement vector of the same Litopenaeus vannamei individual between two adjacent frames is calculated using the optical flow method. This displacement vector is divided by the time interval between the two frames to obtain the velocity vector of that Litopenaeus vannamei individual. The velocity vectors of all Litopenaeus vannamei individuals in each image frame of the feeding behavior image sequence are extracted during the 5th to 15th minute after feeding, and the mean magnitude of the velocity vectors of all Litopenaeus vannamei individuals during this time period is calculated. After feeding on the morning of April 10, 2024, the calculated activity index of the Litopenaeus vannamei group was 0.78 meters per minute, denoted as... .

[0146] Dissolved oxygen concentration values ​​collected throughout the day on April 10, 2024 96 data points, aquaculture water temperature values 96 data points, pH value 96 data points, ammonia nitrogen concentration values 96 data points, nitrite concentration values 96 data points and Litopenaeus vannamei population activity index Both data points are bound to the batch identifier "320501-P008-20240315-V001-0023". The private key described in step 1 is used to digitally sign the data in JSON format. The signed data is then transmitted via a 4G wireless communication network to the data storage smart contract on the blockchain network. The contract address of the data storage smart contract is 0x1A2B3C4D5E6F7A8B9C0D1E2F3A4B5C6D7E8F9A0B. After receiving the signed data, the data storage smart contract retrieves the public key bound to the batch identifier from the blockchain network and verifies the legality of the digital signature. Upon successful verification, the data storage smart contract writes the data to the data storage area of ​​the distributed ledger, indexed by the batch identifier.

[0147] Step 3: Calculate the water quality suitability index and disease risk index for the aquaculture stage based on aquaculture environment parameters.

[0148] Based on the time-series data of aquaculture environmental parameters collected in step 2, the water quality suitability index of the aquaculture water body is calculated at each time point. For Litopenaeus vannamei, the preset values ​​for each parameter are as follows: minimum tolerable dissolved oxygen concentration. The upper limit of the reference range for dissolved oxygen concentration is 3.5 mg / L. It is 8.0 mg / L; optimal pH value It is 7.8; pH tolerance range is wide. The maximum tolerable concentration of ammonia nitrogen is 2.4 (corresponding to a pH tolerance range of 6.6 to 9.0). The maximum tolerable concentration of nitrite is 0.8 mg / L. The concentration was 0.2 mg / L. Litopenaeus vannamei is highly sensitive to dissolved oxygen and ammonia nitrogen, followed by pH and nitrite; therefore, a weighting factor was pre-set. , , , ,satisfy .

[0149] Taking the data at 8:00 AM on April 10, 2024 as an example, the water quality suitability index... The calculation process is as follows:

[0150]

[0151] Water quality suitability index The value ranges from 0 to 1, with a value closer to 1 indicating more suitable water quality for Litopenaeus vannamei growth. A value of 0.7905 indicates good water quality.

[0152] Disease Risk Index In the calculation formula, the optimal growth temperature for Litopenaeus vannamei is... 28.0 degrees Celsius; wide temperature tolerance range The minimum temperature is 12.0 degrees Celsius (corresponding to a temperature tolerance range of 22.0 degrees Celsius to 34.0 degrees Celsius); the contribution coefficient of temperature deviation to disease risk. The preset value is 0.45, representing the contribution coefficient of water quality suitability to disease risk. The default value is 0.55. The calculation process for the disease risk index is as follows:

[0153]

[0154] Due to disease risk index The value of should be between 0 and 1, with negative values ​​taken as 0. Therefore, the disease risk index at 8:00 AM on April 10, 2024 is 0, indicating an extremely low disease risk.

[0155] The calculated water quality suitability index The water quality suitability warning threshold is compared with a preset threshold. In this embodiment, the preset water quality suitability warning threshold is 0.60. When When the value falls below 0.60, an abnormal aquaculture environment warning is generated. (April 10, 2024, all day) The values ​​were all above 0.60, therefore no abnormal aquaculture environment warning was triggered.

[0156] The calculated disease risk index The risk is compared with a preset disease risk warning threshold. In this embodiment, the preset disease risk warning threshold is 0.50. When When the value is above 0.50, a disease risk warning is generated. (April 10, 2024, all day) The values ​​were all 0, therefore no disease risk warning was triggered.

[0157] On the night of May 12, 2024, due to continuous rainy weather, the dissolved oxygen concentration in the pond decreased. At 3:00 AM, the dissolved oxygen concentration at a water depth of 0.5 meters dropped to 3.2 mg / L, the ammonia nitrogen concentration rose to 0.52 mg / L, and the pH value dropped to 7.0. The water quality suitability index at that moment was calculated. The dissolved oxygen concentration (DOC) was 0.47, lower than the water quality suitability warning threshold of 0.60. The system immediately generated an abnormal aquaculture environment warning, with the following information: "Warning type: Abnormal aquaculture environment; Warning time: 2024-05-12 03:00; Batch identification code: 320501-P008-20240315-V001-0023; Dissolved oxygen concentration: 3.2 mg / L; Ammonia nitrogen concentration: 0.52 mg / L; Water quality suitability index: 0.47." Upon receiving the warning, the aquaculture management personnel immediately activated the aeration equipment. After 30 minutes, the dissolved oxygen concentration recovered to above 5.0 mg / L, and the water quality suitability index rose to 0.68, preventing losses of Litopenaeus vannamei shrimp due to low oxygen levels.

[0158] Step 4: Collect processing parameters and quality inspection parameters for the processing stage.

