A wolfberry origin information traceability management system based on blockchain

Abstract

A wolfberry origin information traceability management system based on blockchain, which relates to the field of blockchain technology. The supply process of wolfberries is divided into several process subsequences, the error levels of each process subsequence are obtained, and a feature matching detection mechanism is added to the blockchain nodes according to the error levels; a feature matching detection operation is performed on the wolfberry data received by the blockchain nodes with the added feature matching detection mechanism; the wolfberry batch number in the wolfberry data is obtained, and the wolfberry data stored in the temporary storage spaces of several blockchain nodes is clustered according to the wolfberry batch number to construct a list of delay detection flow programs for several wolfberry batch numbers; delay detection is performed on the wolfberry data stored in the temporary storage spaces of each blockchain node according to the list of delay detection flow programs; data on-chain operation is performed on the wolfberry data that passes the delay detection, significantly improving the efficiency and accuracy of wolfberry origin information traceability management.

Description

Technical Field

[0001] The present invention relates to the technical field of blockchain, and specifically to a wolfberry origin information traceability management system based on blockchain. Background Art

[0002] In the prior art CN116843353B, "An agricultural product traceability system and method based on blockchain and Internet of Things", Internet of Things devices are used to obtain production information of agricultural products and send the production information to a production area server; the production area server is used to generate first verification information of the production information and send the first verification information to a blockchain node; the blockchain node is used to store the first verification information in the blockchain; a terminal device is used to send traceability information to the production area server in response to a user's traceability operation on an agricultural product; the traceability information is used to request feedback of the production information of the agricultural product; the production area server is used to obtain the first verification information from the blockchain node according to the traceability information; the production area server is used to verify the production information according to the first verification information, and when the verification is successful, send the production information to the terminal device according to the traceability information.

[0003] In the prior art CN116883026A, "An agricultural product origin traceability method and system based on big data", a basic information database is constructed; a standard agricultural product sample is established as a reference benchmark, specific features of the agricultural product are extracted, and a multi-dimensional feature extraction set is constructed; sample feature analysis of the same region is carried out, and a feature limit interval of samples in the same region is set; an origin traceability network is established, and based on the established result, feature similarity evaluation of different regions is carried out to determine similar traceability regions; a positioning and recognition sub-network is built for the similar traceability regions, and the sub-network is coupled to the origin traceability network; a target agricultural product data set is extracted, and the target agricultural product data set is input into the origin traceability network to generate an origin traceability result.

[0004] Using blockchain technology for wolfberry origin information traceability management has many advantages. These advantages are mainly reflected in that once data is recorded on the blockchain, it cannot be modified or deleted, which ensures the authenticity and integrity of the data. The non-tamperability enables consumers to believe that the information they see is true, enhancing trust in the product. In the event of a food safety incident, the problem source can be quickly located through the blockchain, and corresponding measures can be taken promptly. However, there are also some technical problems that need to be solved urgently when using blockchain technology for wolfberry origin information traceability management, including data input accuracy problems. When human errors or intentional fraud may lead to inaccurate data input, and once this data is written into the blockchain, it is very difficult to modify, as well as data consistency problems: data in different links may be inconsistent, especially when exchanging data between multiple independent entities. Summary of the Invention

[0005] To solve the above technical problems, the purpose of the present invention is to provide a wolfberry origin information traceability management system based on blockchain, including a wolfberry information management platform, which is communicatively connected with a data analysis module, a full-process prediction module, a feature matching detection module, a batch clustering module, a delay detection module, an identity verification module, and a data uploading module;

[0006] The data analysis module is used to divide the supply process of wolfberries into several process subsequences according to the supply process information of wolfberries in the wolfberry information management platform, obtain the error level of each process subsequence, and add a feature matching detection mechanism to the blockchain nodes according to the error level;

[0007] The full-process prediction module is used to output the predicted wolfberry data uploaded by each participant corresponding to each process subsequence;

[0008] The feature matching detection module is used to perform feature matching detection operations on the wolfberry data received by the blockchain nodes with the added feature matching detection mechanism;

[0009] The batch clustering module obtains the wolfberry batch numbers in the wolfberry data, clusters the wolfberry data stored in the temporary storage spaces of several blockchain nodes according to the wolfberry batch numbers, and constructs a delay detection flow program list for several wolfberry batch numbers;

[0010] The delay detection module is used to perform delay detection on the wolfberry data stored in the temporary storage spaces of each blockchain node according to the delay detection flow program list;

[0011] The identity verification module is used to perform participant identity verification operations according to the data uploading methods of the participants;

[0012] The data uploading module is used to perform data uploading operations on the wolfberry data that has passed the delay detection.

[0013] Furthermore, the construction process of the wolfberry information management platform includes:

[0014] Construct a wolfberry information management platform based on blockchain technology. The wolfberry information management platform is communicatively connected with several blockchain nodes, and each blockchain node is linked to each other to form a blockchain network. Obtain the participants who join the wolfberry information management platform, and each participant who joins the wolfberry information management platform is communicatively linked to a blockchain node. The blockchain node is used to receive the wolfberry data uploaded by the participant and mark the upload time, and set the collection period.

