A traceability authentication method based on blockchain

Abstract

The present invention relates to the field of blockchain technology, and in particular to a traceability authentication method based on blockchain. The method comprises the following steps: dividing the original alliance blockchain into primary and secondary consensus nodes of each alliance member node to obtain primary and secondary alliance chains; performing clustering vector association of upstream and downstream blocks on the block data set to obtain traceability authentication associated data; constructing a three-dimensional credit model for the alliance member data to obtain a three-dimensional credit model; performing unique credit score association based on the three-dimensional credit model to obtain unique identification score data; constructing a consensus probability model for the traceability authentication associated data and the unique identification score data to obtain a feature consensus probability model; constructing a traceability credit network model for the traceability alignment clustering data based on the feature consensus probability model to obtain a traceability credit network model; constructing an authentication feature trust model to obtain an authentication proof trust probability model. The present invention achieves an efficient and reliable blockchain traceability authentication effect.

Description

Technical Field

[0001] The present invention relates to the technical field of blockchain, and in particular to a traceability authentication method based on blockchain. Background Art

[0002] With the acceleration of globalization and the increasing attention of consumers to product quality and safety, product traceability and certification have also begun to develop rapidly. However, traditional traceability and certification methods have problems and challenges such as information asymmetry, information opacity, and opacity of the security and reliability of traceable data. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a traceability authentication method based on blockchain to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a traceability authentication method based on blockchain, comprising the following steps:

[0005] Step S1: Obtain the original alliance blockchain; divide the original alliance blockchain into primary and secondary consensus nodes for each alliance member node, thereby obtaining primary and secondary alliance chains;

[0006] Step S2: Authenticate the traceability business data based on the primary and secondary alliance chains to obtain the traceability data to be agreed upon; publish the block of the traceability data to be agreed upon to obtain the traceability block data;

[0007] Step S3: Request block data from the primary and secondary alliance chains to obtain block data sets; cluster the features of upstream and downstream blocks on the block data sets to obtain traceability alignment cluster data; integrate the proof detail features on the block data sets to obtain authentication proof detail data; perform cluster vector association on the traceability alignment cluster data and the authentication proof detail data to obtain traceability authentication association data;

[0008] Step S4: Acquire alliance member data; construct a three-dimensional credit model for the alliance member data, thereby obtaining a three-dimensional credit model; perform unique credit score association based on the three-dimensional credit model, thereby obtaining unique identification score data;

[0009] Step S5: construct a consensus probability model for the traceability authentication associated data and the unique identification scoring data, thereby obtaining a feature consensus probability model; construct a traceability credit network model for the traceability alignment clustering data based on the feature consensus probability model, thereby obtaining a traceability credit network model;

[0010] Step S6: Based on the traceability credit network model, a product traceability request for a unique identification code is made to the dynamic primary and secondary alliance chains to obtain product traceability data; an authentication feature trust model is constructed for the unique identification scoring data and the authentication proof detail data to obtain an authentication proof trust probability model.

[0011] The present invention uses blockchain technology to divide primary and secondary consensus nodes, ensure the distribution of consensus responsibilities among alliance members, improve consensus efficiency, enhance the credibility and stability of the alliance, help improve the performance and scalability of the system, and enable alliance members to participate in the traceability authentication process more efficiently. Tracing business data authentication based on primary and secondary alliance chains can ensure the authenticity and integrity of data, prevent data tampering and forgery, and enhance the credibility of traceability results; the release of traceability block data can realize the openness and transparency of data, and anyone can verify and review the traceability process, which improves the credibility and traceability of traceability. By performing block data requests and feature clustering on primary and secondary alliance chains, the traceability data can be effectively sorted and analyzed, the readability and comprehensibility of the data can be improved, and the subsequent traceability authentication process is convenient; the acquisition of traceability authentication associated data can help identify and analyze the association between traceability data, discover potential problems and risks, and help make decisions and improve traceability authentication measures. Acquiring alliance member data can provide more comprehensive and accurate traceability information, increasing the credibility and authenticity of traceability data; by building a three-dimensional credit model and performing unique credit score association, the credit of alliance members can be quantified and evaluated, providing credibility assessment indicators for traceability data, and helping to identify high-risk and low-risk traceability data. Building a consensus probability model can further analyze and process traceability certification association data, provide trust and credibility assessment of traceability certification, and help decision makers better understand and use traceability data; building a traceability credit network model based on a feature consensus probability model can reveal the trust relationship and network topology between traceability data, help to discover anomalies and risks, and take corresponding measures to handle and improve them. Product traceability requests based on the traceability credit network model can accurately locate specific product information, provide accurate traceability results, and help consumers and regulators trace and verify products; building an authentication feature trust model can comprehensively consider unique identification score data and authentication certificate detail data, evaluate the credibility of authentication certificates, and provide a corresponding trust probability model, which enhances the credibility and reliability of traceability results. The above steps can improve the credibility and authenticity of traceability data and reduce the risk of data tampering and forgery. Enhance the credibility and traceability of traceability results, and improve the trust of consumers and regulators in product traceability. Discover potential problems and risks, and help decision makers formulate corresponding improvement measures. Provide quantitative credit assessment indicators to conduct credit assessment on traceability data and alliance members. Reveal the trust relationship and network topology between traceability data to help identify anomalies and risks. Provide accurate product traceability results to help consumers and regulators trace and verify products. Comprehensively evaluate the credibility of certification proofs, provide a trust probability model, and enhance the credibility and reliability of traceability results. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1This is a schematic diagram of the steps of the blockchain-based traceability authentication method of the present invention;

[0013] Figure 2 Detailed implementation flow chart of step S1;

[0014] Figure 3 Detailed implementation flow chart of step S2. DETAILED DESCRIPTION

[0015] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0016] This application example provides a blockchain-based traceability authentication method. The execution subject of the blockchain-based traceability authentication method includes but is not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload device, etc. equipped with the system can be regarded as the general computing node of this application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0017] See also Figures 1 to 3 The present invention provides a traceability authentication method based on blockchain, the method comprising the following steps:

[0018] Step S1: Obtain the original alliance blockchain; divide the original alliance blockchain into primary and secondary consensus nodes for each alliance member node, thereby obtaining primary and secondary alliance chains;

[0019] Step S2: Authenticate the traceability business data based on the primary and secondary alliance chains to obtain the traceability data to be agreed upon; publish the block of the traceability data to be agreed upon to obtain the traceability block data;

[0020] Step S3: Request block data from the primary and secondary alliance chains to obtain block data sets; cluster the features of upstream and downstream blocks on the block data sets to obtain traceability alignment cluster data; integrate the proof detail features on the block data sets to obtain authentication proof detail data; perform cluster vector association on the traceability alignment cluster data and the authentication proof detail data to obtain traceability authentication association data;

[0021] Step S4: Acquire alliance member data; construct a three-dimensional credit model for the alliance member data, thereby obtaining a three-dimensional credit model; perform unique credit score association based on the three-dimensional credit model, thereby obtaining unique identification score data;

[0022] Step S5: construct a consensus probability model for the traceability authentication associated data and the unique identification scoring data, thereby obtaining a feature consensus probability model; construct a traceability credit network model for the traceability alignment clustering data based on the feature consensus probability model, thereby obtaining a traceability credit network model;

[0023] Step S6: Based on the traceability credit network model, a product traceability request for a unique identification code is made to the dynamic primary and secondary alliance chains to obtain product traceability data; an authentication feature trust model is constructed for the unique identification scoring data and the authentication proof detail data to obtain an authentication proof trust probability model.

