Blockchain-enabled efficient authentication consultation method and system

Abstract

The application provides a blockchain-enabled efficient authentication consultation method and system in the technical field of cross of artificial intelligence and authentication consultation management, and the method comprises the following steps: S1, constructing a consultation data set and a decision knowledge graph; S2, training an authentication consultation decision model through the consultation data set, and dynamically updating the decision knowledge graph; S3, performing bidirectional authentication on an enterprise client and a server, negotiating a session key, encrypting authentication logs into authentication ciphertext logs and storing the authentication ciphertext logs, and uploading a first log fingerprint of the authentication ciphertext logs to a blockchain; S4, encrypting authentication consultation content into consultation ciphertext by the enterprise client through the session key to generate an authentication consultation request and sending the authentication consultation request to the server; and S5, obtaining a consultation result by reasoning authentication consultation content carried by the authentication consultation request through an authentication consultation decision model of the server. The application has the advantages that the accuracy, timeliness, security, traceability and economy of authentication consultation are greatly improved.

Description

Technical Field

[0001] This invention relates to the field of interdisciplinary technology of artificial intelligence and certification consulting management, and in particular to a blockchain-enabled efficient certification consulting method and system. Background Technology

[0002] Certification consulting refers to the systematic technical guidance and services provided to help companies (organizations) meet the requirements of specific certification standards and technical specifications. Its core objective is to assist companies in establishing, implementing, maintaining, and continuously improving their management systems to ensure compliance. Typical services include:

[0003] 1. Standard Interpretation: In-depth analysis of certification standards, transforming them into easily understandable guidelines for internal staff, clearly defining the specific requirements of the standards. 2. System Establishment Guidance: Assisting companies in reviewing existing management processes, identifying gaps with target certification standards, and customizing a management system framework (including policies, objectives, organizational structure, and responsibility planning) based on the company's actual situation. 3. Document Preparation: Guiding companies in preparing system documents that meet standard requirements and possess operability and effectiveness, such as quality manuals, procedure documents, and work instructions. 4. System Operation and Improvement Coaching: Providing continuous support during system operation, assisting in resolving operational issues, and guiding the identification of system deficiencies through internal audits and management reviews to promote continuous improvement. 5. Certification Preparation Assistance: Through simulated certification audit processes, helping companies familiarize themselves with audit requirements, identify and rectify problems in advance, increasing the probability of passing certification audits and boosting confidence in handling them.

[0004] However, current mainstream authentication and consultation systems, especially web-based portals or online customer service systems, rely heavily on human interaction, which results in the following inherent technical shortcomings:

[0005] 1. Insufficient decision support: The passive question-and-answer model, which relies on static knowledge bases and human experience, lacks an active analysis and decision-making mechanism based on the latest data, resulting in reduced accuracy and timeliness of certification decisions.

[0006] 2. High data security risks and difficulties in tracing: Sensitive information (such as corporate qualifications and internal data) is often transmitted through insecure channels such as email and online forms, facing high risks of cyberattacks (such as phishing and data breaches); at the same time, dynamic interactive data generated during the consultation process (such as communication records, informal plans, and temporary decision-making basis) is mostly stored temporarily, making it difficult to form an immutable and reliable record chain. When service disputes occur (such as losses caused by misjudgment standards), companies lack legally valid and auditable electronic evidence to support the tracing of responsibility.

[0007] 3. Low efficiency and high service costs: Manually answering repetitive questions consumes a lot of human resources, which drives up service costs; and the process is difficult to automate. When the demand for certification consultation surges (such as during policy adjustment periods or standard update cycles), it can easily cause service backlog and delays, which cannot meet the requirements of lean service management.

[0008] In summary, existing certification and consulting systems have significant shortcomings in terms of accuracy, timeliness, data security, process traceability, and service economy. Therefore, how to provide a blockchain-enabled, efficient certification and consulting method and system to improve the accuracy, timeliness, security, traceability, and economy of certification and consulting has become an urgent technical problem to be solved. Summary of the Invention

[0009] The technical problem to be solved by this invention is to provide a blockchain-enabled, efficient authentication and consultation method and system, which improves the accuracy, timeliness, security, traceability and economy of authentication and consultation.

[0010] In a first aspect, the present invention provides a blockchain-enabled, highly efficient authentication and consultation method, comprising the following steps:

[0011] Step S10: The server obtains a large amount of historical certification consultation data and historical certification standard files, preprocesses each of the historical certification consultation data and historical certification standard files, annotates each of the preprocessed historical certification consultation data and constructs a consultation dataset, and constructs a decision knowledge graph based on each of the preprocessed historical certification standard files.

[0012] Step S20: The server creates an authentication consultation decision model that calls the decision knowledge graph to provide authentication consultation services. After performing sample expansion operations on the consultation dataset, it divides it into a training set, a validation set, and a test set. The authentication consultation decision model is trained, validated, and tested sequentially through the training set, validation set, and test set. The authentication consultation decision model that passes the test is deployed to the TEE environment, and a monitoring agent is created to dynamically update the decision knowledge graph.

[0013] Step S30: The enterprise client and the server perform bidirectional authentication and negotiate a shared key. A session key is derived based on the shared key. The consistency of the session key derived by the enterprise client and the server is verified. The server records an authentication log, encrypts the authentication log into an authentication ciphertext log and stores it. The server calculates the first log fingerprint of the authentication ciphertext log and uploads it to the blockchain. The server obtains and stores the first evidence certificate fed back by the blockchain for subsequent authentication and traceability.

[0014] Step S40: The enterprise client obtains the input authentication consultation content, encrypts the authentication consultation content into consultation ciphertext using the session key, records the request time, generates an authentication consultation request based on the consultation ciphertext and the request time, and sends the authentication consultation request to the server via the TLS protocol.

[0015] Step S50: The server verifies and parses the received authentication consultation request to obtain authentication consultation content. The authentication consultation content is de-identified using the k-anonymization algorithm to obtain de-identified consultation content. The de-identified consultation content is input into the deployed authentication consultation decision model for reasoning to obtain real-time consultation results including compliance suggestion reports and authentication execution path diagrams. The plaintext authentication consultation content is then deleted.

[0016] Step S60: The server records consultation logs in real time, encrypts the consultation logs into ciphertext logs and stores them, calculates the second log fingerprint of the ciphertext logs and uploads it to the blockchain, obtains and stores the second evidence certificate fed back by the blockchain, and uses it for subsequent consultation tracing.