[0015] Further, the process of the data analysis module dividing the supply process of wolfberries into several process subsequences according to the supply process information of wolfberries in the wolfberry information management platform, obtaining the error level of each process subsequence, and adding a feature matching detection mechanism to the blockchain node according to the error level includes:

[0016] Obtain the supply process information of wolfberries in the wolfberry information management platform, obtain the supply process characteristics according to the supply process information, split the supply process of wolfberries according to the supply process characteristics, divide it into several process subsequences, use data retrieval to obtain various types of wolfberry monitoring indicators that need to be collected for each process subsequence according to the supply process characteristics of the several process subsequences, obtain the process subsequences to which each participant in the wolfberry information management platform belongs, obtain the historical wolfberry data uploaded by several participants corresponding to each process subsequence in the wolfberry information management platform to the blockchain node. The various types of wolfberry monitoring indicators include origin indicators, processing indicators, logistics indicators, processed quality indicators, and unprocessed quality indicators. Obtain the error input probability and data upload method of various types of wolfberry monitoring indicators corresponding to each process subsequence according to the historical wolfberry data. The data upload method includes Internet of Things device integrated input and manual input;

[0017] Take the error input probability and data upload method of various types of wolfberry monitoring indicators corresponding to each process subsequence as evaluation indicators, set the index weight matrix of the evaluation indicators, judge the membership matrix of each process subsequence to the preset error level through fuzzy comprehensive evaluation, obtain the error level of each process subsequence according to the membership matrix and the index weight matrix, screen out the process subsequences with an error level greater than the preset error level threshold, obtain the participants corresponding to the process subsequences, and add a feature matching detection mechanism to the blockchain nodes connected to the participants.

[0018] Further, the process of the full-process prediction module outputting the predicted wolfberry data uploaded by each participant corresponding to each process subsequence includes:

[0019] Build a full-process prediction model based on deep learning, obtain the wolfberry data within several historical collection cycles of each blockchain node, use the wolfberry data as the training set and the test set, input the training set into the full-process prediction model for training until the loss function is trained stably, and save the model parameters. Test the full-process prediction model through the test set until it meets the preset requirements, and output the full-process prediction model;

[0020] Output the predicted wolfberry data uploaded by each participant corresponding to each process subsequence in the current collection cycle according to the full-process prediction model.

[0021] Further, the process of the feature matching detection module performing feature matching detection operations on the wolfberry data received by the blockchain nodes with the added feature matching detection mechanism includes:

[0022] Obtain the predicted wolfberry data uploaded by each participant corresponding to each process subsequence in the current collection period. When the blockchain node receives the wolfberry data uploaded by the participant, obtain the predicted wolfberry data of the participant, perform feature matching on the wolfberry data and the predicted wolfberry data, obtain the feature matching degree of the wolfberry data uploaded by the participant, compare the feature matching degree with the preset feature matching degree threshold. If the feature matching degree is greater than or equal to the feature matching degree threshold, store the wolfberry data in the temporary storage space of the blockchain node;

[0023] If the feature matching degree is less than the feature matching degree threshold, generate a data misreport warning signal for the participant and feedback it to the blockchain node. The blockchain node sends a data resending instruction to the participant according to the data misreport warning signal. The participant sends new wolfberry data to the blockchain node according to the data resending instruction. If the new wolfberry data is consistent with the wolfberry data, perform participant identity verification operations;

[0024] If the new wolfberry data is inconsistent with the wolfberry data, perform feature matching on the new wolfberry data and the predicted wolfberry data, obtain the feature matching degree of the new wolfberry data. If the feature matching degree of the new wolfberry data is less than the feature matching degree threshold, perform participant identity verification operations. If the feature matching degree of the new wolfberry data is greater than or equal to the feature matching degree threshold, store the new wolfberry data in the temporary storage space of the blockchain node.

[0025] Further, the process of the batch clustering module obtaining the wolfberry batch number in the wolfberry data, clustering the wolfberry data stored in the temporary storage spaces of several blockchain nodes according to the wolfberry batch number, and constructing a delay detection flow program list for several wolfberry batch numbers includes:

[0026] Obtain the wolfberry data stored in the temporary storage spaces of several blockchain nodes in the wolfberry information management platform, extract the wolfberry batch number from the wolfberry data, screen out the wolfberry data with the same wolfberry batch number from the wolfberry data stored in the temporary storage spaces of several blockchain nodes, obtain the process subsequence to which the wolfberry data belongs, obtain the sequential connection relationship of the process subsequences, and sort the wolfberry data of different process subsequences according to the sequential connection relationship to generate a delay detection flow program list;

[0027] Preset the delay detection standard for the last process subsequence in the delay detection process list, obtain the processed quality indicators in the wolfberry data of each process subsequence in the delay detection process list except the last one, obtain the next process subsequence of each process subsequence in the delay detection process list except the last one, and use the processed quality indicators in the wolfberry data of each process subsequence as the delay detection standard for the next process subsequence of each process subsequence.