[0024] The present invention uses blockchain technology to divide primary and secondary consensus nodes, ensure the distribution of consensus responsibilities among alliance members, improve consensus efficiency, enhance the credibility and stability of the alliance, help improve the performance and scalability of the system, and enable alliance members to participate in the traceability authentication process more efficiently. Tracing business data authentication based on primary and secondary alliance chains can ensure the authenticity and integrity of data, prevent data tampering and forgery, and enhance the credibility of traceability results; the release of traceability block data can realize the openness and transparency of data, and anyone can verify and review the traceability process, which improves the credibility and traceability of traceability. By performing block data requests and feature clustering on primary and secondary alliance chains, the traceability data can be effectively sorted and analyzed, the readability and comprehensibility of the data can be improved, and the subsequent traceability authentication process is convenient; the acquisition of traceability authentication associated data can help identify and analyze the association between traceability data, discover potential problems and risks, and help make decisions and improve traceability authentication measures. Acquiring alliance member data can provide more comprehensive and accurate traceability information, increasing the credibility and authenticity of traceability data; by building a three-dimensional credit model and performing unique credit score association, the credit of alliance members can be quantified and evaluated, providing credibility assessment indicators for traceability data, and helping to identify high-risk and low-risk traceability data. Building a consensus probability model can further analyze and process traceability certification association data, provide trust and credibility assessment of traceability certification, and help decision makers better understand and use traceability data; building a traceability credit network model based on a feature consensus probability model can reveal the trust relationship and network topology between traceability data, help to discover anomalies and risks, and take corresponding measures to handle and improve them. Product traceability requests based on the traceability credit network model can accurately locate specific product information, provide accurate traceability results, and help consumers and regulators trace and verify products; building an authentication feature trust model can comprehensively consider unique identification score data and authentication certificate detail data, evaluate the credibility of authentication certificates, and provide a corresponding trust probability model, which enhances the credibility and reliability of traceability results. The above steps can improve the credibility and authenticity of traceability data and reduce the risk of data tampering and forgery. Enhance the credibility and traceability of traceability results, and improve the trust of consumers and regulators in product traceability. Discover potential problems and risks, and help decision makers formulate corresponding improvement measures. Provide quantitative credit assessment indicators to conduct credit assessment on traceability data and alliance members. Reveal the trust relationship and network topology between traceability data to help identify anomalies and risks. Provide accurate product traceability results to help consumers and regulators trace and verify products. Comprehensively evaluate the credibility of certification proofs, provide a trust probability model, and enhance the credibility and reliability of traceability results.

[0025] In this embodiment, reference Figure 1The above is a schematic diagram of the steps of the traceability authentication method based on blockchain of the present invention. The steps of the traceability authentication method based on blockchain include:

[0026] Step S1: Obtain the original alliance blockchain; divide the original alliance blockchain into primary and secondary consensus nodes for each alliance member node, thereby obtaining primary and secondary alliance chains;

[0027] In this embodiment, the original blockchain data, including all blocks and transaction records, is obtained from the alliance member nodes, or the original alliance blockchain, including the associated data of all blocks, is obtained by newly building an alliance blockchain. According to the pre-defined consensus algorithm and consensus rules, each alliance member node is divided into primary and secondary consensus nodes. The primary node usually has higher authority and responsibility, while the secondary node has lower authority and responsibility. The relevant primary and secondary are relative to a certain alliance node, and the primary and secondary are only used for the consensus algorithm; according to the division results of the primary and secondary consensus nodes, the blocks in the original alliance blockchain are respectively divided into the primary alliance chain and the secondary alliance chain. It can be only a soft division without changing the distribution structure of the blockchain, or it can be that the distribution structure of the blockchain is defined after the division, and then the subsequent processing is carried out according to the new distribution structure, so as to improve the connection efficiency between blockchains and reduce the network communication cost. The subsequent optimization of the relevant primary and secondary consensus algorithms can determine whether to re-distribute the blockchain structure according to the actual situation.

[0028] Step S2: Authenticate the traceability business data based on the primary and secondary alliance chains to obtain the traceability data to be agreed upon; publish the block of the traceability data to be agreed upon to obtain the traceability block data;

[0029] In this embodiment, by using the traceability authentication algorithm and rules, the traceability business data in the primary alliance chain and the secondary alliance chain are authenticated to ensure the credibility and integrity of the data, and the traceability data to be agreed upon is generated; the traceability data to be agreed upon is packaged into blocks and published through the blockchain network to become a new block on the blockchain; the new block contains the traceability data to be agreed upon, becomes the traceability block data, and is added to the primary and secondary alliance chains as part of the chain.

[0030] Step S3: Request block data from the primary and secondary alliance chains to obtain block data sets; cluster the features of upstream and downstream blocks on the block data sets to obtain traceability alignment cluster data; integrate the proof detail features on the block data sets to obtain authentication proof detail data; perform cluster vector association on the traceability alignment cluster data and the authentication proof detail data to obtain traceability authentication association data;

[0031] In this embodiment, by sending block data requests to the nodes of the primary and secondary alliance chains according to the required traceability data range, the relevant block data sets are obtained; cluster analysis is performed on the obtained block data sets, and upstream and downstream blocks with similar characteristics are clustered to form traceability alignment cluster data; certification detail feature data related to authentication is extracted from the block data sets, including the signature of the authentication authority, authentication time, authentication report, etc., to form authentication certification detail data; vector association is performed between the traceability alignment cluster data and the authentication certification detail data, and an association relationship is established between them to obtain traceability authentication association data.

[0032] Step S4: Acquire alliance member data; construct a three-dimensional credit model for the alliance member data, thereby obtaining a three-dimensional credit model; perform unique credit score association based on the three-dimensional credit model, thereby obtaining unique identification score data;

[0033] In this embodiment, relevant credit data including credit history records, consensus records, information adoption records, etc. are obtained from alliance members; a three-dimensional credit model is constructed based on the characteristics of the credit data and the relationship between alliance members. The model can comprehensively consider the credit scores in three dimensions; the traceability authentication associated data is associated with the three-dimensional credit model, and unique identification score data is obtained based on the association result. The score can reflect the credit level and reliability of the product traceability data.

[0034] Step S5: construct a consensus probability model for the traceability authentication associated data and the unique identification scoring data, thereby obtaining a feature consensus probability model; construct a traceability credit network model for the traceability alignment clustering data based on the feature consensus probability model, thereby obtaining a traceability credit network model;

[0035] In this embodiment, a consensus probability model is constructed based on the traceability certification associated data and the unique identification scoring data. The model can be used to evaluate the consensus degree and credibility of different feature data. The traceability alignment clustering data is analyzed and modeled using the feature consensus probability model to construct a traceability credit network model. The model can describe the trust relationship and credibility between product traceability data, including the credibility of alliance members and the credibility of the certification certificate itself, as well as the relevant traceability status of the data.

[0036] Step S6: Based on the traceability credit network model, a product traceability request for a unique identification code is made to the dynamic primary and secondary alliance chains to obtain product traceability data; an authentication feature trust model is constructed for the unique identification scoring data and the authentication proof detail data to obtain an authentication proof trust probability model.

[0037] In this embodiment, by using the constructed traceability credit network model, a product traceability request is initiated, and the relevant product traceability data, including authentication-related data, product status data, and traceability trustworthiness data, are retrieved through the unique identification code. Based on the unique identification score data and authentication proof detail data, an authentication feature trust model is constructed to evaluate the trust probability and credibility of the authentication proof.

[0038] In this embodiment, reference Figure 2 The above is a schematic flow chart of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0039] Step S11: Acquire traceability business definition data and business related data;

[0040] Step S12: constructing a consortium chain including all relevant business members for the traceability business definition data and business association data, thereby obtaining an original consortium blockchain;

[0041] Step S13: registering the alliance member's client based on the original alliance blockchain, and allocating the trust base to the business-related data, thereby obtaining alliance trust-related data;

[0042] Step S14: Divide the original alliance blockchain into primary and secondary consensus nodes for each alliance member node according to the alliance trust association data, thereby obtaining primary and secondary alliance chains.

