Aquatic product traceability management method and system based on block chain

Abstract

The invention provides an aquatic product traceability management method and system based on a block chain, and relates to the technical field of aquatic product management, the aquatic product traceability management method based on the block chain comprises the following steps: establishing an aquatic product traceability network platform, and obtaining aquatic product full life cycle data in real time; performing anomaly verification on the acquired aquatic product full life cycle data based on a data verification method, and storing the verified data in an encrypted form in an aquatic product tracing network platform through a curve encryption algorithm; collecting feedback information after the user inquires the aquatic product traceability information through the aquatic product traceability network platform; and analyzing the collected user feedback information, and adjusting and optimizing aquatic product full life cycle management according to an analysis result. According to the method, the data is stored to the block chain in an encrypted form through a curve encryption algorithm, so that the security and non-tampering property of the data are ensured, and comprehensive optimization and guarantee are provided for production and management of aquatic products.

Description

Technical Field

[0001] The present invention relates to the technical field of aquatic product management, and in particular to a blockchain-based aquatic product traceability management method and system. Background Art

[0002] In recent years, with the rapid development of Internet of Things technology and the theoretical and practical exploration of aquatic product safety traceability, aquatic product safety management has made significant progress. However, despite certain achievements, the traditional traceability system still has shortcomings and is difficult to fully meet people's high standards for aquatic product safety. In the existing traceability system, data loss and blind spots frequently occur in the middle links; information asymmetry and data barriers between distributed data centers are serious, which seriously affects the efficiency of information flow; the integration of multi-source data is difficult, which affects the quality of product analysis and modeling; in addition, the existing system cannot completely eliminate the problem of data tampering.

[0003] Blockchain technology, with its unique advantages of distributed storage, data immutability, data synchronization broadcast and protocol data storage, provides new possibilities for solving these problems. It can ensure that the data of aquatic products at every step from fishing to the hands of consumers are securely and transparently recorded and shared. In addition, the introduction of blockchain can effectively break the information island, realize the comprehensive interconnection of data, and improve the transparency and trust of the entire supply chain. By integrating and automating the processing of multi-source data, blockchain can also improve the accuracy of analysis and modeling, thereby optimizing the traceability efficiency and safety of aquatic products. In short, by adopting blockchain technology, the integrity and functionality of the aquatic product traceability system can be greatly improved, and the strict requirements of modern society for food safety can be better met.

[0004] However, the data generated during the entire life cycle of aquatic products may contain anomalies or errors. If these abnormal data are not effectively detected and verified, they will directly affect the accuracy and reliability of the traceability system. The existing technology lacks anomaly detection and verification mechanisms for data throughout the entire life cycle of aquatic products, and is unable to detect and process abnormal data in a timely manner.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In view of this, the present invention provides a blockchain-based aquatic product traceability management method and system to solve the above-mentioned problem of lack of anomaly detection and verification mechanism for the entire life cycle data of aquatic products.

[0007] In order to solve the above problems, the specific technical solutions adopted by the present invention are as follows: According to one aspect of the present invention, a blockchain-based aquatic product traceability management method is provided, and the blockchain-based aquatic product traceability management method includes the following steps: S1. Establish a network platform for aquatic product traceability through blockchain technology, and use Internet of Things technology to obtain real-time data on the entire life cycle of aquatic products; S2. Perform abnormal verification on the acquired aquatic product life cycle data based on the data verification method, and store the verified data in encrypted form on the aquatic product traceability network platform through the curve encryption algorithm; S3. Collect feedback information from users who query aquatic product traceability information through the aquatic product traceability network platform; S4. Analyze the collected user feedback information based on thematic analysis, and adjust and optimize the full life cycle management of aquatic products according to the analysis results; Preferably, performing abnormal verification on the acquired aquatic product life cycle data based on the data verification method, and storing the verified data in an encrypted form in the aquatic product traceability network platform through a curve encryption algorithm includes the following steps: S21. Perform data fusion processing on the acquired aquatic product life cycle data through weight fusion method; S22. Use dynamic time warping and local anomaly factor detection methods to perform anomaly detection on the fused aquatic product life cycle data; S23, analyzing and verifying the detected abnormal data. If the verification passes, executing step S24. If the verification fails, notifying the management personnel to handle the abnormality. S24. Use a curve encryption algorithm to encrypt the verified data on the entire life cycle of aquatic products, and transmit the encrypted data on the entire life cycle of aquatic products to the aquatic product traceability network platform for storage.

[0008] Preferably, the data fusion processing of the acquired aquatic product life cycle data by weight fusion method includes the following steps: S211. For the aquatic product life cycle data of each blockchain node, calculate the expected value and variance value of the aquatic product life cycle data at the blockchain node; S212. Calculate the confidence distance between each pair of data in the aquatic product life cycle data based on the exponential decay function; S213, using the expected weight calculation formula to calculate the expected weight of each type of data in the aquatic product life cycle data; S214. Calculate the variance weight of each type of data in the aquatic product life cycle data using the variance weight calculation formula; S215. The comprehensive weight is obtained by averaging the expected weight and variance weight of each data in the whole life cycle data of aquatic products; S216. Based on the obtained comprehensive weights, weighted fusion processing is performed on the data of the entire life cycle of aquatic products.