[0028] Further, the process of the delay detection module performing delay detection on the wolfberry data stored in the temporary storage space of each blockchain node according to the delay detection process list includes:

[0029] Obtain the delay detection process list corresponding to the wolfberry data stored in the temporary storage space of the blockchain node, obtain the delay detection standard corresponding to the wolfberry data according to the delay detection process list, and at the same time obtain the unprocessed quality indicators in the wolfberry data, and compare the unprocessed quality indicators with the delay detection standard for consistency. If they are consistent, perform the operation of uploading the wolfberry data to the blockchain. If they are inconsistent, mark the participant who uploaded the wolfberry data as a malicious participant and delete the wolfberry data stored in the temporary storage space.

[0030] Further, the process of the identity authentication module performing participant identity authentication operations according to the participant's data upload method includes:

[0031] If the participant's data upload method is integrated input by Internet of Things devices, generate an early warning message for the failure of the participant's Internet of Things devices.

[0032] If the participant's data upload method is manual input, pre - construct a biometric database. The biometric database includes the biometric data of participants whose data upload method is manual input. The blockchain node sends a biometric verification instruction to the participant. The participant sends biometric data to the blockchain according to the biometric verification instruction, and perform a consistency match between the biometric data and the biometric data in the biometric database. If the match is successful, store the wolfberry data uploaded by the participant in the temporary storage space of the blockchain node. If the match fails, delete the wolfberry data uploaded by the participant received by the blockchain node and mark the participant as a malicious participant.

[0033] Further, the process of the data - on - chain module performing data - on - chain operations on the wolfberry data that has passed the delay detection includes:

[0034] Preset the mining nodes, verification rules, and consensus mechanism of the blockchain network. Create a new block through the mining nodes, transfer the wolfberry data stored in the temporary storage space of the blockchain nodes to the new block, and broadcast the new block to the blockchain network. Other blockchain nodes in the blockchain network verify the new block based on the verification rules and consensus mechanism;

[0035] After the verification of the new block passes, link the new block to the blockchain nodes and update the wolfberry data in the new block to the blockchain copies of all blockchain nodes.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] The method for tracing and managing the origin information of wolfberry based on blockchain technology described by you aims to solve the problems of data input accuracy and data consistency. By introducing technical means such as a feature matching detection mechanism and a delay detection flow sequence, the reliability and accuracy of the data are improved. The specific implementation of this method can bring the following beneficial effects:

[0038] 1. Improve data accuracy:

[0039] Feature matching detection mechanism: By adding a feature matching detection mechanism to the blockchain nodes, data that does not meet the preset features can be automatically identified and filtered out, thereby reducing the possibility of human error or intentional fraud;

[0040] Delay detection flow sequence: Use the delay detection flow sequence to further verify the data to ensure that only data that has been confirmed multiple times can finally be uploaded to the chain, which can effectively avoid the influence of one-time incorrect data.

[0041] 2. Ensure data consistency:

[0042] Process subsequence division: Refine the supply process of wolfberry into several process subsequences and conduct specialized management for each subsequence, which helps to ensure the consistency of data between different links;

[0043] Error level assessment: By evaluating the error levels of each process subsequence, the management and supervision of those links that are more prone to errors can be strengthened in a targeted manner.

[0044] 3. Achieve data clustering and traceability:

[0045] Wolfberry batch number: Assign a unique batch number to each batch of wolfberry and cluster the data based on this, which helps to achieve precise traceability of specific batches of wolfberry;

[0046] List of Delayed Detection Processes: By constructing a list of delayed detection processes, data in the temporary storage spaces of individual blockchain nodes can be detected with a delay to ensure the timeliness and accuracy of the data.

[0047] 4. Strengthen Participant Authentication:

[0048] Authentication Operation: By authenticating the data upload methods of participants, it can be ensured that only authenticated participants can upload data, thereby reducing the risk of illegal operations.

[0049] 5. Improve System Flexibility and Scalability:

[0050] Dynamic Adjustment: The feature matching detection mechanism based on the error level can be dynamically adjusted according to the actual situation, enabling the system to adapt to changing business requirements.

[0051] 6. Improve User Experience:

[0052] Transparent Management: Through the information transparent management achieved by blockchain technology, it can not only improve the efficiency and accuracy of the traceability management of wolfberry origin information, but also largely solve the problems of data input accuracy and data consistency, thereby enhancing the transparency and reliability of the entire supply chain. Consumers can more intuitively understand the origin and production process of wolfberries, thus enhancing their trust in the products. Description of the Drawings

[0053] Figure 1 It is a schematic diagram of a wolfberry origin information traceability management system based on blockchain according to an embodiment of the present application. Detailed Embodiments

[0054] Next, in combination with the drawings in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0055] As Figure 1 shown, a wolfberry origin information traceability management system based on blockchain includes a wolfberry information management platform, and the wolfberry information management platform is communicatively connected to a data analysis module, a full-process prediction module, a feature matching detection module, a batch clustering module, a delay detection module, an authentication module, and a data on-chain module;