[0017] Step S70: The server encrypts the real-time consultation results and the second evidence certificate into a consultation feedback encrypted package using the session key, and sends the consultation feedback encrypted package back to the enterprise client in real time via the TLS protocol. Based on the consultation log, the server iteratively optimizes the deployed authentication consultation decision model.

[0018] Secondly, this invention provides a blockchain-enabled high-efficiency authentication and consultation system, comprising the following modules:

[0019] An initialization module is used to obtain a large amount of historical certification consultation data and historical certification standard files from the server, preprocess the historical certification consultation data and historical certification standard files, annotate the preprocessed historical certification consultation data to construct a consultation dataset, and construct a decision knowledge graph based on the preprocessed historical certification standard files.

[0020] The model training and graph update module is used by the server to create an authentication consultation decision model that calls the decision knowledge graph to provide authentication consultation services. After performing sample expansion operations on the consultation dataset, it is divided into a training set, a validation set, and a test set. The authentication consultation decision model is trained, validated, and tested sequentially through the training set, validation set, and test set. The authentication consultation decision model that passes the test is deployed to the TEE environment, and a monitoring agent is created to dynamically update the decision knowledge graph.

[0021] The session key negotiation module is used for bidirectional authentication between the enterprise client and the server and to negotiate a shared key. Based on the shared key, a session key is derived, and the consistency of the session key derived by the enterprise client and the server is verified. The server records an authentication log, encrypts the authentication log into an authentication ciphertext log and stores it, calculates the first log fingerprint of the authentication ciphertext log and uploads it to the blockchain, and obtains and stores the first evidence certificate fed back by the blockchain for subsequent authentication tracing.

[0022] The authentication consultation request sending module is used by the enterprise client to obtain the input authentication consultation content, encrypt the authentication consultation content into consultation ciphertext using the session key, record the request time, generate an authentication consultation request based on the consultation ciphertext and the request time, and send the authentication consultation request to the server via the TLS protocol.

[0023] The model reasoning module is used by the server to verify and parse the received certification consultation request to obtain certification consultation content, to de-identify the certification consultation content through the k-anonymization algorithm to obtain de-identified consultation content, to input the de-identified consultation content into the deployed certification consultation decision model for reasoning, to obtain real-time consultation results including compliance suggestion reports and certification execution path diagrams, and to delete the plaintext certification consultation content.

[0024] The consultation log management module is used to record consultation logs in real time on the server, encrypt the consultation logs into ciphertext logs and store them, calculate the second log fingerprint of the ciphertext logs and upload it to the blockchain, obtain and store the second evidence certificate fed back by the blockchain for subsequent consultation tracing.

[0025] The result feedback and model iteration module is used by the server to encrypt the real-time consultation results and the second evidence certificate into a consultation feedback encrypted package using the session key, and to feed the consultation feedback encrypted package back to the enterprise client in real time via the TLS protocol, and to iteratively optimize the deployed authentication consultation decision model based on the consultation log.

[0026] The advantages of this invention are:

[0027] 1. Obtain a large amount of historical certification consultation data and historical certification standard documents from the server. Preprocess the historical certification consultation data and historical certification standard documents, and then annotate the preprocessed historical certification consultation data to construct a consultation dataset. Based on the preprocessed historical certification standard documents, construct a decision knowledge graph. Next, create a certification consultation decision model that calls the decision knowledge graph to provide certification consultation services. After performing sample expansion operations on the consultation dataset, divide it into training set, validation set, and test set to train, validate, and test the certification consultation decision model. Deploy the certified consultation decision model that passes the test to the TEE environment, and create a monitoring agent to monitor the decision. The knowledge graph is dynamically updated; the enterprise client and server perform two-way authentication and negotiate a session key. The server records the authentication log, encrypts it into an authentication ciphertext log, and stores it. It calculates the first log fingerprint of the authentication ciphertext log, uploads it to the blockchain, and obtains and stores the first evidence certificate fed back from the blockchain. The enterprise client encrypts the authentication consultation content into a consultation ciphertext using the session key, records the request time, and generates an authentication consultation request based on the consultation ciphertext and the request time, sending it to the server. The server verifies and parses the authentication consultation request to obtain the authentication consultation content, and uses the k-anonymization algorithm to de-identify the authentication consultation content to obtain de-identified consultation content, which is then input into the authentication consultation decision. The model performs reasoning to obtain real-time consultation results and deletes plaintext authentication consultation content. The server records consultation logs in real time, encrypts the consultation logs into encrypted consultation logs and stores them, calculates the second log fingerprint of the encrypted consultation logs and uploads it to the blockchain, obtains and stores the second evidence certificate fed back from the blockchain, and sends the real-time consultation results and the second evidence certificate into an encrypted consultation feedback package to the enterprise client using the session key. Based on the consultation logs, the server iteratively optimizes the authentication consultation decision model. In other words, by constructing a decision knowledge graph and training the authentication consultation decision model deployed in the TEE environment, artificial intelligence is used to analyze the de-identified authentication consultation content in real time to generate accurate and valid authentication consultation results. The system includes a recommendation report and certification execution roadmap, significantly improving the accuracy and timeliness of decision-making. It also employs two-way authentication, session key encryption (TLS), sensitive data k-anonymization, and plaintext timely deletion mechanisms. Combined with blockchain technology for encrypted fingerprint storage of key operation logs (authentication / consultation) (with accompanying certificates), it constructs an end-to-end security protection and an immutable traceability chain. Finally, by replacing repetitive manual labor with automated model reasoning, it achieves high-concurrency real-time processing of certification consultation requests and continuous model optimization, significantly reducing service costs and improving operational efficiency. This, in turn, greatly enhances the accuracy, timeliness, security, traceability, and cost-effectiveness of certification consultation.

[0028] 2. By adopting a two-way authentication and shared key derivation mechanism, the system ensures identity authentication and encrypted communication between enterprise clients and servers, preventing man-in-the-middle attacks and data theft; by transmitting data through the TLS protocol and combining it with blockchain notarization, the system provides end-to-end security for the authentication logs and consultation logs, reducing the risk of data leakage; and by deploying the system to a TEE environment, the system ensures the confidentiality and integrity of the authentication consultation decision-making model, avoiding external interference or tampering.

[0029] 3. By using the k-anonymization algorithm to de-identify the authentication consultation content, sensitive data is anonymized, effectively reducing the risk of privacy leakage. At the same time, the plaintext authentication consultation content is deleted, further reducing the possibility of data exposure. The generation and storage of ciphertext consultation ensures that the authentication consultation content remains encrypted during transmission, further enhancing security.