[0009] Preferably, the expected weight calculation formula is: ; In the formula, Indicates the first i The expected weight of the data; d ij Indicates the first i Data and j The confidence distance between the data; 1- d ij Indicates the first i Data and j The degree of mutual support between the data; n Represents the types of data in the entire life cycle of aquatic products.

[0010] Preferably, the variance weight calculation formula is: ; In the formula, Indicates the first i The variance weight of the data; Indicates the first i The variance of the data; Indicates the first k The variance of the data; n Represents the types of data in the entire life cycle of aquatic products.

[0011] Preferably, using dynamic time warping and local anomaly factor detection method to perform anomaly detection on the fused aquatic product life cycle data includes the following steps: S221. For each pair of time series data in the fused aquatic product life cycle data, the DTW algorithm is used to calculate the similarity distance between them; S222. Calculate the local anomaly factor of each data point based on the similarity distance calculation result; S223. Based on the local anomaly factor of each data point, anomaly detection is performed on the fused aquatic product life cycle data according to a pre-set threshold. If the local anomaly factor value of a data point is greater than the pre-set threshold, it is marked as abnormal data.

[0012] Preferably, for each pair of time series data in the fused aquatic product life cycle data, calculating the similarity distance between them using the DTW algorithm includes the following steps: S2211, calculating the Euclidean distance between data points in each pair of time series data, and constructing a cost matrix based on the Euclidean distance; S2212, starting from the lower left corner of the cost matrix, gradually calculating the cumulative distance matrix by a dynamic programming method; S2213, searching for the best curved path from the lower left corner to the upper right corner in the cumulative distance matrix to minimize the total distance; S2214. The sum of the accumulated distances corresponding to the best curved path is taken as the similarity distance between the two sets of time series data.

[0013] Preferably, based on the similarity distance calculation result, calculating the local anomaly factor of each data point comprises the following steps: S2221. Calculate the distances of the K nearest neighbors of each data point in the time series data according to the similarity distance calculation result; S2222. Calculate the K nearest neighbor reachable distance of each data point based on the distances of the K nearest neighbors of each data point; S2223. Calculate the local reachability density of each data point according to the K nearest neighbor reachable distance of each data point; S2224. Calculate the local anomaly factor of each data point according to the local reachable density of each data point.

[0014] Preferably, the verified aquatic product life cycle data is encrypted using a curve encryption algorithm, and the encrypted aquatic product life cycle data is transmitted to the aquatic product traceability network platform for storage, including the following steps: S241. Perform hash operation on the verified aquatic product life cycle data using a hash algorithm and generate an authentication password; S242, generating an encryption key based on the authentication password of the hash operation result combined with the key exchange mechanism, and performing curve encryption processing on the aquatic product life cycle data to generate a ciphertext; S243. The encrypted ciphertext is securely transmitted to the aquatic product traceability network platform through a secure network channel; S244. The aquatic product traceability network platform receives the encrypted data and stores it.

[0015] Preferably, analyzing the collected user feedback information based on the theme analysis method, and adjusting and optimizing the aquatic product life cycle management according to the analysis results include the following steps: S41, extracting keywords from the collected user feedback information using natural language processing technology; S42, using the LDA topic model to perform topic analysis on the extracted keywords to identify problems in the user feedback information; S43, conducting quantitative analysis based on the issues in the user feedback information, and counting the frequency and relevance of each topic; S44. Adjust and optimize the relevant processes of the whole life cycle management of aquatic products based on the frequency and relevance of each topic.

[0016] According to another aspect of the present invention, a blockchain-based aquatic product traceability management system is provided, the blockchain-based aquatic product traceability management system comprising: a platform building module, a data storage module, a feedback collection module and an adjustment and optimization module, and the platform building module, the data storage module, the feedback collection module and the adjustment and optimization module are connected in sequence; The platform building module is used to establish a traceability network platform for aquatic products through blockchain technology, and to obtain real-time data on the entire life cycle of aquatic products using the Internet of Things technology; The data storage module is used to verify the abnormality of the acquired aquatic product life cycle data based on the data verification method, and store the verified data in an encrypted form in the aquatic product traceability network platform through the curve encryption algorithm; A feedback collection module, used to collect feedback information from users after they query the aquatic product traceability information through the aquatic product traceability network platform; The adjustment and optimization module is used to analyze the collected user feedback information based on the theme analysis method, and adjust and optimize the whole life cycle management of aquatic products according to the analysis results.

[0017] The beneficial effects of the present invention are: 1. The present invention uses a curve encryption algorithm to store data in an encrypted form on the blockchain to ensure the security and non-tamperability of the data. The Internet of Things technology is used to obtain real-time data on the entire life cycle of aquatic products, and can timely monitor and record the production, processing, transportation and other links of aquatic products to ensure the accuracy and real-time nature of the data. The characteristic of blockchain technology is the openness and transparency of data. All participants can view and verify the data, which ensures the transparency and credibility of the data. By collecting and analyzing user feedback information, user needs and opinions can be better understood, thereby optimizing products and management processes in a targeted manner, improving user satisfaction and participation, and thus providing all-round optimization and protection for the production and management of aquatic products.