[0159] On June 10, 2024, this batch of farmed Litopenaeus vannamei shrimp completed its farming cycle and was harvested and entered the processing stage. Harvesting began at 6:00 AM that day, and processing began at 7:30 AM. The start time of processing is recorded as follows:

[0160]

[0161] Temperature sensors were deployed at five different locations within the processing workshop. These five sensors synchronously collected ambient temperature values ​​at a fixed sampling interval of 15 minutes, as described in step 2. The arithmetic mean of the temperature values ​​collected by the five sensors at the same time was taken as the ambient temperature value of the processing workshop at that moment, expressed in degrees Celsius. During the processing period from 7:30 a.m. to 2:30 p.m. on June 10, 2024, the average ambient temperature in the processing workshop was 18.5 degrees Celsius, the highest was 20.2 degrees Celsius, and the lowest was 16.8 degrees Celsius.

[0162] The processing steps for this batch are as follows: Step 1 is cleaning and sorting, lasting 25 minutes; Step 2 is head and shell removal, lasting 40 minutes; Step 3 is grading and arranging, lasting 30 minutes; Step 4 is quick-freezing, lasting 15 minutes; and Step 5 is ice-coating and packaging, lasting 20 minutes. The duration of each processing step is recorded in minutes by timing devices deployed on each processing equipment.

[0163]

[0164] At the quality inspection stage after the quick-freezing process, randomly selected samples of processed Litopenaeus vannamei shrimp are subjected to quality inspection. The quality inspection parameters include the following three items:

[0165] Volatile basic nitrogen content: 10.00 g of Litopenaeus vannamei sample was weighed and determined according to the semi-micro nitrogen determination method in GB 5009.228-2016 "National Food Safety Standard - Determination of Volatile Basic Nitrogen in Food". The measured volatile basic nitrogen content was 12.5 mg / 100 g, recorded as follows: .

[0166] Total bacterial count: Weigh 25.00 g of Litopenaeus vannamei sample and perform the test according to GB 4789.2-2022 "National Food Safety Standard - Microbiological Examination of Food - Determination of Total Bacterial Count". Count the colonies after incubation at 36°C ± 1°C for 48 hours ± 2 hours. The measured total bacterial count value is... Colony forming units per gram, specifically 32,000 colony forming units per gram, is denoted as... .

[0167] K-value: 5.00 g of Litopenaeus vannamei sample was weighed, and the molar concentrations of adenosine triphosphate (ATP) and its decomposition products, inosine, adenosine monophosphate (ATP), and adenosine diphosphate (ATP) were determined by high-performance liquid chromatography (HPLC). The K-value is defined as the ratio of the sum of the molar concentrations of inosine and ATP to the total molar concentration of ATP and its decomposition products. The calculation formula is as follows:

[0168]

[0169] in This refers to the molar concentration of hypoxanthine. This refers to the molar concentration of inosine. This refers to the molar concentration of adenosine triphosphate (ATP). This refers to the molar concentration of adenosine diphosphate. This refers to the molar concentration of adenosine monophosphate. This represents the molar concentration of the breakdown products of adenosine monophosphate (ATP). The measured K value is 8.7%, dimensionless, and denoted as [K value missing]. .

[0170] Processing start time Ambient temperature value of the processing workshop The duration of 29 data points and 5 processing steps to Volatile basic nitrogen content value Total bacterial count and K value The data is bound to the batch identifier "320501-P008-20240315-V001-0023". The private key described in step 1 is used to digitally sign the data. The signed data is then transmitted via a wireless communication network to the data storage smart contract on the blockchain network. After verifying the signature, the data storage smart contract writes the data to the data storage area of ​​the distributed ledger.

[0171] Step 5: Collect cold chain environmental parameters during the cold chain distribution process.

[0172] At 3:00 PM on June 10, 2024, the processed and packaged Litopenaeus vannamei shrimp products were loaded into refrigerated transport vehicles, officially commencing the cold chain logistics process. The start time of the cold chain logistics process is recorded as follows:

[0173]

[0174] One cold chain environmental parameter acquisition device is deployed at the front, middle, and rear of the refrigerated compartment of the cold chain transport vehicle. Each device includes one temperature sensor and one humidity sensor. The sampling interval for all three devices is set to a fixed 15-minute interval as described in step 2. The arithmetic mean of the temperature values ​​collected by the three temperature sensors at the same time is taken as the cold chain environmental temperature value at that moment, expressed in degrees Celsius. The arithmetic mean of the relative humidity values ​​collected by three humidity sensors at the same time is taken as the relative humidity value of the cold chain environment at that time, expressed as a percentage. .

[0175] The cold chain transport vehicle departed from Suzhou City, Jiangsu Province, with its destination being the distribution center of a large supermarket in Beijing. The total distance traveled was approximately 1150 kilometers, and the estimated travel time was 16 hours. The cold chain transport vehicle arrived at the destination distribution center at 7:00 AM on June 11, 2024. The end time of the cold chain circulation process is recorded as [date missing].

[0176]

[0177] Over the entire 16-hour cold chain process, temperature sensors collected 64 temperature data points, and humidity sensors collected 64 humidity data points. Statistics show that the overall cold chain environmental temperature values... The average value was -18.2 degrees Celsius, the maximum value was -15.5 degrees Celsius, the minimum value was -19.8 degrees Celsius, and the standard deviation was 0.9 degrees Celsius. The relative humidity value for the entire cold chain environment... The average value is 82%, the maximum value is 88%, and the minimum value is 76%.

[0178] The data includes 64 temperature data points, 64 humidity data points, and the start time of the cold chain circulation process. and termination time It is bound to the batch identifier "320501-P008-20240315-V001-0023". After digitally signing using the private key described in step 1, it is transmitted to the data storage smart contract of the blockchain network through a wireless communication network. After verifying the signature, the data storage smart contract writes the data into the data storage area of ​​the distributed ledger.