[0056] The data analysis module is used to divide the supply process of wolfberries into several process subsequences according to the supply process information of wolfberries in the wolfberry information management platform, obtain the error levels of each process subsequence, and add a feature matching detection mechanism to the blockchain nodes according to the error levels;

[0057] The full-process prediction module is used to output the predicted wolfberry data uploaded by each participant corresponding to each process subsequence;

[0058] The feature matching detection module is used to perform feature matching detection operations on the wolfberry data received by the blockchain nodes with the added feature matching detection mechanism;

[0059] The batch clustering module obtains the wolfberry batch numbers in the wolfberry data, clusters the wolfberry data stored in the temporary storage spaces of several blockchain nodes according to the wolfberry batch numbers, and constructs a list of delay detection flow programs for several wolfberry batch numbers;

[0060] The delay detection module is used to perform delay detection on the wolfberry data stored in the temporary storage spaces of each blockchain node according to the list of delay detection flow programs;

[0061] The identity authentication module is used to perform participant identity authentication operations according to the data upload methods of the participants;

[0062] The data on-chain module is used to perform data on-chain operations on the wolfberry data that has passed the delay detection.

[0063] It should be further noted that in the specific implementation process, the construction process of the wolfberry information management platform includes:

[0064] Build a wolfberry information management platform based on blockchain technology. The wolfberry information management platform is communicatively connected to several blockchain nodes, and each blockchain node is interconnected with each other to form a blockchain network. Obtain the participants who join the wolfberry information management platform. The participants include growers, processing enterprises, distributors, and retailers, etc. Each participant who joins the wolfberry information management platform is communicatively linked to a blockchain node. The blockchain node is used to receive the wolfberry data uploaded by the participant and mark the upload time, and set the collection period.

[0065] It should be further noted that in the specific implementation process, the process in which the data analysis module divides the supply process of wolfberries into several process subsequences according to the supply process information of wolfberries in the wolfberry information management platform, obtains the error levels of each process subsequence, and adds a feature matching detection mechanism to the blockchain nodes according to the error levels includes:

[0066] Obtain the supply process information of wolfberries in the wolfberry information management platform, obtain the supply process characteristics according to the supply process information, split the supply process of wolfberries according to the supply process characteristics, divide it into several process subsequences, and use data retrieval to obtain various types of wolfberry monitoring indicators that need to be collected for the several process subsequences according to the supply process characteristics of the several process subsequences. The supply process characteristics include planting, fertilizing, irrigation, picking, primary processing (such as cleaning, screening), deep processing (such as drying, packaging), and transportation, etc. Obtain the process subsequences to which each participant in the wolfberry information management platform belongs, obtain the historical wolfberry data uploaded by several participants corresponding to each process subsequence in the wolfberry information management platform to the blockchain node. The various types of wolfberry monitoring indicators include origin indicators, processing indicators, logistics indicators, processed quality indicators, and unprocessed quality indicators. Obtain the error input probability and data upload method of various types of wolfberry monitoring indicators corresponding to each process subsequence according to the historical wolfberry data. The data upload method includes Internet of Things device integrated input and manual input;

[0067] Take the error input probability and data upload method of various types of wolfberry monitoring indicators corresponding to each process subsequence as evaluation indicators, set the index weight matrix of the evaluation indicators, judge the membership matrix of each process subsequence to the preset error level through fuzzy comprehensive evaluation, obtain the error level of each process subsequence according to the membership matrix and the index weight matrix, screen out the process subsequences with an error level greater than the preset error level threshold, obtain the participants corresponding to the process subsequences, and add a feature matching detection mechanism to the blockchain nodes connected to the participants.

[0068] It should be further noted that in the specific implementation process, the process of obtaining the error input probability of various types of wolfberry monitoring indicators corresponding to each process subsequence is as follows:

[0069] Obtain the cumulative number of times the participants corresponding to each process subsequence upload wolfberry data in all historical collection cycles, and the cumulative number of malicious times of the participants corresponding to each process subsequence being marked as malicious participants when uploading wolfberry data. Obtain various types of wolfberry monitoring indicators corresponding to each process subsequence, add the cumulative number of times the participants corresponding to each process subsequence upload wolfberry data and the cumulative number of malicious times of the participants corresponding to each process subsequence being marked as malicious participants when uploading wolfberry data to various types of wolfberry monitoring indicators corresponding to each process subsequence. Obtain the cumulative number of times and the cumulative number of malicious times corresponding to various types of wolfberry monitoring indicators. According to the cumulative number of times and the cumulative number of malicious times corresponding to various types of wolfberry monitoring indicators, obtain the error input probability of various types of wolfberry monitoring indicators corresponding to each process subsequence. Its calculation formula is:

[0070]

[0071] Among them, fhi Represents the error input probability of the wolfberry monitoring index i of type NV i Represents the cumulative number of times corresponding to the wolfberry monitoring index i of type NS i Represents the malicious cumulative number of times corresponding to the wolfberry monitoring index i of type