[0043] In this embodiment, by collecting and obtaining the definition data of the traceability business, including business processes, data standards, operating specifications, etc. These data can come from channels such as industry standards, policy regulations, and internal requirements of the enterprise; collect and obtain data related to the traceability business, including product information, supply chain information, audit data, etc. These data can come from the internal system of the enterprise, data sharing of supply chain partners, etc. According to the traceability business definition data and business association data, all relevant business members participating in the traceability business are determined, and the alliance chain construction plan is carried out; corresponding alliance chain nodes are configured for each business member to ensure that each member can participate in the construction and maintenance of the alliance chain; according to the planning and node configuration, the nodes of all relevant business members are connected to form an alliance chain network, and according to business needs and security considerations, appropriate consensus algorithms and encryption mechanisms are selected; through the alliance chain construction, an initial alliance blockchain is obtained, which contains the nodes of all relevant business members and initial block data. Each business member uses the identity information and key of its node to register the client of the alliance chain so that it can participate in the interaction and data verification process of the alliance chain; according to business needs and the trust of relevant members, the trust base is allocated to the business-related data. A higher trust base indicates that the data has higher credibility and weight, and will be referenced and verified by more nodes in the subsequent consensus process. Based on the trust base and business-related data, the trust and credibility indicators of each alliance member node relative to other alliance member nodes are analyzed and calculated. The trust base can be mainly modified by the alliance members to modify the main weight ratio and used as the initial trust value to ensure the consensus efficiency and reliability in the initial stage to a certain extent. According to the trust and credibility indicators, each alliance member node in the original alliance blockchain is divided into primary and secondary consensus nodes. Usually, nodes with higher trust are selected as primary nodes, while nodes with lower trust are selected as secondary nodes. The threshold can be obtained by the alliance members by setting the initial threshold, that is, the existing relevant data can be used to set the relevant initial threshold through data statistics and expert knowledge. According to the division results of primary and secondary consensus nodes, the blocks in the original alliance blockchain are divided into the primary alliance chain and the secondary alliance chain respectively. Note that the primary and secondary are relative to a certain alliance member node.

[0044] The present invention can clarify the specific business scope and requirements of traceability by obtaining traceability business definition data, and provide clear goals and guidance for the subsequent traceability authentication process; obtaining business-related data can help understand the relationship and dependency between different businesses, facilitate the integration and analysis of traceability data, and improve the accuracy and completeness of traceability results. Constructing an alliance chain based on traceability business definition data and business-related data can ensure that all relevant business members are covered, making the participants in the traceability process more representative and authoritative; building an original alliance blockchain can provide a shared, decentralized traceability data storage and management platform, enhancing the security and accessibility of data. Client registration of alliance members can ensure that only authorized and approved members can participate in the traceability authentication process, increasing the security and compliance of the system; allocating trust bases for business-related data can assign corresponding trust weights according to the credibility and importance of different data, which is helpful for the subsequent consensus node division and traceability authentication process. The division of primary and secondary consensus nodes based on alliance trust-related data can reasonably allocate the roles and rights of consensus nodes according to the trust base and trust weight of members, ensuring the stability and credibility of the alliance; the division of primary and secondary alliance chains can improve the performance and scalability of the system, allowing alliance members to participate in the traceability and authentication process more efficiently and improve overall processing capabilities.

[0045] In this embodiment, reference Figure 3 The above is a schematic flow chart of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0046] Step S21: Authentication of traceability business data is performed based on the primary and secondary alliance chains, thereby obtaining the traceability data to be agreed upon;

[0047] Step S22: dividing the consensus traceability data into primary and secondary business nodes, thereby obtaining priority consensus node data and secondary consensus node data;

[0048] Step S23: Prioritize consensus on the consensus traceability data according to the priority consensus node data. When the priority consensus authentication fails, the failure feedback is given to the primary and secondary alliance chains; when the priority consensus authentication succeeds, the credit base is requested to the primary and secondary alliance chains to obtain the priority consensus credit base;

[0049] Step S24: When the priority consensus credit base is greater than the preset consensus threshold, the consensus traceability data is published in a block, thereby obtaining traceability block data;

[0050] Step S25: When the preset consensus threshold is greater than the priority consensus credit base, a secondary consensus is performed on the consensus traceability data according to the secondary consensus node data. When the secondary consensus authentication fails, a failure feedback is given to the primary and secondary alliance chains; when the secondary consensus authentication succeeds, the consensus traceability data is published in blocks, thereby obtaining traceability block data.

[0051] In this embodiment, according to the result of the division of the primary and secondary alliance chains in step S14, the network environment and node configuration of the primary alliance chain and the secondary alliance chain are prepared for subsequent consensus; after the alliance member node authenticates the traceability business data, the traceability data and the authentication certificate are transmitted to the primary and secondary alliance chains, and according to the pre-set rules and priorities, some nodes in the alliance chain are divided into priority consensus nodes, that is, relative to the main node of the node, these nodes have higher authority and credibility relative to the node, and can perform priority consensus operations. The remaining nodes are divided into secondary consensus nodes, and the secondary consensus operation will be performed only when the priority consensus fails. The priority consensus node uses the consensus algorithm to perform consensus operations on the consensus traceability data to ensure the consistency and credibility of the data. If the priority consensus authentication fails, the system will give a failure feedback; when the priority consensus authentication succeeds, the priority consensus node sends a credit base request to the primary and secondary alliance chains to obtain the priority consensus credit base. The credit base is used for subsequent consensus threshold judgment and the release of traceability block data. According to the preset consensus threshold, it is compared with the priority consensus credit base. If the priority consensus credit base is greater than the consensus threshold, it means that the data has sufficient credibility and can be released in blocks. When the priority consensus credit base meets the conditions, the consensus traceability data will be packaged into blocks and released through the main alliance chain. The released blocks become traceability block data and are shared and stored by the nodes in the main alliance chain. If the priority consensus credit base does not reach the preset consensus threshold, a secondary consensus is required. Because of insufficient trust, the secondary consensus node uses the consensus algorithm to perform consensus operations on the consensus traceability data. The secondary consensus node authenticates the consensus traceability data to ensure the consistency and credibility of the data. If the secondary consensus authentication fails, the system will give a failure feedback and notify the primary and secondary alliance chains. At this time, the failure condition is the same as the failure condition of the priority node for consensus authentication, that is, reaching the consensus threshold. When the secondary consensus authentication succeeds, the consensus traceability data will be packaged into blocks and released through the main alliance chain. The released blocks become traceability block data and are shared and stored by the nodes in the main alliance chain. Among them, the consensus threshold can be derived from expert knowledge and relevant data statistics of historical products, and the threshold can be dynamically optimized through model results in the future.

[0052] The present invention can ensure the credibility and accuracy of traceability data and improve the reliability of traceability results by performing data authentication based on primary and secondary alliance chains; obtaining the traceability data to be consensus can provide a data basis for the subsequent consensus node division and authentication process, and lay the foundation for the generation of traceability block data. The primary and secondary business node division of consensus traceability data can reasonably allocate the roles and rights of consensus nodes according to the importance and credibility of the nodes, and improve the performance and credibility of the system; obtaining the priority consensus node data and the secondary consensus node data can provide data support for the subsequent consensus authentication and block release process, and ensure the reliability and consistency of the traceability block data. Priority consensus authentication can be performed based on the priority node data provided by the alliance member nodes, and the consensus requirements of these priority processing important nodes can be used to improve the authentication speed and accuracy of the system for key data; when the priority consensus authentication fails, the failure feedback of the primary and secondary alliance chains can timely notify the relevant nodes, prompting the solution and repair of the problem; when the priority consensus authentication is successful, the credit base request can obtain the priority consensus credit base, which provides a basis for the subsequent consensus threshold judgment and block release. When the priority consensus credit base exceeds the preset consensus threshold, block release can record the traceability data in the blockchain to ensure the immutability and traceability of the data; obtaining traceability block data can provide reliable traceability results and provide verifiable data proof for business participants and stakeholders. When the preset consensus threshold is higher than the priority consensus credit base, the secondary nodes of the alliance member nodes are used for consensus again to improve the system's authentication accuracy and credibility of all node data, ensure consensus in the primary and secondary order, and improve the overall consensus efficiency; when the secondary consensus authentication fails, the failure feedback to the primary and secondary alliance chains can promptly notify the relevant nodes and promote the resolution and repair of the problem; when the secondary consensus authentication succeeds, block release can record the traceability data in the blockchain to ensure the immutability and traceability of the data.

[0053] Preferably, the specific steps of step S3 are:

[0054] Step S31: Request block data from the primary and secondary alliance chains to obtain a block data set, wherein the block data set includes traceability block data, authentication member unique identification data, block status data, traceability status data, and authentication proof data;

[0055] Step S32: integrating the data of upstream and downstream blocks of the traceability block data to obtain a relevant block data set;

[0056] Step S33: performing correlation data analysis of adjacent blocks on the relevant block data set to obtain block correlation data;

[0057] Step S34: performing normalization and alignment processing on the traceability block data according to the block correlation data, thereby obtaining traceability alignment data;

[0058] Step S35: feature clustering is performed on the traceability alignment data to obtain cluster data, and unique identification is performed on the cluster data, block status data and traceability status data according to the authentication member unique identification data to obtain traceability alignment cluster data;

[0059] Step S36: integrating the authentication proof data with the proof detail features, thereby obtaining the authentication proof detail data;

[0060] Step S37: Perform cluster vector association on the traceability alignment cluster data and the authentication proof detail data, thereby obtaining traceability authentication association data.