[0018] 2. The present invention can verify the abnormality of the acquired data of the whole life cycle of aquatic products through the data verification method to ensure the integrity and accuracy of the data. The verified data is encrypted through the curve encryption algorithm to ensure the security of the data and prevent the data from being tampered with or leaked. The dynamic time bending and local anomaly factor detection methods are used to detect the abnormality of the data, which can timely discover the abnormal situation in the data and perform corresponding processing, which helps to take timely measures when the data is abnormal to ensure the quality and safety of aquatic products. The weight fusion method is used to fuse the data, which can comprehensively consider the expected value and variance value of the data, thereby improving the efficiency and accuracy of data processing.

[0019] 3. The present invention uses natural language processing technology and topic analysis to accurately extract keywords from user feedback information and identify problems therein, which helps managers quickly understand user needs and opinions and locate problems. By quantitatively analyzing the frequency and relevance of each topic in user feedback information, it can evaluate issues of different topics and determine their priority and importance in the full life cycle management of aquatic products, which helps managers to reasonably arrange resources, give priority to important issues, and improve management efficiency. Based on the frequency and relevance of each topic, managers can adjust and optimize relevant links and processes of the full life cycle management of aquatic products in a targeted manner to solve problems in user feedback and improve product quality and service experience. By timely adjusting and optimizing the full life cycle management of aquatic products, product design, production processes and service models can be continuously improved to meet user needs, improve product quality and competitiveness, and help enhance brand image, expand market share, and achieve long-term sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 This is a flowchart of a blockchain-based aquatic product traceability management method according to an embodiment of the present invention; Figure 2 This is a principle block diagram of a blockchain-based aquatic product traceability management system according to an embodiment of the present invention; Figure 3 It is a structural schematic diagram of a computer device according to an embodiment of the present invention.

[0021] In the figure: 1. Platform building module; 2. Data storage module; 3. Feedback collection module; 4. Adjustment and optimization module. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0023] According to an embodiment of the present invention, a blockchain-based aquatic product traceability management method and system are provided.

[0024] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a blockchain-based aquatic product traceability management method and system are provided, and the blockchain-based aquatic product traceability management method includes the following steps: S1. Establish a network platform for aquatic product traceability through blockchain technology, and use Internet of Things technology to obtain real-time data on the entire life cycle of aquatic products; Specifically, the establishment of aquatic product traceability network platform through blockchain technology and the use of Internet of Things technology to obtain real-time data on the entire life cycle of aquatic products include the following steps: Choose a blockchain platform suitable for building a traceability system, such as Ethereum or Hyperledger Fabric, which provides the infrastructure for developing smart contracts and distributed ledgers.

[0025] Write smart contracts to record and manage data, ensuring data immutability and transparency. Smart contracts will define data records, access rights, and business logic.

[0026] Determine the node consensus mechanism, such as Proof of Work (PoW) or Proof of Stake (PoS), to ensure the security and consistency of the blockchain network.

[0027] IoT devices are deployed in each link of aquatic product breeding, processing, packaging, transportation and sales to monitor key data such as temperature, humidity, location, quality, etc. in real time.

[0028] S2. Perform abnormal verification on the acquired aquatic product life cycle data based on the data verification method, and store the verified data in encrypted form on the aquatic product traceability network platform through the curve encryption algorithm; As a preferred implementation, the acquired aquatic product life cycle data is verified for abnormality based on the data verification method, and the verified data is stored in an encrypted form in the aquatic product traceability network platform through a curve encryption algorithm, including the following steps: S21. Perform data fusion processing on the acquired aquatic product life cycle data through weight fusion method; As a preferred implementation, the data fusion processing of the acquired aquatic product life cycle data by weight fusion method includes the following steps: S211. For the aquatic product life cycle data of each blockchain node, calculate the expected value (representing the average value of the data within the time period of the blockchain node) and the variance value of the aquatic product life cycle data at the blockchain node; It should be noted that, assuming there is a blockchain node that collects multiple data points about the entire life cycle of aquatic products over a period of time, these data points can represent various indicators, such as temperature, humidity, pH value, etc. These data points can be represented as a set; Add up all the data points to get the total. Then, divide the total by the number of data points to get the expected value. Variance is a statistic that describes the degree of difference between a data point and its mean. The specific calculation steps are: For each data point, calculate its difference from the mean; Square the above differences to get the square of the difference between each data point and the mean; Add the squares of all the differences to get the sum of the squares; Finally, divide the sum of squares by the number of data points to get the variance.

[0029] S212. Calculate the confidence distance between each pair of data in the aquatic product life cycle data based on the exponential decay function; Specifically, the expression of the exponential decay function is: d ij =exp(-( t i - t j )); In the formula, d ij Indicates the first i Data and j The confidence distance between the data; t i and t j Represent the data points i and jThe sequential number of .

[0030] S213, using the expected weight calculation formula to calculate the expected weight of each type of data in the aquatic product life cycle data; Specifically, the expected weight calculation formula is: ; In the formula, Indicates the first i The expected weight of the data; d ij Indicates the first i Data and j The confidence distance between the data; 1- d ij Indicates the first i Data and j The degree of mutual support between the data; n Represents the types of data in the entire life cycle of aquatic products.

[0031] S214. Calculate the variance weight of each type of data in the aquatic product life cycle data using the variance weight calculation formula; Specifically, the variance weight calculation formula is: ; In the formula, Indicates the first i The variance weight of the data; Indicates the first i The variance of the data; Indicates the first k The variance of the data; n Represents the types of data in the entire life cycle of aquatic products.