[0030] 4. Based on the decision knowledge graph and certification consultation decision model, automated reasoning can quickly generate compliance recommendation reports and certification execution path diagrams, reducing consultation delays and improving response speed; the consultation dataset optimizes model performance through sample expansion and training-validation-testing process to ensure more accurate and reliable consultation results.

[0031] 5. Uploading log fingerprints to the blockchain and obtaining evidence certificates ensures the immutability and auditability of data, provides a complete authentication and traceability path (such as obtaining the first and second evidence certificates), enhances the transparency of the solution, and facilitates post-audit and dispute resolution.

[0032] 6. By deeply integrating blockchain, trusted computing, and artificial intelligence technologies, an efficient, secure, and traceable certification consulting system has been built: Blockchain notarization ensures the immutability of data throughout the entire process (such as authentication logs and consulting logs), while the AI ​​model (certification consulting decision model) deployed in the TEE environment enables intelligent and privacy-protected consulting results; two-way encryption and k-anonymization prevent the leakage of sensitive information, and dynamic decision knowledge graphs and model iteration mechanisms ensure the accuracy and adaptability of decisions, significantly improving the automation level, security compliance, and service response efficiency of enterprise certification consulting, fundamentally subverting the traditional manual-dominated certification consulting model.

[0033] 7. By acquiring a large amount of historical certification consultation data (including consultation requests, enterprise status data, compliance advice reports, and certification execution roadmaps) and historical certification standard documents (covering core standard documents, supporting documents, certification process documents, certification body documents, and certification standard interpretation documents), we ensure that the basic data sources are extensive and multi-dimensional, providing comprehensive support for subsequent analysis and decision-making, reducing information blind spots, more accurately reflecting real certification consultation scenarios, and improving the credibility and practicality of the solution.

[0034] 8. Entities are extracted from historical authentication standard files using a pre-trained BiLSTM-CRF model, and the relationships between entities are inferred using the TransE algorithm to construct a decision knowledge graph. This integrates deep learning and knowledge graph technologies (such as NLP and relational reasoning) to structure and semanticize the fuzzy authentication standards, facilitating rapid querying and intelligent reasoning. It effectively improves the accuracy of authentication suggestions (consultation results), supports automated decision-making (such as generating personalized execution paths), and significantly enhances user experience and business efficiency.

[0035] 9. By integrating comprehensive historical certification consultation data and historical certification standard documents to build a complete knowledge system, and using automated preprocessing to ensure data quality and privacy security, while combining BiLSTM-CRF entity extraction and TransE relational reasoning technology, unstructured text is transformed into a structured decision knowledge graph, ultimately achieving efficient and accurate certification consultation, significantly improving the intelligence level and execution success rate of the certification consultation process.

[0036] 10. By designing a clear and complete five-layer structure for the certification consulting decision-making model (input parsing, knowledge graph retrieval, feature fusion, decision generation, and output transformation), the model covers the entire process from raw input (text + numerical values) to final decision output (text report + visual path diagram). This end-to-end design avoids the fragmentation of multiple independent systems or manual steps in traditional consulting, and significantly improves the overall automation level and efficiency of certification consulting decision-making.

[0037] 11. By innovatively combining bidirectional LSTM (which excels at processing sequential text) and fully connected layers (which excel at processing structured numerical data) in the input parsing layer, the features of consultation requests and current enterprise data are effectively extracted. Initial fusion is achieved through vector concatenation. This design can fully understand complex and unstructured user requests while taking into account the specific quantitative situation of the enterprise, providing a more comprehensive and accurate information foundation for subsequent decision-making.

[0038] 12. By setting up a knowledge graph retrieval layer and using graph convolutional networks to encode the decision knowledge graph, the model can learn and utilize the dynamic relationships and semantic information of entities (such as regulations, standards, cases, and process nodes) in the decision knowledge graph, which is superior to static knowledge bases. By adopting a multi-head attention mechanism for retrieval, the model can actively and accurately focus on the most relevant parts (node ​​embeddings) of the decision knowledge graph based on the initial feature vector (representing the current consultation question and enterprise status), generating enhanced feature vectors, which greatly improves the professionalism and relevance of decision recommendations. In other words, the combination of "decision knowledge graph + GCN encoding + multi-head attention retrieval" is used for knowledge enhancement in consultation decisions, effectively improving the accuracy of certification consultation.

[0039] 13. By setting up a feature fusion layer, not only is simple feature concatenation (unifying the feature vector) performed, but a Transformer-based self-attention mechanism is further introduced. This mechanism can automatically learn the importance weights of different features in the unified feature vector and perform weighted fusion of key information, enabling the model to focus more on the most core elements of the current decision, suppress noise or irrelevant information, and generate better fused features. That is, applying the self-attention mechanism to feature fusion and key information filtering in the certification consultation decision model improves the model's reasoning ability and decision quality.

[0040] 14. The decision generation layer uses a seq2seq model in parallel to generate a detailed compliance recommendation report and a first-graph neural network to generate an authentication execution path diagram. This dual-channel output meets the user's dual needs for detailed textual explanations and clear process guidance, and the output results are more intuitive and practical.

[0041] 15. The output transformation layer uses a softmax+template engine to format the compliance recommendation report into a formal report, ensuring professionalism and standardization; it uses a tree decoder to convert the certification execution path diagram into a visual representation, improving the readability and usability of the results, and greatly enhancing the user experience and direct usability of the model output results.

[0042] 16. By setting a loss function that integrates sequence loss, graph structure loss, and regularization term, the sequence loss ensures the accuracy of the generated text report content (cross-entropy), the graph structure loss ensures the reasonable structure of the generated path graph (graph edit distance), and the regularization term prevents overfitting and improves generalization ability (L2+dropout). The optimization direction is flexibly adjusted through weight coefficients α, β, and γ. This joint optimization mechanism can simultaneously improve the quality of the text report and the accuracy of the path graph structure, and synergistically optimize the overall decision-making effect.

[0043] 17. Through an end-to-end five-layer architecture (input parsing, knowledge graph retrieval, feature fusion, decision generation, and output transformation), it innovatively integrates bidirectional LSTM text parsing, graph convolutional network dynamic knowledge encoding, multi-head attention precise retrieval, and Transformer self-attention feature weighting to achieve deep understanding and knowledge enhancement of heterogeneous data (consulting text + enterprise numerical data). Based on multi-task joint optimization of the loss function, it simultaneously generates formatted compliance recommendation reports (Seq2Seq + template engine) and visualized certification path diagrams (graph neural network + tree decoder). Finally, through rigorous dynamic hyperparameter optimization and a multi-dimensional evaluation process (covering indicators such as accuracy, efficiency, and robustness), it significantly improves the automation and intelligence level of enterprise certification consulting decisions and the practicality and professionalism of the output results.