[0061] In this embodiment, a block data request is sent to the primary and secondary alliance chains through the network connection with the primary and secondary alliance chains. The request includes obtaining traceability block data, authentication member unique identification data, block status data, traceability status data and authentication proof data; for each traceability block data, by analyzing the relevant fields and link information in the block, the upstream and downstream traceability blocks are identified, and the data of each traceability block and its upstream and downstream blocks are integrated to form a related block data set. The integration process includes merging fields, deduplicating data, and ensuring the consistency and integrity of the data. For each block in the related block data set, its adjacent blocks, that is, the upstream and downstream blocks that are directly associated with it, are determined, and the correlation data between the blocks is calculated by analyzing the data association relationship between the adjacent blocks. The correlation data may include correlation, similarity or other metrics, which are used to measure the degree of association and similarity between blocks and obtain similar features. According to the block correlation data, the traceability block data is normalized and aligned, that is, firstly, the features with strong correlation are aligned according to similar features to ensure that the subsequent analysis is based on the aligned features, which includes field alignment, data format conversion and data unit unification, so that the data of different blocks can be compared and integrated, and the aligned traceability block data is normalized to ensure that the data is in the same scale and range for subsequent data analysis and processing. Extract key features from the traceability alignment data, such as attributes, indicators or other features that can describe the data, apply clustering algorithms (such as K-means, hierarchical clustering, etc.) to perform cluster analysis on the extracted features, divide data with similar features into the same cluster cluster, assign unique identifiers to cluster data, block status data and traceability status data according to the unique identification data of the authentication member, so as to facilitate subsequent data association and query, and integrate cluster data, block status data and traceability status data to form a traceability alignment cluster data set, in which each data item has a unique identifier and is organized according to clusters. Extract key proof detail features from the certification proof data, including relevant features in the electronic image and signature features, and integrate the extracted proof detail features to form a certification proof detail data set. The integration process may include operations such as deduplication, format conversion, and data cleaning to ensure data consistency and accuracy. Convert the traceability alignment clustering data and the certification proof detail data into vector representation for vector association analysis. Feature extraction technology or vectorization methods can be used to convert the data into numerical vectors, and the corresponding vector association algorithms (such as similarity calculation, association analysis, etc.) can be applied to perform vector association on the traceability alignment clustering data and the certification proof detail data. By calculating the similarity or association between the vectors, the association relationship between them is determined, and based on the results of the vector association, a traceability certification association data set is obtained, which contains the association information between the traceability data and the certification data.This associated information can be used to verify the credibility and integrity of traceability data, as well as the scope of application and validity of certification data.

[0062] The present invention can obtain a complete block data set through a block data request, including traceability block data and related authentication member data, providing a basis for subsequent data integration and analysis; obtaining traceability block data, authentication member unique identification data, block status data, traceability status data, and authentication proof data can provide comprehensive traceability information to support subsequent data analysis and authentication processes. Performing upstream and downstream block data integration can associate the traceability block with its adjacent block data, providing a more complete data view. The benefit of associating in the order of upstream and downstream products is that it can provide a guarantee for the subsequent better revelation of the adoption correlation between traceability data. The traceability data of the association of alliance members between upstream and downstream is directly related to the adoption and adoption of data. At the same time, it is also strongly related to the trust consensus between the upstream and downstream alliance member nodes, so as to facilitate subsequent data analysis and processing. Performing block correlation data analysis can reveal the relationship and mutual influence between different blocks, provide guidance and basis for subsequent data processing and authentication, and obtain block correlation data can help identify the correlation and importance of data, and provide support for traceability alignment and authentication association. According to the block correlation data, the normalization alignment of the traceability block data can be carried out. According to the correlation data of the traceability data between the upstream and downstream blocks, all the upstream and downstream related features between the traceability block data can be found, and the differences and deviations between the data can be eliminated to ensure the consistency and comparability of the data and improve the accuracy of data analysis and authentication. Feature clustering can identify and aggregate data with similar features, help discover the potential patterns and associations of the data, and provide a deeper understanding for data analysis and authentication; uniquely identifying the cluster data, block status data and traceability status data according to the unique identification data of the authentication member can ensure the accurate matching and correspondence of the data and improve the credibility and reliability of the data. Proof detail feature integration can integrate the relevant information in the authentication proof data, extract key features, and provide useful data for subsequent authentication association analysis. Cluster vector association can associate the traceability alignment cluster data with the authentication proof detail data, discover the relationship and matching degree between the two, and provide support and verification for the traceability authentication of the data; obtaining the traceability authentication association data can help confirm the accuracy and credibility of the data, verify the source and authentication process of the data, and provide a basis for the recognition and traceability of the traceability results.

[0063] Preferably, the specific steps of step S36 are:

[0064] Step S361: grayscale processing of the electronic image of the authentication proof data is performed to obtain grayscale image data;

[0065] Step S362: extracting important features of the test report from the authentication certificate data, thereby obtaining important test data;

[0066] Step S363: performing signature edge granularity recognition on the grayscale image data, thereby obtaining signature granularity data;

[0067] Step S364: Analyze the texture information of the grayscale image data according to the signature granularity data, thereby obtaining signature texture data;

[0068] Step S365: performing structural edge detection on the grayscale image data to obtain image structural data;

[0069] Step S366: performing shape inflection point analysis on the image structure data to obtain shape inflection point data;

[0070] Step S367: performing feature filtering at the repeated inflection points on the grayscale image data according to the shape inflection point data, thereby obtaining simplified image data;

[0071] Step S368: performing texture locality analysis on the simplified image data to obtain local texture data;

[0072] Step S369: Integrate the proof detail features of the local texture data and the signature texture data to obtain authentication proof detail data.

[0073] In this embodiment, the electronic image data is extracted from the authentication data and converted into a grayscale image. An image processing library or algorithm can be used to convert a color image into a grayscale image for subsequent processing and analysis. The test report in the authentication data is parsed to extract important feature information therein, and key feature information is extracted using text processing technology, natural language processing methods, etc. according to the structure and content of the test report. These features can be keywords, numerical values, indicators or other important data describing the test results. Edge detection is performed on the grayscale image data to identify the edge information in the image. Edge detection algorithms (such as Sobel, Canny, etc.) can be used to extract the edge of the image, and the granularity of the signature area is identified based on the edge information. The granularity of the signature can be evaluated by calculating the density and distribution pattern of edge pixels. Texture feature extraction is performed on the grayscale image data using a texture analysis method. Commonly used texture feature extraction methods include grayscale co-occurrence matrix, wavelet transform, local binary pattern, etc., and features related to the signature texture are extracted based on the results of texture analysis. These features can include statistical information of texture, texture direction, texture frequency, etc. Use structural edge detection algorithms, such as Laplacian, Sobel, etc., to perform edge detection on grayscale image data. This can help extract structural information in the image and extract structural features from the detected edges, such as edge length, direction, inflection point, etc. These features can be used to describe the structure and shape in the image. Perform inflection point detection on the image structure data to identify the shape inflection points in the image. Inflection point detection algorithms, such as Harris corner detection, Shi-Tomasi corner detection, etc., can be used to extract relevant features from the detected inflection points, such as the position, number, curvature, etc. of the inflection points. These features can help describe the changes and characteristics of the shape in the image. Based on the shape inflection point data, identify the repeated inflection points in the image. These repeated inflection points may represent some important features or structures in the image. Based on the position and characteristics of the repeated inflection points, feature filtering is performed on the grayscale image data. Filters, thresholds, or other image processing techniques can be used to reduce noise and redundant information in the image to obtain simplified image data. Use texture analysis methods to extract local texture features from simplified image data. Local texture descriptors (such as local binary patterns, local directional patterns, etc.) can be used to describe the texture features of different areas in the image. Based on the results of texture locality analysis, local texture features of different areas in the image can be extracted. These features can include statistical information of the texture, texture direction, texture frequency, etc. The local texture data and signature texture data can be integrated. Feature fusion, feature matching or other data integration methods can be used to merge the feature information of the two. Based on the integrated feature data, detailed information in the authentication certificate can be extracted. This information can include texture change patterns, the location of local textures, the location and form of signatures, etc., for further authentication analysis and judgment.