[0072] It should be further noted that in the specific implementation process, the data upload methods include integrated input of Internet of Things devices and manual input. The integrated input of Internet of Things devices specifically refers to installing sensors and other Internet of Things devices in the planting base to monitor environmental indicators such as soil humidity, temperature, and light intensity in real time, as well as relevant indicators in the processes of processing, packaging, storage, and transportation collected by Internet of Things devices in the supply chain process, such as batch numbers, processing dates, storage conditions, etc. The manual input specifically refers to the staff manually inputting the index data of important activities such as planting, fertilizing, irrigating, and picking;

[0073] It should be further noted that in the specific implementation process, the wolfberry monitoring indicators of each type include:

[0074] Origin indicators: Include index data such as the wolfberry planting area, soil composition, climate conditions, irrigation water, fertilizer and pesticide usage in the planting area;

[0075] Processing indicators: Include index data of each link such as wolfberry planting, fertilizing, irrigating, picking, primary processing (such as cleaning, screening), and deep processing (such as drying, packaging);

[0076] Logistics indicators: Include timestamp and location information, batch numbers, processing dates, storage conditions, etc. of each logistics node from the warehouse to the transport vehicle and then to the retailer;

[0077] Processed quality indicators: The processed quality indicators represent the indicators of wolfberries after processing by the participants in the process subsequence where the wolfberries are located according to the supply process characteristics of the process subsequence where the wolfberries are located after receiving the wolfberry goods. The indicators include color, size, shape, dryness and wetness, impurity (such as branches, leaves, soil clods, etc.) content, betaine, wolfberry polysaccharide (LBP): One of the main active ingredients of wolfberries, with immunomodulatory effects, carotenoids: Such as β-carotene, beneficial to eyesight, flavonoids: With antioxidant effects, amino acids: Multiple essential amino acids for the human body, mineral elements: Such as trace elements such as calcium, iron, and zinc, vitamin content, total bacterial count: Ensure that wolfberries are not contaminated by harmful microorganisms, molds, and yeasts, etc.;

[0078] Untreated quality indicators: The indicators of goji berries when the participants in the process subsequence where the untreated quality indicator goji berries are located have just received the goji berry goods and have not performed any processing on the goji berries in the goji berry goods. The initial indicators include color, size, shape, dryness and wetness, impurity (such as branches, leaves, soil clods, etc.) content, betaine, lycium barbarum polysaccharide (LBP): One of the main active ingredients of goji berries, having immunomodulatory effects, carotenoids: Such as β-carotene, beneficial to eyesight, flavonoids: Having antioxidant effects, amino acids: A variety of essential amino acids for the human body, mineral elements: Such as trace elements like calcium, iron, zinc, etc., vitamin content, total bacterial count: Ensuring that goji berries are not contaminated by harmful microorganisms, molds and yeasts, etc.;

[0079] It should be further noted that in the specific implementation process, several process subsequences include the planting preparation stage, growth stage, harvesting stage, processing stage, logistics and warehousing stage, and sales stage;

[0080] It should be further noted that in the specific implementation process, the process of obtaining the error level of each process subsequence according to the membership matrix and the index weight matrix includes:

[0081] Fusing the index weight matrix and the membership matrix of the evaluation index through a formula to obtain the fuzzy comprehensive evaluation matrix of the evaluation index, obtaining the membership degree of each process subsequence for different error levels according to the fuzzy comprehensive evaluation matrix, screening out the error level with the highest membership degree corresponding to each process subsequence, and taking the error level with the highest membership degree corresponding to each process subsequence as the error level of each process subsequence;

[0082] Among them, the formula is:

[0083] M = αM1 × βM2;

[0084] Among them, M is the fuzzy comprehensive evaluation matrix of the evaluation index, M1 is the index weight matrix of the evaluation index, M2 is the membership matrix, "×" represents the multiplication of the elements at the corresponding positions of the weight matrix and the membership matrix of the evaluation index, and α and β are weighted parameters used to control the balance between the weight matrix and the membership matrix in the fuzzy comprehensive evaluation matrix of the evaluation index.

[0085] It should be further noted that in the specific implementation process, the process by which the full-process prediction module outputs the predicted goji berry data uploaded by each participant corresponding to each process subsequence includes:

[0086] Build a full - process prediction model based on deep learning, obtain the wolfberry data of each blockchain node within a number of historical collection cycles, use the wolfberry data as the training set and the test set, input the training set into the full - process prediction model for training until the loss function is trained stably, save the model parameters, test the full - process prediction model with the test set until it meets the preset requirements, and output the full - process prediction model;

[0087] Output the predicted wolfberry data uploaded by each participant corresponding to each process subsequence in the current collection cycle according to the full - process prediction model.