[0044] 18. By creating a monitoring agent and setting monitoring parameters (such as monitoring cycle, monitoring source, and access permissions), the server can periodically and proactively monitor the latest certification standard documents, enabling dynamic updates of the decision knowledge graph without manual intervention. The pre-processed latest certification standard documents are fused into the decision knowledge graph by a second graph neural network, enhancing the intelligence and accuracy of data integration and ensuring that the decision knowledge graph always reflects the latest standards. At the same time, dynamic caching based on retrieval records significantly improves query efficiency, reduces latency, optimizes resource utilization, and improves the overall real-time response capability and processing efficiency of the system.

[0045] 19. By using two-way authentication and session key fingerprint verification (based on the SHA3-256 algorithm), the security of the communication terminal's identity and the consistency of the key are ensured, preventing man-in-the-middle attacks from the source. At the same time, dynamic key derivation (BLAKE2 hash truncation to generate K1) combined with layered encryption (ChaCha20+AES256) is used to efficiently protect the integrity and confidentiality of the authentication log. Innovatively, after storing the authentication ciphertext log in the IPFS distributed system, its hash fingerprint (first log fingerprint) is anchored to the blockchain to generate the first evidence certificate of all elements, realizing the immutability of log data and the traceability of operations. Overall, while improving the anti-attack capability and reducing audit costs, it provides an end-to-end security closed loop and efficient risk management capabilities.

[0046] 20. By integrating multiple encryption mechanisms and security protocols, the security and reliability of the authentication consultation process are significantly improved: The enterprise client uses the IDEA algorithm to encrypt the core authentication consultation content to generate ciphertext. Combined with the request time, it generates a hash value H2 using the BLAKE2 algorithm to verify data integrity. Then, the RC6 algorithm is used to perform secondary encryption on all key information (including the ciphertext, request time, and hash value H2) to form a high-strength encrypted string. Finally, it is transmitted to the server via TLS protocol. This layered protection structure not only effectively resists data theft, tampering, and replay attacks, ensuring the confidentiality and authenticity of information, but also balances processing efficiency by optimizing the algorithm combination (such as the efficient hashing of BLAKE2 and the flexible encryption of RC6), providing a scalable and low-latency secure authentication solution.

[0047] 21. By combining multiple encryption algorithms (such as RC6 and IDEA) with hash verification and timeliness verification, an end-to-end security protection system is constructed to ensure the anti-tampering and anti-replay attack capabilities of data transmission and processing. At the same time, the k-anonymization algorithm is used to de-identify sensitive data. Under the premise of ensuring user privacy compliance, the authentication consultation decision model driven by hardware acceleration technology efficiently generates structured consultation results (compliance recommendation reports, authentication execution path diagrams). Its rule engine's automated data integrity verification and plaintext data synchronous deletion mechanism further improves processing accuracy and resource security, ultimately forming a highly efficient processing closed loop that takes into account real-time response, high security standards, privacy protection, and intelligent decision-making.

[0048] 22. By integrating multi-layered dynamic encryption (based on SM3 dynamic derived keys combined with ChaCha20 and 3DES), distributed storage (IPFS), and blockchain notarization technology into the storage of consultation logs, a highly secure and robust consultation log management system has been constructed. This system generates crack-resistant composite encrypted data streams in real time to mitigate leakage risks, utilizes hash verification (SM3 / SHA3-256) and the immutability of blockchain to ensure data trustworthiness throughout the process, and leverages IPFS's decentralized storage to achieve efficient and low-cost resource scheduling. Its dynamic key mechanism and automated notarization certificate generation (including notarization time and digital signature) significantly improve traceability, audit efficiency, and compliance levels, providing a fully optimized data protection solution for certification consultations.

[0049] 23. By combining dynamic key (K3, K4) generation with multiple encryption mechanisms (key extraction based on SM3 hash and segmented AES encryption) and the TLS transport protocol, the security and integrity of data transmission are significantly improved. Simultaneously, real-time block processing and session key packaging feedback optimize the low-latency interaction and user experience of consultation results. Furthermore, through an incremental model training mechanism triggered by a log quantity threshold, the authentication consultation decision model is dynamically optimized during idle periods, achieving efficient utilization of computing resources and system adaptability. Overall, security, real-time performance, and scalability are balanced, constructing an efficient and reliable security protection and intelligent optimization system for online authentication consultation.

[0050] 24. Through the collaborative innovation of blockchain notarization, TEE trusted execution environment, dynamic decision knowledge graph and multi-layer encryption system, we have achieved efficient and secure certification consulting services: Based on AI decision model (integrating BiLSTM, graph attention mechanism and Seq2Seq), we accurately generate compliance recommendation reports and certification execution path diagrams; We use k-anonymization desensitization, dynamic session keys and block encryption technology to protect enterprise data privacy; We build a full-process traceability mechanism through log fingerprint notarization and IPFS distributed storage, and continuously improve decision robustness by dynamically updating the knowledge graph and optimizing model idle time. Under the premise of ensuring end-to-end security and tamper-proof, we significantly improve the real-time performance and reliability of certification consulting. Attached Figure Description

[0051] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0052] Figure 1 This is a flowchart of a blockchain-enabled, highly efficient authentication and consultation method according to the present invention.

[0053] Figure 2 This is a schematic diagram of the structure of a blockchain-enabled high-efficiency authentication and consultation system according to the present invention. Detailed Implementation

[0054] The overall approach of the technical solution in this application is as follows: By constructing a decision knowledge graph and training an authentication consultation decision model deployed in a TEE environment, artificial intelligence is used to analyze the anonymized authentication consultation content in real time to generate accurate compliance advice reports and authentication execution path diagrams, significantly improving the accuracy and timeliness of decision-making. Simultaneously, two-way authentication, session key encryption transmission (TLS), sensitive data k-anonymization, and plaintext timely deletion mechanisms are adopted, combined with blockchain for encrypted fingerprint storage of key operation logs (authentication / consultation) (with accompanying storage certificates), constructing an end-to-end security protection and an immutable traceability chain. Finally, automated model reasoning replaces repetitive manual labor, achieving high-concurrency real-time processing of authentication consultation requests and continuous model optimization, significantly reducing service costs and improving operational efficiency, thereby enhancing the accuracy, timeliness, security, traceability, and economy of authentication consultation.