[0074] The present invention can convert the electronic image in the authentication data into a grayscale image by grayscale processing, simplify the complexity of the image data, and obtain grayscale image data, which can reduce the dimension of the data, improve the efficiency of image processing and feature extraction, and facilitate subsequent image analysis and recognition. Performing important feature extraction can extract key features from the test report of the authentication data, such as indicator values, abnormal conditions, etc. Obtaining important detection data can help identify and focus on key information in the authentication process, and provide support and verification for traceability authentication association. Performing edge granularity recognition can extract the edge information of the signature from the grayscale image data, understand the morphology and granularity characteristics of the signature, and obtain signature granularity data to help determine the characteristics and patterns of the signature, and provide support and judgment basis for the authenticity and credibility of the authentication certificate. Performing texture information analysis can extract the texture features of the signature from the grayscale image data, such as texture direction, texture density, etc. Obtaining signature texture data can provide a data basis for texture features for subsequent authentication and association analysis, and support the evaluation of the authenticity and credibility of the authentication certificate. Structural edge detection can extract the structural edge information of the image from the grayscale image data, help identify the structural features and boundaries in the image, and obtain image structural data to provide a basis for subsequent shape analysis and inflection point identification, and support the analysis and association analysis of the structural features of the certification. Shape inflection point analysis can identify the inflection points and corners in the image structure, understand the shape characteristics and topological structure of the image, and obtain shape inflection point data that can be used for the unique identification and description of the image shape, providing support for the structural features and shape association of the certification. Feature filtering at repeated inflection points can filter out the repeated inflection points in the image based on the shape inflection point data, simplify the image data, reduce redundant information, and obtain simplified image data, which can reduce the complexity of the data and improve the efficiency of subsequent processing and analysis, while retaining key shape features and structural information. Texture locality analysis can extract local texture features from simplified image data, understand the texture characteristics and changes in different areas of the image, and obtain local texture data that can provide detailed information of the image, supporting subsequent texture feature integration and analysis of certification details. The integration of certification detail features can integrate local texture data and signature texture data, integrate key detail features in the certification, and obtain certification detail data, which can provide complete certification information, including signature features, texture features, etc., and provide a basis for comprehensive analysis of the authenticity and credibility of the certification. The above steps can be more adaptively filtered and extracted for important features of this type of image based on the certification characteristics of electronic reports and electronic image qualification certificates, while improving the efficiency of feature extraction and ensuring the importance and clarity of the features.

[0075] Preferably, the specific steps of step S4 are:

[0076] Step S41: Request alliance member data to the primary and secondary alliance chains to obtain alliance member data, where the alliance member data includes information release data, information authentication consensus number, information adoption data, information authentication data, and unique identification data of authenticated members;

[0077] Step S42: performing time series conversion on the information release data and the information adoption data, thereby obtaining information time series data;

[0078] Step S43: Analyze the frequency peak of the information time series data being published and adopted, so as to obtain the information frequency peak data;

[0079] Step S44: performing peak difference fluctuation statistics on the information frequency peak data, thereby obtaining peak difference fluctuation data;

[0080] Step S45: constructing a three-dimensional credit model based on the information authentication consensus number, the participating information authentication data, and the peak difference fluctuation data, thereby obtaining a three-dimensional credit model;

[0081] Step S46: Associating the unique identification data of the authenticated member with a unique credit score based on the three-dimensional credit model, thereby obtaining unique identification score data.

[0082] In this embodiment, by communicating with the primary and secondary alliance chains, request to obtain alliance member data. Appropriate network communication protocols and API interfaces can be used to implement data requests, and receive alliance member data returned by the alliance chain, including information release data, information authentication consensus number, information adoption data, participating information authentication data, and unique identification data of authenticated members. The required data can be parsed and extracted according to the data structure and interface specifications of the alliance chain. The information release data and information adoption data are sorted and sorted, arranged in chronological order, and the sorted data are converted into information time series data, that is, the data is associated with its corresponding timestamp to form a time series data set. The information time series data is subjected to frequency statistics, the number of information releases and adoptions in each time period is calculated, and the frequency peaks of information release and adoption are identified by analyzing the frequency statistics results. Peak detection algorithms, such as peak point detection, filters, etc., can be used to locate frequency peaks. Calculate the difference between adjacent peak values ​​of the information frequency peak data to obtain a peak difference sequence, perform fluctuation statistics on the peak difference sequence, and calculate the average value, standard deviation, maximum value, minimum value and other statistical indicators of the peak difference to describe the fluctuation of the peak difference, reflect the direct temporal relationship between information release and adoption, and obtain all the current relevant feature points when the temporal sequence fluctuates. Based on the information authentication consensus number, the information authentication data and the peak difference fluctuation data as three-dimensional credit dimensions, a credit model is constructed. Machine learning algorithms, statistical models or other data analysis methods can be used to establish the association between information authentication related data and credit scores, thereby obtaining a three-dimensional credit model. Using the three-dimensional credit model, the unique identification data of the authentication member is associated with the credit score. According to the performance of the unique identification data in the credit model, the corresponding credit score is determined, and the unique identification score data is generated according to the credit score association result of the unique identification data. This can be a data set containing the unique identification of the authentication member and the corresponding credit score.

[0083] The present invention can obtain key data in the primary and secondary alliance chains by requesting alliance member data, including information release, authentication consensus, information adoption, participation in information authentication, and unique identification of authenticated members. Acquiring alliance member data can provide the activities and participation of each member in the alliance. Time series conversion can organize and sort the data of information release and adoption in chronological order to form information time series data. Obtaining information time series data can help analyze the release and adoption trends of information, understand the time change characteristics of information, and provide a basis for subsequent frequency peak analysis and fluctuation statistics. Frequency peak analysis can identify the frequency peaks of information release and adoption, that is, the peak period of release and adoption, help understand the hot spots and attention of information, and can provide the fluctuation peaks between important time nodes of information release and adoption, providing a basis for subsequent fluctuation statistics and credit model construction. Peak difference fluctuation statistics can analyze the differences and fluctuations between information frequency peaks, understand the volatility characteristics of information release and adoption, and obtain peak difference fluctuation data, which can provide quantitative indicators of the degree of fluctuation and stability of information release and adoption. The construction of a three-dimensional credit model can combine the information authentication consensus number, the data of participating information authentication, and the peak difference fluctuation data to build a comprehensive evaluation credit model. The three-dimensional credit model can comprehensively consider the consensus of information authentication, the degree of authentication participation, and the volatility of information release and adoption, and provide a comprehensive basis for the credit evaluation and association analysis of authentication members. The unique credit score association can be based on the three-dimensional credit model to credit score the unique identifier of the authentication member, evaluate its credit level and contribution in the alliance, and obtain the unique identifier score data to provide the credit evaluation results of the authentication member, help identify and distinguish the authentication members, and provide a basis for alliance management and decision-making.

[0084] Preferably, the specific steps of step S5 are:

[0085] Step S51: constructing a consensus probability model for the traceability authentication associated data and the unique identification scoring data, thereby obtaining a feature consensus probability model;

[0086] Step S52: Based on the characteristic consensus probability model, the characteristic probability of the priority consensus credit base of the primary and secondary alliance chains is weighted to obtain a priority consensus weighted data set;

[0087] Step S53: weighting the data set according to the priority consensus and conducting a traceability data consensus based on the primary and secondary alliance chains, thereby obtaining optimized traceability data;

[0088] Step S54: credit scoring the optimized traceability data based on the three-dimensional credit model, thereby obtaining optimized credit scoring data;

[0089] Step S55: performing genetic forest model migration on the feature consensus probability model to obtain a genetic forest model;

[0090] Step S56: performing feature pruning processing on the genetic forest model according to the optimized credit score data, thereby obtaining an optimized genetic forest model, wherein the feature pruning processing includes pruning processing of repeated features associated with the credit score and pruning processing of low-probability related features;

[0091] Step S57: constructing a traceability credit network model for the traceability alignment clustering data based on the optimized genetic forest model, thereby obtaining a traceability credit network model.