[0179] Step 6: Calculate the cumulative quality decay potential of the aquatic product batch.

[0180] After the Litopenaeus vannamei shrimp products arrived at the Beijing distribution center, at 7:00 AM on June 11, 2024 (the end of the cold chain distribution process), the cumulative quality degradation potential of this batch was calculated. The current time is the end of the cold chain distribution process.

[0181]

[0182] Construct a complete temperature history curve The ambient temperature value of the processing workshop 29 data points and cold chain environment temperature values The 64 data points were concatenated sequentially. The time range for the processing workshop ambient temperature data points is from 7:30 AM to 2:30 PM on June 10, 2024, while the time range for the cold chain ambient temperature data points is from 3:00 PM on June 10, 2024 to 7:00 AM on June 11, 2024. There is no time overlap between the two time series, and the concatenated data forms a sequence starting from the beginning of processing. Up to the current moment Complete temperature history curve , The range of values ​​is .

[0183] The kinetic parameters of quality degradation in Litopenaeus vannamei were obtained through previous experimental calibration. Reference temperature. 273 Kelvin (0 degrees Celsius) was used. Litopenaeus vannamei samples were subjected to constant-temperature storage experiments at 0 degrees Celsius. The K value was measured periodically, and the curve of K value versus storage time was fitted to obtain the quality degradation rate constant of Litopenaeus vannamei under 0 degrees Celsius conditions. The value is 0.0085 per hour. By determining the linear relationship between the logarithm of the rate of quality decay in Litopenaeus vannamei under different temperature conditions and the reciprocal of the temperature, the activation energy for quality decay in Litopenaeus vannamei was obtained by multiplying the negative of the slope of the Arrhenius equation by the ideal gas constant R. It is 78,000 joules per mole. The ideal gas constant R is taken as 8.314 joules per mole per Kelvin.

[0184] Initial quality correction factor In the calculation, the K value of Litopenaeus vannamei under reference conditions is a reference value. The reference value for volatile basic nitrogen content is 5.0%. The reference value is 10.0 mg per 100g; total bacterial count. The value is 10,000 colony-forming units per gram. Based on the quality degradation pattern of Litopenaeus vannamei, the K value contributes most significantly to the rate of quality degradation, followed by volatile basic nitrogen content, while the total colony count is relatively small. Therefore, a weighting coefficient was preset. , , The measurements obtained in step 4 , , Substitute into the calculation formula:

[0185]

[0186] An initial quality correction factor greater than 1 indicates that the initial quality of this batch of Litopenaeus vannamei shrimp was slightly worse than the reference quality at the time of processing, and its subsequent quality degradation rate will be accelerated accordingly.

[0187] Since the collected temperature data is a discrete time series, the cumulative quality decay potential is... The calculation uses a discrete accumulation method. There are a total of 93 sampling periods from the start of processing to the current time, and the duration of each sampling period is... The time is 0.25 hours. The Kelvin temperature value for the j-th sampling period. It is obtained by adding 273.15 to the Celsius temperature value corresponding to the sampling period.

[0188] Taking the first sampling period as an example, the corresponding time for this period is from 7:30 AM to 7:45 AM on June 10, 2024, and the ambient temperature value in the processing workshop is... It is 17.2 degrees Celsius, which can be converted to Kelvin. Kelvin. The temperature acceleration factor for this cycle is calculated as:

[0189]

[0190] The contribution of quality degradation in this cycle is:

[0191]

[0192] The contribution of quality degradation was calculated and accumulated for each of the 93 sampling periods to obtain the cumulative quality degradation potential up to the end of the cold chain circulation process. .

[0193] Step 7: Calculate the real-time remaining shelf life of the seafood batch based on the cumulative quality decay potential.

[0194] Critical value of quality degradation potential of Litopenaeus vannamei Standard shelf-life calibration was performed using a standard shelf-life experiment. The specific calibration method was as follows: Freshly processed Litopenaeus vannamei samples were stored at 0 degrees Celsius, and the K value was measured daily until it reached 60%. The number of storage days at this point was multiplied by 24 to convert to hours, and then multiplied by... ,get Experiments have shown that the standard shelf life of Litopenaeus vannamei at 0 degrees Celsius is 360 hours. .

[0195] After arriving at the distribution center, this batch of Litopenaeus vannamei shrimp will be transferred to a -18°C cold storage facility for standard storage. The expected storage temperature under standard storage conditions will be as follows. The temperature is -18 degrees Celsius, which is equivalent to 255.15 Kelvin.

[0196] Calculate real-time remaining shelf life :

[0197] First, calculate the temperature acceleration factor under standard storage conditions:

[0198]

[0199] Then substitute the formula for calculating the remaining shelf life:

[0200]

[0201] The current shelf life of this batch of Litopenaeus vannamei shrimp is 146.9 hours, or approximately 6.1 days.

[0202] In contrast, if the existing fixed shelf-life labeling method were used, the shelf life marked on the packaging of this batch of products would be "12 months at -18 degrees Celsius". Based on this fixed shelf life, the product's remaining shelf life, calculated from the production date of June 10, 2024, to June 11, 2024, would be approximately 364 days. This fixed shelf life completely fails to reflect the true impact of actual temperature fluctuations during processing and cold chain transportation on product quality, providing severely distorted information about the remaining shelf life.

[0203] Step 8: Calculate the intervention urgency for each batch of aquatic products and generate dynamic scheduling decisions.