[0055] Please refer to Figures 1 to 2 As shown, a preferred embodiment of the blockchain-enabled efficient authentication and consultation method of the present invention includes the following steps:

[0056] Step S10: The server obtains a large amount of historical certification consultation data and historical certification standard files, preprocesses each of the historical certification consultation data and historical certification standard files, annotates each of the preprocessed historical certification consultation data and constructs a consultation dataset, and constructs a decision knowledge graph based on each of the preprocessed historical certification standard files.

[0057] Step S20: The server creates an authentication consultation decision model that calls the decision knowledge graph to provide authentication consultation services. After performing sample expansion operations on the consultation dataset, it divides it into a training set, a validation set, and a test set. The authentication consultation decision model is trained, validated, and tested sequentially through the training set, validation set, and test set. The authentication consultation decision model that passes the test is deployed to the TEE environment, and a monitoring agent is created to dynamically update the decision knowledge graph.

[0058] A TEE (Trusted Execution Environment) is a secure execution environment that runs in parallel with the device's operating system. Only authorized and reliable applications (trusted applications) can run in this environment. It uses hardware and software security resources to protect the applications and data executed in the TEE.

[0059] Step S30: The enterprise client and the server perform bidirectional authentication and negotiate a shared key. A session key is derived based on the shared key. The consistency of the session key derived by the enterprise client and the server is verified. The server records an authentication log, encrypts the authentication log into an authentication ciphertext log and stores it. The server calculates the first log fingerprint of the authentication ciphertext log and uploads it to the blockchain. The server obtains and stores the first evidence certificate fed back by the blockchain for subsequent authentication and traceability.

[0060] Step S40: The enterprise client obtains the input authentication consultation content, encrypts the authentication consultation content into consultation ciphertext using the session key, records the request time, generates an authentication consultation request based on the consultation ciphertext and the request time, and sends the authentication consultation request to the server via the TLS protocol.

[0061] Step S50: The server verifies and parses the received authentication consultation request to obtain authentication consultation content. The authentication consultation content is de-identified using the k-anonymization algorithm to obtain de-identified consultation content. The de-identified consultation content is input into the deployed authentication consultation decision model for reasoning to obtain real-time consultation results including compliance suggestion reports and authentication execution path diagrams. The plaintext authentication consultation content is then deleted.

[0062] Step S60: The server records consultation logs in real time, encrypts the consultation logs into ciphertext logs and stores them, calculates the second log fingerprint of the ciphertext logs and uploads it to the blockchain, obtains and stores the second evidence certificate fed back by the blockchain, and uses it for subsequent consultation tracing.

[0063] Step S70: The server encrypts the real-time consultation results and the second evidence certificate into a consultation feedback encrypted package using the session key, and sends the consultation feedback encrypted package back to the enterprise client in real time via the TLS protocol. Based on the consultation log, the server iteratively optimizes the deployed authentication consultation decision model.

[0064] Step S10 specifically involves:

[0065] The server acquires a large amount of historical certification consultation data and historical certification standard documents; the historical certification consultation data includes at least certification consultation content, compliance recommendation reports, and certification execution path diagrams; the certification consultation content includes at least consultation requests and current enterprise data; the historical certification standard documents include at least core standard documents, supporting documents, certification process documents, certification body documents, and certification standard interpretation documents.

[0066] The enterprise's current status data should include at least the following: a) Basic enterprise information: the enterprise's size, industry sector, business scope, organizational structure, etc. This information helps to understand the overall situation of the enterprise and tailor a management system accordingly. b) Existing management system documents: the enterprise's existing management systems, process documents, operating procedures, etc., used to identify gaps with the target certification standards and provide a basis for system establishment and improvement. c) Current status of management processes: the enterprise's actual management processes, including business connections, information transmission, and decision-making mechanisms between departments, used to identify problems and weaknesses in the processes, and to propose optimization suggestions to make the management system smoother and more efficient. d) Personnel capabilities and responsibilities: the professional skills, work experience, and level of understanding and knowledge of the management system among the enterprise's internal personnel, while clearly defining the allocation of responsibilities for each department and position, so as to reasonably arrange personnel and ensure that all responsibilities are effectively implemented when establishing and operating the management system.

[0067] The core standard document includes at least the standard text and interpretations of the standard clauses. The standard text is the core part of the certification standard, which specifies in detail the specific requirements that enterprises or organizations need to meet, such as ISO 9001 quality management system standard, ISO 14001 environmental management system standard, and ISO 45001 occupational health and safety management system standard. The interpretations of the standard clauses are to help enterprises better understand and apply the standard clauses, and usually include the background, purpose, detailed explanation of the specific requirements, and how to implement these requirements in practice.

[0068] The supporting documents include at least application guidelines, industry-specific requirements, and technical specifications. The application guidelines provide guidance for the specific application of the standard, helping companies better implement the standard in different industries or specific situations. For example, the application guidelines for ISO 9001 may provide specific implementation suggestions for different industries such as manufacturing and services. The industry-specific requirements supplement or refine general standards for specific industries. For example, the automotive industry has the IATF 16949 standard, which is a more detailed quality management system standard for the automotive industry based on ISO 9001. The technical specifications provide technical details and specifications related to the standard, ensuring that companies can meet the technical requirements during implementation. For example, environmental management system standards may involve emission standards for specific pollutants, environmental monitoring technical specifications, etc.

[0069] The certification process documents include at least a certification application guide, audit process documents, and a certification certificate sample. The certification application guide details how companies can apply for certification, including application requirements, required documents and materials, and the application process, helping companies understand the entry requirements and initial steps. The audit process documents include an audit plan, audit checklist, and audit report template. These documents standardize the certification audit process, ensuring the fairness, objectivity, and consistency of the audit. The audit plan clarifies the audit timeline, scope, and focus. The audit checklist lists the specific clauses and contents to be checked during the audit. The audit report template specifies the format and content requirements for the audit report. The certification certificate sample demonstrates the style and content of the certification certificate, including the company name, certification scope, certificate number, issuing authority, and validity period, helping companies correctly use and display the certification certificate after obtaining it.

[0070] The certification body documents include at least the certification body rules and procedures, and certification body qualification certificates. The certification body rules and procedures are the certification body's own operating rules and procedures, including the certification body's qualification requirements, certification process, auditor qualification management, certification decision-making procedures, appeal and complaint handling mechanisms, etc., to ensure that the certification body's operation complies with regulations. The certification body qualification certificates are the certification body's qualification certificates, accreditation certificates, and other documents, proving that it has the legal qualifications and capabilities to carry out specific certification business.