[0032] S215. The comprehensive weight is obtained by averaging the expected weight and variance weight of each data in the whole life cycle data of aquatic products; S216. Based on the obtained comprehensive weights, weighted fusion processing is performed on the data of the entire life cycle of aquatic products.

[0033] It should be noted that each data point or data subset (such as data for a certain time period) is weighted according to its comprehensive weight; the weighted operation is usually achieved by multiplying the value of each data point by its corresponding weight; the weighted data points or data subsets are accumulated or averaged to obtain the fused data.

[0034] S22. Use dynamic time warping and local anomaly factor detection methods to perform anomaly detection on the fused aquatic product life cycle data; As a preferred implementation, the anomaly detection of the fused aquatic product life cycle data using dynamic time warping and local anomaly factor detection method includes the following steps: S221. For each pair of time series data in the fused aquatic product life cycle data, the DTW algorithm is used to calculate the similarity distance between them; As a preferred implementation, for each pair of time series data in the fused aquatic product life cycle data, using the DTW algorithm to calculate the similarity distance between them includes the following steps: S2211, calculating the Euclidean distance between data points in each pair of time series data, and constructing a cost matrix based on the Euclidean distance; It should be noted that calculating the Euclidean distance between data points in each pair of time series data and constructing a cost matrix based on the Euclidean distance includes the following steps: For each pair of time series data, calculate their Euclidean distance point by point; Create a matrix whose size is the sum of the lengths of the two time series minus one (because it is a symmetric matrix, you only need to calculate the upper or lower triangle); Fill the calculated Euclidean distance into the corresponding position of the cost matrix; each element in the cost matrix represents the Euclidean distance at the corresponding time point.

[0035] S2212, starting from the lower left corner of the cost matrix, gradually calculating the cumulative distance matrix by a dynamic programming method; It should be noted that, through the dynamic programming method, starting from the lower left corner of the cost matrix, the cumulative distance matrix is ​​calculated step by step, including the following steps: Create a cumulative distance matrix of the same size as the cost matrix and initialize all its elements to infinity (or a very large number), except for the top-left element, which is usually initialized to 0; The cumulative distance is calculated starting from the lower left corner of the cost matrix; For each position in the cumulative distance matrix, calculate the minimum cumulative distance of the current position; S2213, searching for the best curved path from the lower left corner to the upper right corner in the cumulative distance matrix to minimize the total distance; It should be noted that in the dynamic time warping (DTW) algorithm, after the cumulative distance matrix (also called the DTW matrix) is calculated, the next step is to search for the best curved path from the lower left corner of the matrix (usually representing the end of the two time series) to the upper right corner (representing the beginning of the two time series). This path is selected by the elements in the cumulative distance matrix, aiming to minimize the total distance between the two time series. The process of searching for the best curved path is often referred to as "backtracking"; backtracking starts from the lower right corner of the cumulative distance matrix and then moves step by step to the upper left, each time selecting the direction that results in the minimum cumulative distance. The specific steps are as follows: Step 1: Starting from the lower right corner of the cumulative distance matrix, record the current position as part of the path; Step 2: Check the three adjacent positions to the left, above, and above the left of the current position (i.e., the previous time point, the previous sequence point, and the intersection of the previous time point and sequence point); these three positions represent three possible bending directions respectively; Step 3: Compare the cumulative distance values ​​of the three adjacent positions and find the smallest one; this minimum cumulative distance represents the optimal path from the starting point to the current position so far; Step 4: Move to the corresponding adjacent position (left, top, or top-left) based on the minimum cumulative distance found; this new position becomes the new current position; Step 5: Repeat steps 2 to 4 until you reach the upper left corner of the cumulative distance matrix (i.e., the starting point of the two time series); Step 3: Use and add the position of the upper left corner to the path to complete the optimal curved path from the lower left corner to the upper right corner.

[0036] S2214. The sum of the accumulated distances corresponding to the best curved path is taken as the similarity distance between the two sets of time series data.

[0037] It should be noted that, along the optimal curved path, starting from the starting point (lower left corner), the cumulative distance values ​​corresponding to each coordinate point on the path are added until the end point (upper right corner) is reached; this cumulative sum is the similarity distance between the two sets of time series data. The smaller the similarity distance obtained, the more similar the two sets of time series data are in shape and pattern. If the similarity distance is close to zero, then the two sets of time series data are almost the same; on the contrary, if the similarity distance is large, it means that the two sets of time series data are very different in shape and pattern.

[0038] S222. Calculate the local anomaly factor of each data point based on the similarity distance calculation result; As a preferred implementation, based on the similarity distance calculation result, calculating the local anomaly factor of each data point includes the following steps: S2221. Calculate the distances of K nearest neighbors of each data point in the time series data according to the similarity distance calculation result; It should be noted that, according to the similarity distance calculation result, calculating the distances of the K nearest neighbors of each data point in the time series data includes the following steps: Create a distance matrix where the rows and columns correspond to each data point in the time series, fill the calculated similarity distance into the matrix, and the elements on the diagonal (i.e. the distance between the data point and itself) can be set to 0 or ignored; For each data point, find the K data points closest to it from the distance matrix; Arrange the elements in the distance matrix in ascending order and select the first K smallest distances.