[0204] At 8:00 AM on June 11, 2024, the distribution center management personnel used the management method of this invention to query the batch list of all Litopenaeus vannamei batches currently in the cold chain distribution or sales process. At this time, the distribution center had a total of 4 Litopenaeus vannamei batches in stock, and the key parameters of each batch are shown in Table 1.

[0205] Table 1. Batch Parameters of Litopenaeus vannamei Shrimp at the Distribution Center

[0206] Batch Identification Code Current location Target sales terminals Distance d (km) Real-time remaining shelf life 320501-P008-20240315-V001-0023 Beijing Distribution Center A supermarket in Chaoyang District, Beijing 18 146.9 320501-P012-20240322-V001-0035 Beijing Distribution Center A supermarket in Tianjin 125 85.3 320501-P005-20240310-V001-0018 Beijing Distribution Center A supermarket in Shijiazhuang 280 210.5 320501-P015-20240328-V001-0042 Beijing Distribution Center A supermarket in Haidian District, Beijing 25 32.8

[0207] In the formula for calculating the urgency of intervention, Pick Average speed of cold chain transport vehicles Take 60 km / h; distance attenuation coefficient The preset value is 0.25 based on the characteristics of urban delivery road conditions.

[0208] Taking batch "320501-P008-20240315-V001-0023" as an example, the calculation process for its intervention urgency is as follows:

[0209]

[0210] The urgency of intervention for the remaining three batches was calculated as follows:

[0211] Batch "320501-P012-20240322-V001-0035":

[0212]

[0213] Batch "320501-P005-20240310-V001-0018":

[0214]

[0215] Batch "320501-P015-20240328-V001-0042":

[0216]

[0217] The four batches were categorized according to the urgency of intervention. The values ​​are sorted from largest to smallest to generate the intervention priority sequence as follows:

[0218] 1. First priority: Batch "320501-P015-20240328-V001-0042", intervention urgency 0.03384;

[0219] 2. Second priority: Batch "320501-P012-20240322-V001-0035", intervention urgency 0.01973;

[0220] 3. Third priority: Batch "320501-P005-20240310-V001-0018", intervention urgency 0.01525;

[0221] 4. Fourth priority: Batch "320501-P008-20240315-V001-0023", intervention urgency 0.00734.

[0222] In this embodiment, the preset high intervention threshold is 0.030, and the medium intervention threshold is 0.010. Based on the intervention priority sequence and the intervention urgency value of each batch, the dynamic scheduling decision is generated as follows:

[0223] For batch "320501-P015-20240328-V001-0042", its intervention urgency (0.03384) is greater than the high intervention threshold (0.030), and its real-time remaining shelf life (32.8 hours) is greater than the preset safety threshold (24 hours). Therefore, a priority delivery instruction is generated. The instruction content is: "Batch Identifier: 320501-P015-20240328-V001-0042; Current Location: Beijing Distribution Center; Target Sales Terminal: A supermarket in Haidian District, Beijing; Priority Level: Level 1 Priority Delivery; Suggested Delivery Departure Time: Immediate."

[0224] For batch "320501-P012-20240322-V001-0035", its intervention urgency of 0.01973 is between the high intervention threshold of 0.030 and the medium intervention threshold of 0.010, and a normal delivery instruction is generated.

[0225] For batch "320501-P005-20240310-V001-0018", its intervention urgency of 0.01525 is between the high intervention threshold of 0.030 and the medium intervention threshold of 0.010, and a normal delivery instruction is generated.

[0226] For batch "320501-P008-20240315-V001-0023", its intervention urgency of 0.00734 is less than the medium intervention threshold of 0.010, so a temporary delivery delay instruction is generated.

[0227] The four dynamic scheduling decisions mentioned above are bound to their corresponding batch identifiers and then written into the decision record smart contract on the blockchain network. The contract address of the decision record smart contract is 0x9A8B7C6D5E4F3A2B1C0D9E8F7A6B5C4D3E2F1A0B. After receiving the scheduling decision data, the contract verifies the signature of the data source. Once the verification is successful, the decision data is written into the decision record area of ​​the distributed ledger.

[0228] Step 9: Generate a full supply chain quality traceability report.

[0229] On June 12, 2024, a consumer in Chaoyang District, Beijing, purchased a package of Litopenaeus vannamei shrimp at a supermarket. The product packaging had a traceability code printed on it, which was a QR code image converted from the batch identification code "320501-P008-20240315-V001-0023". The consumer used a smartphone to scan the traceability code to initiate a traceability query request.

[0230] The system responded to the traceability query request and retrieved all data associated with the batch identifier "320501-P008-20240315-V001-0023" from the distributed ledger of the blockchain network. The retrieved data includes:

[0231] Batch metadata: The aquatic product species name is "Litopenaeus vannamei", the number of seedlings is "50,000", the seedling size is "body length 1.2 cm", and the seedling source information is "SPF shrimp seedlings from a certain hatchery in Hainan".

[0232] Time series data of aquaculture environmental parameters: dissolved oxygen concentration values 5760 data points, aquaculture water temperature values 5760 data points, pH value 5760 data points, ammonia nitrogen concentration values 5760 data points, nitrite concentration values The group activity index is based on 5760 data points. 120 data points.

[0233] Water quality suitability index 5760 data points, disease risk index 5760 data points.

[0234] Processing parameters and quality inspection parameters: ambient temperature of the processing workshop The 29 data points and the durations of the 5 processing steps were 25, 40, 30, 15, and 20 minutes, respectively. mg per 100g Colony forming units per gram, .

[0235] Time series data of cold chain environmental parameters: cold chain environmental temperature values The 64 data points represent the relative humidity values ​​in the cold chain environment. 64 data points.