[0071] The certification standard interpretation documents include at least a standard clarification document and a frequently asked questions (FAQs). The standard clarification document is used to further explain and clarify controversial or easily misunderstood clauses to ensure the correct understanding and application of the standard. The frequently asked questions are answers to questions that enterprises often encounter during the implementation of certification standards, providing a way to quickly resolve problems and improve the efficiency and accuracy of certification implementation.

[0072] The historical certified consultation data shall undergo preprocessing including at least data cleaning, data formatting, data classification, and tagging; the data cleaning shall at least include removing duplicate data, handling missing values, and correcting erroneous data; the data formatting shall at least include unifying text format and standardizing data structure; the data classification and tagging shall at least include consultation type classification and adding tags.

[0073] The process of removing duplicate data involves checking for duplicate records in certification consultation content, compliance recommendation reports, and certification execution path diagrams. For example, the same consultation case might be recorded repeatedly due to data entry errors or multiple backups. Duplicates can be identified and deleted by comparing key data fields. Handling missing values ​​involves taking corresponding measures when certain key information in the consultation request (such as the specific type of consultation issue) or enterprise status data (such as some financial indicators) is missing. If the missing data significantly impacts the analysis and cannot be completed, the data entry can be deleted. If the missing information is minor, interpolation or filling with default values ​​can be used. Correcting erroneous data involves checking for errors in the data, such as incorrect consultation date formats or numerical errors in enterprise status data (such as incorrect sales unit). Standardizing text format involves standardizing the font, font size, and other formats for text data such as certification consultation content and compliance recommendation reports. Simultaneously, the text is segmented to ensure a clear structure. The standardized data structure standardizes the data structure of the certification execution path diagram. If the certification execution path diagram is stored in image form, it can be converted into a graphical data structure, such as nodes and edges. Each node represents a certification stage, and the edges represent the transformation relationship between stages. Corresponding attributes are added to each node and edge. The consultation type classification divides historical certification consultation data into different consultation categories based on the content of the consultation request. For example, it can be divided into quality management system certification consultation, environmental management system certification consultation, etc. Adding tags involves adding tags to the data, such as consultation result tags (certification successful, certification failed, not certified, etc.) and compliance recommendation severity tags (high risk, medium risk, low risk), etc.

[0074] The historical authentication standard documents are preprocessed in at least the following ways: document organization and classification, text content extraction and cleaning, and key information annotation and association. The document organization and classification includes at least physical organization and index creation. The text content extraction and cleaning includes at least text extraction and text format cleaning. The key information annotation and association includes at least annotation of key information and establishment of document associations.

[0075] The physical organization involves classifying and storing core standard documents, supporting documents, certification process documents, certification body documents, and certification standard interpretation documents separately. In practice, this can be done by file type (e.g., Word document, PDF document) or subject (e.g., quality certification, environmental certification). Indexing involves creating an index for each file, including file name, file type, file category, and file version, facilitating quick file retrieval and management. Text extraction involves using PDF parsing tools to extract text content from PDF files and directly reading text from Word documents. During extraction, the integrity of the text must be ensured to avoid garbled characters. Text formatting removal involves removing redundant formatting elements such as headers, footers, and page numbers. Tables in the text can be converted to structured data formats such as CSV files. Marking key information involves marking key clauses and keywords in core standard documents, certification standard interpretation documents, etc. For example, in quality management system certification standard documents, key concepts such as "quality policy" and "quality objectives" are marked. Establishing file associations involves analyzing the relationships between files, such as the reference relationship between core standard documents and supporting documents, and the matching relationship between certification process documents and certification body documents.

[0076] In the preprocessed historical certification consultation data, the certification consultation content, compliance suggestion report, and certification execution path diagram are associated and labeled with consultation result tags. Based on the labeled historical certification consultation data, a consultation dataset is constructed. The enterprise information carried by the enterprise status data in the consultation dataset is anonymized and desensitized using the k-anonymization algorithm. The consultation result tags are certification successful, certification failed, or not certified.

[0077] Entities are extracted from the pre-processed historical certification standard documents using a pre-trained BiLSTM-CRF model. Relationships between these entities are inferred using the TransE algorithm. A decision knowledge graph is then constructed based on these entities and their relationships. The entities include at least standard-related entities, supporting document entities, certification process document entities, certification body document entities, and enterprise-related entities. The relationships include at least standard-related relationships, supporting document relationships, certification process document relationships, certification body document relationships, enterprise-standard relationships, and internal enterprise relationships.

[0078] The LSTM (Long Short-Term Memory) network in the BiLSTM-CRF model is a special type of recurrent neural network (RNN). By introducing input gates, forget gates, and output gates, it solves the gradient vanishing or exploding problems that traditional RNNs often encounter when processing long sequences of data, and can better capture long-term dependencies in the sequence. BILSTM (Bidirectional Long Short-Term Memory) is an improvement on LSTM, containing two LSTM layers: a forward LSTM layer that processes data sequentially from the beginning to the end of the sequence, and a backward LSTM layer that processes data sequentially from the end to the beginning of the sequence. This allows for the simultaneous acquisition of information from both directions in the sequence. This bidirectional information is crucial for many natural language processing tasks, such as named entity recognition. In sequence labeling tasks, whether a word is part of an entity depends not only on the words preceding it but also on the words following it. CRF (Conditional Random Field) is a discriminative model used to model a given observation sequence labeled with another entity. In sequence labeling tasks, there are often certain relationships between the labels of a labeled sequence. For example, in named entity recognition tasks, the start label of an entity (such as "B-PER" indicating the beginning of a person's name) is usually followed by an intermediate label (such as "I-PER") or an end label (such as "E-PER"), and it will not jump directly to other types of labels. CRF can model this transition relationship between labels very well. It calculates the probability of a certain labeled sequence under a given observation sequence by defining a conditional probability distribution, so as to maximize the probability that the labeled sequence conforms to the labeling rules.

[0079] TransE (Translating Embedding) is an algorithm for embedding knowledge graphs. The TransE algorithm maps entities and relations to a vector space, so that pairs of entities that satisfy the relations satisfy certain geometric relationships in the vector space. This allows the TransE algorithm to be used to predict missing triples in a knowledge graph, that is, to infer the relationships between entities.

[0080] Step S20 specifically includes:

[0081] Step S21: The server creates an authentication consultation decision model based on the input parsing layer, knowledge graph retrieval layer, feature fusion layer, decision generation layer, and output transformation layer, and sets the loss function of the authentication consultation decision model;

[0082] The input parsing layer is constructed based on a bidirectional LSTM module, an enterprise status encoding module, and a vector concatenation module. The bidirectional LSTM module is used to extract text feature vectors from consultation requests; the enterprise status encoding module is used to extract numerical feature vectors from enterprise status data through a fully connected layer (with ReLU activation); and the vector concatenation module is used to concatenate the text feature vectors and numerical feature vectors into a preliminary feature vector.