[0092] In this embodiment, by collating the traceability authentication associated data and the unique identification scoring data, ensuring that the data format and quality meet the requirements of model construction, based on the prepared data, a consensus probability model is constructed using an appropriate machine learning algorithm or statistical model. This model can be used to estimate the consensus probability between features, that is, the relevance and credibility of the features in the authentication process. Using the feature consensus probability model, the features in the primary and secondary alliance chains are probabilistically weighted. According to the consensus probability of the features, the features are weighted to increase the weight of the features with high consensus probability in the credit assessment, and according to the weighted features, a priority consensus weighted data set is generated in the primary and secondary alliance chains. This data set associates the weighted features with their corresponding data, that is, it is no longer based on the trust base, but the final trust obtained by the probability weighting of the trust base based on the data features. The priority consensus weighted data set is collated and prepared to ensure that the data format and quality meet the requirements of the traceability data consensus, and the traceability data consensus is carried out based on the primary and secondary alliance chains, that is, the traceability data is verified and confirmed. Appropriate consensus algorithms and verification mechanisms can be used to ensure the accuracy and credibility of the traceability data, and an optimized traceability data set is generated according to the results of the traceability data consensus, including verified and confirmed traceability data. Ensure that the constructed three-dimensional credit model can be used for credit scoring. Based on the optimized traceability data and the three-dimensional credit model, credit scoring is performed on the traceability data. Determine the corresponding credit score based on the performance of the traceability data in the three-dimensional credit model. Generate an optimized credit scoring data set based on the credit scoring results, which includes the traceability data and the corresponding credit score. Ensure that the feature consensus probability model has been constructed and can be used for model migration. Based on the feature consensus probability model, use the genetic forest algorithm to migrate the model. The genetic forest model can transform the feature consensus probability model into a genetic forest model through the iteration and evolution of the genetic algorithm to improve the model performance and effect. Organize and prepare the optimized credit scoring data set to ensure that the data format and quality meet the requirements of feature pruning processing. Based on the optimized credit scoring data, detect and identify possible duplicate features. For duplicate features, prune them and only retain one representative feature. Analyze the correlation and probability between features based on the optimized credit scoring data. For features with low probability correlation, prune them to reduce the redundancy and noise impact of features. Based on the results of feature pruning, generate an optimized genetic forest model, which includes pruned features and corresponding model parameters. Organize and prepare traceability alignment clustering data to ensure that the data format and quality meet the requirements for the construction of the traceability credit network model. Construct a traceability credit network model based on the optimized genetic forest model and traceability alignment clustering data. This model can be used to describe and analyze the relationship and credit between traceability data to support the credibility assessment and credit propagation analysis of the traceability process. Use the constructed traceability credit network model to carry out related credit assessment, credit propagation analysis and other applications.

[0093] The present invention can combine the traceability authentication associated data with the unique identification scoring data by constructing a consensus probability model, and establish a feature consensus probability model. The feature consensus probability model can reveal the consensus relationship between the various features in the traceability data, and mine the connection between the relevant features of different traceability data and different authentication certificates and the credit scores of alliance members, thereby obtaining the data connection in the blockchain consensus stage, and providing a basis for subsequent consensus weighting and credit scoring. Priority consensus weighting can use the feature consensus probability model to weight the data in the primary and secondary alliance chains, highlighting the data features with higher consensus probabilities. Priority consensus weighted data sets can provide consensus-optimized data sets, so that data features with higher consensus probabilities play a more important role in the subsequent traceability data consensus and credit scoring. By using the consensus probabilities with high credibility of different data features for comprehensive judgment, the rough consensus process in which the previous alliance chain only uses the credit base selected by the alliance members for judgment can be converted into an optimized weighting after the comprehensive judgment of the base by artificial intelligence based on the credit base selected by the alliance members. Different features have different weights, thereby changing the different credit bases of different data, improving the consensus efficiency and reliability of the blockchain, and at the same time, without changing the structure of the blockchain, only changing the consensus algorithm, greatly reducing the corresponding optimization cost. Afterwards, the traceability data consensus can be based on the priority consensus weighted data set to consensus the data in the primary and secondary alliance chains, improve the accuracy and credibility of the traceability data, and provide a more reliable data foundation for the subsequent credit scoring and credit network construction. Credit scoring can evaluate the optimized traceability data based on the three-dimensional credit model, quantify the credit level and quality of the traceability data, and obtain optimized credit scoring data, which can provide credit evaluation results for the optimized traceability data, help identify and distinguish traceability data with different credit levels, and re-evaluate and obtain data for the consensus algorithm of the optimized blockchain, so as to ensure further optimization in the future. Genetic forest model migration can convert the feature consensus probability model into a genetic forest model, so that the genetic forest algorithm can be used to further analyze and mine the features. The genetic forest model can provide a feature selection and model building method based on the genetic algorithm, which has the advantages of high efficiency and reliability in identifying whether it is a feature problem. Feature pruning can screen and prune the features in the genetic forest model according to the optimized credit score data, remove redundant features and low-probability related features, and improve the simplicity and accuracy of the model. Because different scores are based on different data features, the correlation of different features in the decision tree and the correlation between different decision trees in the genetic forest can be accurately identified according to the score, and the decision feature factors with extremely low impact on the decision can be found. According to these feature factors, the decision trees or feature points related to them are found, and the branches that are strongly related to them are correspondingly pruned, making the model more efficient and effective, and improving the performance of the subsequent traceability credit network model construction.The construction of the traceability credit network model can be based on the optimization of the genetic forest model to model and analyze the traceability alignment clustering data, and construct a network model that reflects the credit network relationship of the traceability data and the traceability network relationship of the traceability data itself. It can be used for user traceability and credibility judgment, as well as for iterative upgrades of subsequent models, providing relevant suggestions to alliance members, and providing abnormal warnings to managers who manage blockchains. It provides a data visualization model foundation.

[0094] Preferably, the specific steps of step S57 are:

[0095] Step S571: Perform secondary allocation of primary and secondary consensus nodes on primary and secondary alliance chains based on the optimized genetic forest model, thereby obtaining optimized primary and secondary node data;

[0096] Step S572: Optimizing the consensus algorithm of the primary and secondary alliance chains according to the optimized primary and secondary node data, thereby obtaining a dynamic primary and secondary alliance chain;

[0097] Step S573: requesting alliance member association data for the dynamic primary and secondary alliance chains, thereby obtaining dynamic alliance association data;

[0098] Step S574: extracting features of abnormal state update on the traceability alignment clustering data, thereby obtaining abnormal state clustering data;

[0099] Step S575: construct a traceability credit network model for the abnormal state clustering data and the traceability alignment clustering data according to the dynamic alliance association data, thereby obtaining a traceability credit network model.

[0100] In this embodiment, the consensus nodes in the primary and secondary alliance chains are secondary distributed by using the optimized genetic forest model. According to the credit score of the node and other relevant factors, the role and weight of each node in the primary and secondary alliance chains are determined, and according to the results of the secondary distribution, the optimized primary and secondary node data sets are generated, including the role, weight and other relevant information of each node. The optimized primary and secondary node data sets are sorted and prepared to ensure that the data format and quality meet the requirements of consensus algorithm optimization, and the consensus algorithm in the primary and secondary alliance chains is optimized based on the optimized primary and secondary node data. It can be considered to adjust the parameters of the consensus algorithm, introduce a new consensus algorithm or improve the existing consensus algorithm to improve the performance and effect of the primary and secondary alliance chains. According to the results of the consensus algorithm optimization, a dynamic primary and secondary alliance chain is generated, which includes the optimized consensus algorithm and the corresponding node role and weight information. According to the node role and weight of the dynamic primary and secondary alliance chain, a request for associated data is initiated to the alliance members. Request the alliance members to provide their relevant data for the subsequent construction of the traceability credit network model. According to the responses of the alliance members, the dynamic alliance associated data is obtained, including the traceability-related data provided by the alliance members. Based on the traceability alignment clustering data, the features related to the abnormal state update are extracted. Appropriate feature extraction algorithms or methods can be used to extract feature information related to abnormal state changes from cluster data. Based on the extracted features, an abnormal state clustering data set is generated, which includes features and corresponding abnormal state information. A traceability credit network model is constructed based on dynamic alliance association data, abnormal state clustering data, and traceability alignment clustering data. Appropriate network construction algorithms or graph structure methods can be used to combine nodes, edges, and related attributes in the data to form a traceability credit network model. Based on the constructed traceability credit network model, a final traceability credit network model is generated, which includes nodes, edges, and corresponding credit attribute information.