[0039] S2222. Calculate the K nearest neighbor reachable distance of each data point based on the distances of the K nearest neighbors of each data point; S2223. Calculate the local reachability density of each data point according to the K nearest neighbor reachable distance of each data point; It should be noted that local reachability density is an indicator that measures the density level of a single data point in its neighborhood in time series data. It is calculated based on the K nearest neighbor reachability distance of each data point. For each data point in the time series, first determine its K nearest neighbors and calculate the reachable distance between these neighbors and the data point. The reachable distance refers to the Euclidean distance from the data point to each of its nearest neighbors; For each data point, the reachable distances of its K nearest neighbors are summed, and K (the number of nearest neighbors) is divided by this distance sum. The result is the local reachability density of the data point.

[0040] S2224. Calculate the local anomaly factor of each data point according to the local reachable density of each data point.

[0041] It should be noted that the local outlier factor is determined by comparing the local reachability density of a data point with the average of the local reachability densities of all data points in its neighborhood. If the local reachability density of a data point is much lower than the average of its neighborhood, then it may have a high local outlier factor.

[0042] S223. Based on the local anomaly factor of each data point, anomaly detection is performed on the fused aquatic product life cycle data according to a pre-set threshold. If the local anomaly factor value of a data point is greater than the pre-set threshold, it is marked as abnormal data.

[0043] S23, analyzing and verifying the detected abnormal data. If the verification passes, executing step S24. If the verification fails, notifying the management personnel to handle the abnormality. It should be noted that the analysis and verification of the detected abnormal data includes the following steps: Conduct a preliminary review of the detected abnormal data, including checking the value of the abnormal data point, occurrence time and other basic information; analyze the possible causes of the abnormality, such as data collection errors, system failures, external interference, etc.; Use statistical methods (such as box plots and hypothesis tests) to verify whether abnormal data deviates significantly from the normal data distribution; or combine domain knowledge and expert experience to determine whether the anomaly conforms to business logic and actual conditions.

[0044] Specifically, if the data deviates significantly from the normal distribution and does not conform to business logic or domain knowledge, it needs to be marked as abnormal and the management personnel should be notified for further processing. This includes: Take necessary corrective measures, such as recollecting data, adjusting system settings, repairing equipment failures, etc.

[0045] Analyze the root cause of the anomaly and develop prevention strategies to prevent similar anomalies from happening again.

[0046] S24. Use a curve encryption algorithm to encrypt the verified data on the entire life cycle of aquatic products, and transmit the encrypted data on the entire life cycle of aquatic products to the aquatic product traceability network platform for storage.

[0047] As a preferred implementation, the verified aquatic product life cycle data is encrypted using a curve encryption algorithm, and the encrypted aquatic product life cycle data is transmitted to the aquatic product traceability network platform for storage, including the following steps: S241. Perform hash operation on the verified aquatic product life cycle data using a hash algorithm and generate an authentication password; It should be noted that the verified aquatic product life cycle data is used as input, and the hash operation formula is used for calculation, and the obtained hash values ​​are combined to form the final authentication password.

[0048] Specifically, the hash calculation formula is: ; In the formula, hash(X) represents hash operation; R represents the power number, which determines the depth of the result value, and is usually a multiple of 2; W represents the byte length of the computer to which the data belongs, which affects the result range of the hash operation; G represents the anti-reversal factor, which is used to increase the complexity of the hash operation; X m Represents each data point in the life cycle data of aquatic products; Mod stands for modulus operation, which is a mathematical operator.

[0049] S242, generating an encryption key based on the authentication password of the hash operation result combined with the key exchange mechanism, and performing curve encryption processing on the aquatic product life cycle data to generate a ciphertext; It should be noted that the authentication password based on the hash operation result is combined with the key exchange mechanism to generate the encryption key, and the curve encryption processing is performed on the aquatic product life cycle data. The generation of ciphertext includes the following steps: A key exchange protocol (such as Diffie-Hellman key exchange, used to generate a shared key) is performed between the communicating parties to generate a shared encryption key. The generated authentication password is used as the seed value, combined with the shared key, and the final encryption key is generated through a key derivation function (such as HKDF); Select appropriate elliptic curve parameters, including curve equation, base point, etc., and use the encryption key to generate a pair of public and private keys based on the elliptic curve encryption algorithm. Use the public key to encrypt the aquatic product life cycle data to be encrypted to generate ciphertext.

[0050] S243. The encrypted ciphertext is securely transmitted to the aquatic product traceability network platform through a secure network channel; It should be noted that the Secure Sockets Layer (SSL) or Transport Layer Security (TLS) protocol is used to establish a secure network connection, and the encrypted ciphertext is encapsulated in a secure data packet, ready for transmission over the network, and the encapsulated ciphertext data packet is sent to the aquatic product traceability network platform.

[0051] S244. The aquatic product traceability network platform receives the encrypted data and stores it.

[0052] S3. Collect feedback information from users who query aquatic product traceability information through the aquatic product traceability network platform; It should be noted that collecting feedback information from users after they query aquatic product traceability information through the aquatic product traceability network platform includes the following steps: Establish a user-friendly and conspicuous feedback interface or link on the aquatic product traceability network platform. This interface can include a satisfaction evaluation of traceability information, an input box for specific opinions or suggestions, etc. After users have searched for traceability information of aquatic products, timely remind or invite users to provide feedback; users can be reminded through pop-up windows, emails, text messages or other notification methods; Regularly collect user feedback data and organize it.