[0083] The input parsing layer is used to parse and standardize the input authentication consultation content, encoding the consultation request into a text feature vector and the enterprise status data into a structured numerical feature vector for easier subsequent processing. In specific implementation, an adaptive length mechanism is adopted to handle variable-length consultation requests and missing enterprise data; dropout regularization is used to reduce the risk of overfitting and ensure robustness across various enterprise sizes.

[0084] The knowledge graph retrieval layer is constructed based on a graph embedding module and a graph attention retrieval module; the graph embedding module is used to encode the decision knowledge graph into node embeddings through a graph convolutional network (GCN); the graph attention retrieval module is used to retrieve enhanced feature vectors related to the initial feature vectors from each of the node embeddings through a multi-head attention mechanism.

[0085] The knowledge graph retrieval layer dynamically accesses the decision knowledge graph, retrieves contextual features related to the input (preliminary feature vector), such as compliance standards and industry best practices, and outputs enhanced feature vectors (knowledge-driven features). These enhanced feature vectors include entity embeddings and relation weights. In practice, a caching mechanism can be used to improve retrieval efficiency; and an error-tolerant module can be added to handle noise or missing data in the decision knowledge graph, ensuring decision reliability.

[0086] The feature fusion layer is constructed based on a feature concatenation module and a self-attention fusion module. The feature concatenation module is used to concatenate the initial feature vector and the enhanced feature vector into a unified feature vector. The self-attention fusion module is used to perform weighted fusion of key features in the unified feature vector through a transformer-based self-attention mechanism to obtain fused features.

[0087] The feature fusion layer is used to unify features from different sources (preliminary feature vectors and enhanced feature vectors), capture the dependencies between features (such as the correlation between the current state of the enterprise and the consulting needs), and output high-dimensional fused features to support subsequent decision-making. In specific implementation, a gating mechanism (such as GRU units) is introduced to prioritize the fusion of enhanced feature vectors from the decision knowledge graph to emphasize compliance knowledge; feature normalization is added to balance the scale differences between textual and numerical features and improve decision robustness.

[0088] The decision generation layer is constructed based on a suggestion generation module and a path graph generation module. The suggestion generation module is used to infer compliance suggestion reports by using a seq2seq model (encoder-decoder structure, mainly LSTM) to the fused features. The path graph generation module is used to decode the fused features by a first graph neural network (GNN) to obtain an authentication execution path graph.

[0089] The decision generation layer generates structured output based on fusion features; the suggestion generation module outputs a text sequence report (compliance suggestion report), and the path graph generation module outputs a directed graph (certification execution path graph). In specific implementation, the suggestion generation module integrates rule constraint decoding to ensure that the compliance suggestion report conforms to industry standards; the path graph generation module adds a dynamic path optimization sublayer (based on a reinforcement learning reward mechanism) to generate the shortest or lowest-risk execution path, adapting to the diversity of enterprises.

[0090] The output conversion layer is built upon a text formatting module and a graph rendering module; the text formatting module is used to convert compliance recommendation reports into formal report formats through a softmax layer and a template engine; the graph rendering module is used to convert the certification execution path graph into a visual graph representation through a tree decoder.

[0091] The output conversion layer is used for formatting compliance recommendation reports and certification execution path diagrams, generating the final consultation results.

[0092] The formula for the loss function is:

[0093] L total =α·L report +β·L path +γ·L reg ;

[0094] Among them, L total L represents the loss value of the loss function; report The sequence loss for compliance recommendation reports is represented by cross-entropy loss, which is suitable for text generation tasks; L path The graph structure loss representing the authentication execution path graph is represented by the graph edit distance loss, which measures the deviation between the generated path and the ideal path; L reg α represents the regularization term, including L2 regularization (weight decay) and dropout noise regularization; α, β, and γ all represent weight coefficients;

[0095] Step S22: After the server performs sample augmentation on the consultation dataset based on the consultation category, it divides the consultation dataset into a training set, a validation set, and a test set in a ratio of 7:2:1. The certification consultation decision model is trained using the training set and the loss function. During the training process, the hyperparameters of the certification consultation decision model are continuously optimized, including at least the learning rate, learning warm-up rate, learning decay rate, random dropout rate, batch size, and number of hidden layers, until the loss value of the loss function is less than the preset loss threshold, or the preset early stopping condition is reached (e.g., the training time or number of iterations reaches the upper limit, or the model parameters change too little).

[0096] The training set is used to calculate the accuracy of consultation results, inference latency, completeness of compliance recommendation report content, completeness of certification execution path rendering, and retrieval relevance of decision knowledge graph to validate the trained certification consultation decision model. If the validation fails, the training set is expanded and training continues; if the validation passes, then:

[0097] The test set is used to calculate task completion efficiency, actual path deviation rate, noise tolerance, resource consumption, and maximum processing request rate to test the verified certification consultation decision model. If the test fails, the training set is expanded and training continues; if the test passes, training ends and the verified certification consultation decision model is deployed to the TEE environment.

[0098] Step S23: The server creates a monitoring agent, sets the monitoring parameters of the monitoring agent, monitors the latest authentication standard file through the monitoring agent, preprocesses the latest authentication standard file, and then integrates the latest authentication standard file into the decision knowledge graph through a second graph neural network (updating or adding entities and relationships in the decision knowledge graph) to dynamically update the decision knowledge graph; the monitoring parameters include at least the monitoring period, monitoring source, and access permissions;

[0099] The server dynamically caches the decision knowledge graph based on the retrieval records.

[0100] Step S30 specifically includes:

[0101] Step S31: The enterprise client and the server perform bidirectional authentication and negotiate a shared key. Based on the shared key, they derive session keys. The enterprise client calculates the first key fingerprint of the session key using the SHA3-256 algorithm and sends it to the server. The server calculates the second key fingerprint of the session key using the SHA3-256 algorithm and sends it to the enterprise client. The enterprise client and the server verify the consistency of the session key using the first key fingerprint and the second key fingerprint.