[0101] The present invention can redistribute the nodes in the primary and secondary alliance chains based on the optimized genetic forest model by performing a secondary distribution of primary and secondary consensus nodes, so that the roles of the nodes are more reasonable and optimized, that is, the primary and secondary nodes of each alliance node in the alliance chain are completely iterated according to the consensus algorithm after the second update. The first update only performs probability weighting of different data features on the priority nodes of each alliance node, but does not change the role authority of the priority node. This update, that is, the second update, can be based on the optimized genetic forest model obtained after training based on the new training set after the first update, and the feature set with more accurate similarity and the consensus credibility of the relevant nodes on the data of the current alliance node can be judged. The secondary distribution of primary and secondary consensus nodes based on this makes the distribution of primary and secondary nodes more balanced and efficient, providing a good foundation for the subsequent optimization of the consensus algorithm. The optimization of the consensus algorithm can adjust and optimize the consensus algorithm in the primary and secondary alliance chain based on the optimization of the primary and secondary node data to improve the efficiency and accuracy of the consensus, and the dynamic primary and secondary alliance chain can provide the primary and secondary alliance chain optimized by the consensus algorithm, so that it can adapt to the dynamic environment and have better adaptability and robustness. Requests for alliance member-associated data can be made based on the dynamic primary and secondary alliance chains to request relevant data from alliance members to obtain more comprehensive and accurate data information. Feature extraction for abnormal status updates can analyze and extract abnormal states in traceability alignment clustering data, identify potential abnormal situations and problems, and construct a traceability credit network model. Based on dynamic alliance-associated data, model and analyze abnormal state clustering data and traceability alignment clustering data to construct a network model that reflects the credit relationship of traceability data. The traceability credit network model can provide a network model based on the latest alliance-associated data, which has abnormal state warning tracking and tracing, and is used to evaluate and analyze the credit and credibility of traceability data.

[0102] Preferably, the specific steps of step S574 are:

[0103] Extracting the time series data of the state of the traceability alignment clustering data, thereby obtaining the traceability state time series data;

[0104] Perform time series ratio analysis on the traceability status time series data when the status is updated, so as to obtain the status time series ratio data;

[0105] The abnormal state update feature extraction is performed on the retroactive aligned clustering data according to the state time series ratio data, so as to obtain the abnormal state clustering data.

[0106] In this embodiment, time series data extraction is performed on the traceable aligned cluster data. According to the timestamp or other time identifier, the cluster data is arranged in chronological order, and the time series data of the relevant state is extracted. This may include information such as changes in different states, duration, etc. According to the results of the time series data extraction, the traceable state time series data is generated, including records of changes in different states over time and related information. Ensure that the traceable state time series data has been generated and prepared for time series ratio analysis. Perform time series ratio analysis on the traceable state time series data. Calculate the proportion or ratio of each state in different time periods to understand the trend and distribution of state changes. Statistical analysis or time series analysis methods such as moving average, trend analysis, etc. can be used. According to the results of the time series ratio analysis, state time series ratio data is generated, including the proportion or ratio information of the state in different time periods. Based on the state time series ratio data, features related to abnormal state updates are extracted. Suitable feature extraction algorithms or methods, such as difference analysis, anomaly detection, etc., can be used to extract feature information related to abnormal state changes from the time series ratio data. According to the extracted features, an abnormal state clustering data set is generated, which includes features and corresponding abnormal state information.

[0107] The present invention can extract the evolution and change of different states in time from the traceability alignment clustering data by extracting the time series data of the state, forming the time series data of the state, which is helpful to understand the evolution trend and change law of the state. The time series proportion analysis when updating the state can perform a proportion analysis of different states in time series on the traceability state time series data, understand the distribution of the state in different time periods, and obtain the state time series proportion data, which can provide the proportional relationship of different states in time, and provide basic data for subsequent abnormal state feature extraction and analysis. The feature extraction of abnormal state update based on the state time series proportion data can extract features related to abnormal states from the traceability alignment clustering data, identify and mark potential abnormal situations, and obtain abnormal state clustering data, which can provide an abnormal state data set after feature extraction, further analyze and study the clustering characteristics of abnormal states, and provide more accurate abnormal data for the construction of the traceability credit network model.

[0108] Preferably, the specific steps of step S6 are:

[0109] Step S61: Based on the traceability credit network model, a product traceability request for a unique identification code is made to the dynamic primary and secondary alliance chains, thereby obtaining product traceability data, wherein the product traceability data includes authentication-related data, product status data, and traceability trustworthiness data;

[0110] Step S62: constructing an authentication feature trust model for the unique identification score data and the authentication proof detail data, thereby obtaining an authentication proof trust probability model;

[0111] Step S63: Perform authentication trust probability analysis on the traceability data based on the authentication proof trust probability model to obtain the authentication trust probability.

[0112] In this embodiment, a product traceability request is initiated to the traceability credit network model through a unique identification code based on the dynamic primary and secondary alliance chain. The traceability credit network is requested to provide authentication-related data, product status data, and traceability trust data about the product. According to the response of the traceability credit network model, product traceability data is obtained. Product traceability data includes authentication-related data (such as authentication certificates, inspection reports, etc.), product status data (such as production date, transportation records, etc.), and traceability trust data (such as the trust score of the node, the trustworthiness of the traceability path, etc.). The unique identification scoring data and authentication proof detail data are sorted and prepared to ensure that the data format and quality meet the requirements for the construction of the authentication feature trust model. Based on the unique identification scoring data and authentication proof detail data, features related to the authentication feature are extracted. A suitable feature extraction algorithm or method can be used to extract feature information related to the authentication feature trust from the data. Based on the extracted features, an authentication feature trust model is constructed. A machine learning method (such as a classification algorithm, a regression algorithm, etc.) or a statistical modeling method can be used to establish a trust model to evaluate the trust probability of the authentication feature. According to the constructed authentication feature trust model, an authentication proof trust probability model is generated, which includes features and corresponding trust probability information. Organize and prepare the traceability data to be analyzed, including certification-related data, product status data, and traceability trust data. Perform certification trust probability analysis on the traceability data based on the certification proof trust probability model. Calculate or predict the certification trust probability of the traceability data based on the characteristics of the data and the trust probability of the model. Generate a certification trust probability based on the results of the certification trust probability analysis to measure the certification trustworthiness of the traceability data.

[0113] The present invention can trace products in the dynamic primary and secondary alliance chains through unique identification codes by making product traceability requests based on the traceability credit network model, and obtain various data related to the products, including authentication-related data, product status data, and traceability trustworthiness data, so as to provide consumers with more comprehensive and reliable product traceability information. The construction of the authentication feature trust model can be based on the unique identification scoring data and the authentication proof detail data to build a model for evaluating the trust of the authentication proof. The authentication proof trust probability model can provide a probabilistic evaluation of the trust of the authentication proof, helping the alliance member nodes to judge the credibility and reliability of the authentication proof. The authentication trust probability analysis of the traceability data based on the authentication proof trust probability model can analyze the authentication and credibility of the traceability data according to the trust probability of the authentication proof. Alliance members can refer to the trust probability obtained by the model for the authentication proof of other nodes in the blockchain network, and make more efficient consensus or non-consensus judgments on the authentication proof. At the same time, artificial intelligence is used to help managers with the reliability of the authentication proof of the traced data. When problems or abnormalities occur, the system can quickly trace and locate the location of possible problem points according to the traceability credit network model, and quickly analyze the credibility probability of the authentication proof through the authentication proof trust probability model, thereby helping the system and managers or regulators to quickly find related problems and the complete traceability chain where the problems arise.