[0053] S4. Analyze the collected user feedback information based on thematic analysis, and adjust and optimize the full life cycle management of aquatic products according to the analysis results; As a preferred implementation method, the collected user feedback information is analyzed based on the theme analysis method, and the whole life cycle management of aquatic products is adjusted and optimized according to the analysis results, including the following steps: S41, extracting keywords from the collected user feedback information using natural language processing technology; It should be noted that the use of natural language processing technology to extract keywords from the collected user feedback information includes the following steps: Remove irrelevant characters in the feedback, such as HTML tags, punctuation marks, etc., and split the feedback information into words or phrases; Perform part-of-speech tagging on the segmented text and identify named entities in the text; Use the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm to find words that appear frequently in the feedback and are relatively sparse in the entire corpus; Using the TextRank algorithm, keywords are extracted based on the co-occurrence relationship between words.

[0054] S42, using the LDA topic model to perform topic analysis on the extracted keywords to identify problems in the user feedback information; It should be noted that using the LDA topic model to perform topic analysis on the extracted keywords and identify problems in user feedback information includes the following steps: Obtain the topics of historical feedback information and their corresponding keywords as training sets, and train the LDA topic model. During the training process, the model will learn how to map keywords to different topics; After training is complete, the LDA topic model is evaluated to ensure that it accurately captures the topics in the keywords; The extracted keywords are input into the trained LDA topic model to obtain the topics in the user feedback information.

[0055] S43, conducting quantitative analysis based on the issues in the user feedback information, and counting the frequency and relevance of each topic; It should be noted that for each user feedback, the LDA topic model will assign one or more topics to it. The frequency of each topic is obtained by counting the number of times each topic appears in all user feedback.

[0056] Each topic generated by the LDA model is represented by a set of keywords. The co-occurrence relationship between these keywords can reflect the correlation between topics. Text similarity algorithms (such as cosine similarity, Jaccard similarity, etc.) can be used to calculate the correlation between different topics. S44. Adjust and optimize the relevant processes of the whole life cycle management of aquatic products based on the frequency and relevance of each topic.

[0057] It should be noted that by focusing on topics with higher frequency, which usually reflect the core issues and concerns in user feedback, similar or related problem topics are clustered together for more systematic analysis, and the topics that need to be prioritized are identified based on topic frequency and relevance.

[0058] For example, we optimize breeding technology and management methods for topics related to raw materials, breeding environment, feed, etc. to ensure the quality and safety of aquatic products; introduce intelligent monitoring and early warning systems to track key indicators in the production process in real time to identify and solve problems in a timely manner.

[0059] Focusing on topics related to processing technology, equipment, packaging, etc., improve processing technology and equipment to improve the processing efficiency and quality of aquatic products; strengthen hygiene management and quality control during the processing to ensure that products meet relevant standards and requirements.

[0060] Focusing on topics related to transportation, storage, and distribution, we will optimize the logistics network and distribution methods to improve the transportation efficiency and freshness of aquatic products. We will introduce the Internet of Things and big data technologies to monitor key indicators in the logistics process in real time to ensure product safety and traceability.

[0061] For topics related to sales channels, promotion strategies, after-sales services, etc., optimize sales strategies and customer service systems, improve customer satisfaction and loyalty, collect and analyze sales data, understand customer needs and market trends, and provide strong support for product development and market strategies.

[0062] In order to make it easier to understand the above technical solutions, the collected user feedback information is analyzed based on the theme analysis method, and the specific implementation methods of adjusting and optimizing the full life cycle management of aquatic products are as follows based on the analysis results: A certain aquatic product company has established an aquatic product traceability network platform using blockchain technology and collected feedback from users who queried aquatic product traceability information. These feedbacks include users’ evaluations and suggestions on aquatic product quality, transportation methods, packaging, etc.

[0063] Suppose a user feedback collected is: "The seafood I purchased was not tightly packaged, resulting in the product being not fresh and also damaged during transportation."

[0064] By using natural language processing technology, we can extract key words: "inadequate packaging", "unfresh product", and "damaged during transportation".

[0065] By inputting keywords of multiple user feedback into the LDA topic model for topic analysis, several main topics can be identified: Topic 1: Packaging issues (including key words such as “not tight packaging”); Topic 2: Transportation issues (including keywords such as “transportation damage”); Topic 3: Product freshness (including keywords such as “product is not fresh”); Further analyze user feedback and count the frequency of each topic and its correlation with other topics. For example: Topic 1 (packaging issues) appeared 30 times in 100 responses and had low correlation with other topics; Theme 2 (transportation issues) appeared 20 times in 100 responses and was somewhat correlated with Theme 3 (product freshness); Theme 3 (product freshness) appeared 25 times in 100 responses and was somewhat related to Theme 2 (transportation issues); Based on the analysis results, seafood companies can formulate the following improvement measures: For Topic 1 (Packaging Issues), redesign the packaging of aquatic products to ensure the tightness and durability of the packaging to prevent the product from being damaged during transportation.

[0066] For Topic 2 (transportation issues) and Topic 3 (product freshness), optimize transportation methods, such as using faster transportation tools, adding temperature control equipment, etc., to ensure that products remain fresh during transportation.

[0067] At the same time, since there is a certain correlation between Topic 2 and Topic 3, the influencing factors in the transportation process, such as temperature control, transportation time, etc., can be further investigated to find the best transportation solution.