[0236] Cumulative quality degradation potential Real-time remaining shelf life Hour.

[0237] Statistical analysis was conducted on time-series data of aquaculture environmental parameters to generate a quality overview of the aquaculture process. The results showed that the average dissolved oxygen concentration during the aquaculture cycle was 6.5 mg / L, the maximum was 7.8 mg / L, the minimum was 3.2 mg / L, and the standard deviation was 0.8 mg / L; the average aquaculture water temperature during the aquaculture cycle was 26.3°C, the maximum was 31.5°C, the minimum was 22.1°C, and the standard deviation was 2.1°C; the water quality suitability index... The average value during the breeding cycle was 0.78, the maximum value was 0.91, the minimum value was 0.47, and the standard deviation was 0.09.

[0238] Statistical analysis and summarization of time-series data on cold chain environmental parameters were performed to generate a quality overview of the cold chain process. The statistical results show: cold chain environmental temperature values... The average temperature was -18.2 degrees Celsius, the maximum was -15.5 degrees Celsius, the minimum was -19.8 degrees Celsius, and the standard deviation was 0.9 degrees Celsius. The threshold for a temperature exceeding the threshold event was set at -15.0 degrees Celsius, and an event was counted as exceeding the threshold event if the temperature lasted for more than 30 minutes. Testing showed that no temperature exceeding the threshold events occurred during the entire 16-hour cold chain process.

[0239] The data and statistical summaries collected above are organized into a full-chain quality traceability report according to the time sequence of the aquaculture, processing, cold chain distribution, and quality assessment results. The report structure is as follows: Part 1: Basic product information (batch identification code, aquatic product type, stocking date, harvest date, etc.); Part 2: Quality overview of the aquaculture stage (showing the trend of water quality suitability index changes during the aquaculture cycle in the form of tables and line graphs); Part 3: Quality inspection parameters of the processing stage (listing the test results of volatile basic nitrogen content, total bacterial count, and K value, and comparing them with reference values); Part 4: Quality overview of the cold chain distribution stage (showing the change curve of cold chain environmental temperature values ​​and statistical indicators); Part 5: Current quality status (prominently displaying the real-time remaining shelf life of 146.9 hours, approximately 6.1 days). The full-chain quality traceability report is then displayed on the consumer's smartphone query interface.

[0240] Comparative Example

[0241] To verify the technical effect of the present invention, the traditional cold chain management method based on fixed shelf life and static temperature threshold in the prior art was used as a comparative example to manage the same batch of Litopenaeus vannamei products in this embodiment.

[0242] The specific method for comparison is as follows: A fixed shelf-life label is printed on the packaging of Litopenaeus vannamei products, with a shelf life of 12 months and a production date of June 10, 2024. During cold chain transportation, a thermometer with temperature recording function is used to record the temperature of the transport compartment. The temperature data is not linked to any decision-making system and is only used for post-transaction traceability. When the products arrive at the distribution center, management personnel arrange the delivery order according to the "first-in, first-out" principle, without dynamic scheduling based on the actual quality status of the products.

[0243] In this comparative example, after this batch of Litopenaeus vannamei products arrived at the distribution center, its remaining shelf life was determined to be 364 days due to the fixed shelf life of 12 months. At the distribution center, this batch was scheduled for delivery third out of four batches according to the "first-in, first-out" principle, with the actual delivery time being the afternoon of June 12, 2024. However, after adopting the method of this invention, this batch, due to its lower urgency of intervention, was reasonably arranged for delayed delivery, and priority delivery resources were allocated to the batch "320501-P015-20240328-V001-0042" with a higher urgency of intervention.

[0244] To quantify and compare the technical effectiveness of the two methods, the following three evaluation metrics were selected:

[0245] 1. Accuracy of quality early warning: The standard is whether the product can provide early warning of quality deterioration in the actual circulation process. Early warning that can be given more than 12 hours in advance is called "accurate warning". Early warning that is given only after the quality has deteriorated significantly is called "delayed warning". No warning is called "no warning".

[0246] 2. Shelf life prediction error: This is measured by the deviation between the real-time remaining shelf life calculated using the method of this invention and the actual number of days available for sale. The actual number of days available for sale is determined through a combination of sensory evaluation and microbiological testing after the product arrives at the point of sale.

[0247] 3. Distribution resource utilization efficiency: Measured by the number of batches with the highest urgency of intervention to be delivered by the distribution center within 24 hours.

[0248] The results of comparing the technical effects of the method of the present invention with those of the comparative method are shown in Table 2.

[0249] Table 2 Comparison of the technical effects of the method of the present invention and the comparative method.

[0250] Evaluation indicators Method of the present invention Comparative method (fixed shelf life + first-in, first-out) Accuracy of quality early warning Accurate early warning. An early warning is issued when the water quality suitability index falls below 0.60 during the aquaculture stage. In the cold chain stage, the remaining shelf life is dynamically updated in real time, and when consumers scan the code, the actual remaining shelf life of 6.1 days is displayed. No warning. The fixed shelf life display shows 364 days remaining, which cannot reflect the actual quality deterioration, and consumers cannot know the true freshness of the product. Shelf life prediction error The error is less than 5%. The product arrived at the sales terminal on June 12, 2024. After sensory evaluation and microbiological testing, the actual number of days it could be sold was 6.5 days, which is 0.4 days less than the predicted 6.1 days. The error is enormous. The fixed shelf life is displayed as 364 days, which differs from the actual salable days of 6.5 days by approximately 357.5 days, resulting in an error rate as high as 5500%. Distribution resource utilization efficiency Highly efficient. Complete the highest-urgency intervention batches within 24 hours. Prioritized delivery avoided potential quality deterioration and loss of this batch due to its short remaining shelf life. Inefficient. The batch with the highest urgency for intervention was ranked second in the "first-in, first-out" sequence and was not prioritized for delivery. Delivery delays may result in insufficient remaining shelf life of the batch at the point of sale.