[0088] It should be further noted that in the specific implementation process, the process of the feature matching detection module performing feature matching detection operations on the wolfberry data received by the blockchain node with the added feature matching detection mechanism includes:

[0089] Obtain the predicted wolfberry data uploaded by each participant corresponding to each process subsequence in the current collection cycle. When the blockchain node receives the wolfberry data uploaded by the participant, obtain the predicted wolfberry data of the participant, perform feature matching on the wolfberry data and the predicted wolfberry data, obtain the feature matching degree of the wolfberry data uploaded by the participant, compare the feature matching degree with the preset feature matching degree threshold. If the feature matching degree is greater than or equal to the feature matching degree threshold, store the wolfberry data in the temporary storage space of the blockchain node;

[0090] Among them, the calculation formula for obtaining the feature matching degree of the wolfberry data uploaded by the participant is:

[0091]

[0092] Among them, g represents the feature matching degree, D i represents the value of the wolfberry monitoring index i in the wolfberry data, DA i represents the value of the wolfberry monitoring index i in the predicted wolfberry data, and n represents the total number of wolfberry monitoring index types in the wolfberry data.

[0093] If the feature matching degree is less than the feature matching degree threshold, generate a data misreport warning signal for the participant and feedback it to the blockchain node. The blockchain node sends a data resend instruction to the participant according to the data misreport warning signal. The participant sends new wolfberry data to the blockchain node according to the data resend instruction. If the new wolfberry data is consistent with the wolfberry data, perform the participant identity verification operation;

[0094] If the new wolfberry data is inconsistent with the wolfberry data, the new wolfberry data is feature-matched with the predicted wolfberry data to obtain the feature matching degree of the new wolfberry data. If the feature matching degree of the new wolfberry data is less than the feature matching degree threshold, a participant identity verification operation is performed. If the feature matching degree of the new wolfberry data is greater than or equal to the feature matching degree threshold, the new wolfberry data is stored in the temporary storage space of the blockchain node.

[0095] It should be further noted that in the specific implementation process, the process of the batch clustering module obtaining the wolfberry batch numbers in the wolfberry data and clustering the wolfberry data stored in the temporary storage spaces of several blockchain nodes according to the wolfberry batch numbers to construct a delay detection flow program list for several wolfberry batch numbers includes:

[0096] Obtain the wolfberry data stored in the temporary storage spaces of several blockchain nodes in the wolfberry information management platform, extract the wolfberry batch numbers from the wolfberry data, screen out the wolfberry data with the same wolfberry batch number from the wolfberry data stored in the temporary storage spaces of several blockchain nodes, obtain the process subsequence to which the wolfberry data belongs, obtain the sequential connection relationship of the process subsequences, and sort the wolfberry data of different process subsequences according to the sequential connection relationship to generate a delay detection flow program list;

[0097] Pre-set the delay detection criteria for the last process subsequence in the delay detection flow program list, obtain the processed quality indicators in the wolfberry data of each process subsequence except the last process subsequence in the delay detection flow program list, obtain the next process subsequence of each process subsequence except the last process subsequence in the delay detection flow program list, and use the processed quality indicators in the wolfberry data of each process subsequence as the delay detection criteria for the next process subsequence of each process subsequence.

[0098] It should be further noted that in the specific implementation process, the process of the delay detection module performing delay detection on the wolfberry data stored in the temporary storage spaces of each blockchain node according to the delay detection flow program list includes:

[0099] Obtain the delay detection flow program list corresponding to the wolfberry data stored in the temporary storage space of the blockchain node, obtain the delay detection criteria corresponding to the wolfberry data according to the delay detection flow program list, and at the same time obtain the unprocessed quality indicators in the wolfberry data. Compare the unprocessed quality indicators with the delay detection criteria. If they are consistent, perform the operation of uploading the wolfberry data to the blockchain. If they are inconsistent, mark the participant who uploaded the wolfberry data as a malicious participant and delete the wolfberry data stored in the temporary storage space.

[0100] It should be further noted that, in the specific implementation process, the process of the identity authentication module performing the participant identity authentication operation according to the participant's data upload method includes:

[0101] If the participant's data upload method is Internet of Things device integrated input, an Internet of Things device fault warning message for the participant is generated;

[0102] If the participant's data upload method is manual input, a biometric database is pre-constructed. The biometric database includes the biometric data of participants whose data upload method is manual input. The blockchain node sends a biometric verification instruction to the participant. The participant sends the biometric data to the blockchain according to the biometric verification instruction. The biometric data is matched with the biometric data in the biometric database for consistency. If the match is successful, the wolfberry data uploaded by the participant is stored in the temporary storage space of the blockchain node. If the match fails, the wolfberry data uploaded by the participant received by the blockchain node is eliminated, and the participant is marked as a malicious participant.

[0103] It should be further noted that, in the specific implementation process, the process of the data on-chain module performing the data on-chain operation on the wolfberry data that has passed the delay detection includes:

[0104] Preset the mining nodes, verification rules, and consensus mechanism of the blockchain network. Create a new block through the mining node, transfer the wolfberry data stored in the temporary storage space of the blockchain node to the new block, and broadcast the new block to the blockchain network. Other blockchain nodes in the blockchain network verify the new block based on the verification rules and consensus mechanism;

[0105] After the verification of the new block passes, link the new block with the blockchain node, and update the wolfberry data in the new block to the blockchain copies of all blockchain nodes.