[0068] like Figure 2 As shown, according to another embodiment of the present invention, a blockchain-based aquatic product traceability management system is provided, and the blockchain-based aquatic product traceability management system includes: a platform building module 1, a data storage module 2, a feedback collection module 3 and an adjustment and optimization module 4, and the platform building module 1, the data storage module 2, the feedback collection module 3 and the adjustment and optimization module 4 are connected in sequence; Platform building module 1 is used to establish a fishery product traceability network platform through blockchain technology and use the Internet of Things technology to obtain real-time data on the entire life cycle of fishery products; Data storage module 2, used to perform abnormal verification on the acquired aquatic product life cycle data based on the data verification method, and store the verified data in encrypted form in the aquatic product traceability network platform through the curve encryption algorithm; Feedback collection module 3, used to collect feedback information after users query aquatic product traceability information through the aquatic product traceability network platform; The adjustment and optimization module 4 is used to analyze the collected user feedback information based on the theme analysis method, and adjust and optimize the whole life cycle management of aquatic products according to the analysis results.

[0069] Figure 3 An embodiment of a computer device of the present invention is shown. The computer device may be a server, and the computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0070] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present invention, and does not constitute a limitation on the computer device to which the scheme of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0071] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0072] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0073] In summary, with the help of the above technical scheme of the present invention, the present invention stores the data in an encrypted form on the blockchain through a curve encryption algorithm to ensure the security and non-tamperability of the data. The Internet of Things technology is used to obtain the data of the entire life cycle of aquatic products in real time, and the production, processing, transportation and other links of aquatic products can be monitored and recorded in time to ensure the accuracy and real-time nature of the data. The characteristic of blockchain technology is the openness and transparency of the data. All participants can view and verify the data, which ensures the transparency and credibility of the data. By collecting and analyzing user feedback information, user needs and opinions can be better understood, so as to optimize products and management processes in a targeted manner, improve user satisfaction and participation, and thus provide all-round optimization and guarantee for the production and management of aquatic products. The present invention can perform abnormal verification on the acquired data of the entire life cycle of aquatic products through a data verification method to ensure the integrity and accuracy of the data, and encrypt the verified data through a curve encryption algorithm to ensure the security of the data and prevent the data from being tampered with or leaked. The dynamic time bending and local anomaly factor detection method are used to detect the data anomaly, which can timely discover the abnormal situation in the data and perform corresponding processing, which is helpful in data verification. When an abnormality occurs, timely measures are taken to ensure the quality and safety of aquatic products. By fusing data through the weight fusion method, the expected value and variance value of the data can be comprehensively considered, thereby improving the efficiency and accuracy of data processing. The present invention uses natural language processing technology and topic analysis to accurately extract keywords in user feedback information and identify the problems therein, which helps managers quickly understand user needs and opinions and locate problems. By quantitatively analyzing the frequency and relevance of each topic in user feedback information, issues of different topics can be evaluated to determine their priority and importance in the full life cycle management of aquatic products, which helps managers to reasonably arrange resources, give priority to important issues, and improve management efficiency. Based on the frequency and relevance of each topic, managers can adjust and optimize the relevant links and processes of the full life cycle management of aquatic products in a targeted manner to solve problems in user feedback and improve product quality and service experience. By timely adjusting and optimizing the full life cycle management of aquatic products, product design, production processes and service models can be continuously improved to meet user needs, improve product quality and competitiveness, and help enhance brand image, expand market share, and achieve long-term sustainable development.

[0074] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

[0075] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A blockchain-based aquatic product traceability management method, characterized in that: The blockchain-based aquatic product traceability management method includes the following steps: S1. Establish a network platform for aquatic product traceability through blockchain technology, and use Internet of Things technology to obtain real-time data on the entire life cycle of aquatic products; S2. Perform abnormal verification on the acquired aquatic product life cycle data based on the data verification method, and store the verified data in encrypted form on the aquatic product traceability network platform through the curve encryption algorithm; S3. Collect feedback information from users who query aquatic product traceability information through the aquatic product traceability network platform; S4. Analyze the collected user feedback information based on thematic analysis, and adjust and optimize the full life cycle management of aquatic products according to the analysis results; The method of performing abnormal verification on the acquired aquatic product life cycle data based on the data verification method, and storing the verified data in an encrypted form in the aquatic product traceability network platform through a curve encryption algorithm includes the following steps: S21. Perform data fusion processing on the acquired aquatic product life cycle data through weight fusion method; S22. Use dynamic time warping and local anomaly factor detection methods to perform anomaly detection on the fused aquatic product life cycle data; S23, analyzing and verifying the detected abnormal data. If the verification passes, executing step S24. If the verification fails, notifying the management personnel to handle the abnormality. S24. Use a curve encryption algorithm to encrypt the verified data on the entire life cycle of aquatic products, and transmit the encrypted data on the entire life cycle of aquatic products to the aquatic product traceability network platform for storage.

2. According to the blockchain-based aquatic product traceability management method of claim 1, it is characterized in that: The data fusion processing of the acquired aquatic product life cycle data by the weight fusion method includes the following steps: S211. For the aquatic product life cycle data of each blockchain node, calculate the expected value and variance value of the aquatic product life cycle data at the blockchain node; S212. Calculate the confidence distance between each pair of data in the aquatic product life cycle data based on the exponential decay function; S213, using the expected weight calculation formula to calculate the expected weight of each type of data in the aquatic product life cycle data; S214. Calculate the variance weight of each type of data in the aquatic product life cycle data using the variance weight calculation formula; S215. The comprehensive weight is obtained by averaging the expected weight and variance weight of each data in the whole life cycle data of aquatic products; S216. Based on the obtained comprehensive weights, weighted fusion processing is performed on the data of the entire life cycle of aquatic products.