[0251] As shown in Table 2, the method of this invention significantly outperforms the comparative method in three aspects: accuracy of quality early warning, shelf-life prediction error, and efficiency of distribution resource utilization. This invention achieves precise quantification and early warning of aquatic product quality status by constructing a data collection network spanning the entire industry chain and a dynamic quality assessment system based on cumulative quality decay potential; it also achieves precise matching of distribution resources with actual product quality requirements through a dynamic scheduling decision-making mechanism based on intervention urgency. The realization of these technical effects depends on the synergistic effect of all the technical features described in steps 1 to 9; the absence of any one link will lead to a significant decrease in the overall technical effect.

[0252] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details have been described in detail in the preferred embodiments above; however, those skilled in the art will fully understand the invention even without these detailed descriptions. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits have not been described in detail.

[0253] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An intelligent management platform and data processing method for the entire aquatic product industry chain, characterized in that, Includes the following steps: Step 1: Generate a batch identification code for the aquaculture batch, which includes the aquaculture entity code, aquaculture water body code, seeding date, aquatic product type code, and batch serial number. Store the batch identification code in the distributed ledger of the blockchain network and assign a digital identity public-private key pair to the aquaculture batch. Step 2: Collect dissolved oxygen concentration, aquaculture water temperature, pH, ammonia nitrogen concentration, and nitrite concentration values ​​using a multi-parameter water quality sensor array deployed in the aquaculture water body. Collect the aquatic product population activity index using a camera device deployed above the aquaculture water body. After binding the collected dissolved oxygen concentration, aquaculture water temperature, pH, ammonia nitrogen concentration, nitrite concentration, and aquatic product population activity index with the batch identification code, write them into the distributed ledger of the blockchain network through digital signature. Step 3: Calculate the water quality suitability index and disease risk index based on the dissolved oxygen concentration, aquaculture water temperature, pH value, ammonia nitrogen concentration, and nitrite concentration. Step 4: Collect the ambient temperature value of the processing workshop, the duration of each processing step, the volatile basic nitrogen content value, the total bacterial count value, and the K value of the processing workshop. After binding the ambient temperature value of the processing workshop, the duration of each processing step, the volatile basic nitrogen content value, the total bacterial count value, and the K value with the batch identification code, write them into the distributed ledger of the blockchain network through digital signature. Step 5: Collect the cold chain environment temperature and relative humidity values ​​in the cold chain circulation process, bind the cold chain environment temperature and relative humidity values ​​with the batch identification code, and then write them into the distributed ledger of the blockchain network through digital signature. Step 6: Construct a complete temperature history curve from the start of processing to the current time based on the ambient temperature values ​​of the processing workshop and the cold chain environment. Calculate the cumulative quality degradation potential based on the complete temperature history curve, the volatile basic nitrogen content, the total bacterial count, and the K value. Step 7: Calculate the real-time remaining shelf life of the aquatic product batch based on the cumulative quality decay potential; Step 8: Calculate the intervention urgency based on the real-time remaining shelf life of each batch of aquatic products and the geographical distance between the current location and the target sales terminal. Sort the intervention urgency from largest to smallest to generate an intervention priority sequence and generate dynamic scheduling decisions accordingly. Step 9: Respond to the traceability query request, read all data associated with the batch identifier from the distributed ledger of the blockchain network, and generate a full-chain quality traceability report including the real-time remaining shelf life.

2. The intelligent management platform and data processing method for the entire aquatic product industry chain according to claim 1, characterized in that, The batch identification code in step 1 is encoded in the following format: the aquaculture entity code is 6 digits, the aquaculture water body code is 4 digits, the seeding date is 8 digits, the aquatic product type code is 4 digits, and the batch serial number is 4 digits. The aquaculture entity code, aquaculture water body code, seeding date, aquatic product type code, and batch serial number are connected by hyphens. The specific process of storing the batch identification code in the distributed ledger of the blockchain network is as follows: the identification registration smart contract in the blockchain network is called. The identification registration smart contract receives the batch identification code and batch metadata as input parameters. The batch metadata includes the aquatic product type name, seedling quantity, seedling specifications and seedling source information. The identification registration smart contract verifies the format of the batch identification code. After the verification is passed, the batch identification code and batch metadata are written into the distributed ledger as a set of key-value pairs. The identification registration smart contract returns the transaction hash value as a storage certificate. The public key in the digital identity public-private key pair is bound to the batch identifier code and written into the batch status storage area of ​​the identifier registration smart contract. The private key is kept by the breeding entity. Data generated in each subsequent stage is digitally signed using the private key before being written into the blockchain network. The data recipient verifies the legitimacy of the data source using the public key.