[0114] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0115] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0116] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A traceability authentication method based on blockchain, characterized in that: The following steps are involved: Step S1: Obtain the original alliance blockchain; divide the original alliance blockchain into primary and secondary consensus nodes for each alliance member node, thereby obtaining primary and secondary alliance chains; Step S2: Authenticate the traceability business data based on the primary and secondary alliance chains to obtain the traceability data to be agreed upon; publish the block of the traceability data to be agreed upon to obtain the traceability block data; Step S3: Request block data from the primary and secondary alliance chains to obtain block data sets; Perform feature clustering of upstream and downstream blocks on the block data set to obtain retrospective alignment clustering data; Integrate the proof details of the block data set to obtain the authentication proof details data; Perform cluster vector association on the traceability alignment cluster data and the certification detail data, so as to obtain the traceability certification association data; Step S4: Obtain alliance member data; Construct a three-dimensional credit model for alliance member data to obtain a three-dimensional credit model; perform unique credit score association based on the three-dimensional credit model to obtain unique identification score data; Step S5: constructing a consensus probability model for the traceability authentication associated data and the unique identification scoring data, thereby obtaining a feature consensus probability model; Based on the feature consensus probability model, the traceability credit network model is constructed for the traceability alignment clustering data, thereby obtaining the traceability credit network model; Step S6: Based on the traceability credit network model, a product traceability request for a unique identification code is made to the dynamic primary and secondary alliance chains, thereby obtaining product traceability data; an authentication feature trust model is constructed for the unique identification scoring data and the authentication proof detail data, thereby obtaining an authentication proof trust probability model; The specific steps of step S1 are: step S11: obtaining traceability business definition data and business-related data; step S12: constructing a consortium chain including all relevant business members for the traceability business definition data and business-related data, thereby obtaining the original consortium blockchain; step S13: registering the clients of consortium members based on the original consortium blockchain, and allocating the trust base for the business-related data, thereby obtaining consortium trust-related data; step S14: dividing the original consortium blockchain into primary and secondary consensus nodes for each consortium member node according to the consortium trust-related data, thereby obtaining primary and secondary consortium chains; The specific steps of step S2 are as follows: step S21: authenticating the traceability business data based on the primary and secondary alliance chains, thereby obtaining the traceability data to be agreed upon; step S22: dividing the traceability data to be agreed upon into primary and secondary business nodes, thereby obtaining the priority consensus node data and the secondary consensus node data; step S23: performing priority consensus on the traceability data to be agreed upon according to the priority consensus node data, and when the priority consensus authentication fails, the primary and secondary alliance chains are fed back with failure information; when the priority consensus authentication succeeds, a credit base number request is made to the primary and secondary alliance chains, thereby obtaining the priority consensus credit base number; step S24: when the priority consensus credit base number is greater than the preset consensus threshold, the traceability data to be agreed upon is published in a block, thereby obtaining the traceability block data; step S25: when the preset consensus threshold is greater than the priority consensus credit base number, a secondary consensus is performed on the traceability data to be agreed upon according to the secondary consensus node data, and when the secondary consensus authentication fails, the primary and secondary alliance chains are fed back with failure information; when the secondary consensus authentication succeeds, the traceability data to be agreed upon is published in a block, thereby obtaining the traceability block data; The specific steps of step S3 are as follows: step S31: making a block data request to the primary and secondary alliance chains, thereby obtaining a block data set, wherein the block data set includes traceability block data, authentication member unique identification data, block status data, traceability status data and authentication proof data; step S32: integrating the data of upstream and downstream blocks of the traceability block data, thereby obtaining a related block data set; step S33: performing correlation data analysis of adjacent blocks on the related block data set, thereby obtaining block correlation data; step S34: performing normalization alignment processing on the traceability block data according to the block correlation data, thereby obtaining traceability alignment data; step S35: performing feature clustering on the traceability alignment data, thereby obtaining cluster data, and uniquely identifying the cluster data, block status data and traceability status data according to the authentication member unique identification data, thereby obtaining traceability alignment cluster data; step S36: performing proof detail feature integration on the authentication proof data, thereby obtaining authentication proof detail data; step S37: performing cluster vector association on the traceability alignment cluster data and the authentication proof detail data, thereby obtaining traceability authentication association data; The specific steps of step S36 are: Step S361: grayscale processing of the electronic image of the authentication proof data is performed to obtain grayscale image data; Step S362: extracting important features of the test report from the authentication certificate data, thereby obtaining important test data; Step S363: performing signature edge granularity recognition on the grayscale image data, thereby obtaining signature granularity data; Step S364: Analyze the texture information of the grayscale image data according to the signature granularity data, thereby obtaining signature texture data; Step S365: performing structural edge detection on the grayscale image data to obtain image structural data; Step S366: performing shape inflection point analysis on the image structure data to obtain shape inflection point data; Step S367: performing feature filtering at the repeated inflection points on the grayscale image data according to the shape inflection point data, thereby obtaining simplified image data; Step S368: performing texture locality analysis on the simplified image data to obtain local texture data; Step S369: Integrate the proof detail features of the local texture data and the signature texture data to obtain authentication proof detail data.

2. The blockchain-based traceability authentication method according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: Request alliance member data to the primary and secondary alliance chains to obtain alliance member data, where the alliance member data includes information release data, information authentication consensus number, information adoption data, information authentication data, and unique identification data of authenticated members; Step S42: performing time series conversion on the information release data and the information adoption data, thereby obtaining information time series data; Step S43: Analyze the frequency peak of the information time series data being published and adopted, so as to obtain the information frequency peak data; Step S44: performing peak difference fluctuation statistics on the information frequency peak data, thereby obtaining peak difference fluctuation data; Step S45: constructing a three-dimensional credit model based on the information authentication consensus number, the participating information authentication data, and the peak difference fluctuation data, thereby obtaining a three-dimensional credit model; Step S46: Associating the unique identification data of the authenticated member with a unique credit score based on the three-dimensional credit model, thereby obtaining unique identification score data.

3. The blockchain-based traceability authentication method according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: constructing a consensus probability model for the traceability authentication associated data and the unique identification scoring data, thereby obtaining a feature consensus probability model; Step S52: Based on the characteristic consensus probability model, the characteristic probability of the priority consensus credit base of the primary and secondary alliance chains is weighted to obtain a priority consensus weighted data set; Step S53: weighting the data set according to the priority consensus and conducting a traceability data consensus based on the primary and secondary alliance chains, thereby obtaining optimized traceability data; Step S54: credit scoring the optimized traceability data based on the three-dimensional credit model, thereby obtaining optimized credit scoring data; Step S55: performing genetic forest model migration on the feature consensus probability model to obtain a genetic forest model; Step S56: performing feature pruning processing on the genetic forest model according to the optimized credit score data, thereby obtaining an optimized genetic forest model, wherein the feature pruning processing includes pruning processing of repeated features associated with the credit score and pruning processing of low-probability related features; Step S57: constructing a traceability credit network model for the traceability alignment clustering data based on the optimized genetic forest model, thereby obtaining a traceability credit network model.

4. The blockchain-based traceability authentication method according to claim 3 is characterized in that: The specific steps of step S57 are: Step S571: Perform secondary allocation of primary and secondary consensus nodes on primary and secondary alliance chains based on the optimized genetic forest model, thereby obtaining optimized primary and secondary node data; Step S572: Optimizing the consensus algorithm of the primary and secondary alliance chains according to the optimized primary and secondary node data, thereby obtaining a dynamic primary and secondary alliance chain; Step S573: requesting alliance member association data for the dynamic primary and secondary alliance chains, thereby obtaining dynamic alliance association data; Step S574: extracting features of abnormal state update on the traceability alignment clustering data, thereby obtaining abnormal state clustering data; Step S575: construct a traceability credit network model for the abnormal state clustering data and the traceability alignment clustering data according to the dynamic alliance association data, thereby obtaining a traceability credit network model.

5. The blockchain-based traceability authentication method according to claim 4 is characterized in that: The specific steps of step S574 are: Extracting the time series data of the state of the traceability alignment clustering data, thereby obtaining the traceability state time series data; Perform time series ratio analysis on the traceability status time series data when the status is updated, so as to obtain the status time series ratio data; The abnormal state update feature extraction is performed on the retroactive aligned clustering data according to the state time series ratio data, so as to obtain the abnormal state clustering data.

6. The blockchain-based traceability authentication method according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: Based on the traceability credit network model, a product traceability request for a unique identification code is made to the dynamic primary and secondary alliance chains, thereby obtaining product traceability data, wherein the product traceability data includes authentication-related data, product status data, and traceability trustworthiness data; Step S62: constructing an authentication feature trust model for the unique identification score data and the authentication proof detail data, thereby obtaining an authentication proof trust probability model; Step S63: Perform authentication trust probability analysis on the traceability data based on the authentication proof trust probability model to obtain the authentication trust probability.

Images