[0106] It should be further noted that, in the specific implementation process, the wolfberry information management platform sets up a wolfberry product traceability window. Users can log in to the wolfberry information management platform and input the wolfberry batch number of the wolfberry to be traced through the wolfberry product traceability window. The wolfberry information management platform retrieves the wolfberry data corresponding to each process subsequence corresponding to the wolfberry batch number from the blockchain network and feedbacks it to the user.

[0107] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A wolfberry origin information traceability management system based on blockchain, characterized in that, It includes a wolfberry information management platform, which is communicatively connected to a data analysis module, a full-process prediction module, a feature matching detection module, a batch clustering module, a delay detection module, an identity authentication module, and a data uploading module to the blockchain; The data analysis module is used to divide the supply process of wolfberries into several process subsequences according to the supply process information of wolfberries in the wolfberry information management platform, obtain the error levels of each process subsequence, and add a feature matching detection mechanism to the blockchain nodes according to the error levels; The full-process prediction module is used to output the predicted wolfberry data uploaded by each participant corresponding to each process subsequence; The feature matching detection module is used to perform feature matching detection operations on the wolfberry data received by the blockchain nodes with the added feature matching detection mechanism; The batch clustering module obtains the wolfberry batch numbers in the wolfberry data, clusters the wolfberry data stored in the temporary storage spaces of several blockchain nodes according to the wolfberry batch numbers, and constructs a list of delay detection flow programs for several wolfberry batch numbers; The delay detection module is used to perform delay detection on the wolfberry data stored in the temporary storage spaces of each blockchain node according to the list of delay detection flow programs; The identity authentication module is used to perform participant identity authentication operations according to the data uploading methods of the participants; The data uploading module to the blockchain is used to perform data uploading operations on the wolfberry data that has passed the delay detection; The process in which the delay detection module performs delay detection on the wolfberry data stored in the temporary storage spaces of each blockchain node according to the list of delay detection flow programs includes: Obtain the list of delay detection flow programs corresponding to the wolfberry data stored in the temporary storage space of the blockchain node, obtain the delay detection standards corresponding to the wolfberry data according to the list of delay detection flow programs, and at the same time obtain the unprocessed quality indicators in the wolfberry data. Compare the unprocessed quality indicators with the delay detection standards for consistency. If they are consistent, perform data uploading operations on the wolfberry data. If they are inconsistent, mark the participant who uploaded the wolfberry data as a malicious participant and delete the wolfberry data stored in the temporary storage space.

2. The wolfberry origin information traceability management system based on blockchain according to claim 1, wherein, The construction process of the wolfberry information management platform includes: Build a wolfberry information management platform based on blockchain technology. The wolfberry information management platform is communicatively connected to several blockchain nodes, and each blockchain node is interconnected with each other to form a blockchain network. Obtain the participants who join the wolfberry information management platform, and each participant who joins the wolfberry information management platform is communicatively linked to a blockchain node. The blockchain node is used to receive the wolfberry data uploaded by the participant and mark the upload time, and set the collection period.

3. The Lycium barbarum origin information traceability management system based on blockchain according to claim 2, wherein, The process in which the data analysis module divides the supply process of wolfberries into several process subsequences according to the supply process information of wolfberries in the wolfberry information management platform, obtains the error levels of each process subsequence, and adds a feature matching detection mechanism to the blockchain nodes according to the error levels includes: Obtain the supply process information of wolfberries in the wolfberry information management platform, obtain the supply process characteristics according to the supply process information, split the supply process of wolfberries according to the supply process characteristics, divide it into several process subsequences, use data retrieval to obtain various types of wolfberry monitoring indicators that need to be collected for several process subsequences according to the supply process characteristics of several process subsequences, obtain the process subsequences to which each participant in the wolfberry information management platform belongs, obtain the historical wolfberry data uploaded by several participants corresponding to each process subsequence in the wolfberry information management platform to the blockchain node. The various types of wolfberry monitoring indicators include origin indicators, processing indicators, logistics indicators, processed quality indicators, and unprocessed quality indicators. Obtain the error input probability and data upload method of various types of wolfberry monitoring indicators corresponding to each process subsequence according to the historical wolfberry data. The data upload method includes Internet of Things device integrated input and manual input; Take the error input probability and data upload method of various types of wolfberry monitoring indicators corresponding to each process subsequence as evaluation indicators, set the index weight matrix of the evaluation indicators, judge the membership degree matrix of each process subsequence to the preset error level through fuzzy comprehensive evaluation, obtain the error level of each process subsequence according to the membership degree matrix and the index weight matrix, screen out the process subsequences whose error level is greater than the preset error level threshold, obtain the participants corresponding to the process subsequences, and add a feature matching detection mechanism to the blockchain nodes connected to the participants.