3. The intelligent management platform and data processing method for the entire aquatic product industry chain according to claim 1, characterized in that, In step 2, the multi-parameter water quality sensor array is deployed at different depths in the aquaculture water body. The multi-parameter water quality sensor array includes a dissolved oxygen sensor, a temperature sensor, a pH sensor, an ammonia nitrogen concentration sensor, and a nitrite concentration sensor. The above sensors collect aquaculture environmental parameters at a fixed sampling interval, which is set to a fixed value within the range of 15 minutes to 30 minutes. The dissolved oxygen concentration value collected by the dissolved oxygen sensor is expressed in milligrams per liter and is denoted as . Where t represents the sampling time; the temperature values ​​of the aquaculture water collected by the temperature sensor are in degrees Celsius, denoted as . The pH value collected by the pH sensor is dimensionless and is denoted as . The ammonia nitrogen concentration value collected by the ammonia nitrogen concentration sensor is expressed in milligrams per liter and is denoted as . The nitrite concentration value collected by the nitrite concentration sensor is expressed in milligrams per liter and is denoted as . ; The camera device is deployed above the aquaculture water body. Its sampling interval is synchronized with that of the multi-parameter water quality sensor array. It performs target detection and motion analysis on the feeding behavior image sequences, extracting the activity index of the aquatic product group after feeding, denoted as... The aquatic product group activity index is calculated as follows: The movement velocity vectors of individual aquatic products are extracted from each image frame of the feeding behavior image sequence during the 5th to 15th minute after feeding. The mean value of the magnitude of the movement velocity vectors of all aquatic products during this time period is calculated, and this mean value is used as the aquatic product group activity index. .

4. The intelligent management platform and data processing method for the entire aquatic product industry chain according to claim 3, characterized in that, The formula for calculating the water quality suitability index in step 3 is as follows: in, Let be the water quality suitability index at time t, with a value ranging from 0 to 1; This represents the minimum tolerable dissolved oxygen concentration for aquatic product species. This is the upper reference limit for dissolved oxygen concentration; The optimal pH value for aquatic products, The pH tolerance range of aquatic product species; This represents the maximum tolerable concentration of ammonia nitrogen for aquatic product species. The maximum tolerable concentration of nitrite for aquatic product species; Let be the weighting coefficient, satisfying Each weighting coefficient is preset based on the sensitivity of aquatic product types to various water quality parameters; The formula for calculating the disease risk index is: in, The disease risk index at time t, with a value ranging from 0 to 1; The optimal growth temperature for aquatic product species; The temperature tolerance range of aquatic product types; This represents the contribution coefficient of temperature deviation to disease risk. This represents the contribution coefficient of water quality suitability to disease risk, and ; Water quality suitability index Compared with the preset water quality suitability warning threshold, when When the water quality falls below the warning threshold, an abnormal aquaculture environment warning is generated; the disease risk index is also considered. Compared with the preset disease risk warning threshold, when When the risk level exceeds the disease risk warning threshold, a disease risk warning message is generated. The warning message includes the warning type, the time of the warning, the batch identification code corresponding to the warning, the current aquaculture environment parameter value, and the calculated index value.

5. The intelligent management platform and data processing method for the entire aquatic product industry chain according to claim 3, characterized in that, The start time of the processing step in step 4 is recorded as follows: The ambient temperature in the processing workshop is recorded in degrees Celsius. The ambient temperature in the processing workshop is collected by temperature sensors deployed in the workshop at the fixed sampling interval described in step 2; the duration of each processing step is in minutes and denoted as... , where i represents the i-th processing step, and the duration of each processing step is recorded by a timing device deployed on the processing equipment; The volatile basic nitrogen content value in the quality inspection parameters is expressed in milligrams per 100 grams, denoted as... ; The total colony count is measured in colony-forming units per gram (CFU), denoted as CFU / C. The K value is defined as the ratio of the sum of the molar concentrations of hypoxanthine and inosine to the total molar concentration of adenosine triphosphate and its breakdown products. It is dimensionless and denoted as K. ; Processing start time Ambient temperature value of the processing workshop Time series data, duration of each processing step Volatile basic nitrogen content value Total bacterial count and K value The data is bound to the batch identifier code, digitally signed using the private key described in step 1, and then transmitted to the data storage smart contract of the blockchain network via a wireless communication network. After receiving the signed data, the data storage smart contract uses the public key to verify the legality of the signature. Once the verification is successful, the data is written into the data storage area of ​​the distributed ledger.

6. The intelligent management platform and data processing method for the entire aquatic product industry chain according to claim 5, characterized in that, In step 5, the temperature and humidity values ​​in the cold chain circulation process are collected by a cold chain environmental parameter acquisition device deployed inside the cold chain transport container or vehicle. This device includes a temperature sensor and a humidity sensor. The temperature sensor collects the air temperature value inside the cold chain transport container or vehicle at the fixed sampling interval described in step 2, and the value is recorded in degrees Celsius. The humidity sensor collects the relative humidity value of the air inside the cold chain transport container or cold chain transport vehicle at the fixed sampling interval described in step 2, and records it as a percentage. ; The start time of the cold chain distribution process is recorded as follows: The end time of the cold chain distribution process is recorded as ; Temperature value Time series data, humidity values Time series data, start time of cold chain distribution and termination time The data is bound to the batch identifier code, digitally signed using the private key described in step 1, and then transmitted to the data storage smart contract of the blockchain network via a wireless communication network. After receiving the signed data, the data storage smart contract uses the public key to verify the legality of the signature. Once the verification is successful, the data is written into the data storage area of ​​the distributed ledger.