3. According to claim 2, a blockchain-based aquatic product traceability management method is characterized in that: The expected weight calculation formula is: ； In the formula, Indicates the first i The expected weight of the data; d ij Indicates the first i Data and j The confidence distance between the data; 1- d ij Indicates the first i Data and j The degree of mutual support between the data; n Represents the types of data in the entire life cycle of aquatic products.

4. According to claim 3, a blockchain-based aquatic product traceability management method is characterized in that: The variance weight calculation formula is: ； In the formula, Indicates the first i The variance weight of the data; Indicates the first i The variance of the data; Indicates the first k The variance of the data; n Represents the types of data in the entire life cycle of aquatic products.

5. According to claim 1, a blockchain-based aquatic product traceability management method is characterized in that: The method of using dynamic time warping and local anomaly factor detection to detect anomalies in the fused aquatic product life cycle data includes the following steps: S221. For each pair of time series data in the fused aquatic product life cycle data, the DTW algorithm is used to calculate the similarity distance between them; S222. Calculate the local anomaly factor of each data point based on the similarity distance calculation result; S223. Based on the local anomaly factor of each data point, anomaly detection is performed on the fused aquatic product life cycle data according to a pre-set threshold. If the local anomaly factor value of a data point is greater than the pre-set threshold, it is marked as abnormal data.

6. According to claim 5, a blockchain-based aquatic product traceability management method is characterized in that: For each pair of time series data in the fused aquatic product life cycle data, using the DTW algorithm to calculate the similarity distance between them includes the following steps: S2211, calculating the Euclidean distance between data points in each pair of time series data, and constructing a cost matrix based on the Euclidean distance; S2212, starting from the lower left corner of the cost matrix, gradually calculating the cumulative distance matrix by a dynamic programming method; S2213, searching for the best curved path from the lower left corner to the upper right corner in the cumulative distance matrix to minimize the total distance; S2214. The sum of the accumulated distances corresponding to the best curved path is taken as the similarity distance between the two sets of time series data.

7. According to claim 5, a blockchain-based aquatic product traceability management method is characterized in that: The calculation of the local anomaly factor of each data point based on the similarity distance calculation result comprises the following steps: S2221. Calculate the distances of the K nearest neighbors of each data point in the time series data according to the similarity distance calculation result; S2222. Calculate the K nearest neighbor reachable distance of each data point based on the distances of the K nearest neighbors of each data point; S2223. Calculate the local reachability density of each data point according to the K nearest neighbor reachable distance of each data point; S2224. Calculate the local anomaly factor of each data point according to the local reachable density of each data point.

8. According to claim 1, a blockchain-based aquatic product traceability management method is characterized in that: The method of encrypting the verified aquatic product life cycle data by using a curve encryption algorithm, and transmitting the encrypted aquatic product life cycle data to the aquatic product traceability network platform for storage comprises the following steps: S241. Perform hash operation on the verified aquatic product life cycle data using a hash algorithm and generate an authentication password; S242, generating an encryption key based on the authentication password of the hash operation result combined with the key exchange mechanism, and performing curve encryption processing on the aquatic product life cycle data to generate a ciphertext; S243. The encrypted ciphertext is securely transmitted to the aquatic product traceability network platform through a secure network channel; S244. The aquatic product traceability network platform receives the encrypted data and stores it.

9. The blockchain-based aquatic product traceability management method according to claim 1 is characterized in that: The method of analyzing the collected user feedback information based on the theme analysis method and adjusting and optimizing the whole life cycle management of aquatic products according to the analysis results includes the following steps: S41, extracting keywords from the collected user feedback information using natural language processing technology; S42, using the LDA topic model to perform topic analysis on the extracted keywords to identify problems in the user feedback information; S43, conducting quantitative analysis based on the issues in the user feedback information, and counting the frequency and relevance of each topic; S44. Adjust and optimize the relevant processes of the whole life cycle management of aquatic products based on the frequency and relevance of each topic.

10. A blockchain-based aquatic product traceability management system, used to implement the blockchain-based aquatic product traceability management method according to any one of claims 1 to 9, characterized in that: The blockchain-based aquatic product traceability management system includes: a platform building module, a data storage module, a feedback collection module and an adjustment and optimization module, and the platform building module, the data storage module, the feedback collection module and the adjustment and optimization module are connected in sequence; The platform building module is used to establish a fishery product traceability network platform through blockchain technology and to obtain fishery product life cycle data in real time using Internet of Things technology; The data storage module is used to perform abnormal verification on the acquired aquatic product life cycle data based on the data verification method, and store the verified data in an encrypted form in the aquatic product traceability network platform through a curve encryption algorithm; The feedback collection module is used to collect feedback information from users after they query the aquatic product traceability information through the aquatic product traceability network platform; The adjustment and optimization module is used to analyze the collected user feedback information based on the theme analysis method, and adjust and optimize the full life cycle management of aquatic products according to the analysis results.

Images