4. The traceability management system for wolfberry origin information based on blockchain according to claim 3, characterized in that, The process of the full-process prediction module outputting the predicted wolfberry data uploaded by each participant corresponding to each process subsequence includes: Build a full-process prediction model based on deep learning, obtain the wolfberry data in several historical collection periods of each blockchain node, use the wolfberry data as the training set and the test set, input the training set into the full-process prediction model for training until the loss function is trained stably, save the model parameters, test the full-process prediction model through the test set until it meets the preset requirements, and output the full-process prediction model; Output the predicted wolfberry data uploaded by each participant corresponding to each process subsequence in the current collection period according to the full-process prediction model.

5. The wolfberry origin information traceability management system based on blockchain according to claim 4, characterized in that, The process of the feature matching detection module performing feature matching detection operations on the wolfberry data received by the blockchain node with the added feature matching detection mechanism includes: Obtain the predicted wolfberry data uploaded by each participant corresponding to each process subsequence in the current collection period. When the blockchain node receives the wolfberry data uploaded by the participant, obtain the predicted wolfberry data of the participant, perform feature matching on the wolfberry data and the predicted wolfberry data, obtain the feature matching degree of the wolfberry data uploaded by the participant, compare the feature matching degree with the preset feature matching degree threshold. If the feature matching degree is greater than or equal to the feature matching degree threshold, store the wolfberry data in the temporary storage space of the blockchain node; If the feature matching degree is less than the feature matching degree threshold, a data misreport warning signal of the participant is generated and fed back to the blockchain node. The blockchain node sends a data resending instruction to the participant according to the data misreport warning signal. The participant sends new wolfberry data to the blockchain node according to the data resending instruction. If the new wolfberry data is consistent with the wolfberry data, the participant identity verification operation is performed; If the new wolfberry data is inconsistent with the wolfberry data, the new wolfberry data is feature-matched with the predicted wolfberry data to obtain the feature matching degree of the new wolfberry data. If the feature matching degree of the new wolfberry data is less than the feature matching degree threshold, the participant identity verification operation is performed. If the feature matching degree of the new wolfberry data is greater than or equal to the feature matching degree threshold, the new wolfberry data is stored in the temporary storage space of the blockchain node.

6. The wolfberry origin information traceability management system based on blockchain according to claim 5, characterized in that, The process that the batch clustering module obtains the wolfberry batch numbers in the wolfberry data and clusters the wolfberry data stored in the temporary storage spaces of several blockchain nodes according to the wolfberry batch numbers to construct a list of delay detection flow programs for several wolfberry batch numbers includes: Obtain the wolfberry data stored in the temporary storage spaces of several blockchain nodes in the wolfberry information management platform, extract the wolfberry batch numbers from the wolfberry data, screen out the wolfberry data with the same wolfberry batch numbers as the extracted wolfberry batch numbers from the wolfberry data stored in the temporary storage spaces of several blockchain nodes, obtain the process subsequences to which the wolfberry data belongs, obtain the sequential connection relationship of the process subsequences, and sort the wolfberry data of different process subsequences according to the sequential connection relationship to generate a list of delay detection flow programs; Preset the delay detection criteria for the last process subsequence in the list of delay detection flow programs, obtain the processed quality indicators in the wolfberry data of each process subsequence except the last process subsequence in the list of delay detection flow programs, obtain the next process subsequence of each process subsequence except the last process subsequence in the list of delay detection flow programs, and use the processed quality indicators in the wolfberry data of each process subsequence as the delay detection criteria for the next process subsequence of each process subsequence.

7. The traceability management system for wolfberry origin information based on blockchain according to claim 6, characterized in that, The process that the identity verification module performs the participant identity verification operation according to the data upload method of the participant includes: If the data upload method of the participant is integrated input by an Internet of Things device, an Internet of Things device failure warning message of the participant is generated; If the data upload method of the participant is manual input, a biometric database is pre-constructed. The biometric database includes the biometric data of the participants whose data upload method is manual input. The blockchain node sends a biometric verification instruction to the participant. The participant sends biometric data to the blockchain according to the biometric verification instruction. The biometric data is matched for consistency with the biometric data in the biometric database. If the match is successful, the wolfberry data uploaded by the participant is stored in the temporary storage space of the blockchain node. If the match fails, the wolfberry data uploaded by the participant received by the blockchain node is excluded, and the participant is marked as a malicious participant.

8. The wolfberry origin information traceability management system based on blockchain according to claim 7, characterized in that, The process that the data on-chain module performs the data on-chain operation on the wolfberry data that has passed the delay detection includes: Preset the mining nodes, verification rules, and consensus mechanism of the blockchain network. Create a new block through the mining nodes, transfer the wolfberry data stored in the temporary storage space of the blockchain nodes to the new block, and broadcast the new block to the blockchain network. Other blockchain nodes in the blockchain network verify the new block based on the verification rules and consensus mechanism; After the verification of the new block passes, link the new block to the blockchain nodes and update the wolfberry data in the new block to the blockchain copies of all blockchain nodes.

Images