7. The intelligent management platform and data processing method for the entire aquatic product industry chain according to claim 6, characterized in that, The method for constructing the complete temperature history curve in step 6 is as follows: The ambient temperature value of the processing workshop is... Time series data and cold chain environment temperature values Time series data are spliced ​​together in chronological order to form a sequence starting from the beginning of the processing stage. Up to the current moment Complete temperature history curve ,in For time variables, The range of values ​​is ; The formula for calculating the cumulative quality decay potential is: in, This represents the cumulative quality decay potential up to the current moment. For aquatic product types at reference temperatures The quality decay rate constant under the given conditions, Take 273 Kelvin; The activation energy for quality degradation of aquatic products is expressed in joules per mole; R is the ideal gas constant, taken as 8.314 joules per mole per Kelvin. For a moment The Kelvin temperature value of the environment in which the aquatic products are located is obtained by adding 273.15 to the Celsius temperature value; The initial quality correction factor is calculated using the following formula: in, This provides a reference value for the K-value of aquatic product species under reference conditions. This provides reference values ​​for the volatile basic nitrogen content of aquatic product species under reference conditions. This provides reference values ​​for the total bacterial count of aquatic product species under reference conditions. Let be the weighting coefficient, satisfying Each weighting coefficient is preset based on the contribution of volatile basic nitrogen content, total bacterial count, and K value to the rate of quality degradation of aquatic products. For discrete data, the discrete summation form of the cumulative quality decay potential is: Where N is the total number of sampling periods from the start of processing to the current time. Let Kelvin be the temperature value in the j-th sampling period. This refers to the time length corresponding to the fixed sampling interval mentioned in step 2.

8. The intelligent management platform and data processing method for the entire aquatic product industry chain according to claim 7, characterized in that, The formula for calculating the real-time remaining shelf life in step 7 is as follows: in, The remaining shelf life as of the current moment, in hours; This is the critical value for the quality degradation potential of aquatic product species, which is determined by the aquatic product species at a reference temperature. The standard shelf-life experimental data were obtained under the following conditions; The expected storage temperature value for a batch of aquatic products under subsequent standard storage conditions, in Kelvin; For the aforementioned aquatic product types at a reference temperature The constant of the quality decay rate under the given conditions; R is the activation energy for quality degradation of the aforementioned aquatic product species; R is the ideal gas constant. This is the initial quality correction factor.

9. The intelligent management platform and data processing method for the entire aquatic product industry chain according to claim 8, characterized in that, The method for calculating the urgency of intervention in step 8 is as follows: at any given time, obtain a batch list of all aquatic product batches currently in the cold chain distribution or sales stage; for each aquatic product batch in the batch list, read the real-time remaining shelf life of that aquatic product batch from the distributed ledger of the blockchain network. and current geographical location information; The formula for calculating the urgency of intervention is: in, The urgency of intervention for aquatic product batches; The real-time remaining shelf life of aquatic product batches, in hours; For a less than A positive number; d represents the geographical distance between the current location of the aquatic product batch and the target sales terminal, in kilometers; The average speed of cold chain transport vehicles, expressed in kilometers per hour; This is the distance attenuation coefficient, with a value ranging from 0.1 to 0.5; All aquatic product batches are classified according to the urgency of intervention. The values ​​are sorted from largest to smallest to generate an intervention priority sequence; Dynamic scheduling decisions are generated based on intervention priority sequences. These decisions include at least one of the following: for batches with intervention urgency greater than a preset high intervention threshold, a priority delivery instruction is generated, including the batch identifier, current location, target sales terminal, and priority level; for batches with intervention urgency between the preset high and medium intervention thresholds, a normal delivery instruction is generated; for batches with intervention urgency less than the preset medium intervention threshold, a delayed delivery instruction is generated; and for batches with real-time remaining shelf life... For batches that are less than the preset safety threshold, generate a price reduction promotion order or a return processing order; The generated dynamic scheduling decision is bound to the corresponding batch identifier code and written into the decision record smart contract of the blockchain network. After receiving the dynamic scheduling decision data, the decision record smart contract verifies the data source by signature. After successful verification, the decision data is written into the decision record area of ​​the distributed ledger.

10. The intelligent management platform and data processing method for the entire aquatic product industry chain according to claim 9, characterized in that, The generation method of the full-chain quality traceability report in step 9 is as follows: in response to the traceability query request initiated by the end user by scanning the traceability code on the outer packaging of aquatic products, all data associated with the batch identification code corresponding to the traceability code is read from the distributed ledger of the blockchain network. The data retrieved includes: batch metadata stored in step 1, which includes the aquatic product species name, number of seedlings, seedling specifications, and seedling source information; and dissolved oxygen concentration values ​​stored in step 2. Aquaculture water temperature value pH value ammonia nitrogen concentration value nitrite concentration value and the activity index of aquatic product groups Time series data; water quality suitability index calculated in step 3 Disease risk index Time series data; ambient temperature values ​​of the processing workshop stored in step 4. Time series data, duration of each processing step Volatile basic nitrogen content value Total bacterial count and K value Step 5: Store the cold chain environment temperature value. Time series data and relative humidity values ​​in cold chain environments Time series data; cumulative quality decay potential calculated in step 6 Step 7 calculates the real-time remaining shelf life. ; The time series data of aquaculture environmental parameters and the time series data of water quality suitability index are statistically summarized to generate a quality overview of the aquaculture process. The quality overview of the aquaculture process includes the average, maximum, minimum and standard deviation of dissolved oxygen concentration, aquaculture water temperature, pH, ammonia nitrogen concentration, nitrite concentration and water quality suitability index during the aquaculture cycle. Statistical analysis and summarization of time-series data on cold chain environmental parameters are performed to generate a quality overview of the cold chain process, which includes cold chain environmental temperature values. The average, maximum, minimum, and standard deviation of the temperature, as well as the number and cumulative duration of temperature exceedance events. A temperature exceedance event is defined as the temperature value of the cold chain environment. An event that exceeds the preset cold chain temperature limit for a duration exceeding the preset time tolerance; All the data and statistical summary results are organized in chronological order into a full-chain quality traceability report. The full-chain quality traceability report includes an overview of the quality of the breeding process, a summary of quality inspection parameters of the processing process, an overview of the quality of the cold chain process, and the current real-time remaining shelf life. The full-chain quality traceability report is returned to the end user's query interface for display.

Images