[0102] Step S32: The server records the authentication log in real time. After authentication, it obtains the current timestamp T1, calculates the hash value H1 of the authentication log and timestamp T1 using the BLAKE2 algorithm, selects the first 64 bits of the hash value H1 as the dynamic key K1, calls the dynamic key K1 using the ChaCha20 algorithm to encrypt the authentication log into first-level encrypted data, encrypts the first-level encrypted data, timestamp T1 and hash value H1 into authentication ciphertext log using the AES256 algorithm, stores the authentication ciphertext log in the IPFS system, calculates the first log fingerprint of the authentication ciphertext log using the SHA3-256 algorithm and uploads it to the blockchain, obtains and stores the first evidence certificate fed back by the blockchain, which carries at least the evidence number, evidence time, evidence subject information, data information, blockchain information and signature information, for subsequent authentication and traceability.

[0103] Step S31 specifically includes:

[0104] Step S311: The enterprise client presets a certificate Cert_C carrying a long-term public key PublicKey_C, a long-term private key PrivateKey_C matching the long-term public key PublicKey_C, and a CA root certificate through the CA center.

[0105] The server pre-sets a certificate Cert_S carrying a long-term public key PublicKey_S, a long-term private key PrivateKey_S matching the long-term public key PublicKey_S, and a CA root certificate through the CA center.

[0106] The CA root certificate is used to verify the validity of certificates Cert_C and Cert_S;

[0107] Step S312: The enterprise client generates a random number Nonce_C, generates a first authentication request based on the list of cipher suites supported by the local machine and the random number Nonce_C, and sends it to the server;

[0108] Step S313: The server parses the received first authentication request to obtain a list of cipher suites and a random number Nonce_C. It selects a cipher suite from the list, generates a random number Nonce_S, and creates a pair of temporary public keys EphemeralPublicKey_S and temporary private keys EphemeralPrivateKey_S based on the ECDHE algorithm in the cipher suite. The server then signs the random number Nonce_C, the random number Nonce_S, and the temporary public key EphemeralPublicKey_S using the long-term private key PrivateKey_S to obtain the server signature Sig_S.

[0109] The server generates a second authentication request based on the cipher suite, the random number Nonce_S, the certificate Cert_S, the temporary public key EphemeralPublicKey_S, and the server signature Sig_S, and sends it to the enterprise client.

[0110] Step S314: The enterprise client parses the received second authentication request to obtain the cipher suite, random number Nonce_S, certificate Cert_S, temporary public key EphemeralPublicKey_S, and server signature Sig_S;

[0111] The enterprise client verifies the certificate Cert_S using the CA root certificate, and verifies the server signature Sig_S using the long-term public key PublicKey_S carried by the certificate Cert_S. Upon successful verification:

[0112] The enterprise client creates a pair of temporary public keys EphemeralPublicKey_C and temporary private keys EphemeralPrivateKey_C based on the ECDHE algorithm in the cryptographic suite. The client then uses the long-term private key PrivateKey_C to sign the random number Nonce_C, the random number Nonce_S, and the temporary public key EphemeralPublicKey_C to obtain the client signature Sig_C.

[0113] The enterprise client generates a third authentication request based on the certificate Cert_C, the temporary public key EphemeralPublicKey_C, and the client signature Sig_C, and sends it to the server.

[0114] Step S315: The server parses the received third authentication request to obtain the certificate Cert_C, the temporary public key EphemeralPublicKey_C, and the client signature Sig_C;

[0115] The server verifies the certificate Cert_C using the CA root certificate, verifies the client signature Sig_C using the public key PublicKey_C carried by the certificate Cert_C, and sends a verification result to the enterprise client indicating whether the verification was successful or failed.

[0116] Step S316: If the verification result is a verification failure, the process ends; if the verification result is a verification success, the enterprise client uses the ECDHE algorithm to call the temporary private key EphemeralPrivateKey_C and the temporary public key EphemeralPublicKey_S to calculate the shared key SharedSecret_C; the server uses the ECDHE algorithm to call the temporary private key EphemeralPrivateKey_S and the temporary public key EphemeralPublicKey_C to calculate the shared key SharedSecret_S, where the shared key SharedSecret_C and the shared key SharedSecret_S are the same key.

[0117] The ECDHE algorithm is a key negotiation algorithm based on elliptic curve cryptography. It allows two communicating parties to negotiate a shared key over an insecure channel without sharing any secret information beforehand. Its core idea is to leverage the one-way nature of dot product operations on elliptic curves, ensuring that even if an attacker intercepts the public keys of both parties, they cannot compute the shared key.

[0118] The enterprise client derives a session key from the shared key SharedSecret_C, the random number Nonce_C, and the random number Nonce_S using KDF functions; the server derives a session key from the shared key SharedSecret_S, the random number Nonce_C, and the random number Nonce_S using KDF functions.

[0119] Step S317: The enterprise client calculates the first key fingerprint of the session key using the SHA3-256 algorithm and sends it to the server. The server calculates the second key fingerprint of the session key using the SHA3-256 algorithm and sends it to the enterprise client. The enterprise client and the server verify the consistency of the session key using the first key fingerprint and the second key fingerprint.

[0120] Step S40 specifically involves:

[0121] The enterprise client obtains the input authentication consultation content, uses the IDEA algorithm to call the session key to encrypt the authentication consultation content into consultation ciphertext, records the request time, calculates the hash value H2 of the consultation ciphertext and the request time using the BLAKE2 algorithm, encrypts the consultation ciphertext, the request time and the hash value H2 into an encrypted string using the RC6 algorithm, generates an authentication consultation request based on the encrypted string, and sends the authentication consultation request to the server via the TLS protocol.

[0122] Step S50 specifically involves:

[0123] The server receives the authentication consultation request in real time, parses the request to obtain an encrypted string, decrypts the encrypted string using the RC6 algorithm to obtain the consultation ciphertext, request time, and hash value H2, performs integrity verification on the consultation ciphertext and request time using the hash value H2, performs timeliness verification using the request time, and then uses the IDEA algorithm to call the session key to decrypt the consultation ciphertext to obtain the authentication consultation content. The rule engine calls preset data detection rules to verify the data completeness of the authentication consultation content, that is, to determine whether the enterprise status data corresponding to the consultation request is missing. If the content is missing, feedback is given to the enterprise client to avoid invalid reasoning.

[0124] The server uses the k-anonymization algorithm to de-identify the certification consultation content to obtain de-identified consultation content. The de-identified consultation content is then input into the deployed certification consultation decision model. The certification consultation decision model performs inference based on hardware acceleration technology to obtain real-time consultation results, including compliance recommendation reports and certification execution path diagrams, and simultaneously deletes the plaintext certification consultation content.

[0125] Step S60 specifically involves:

[0126] The server records in real time a consultation log that includes at least authentication consultation requests, real-time consultation results, client information, and authentication feedback, wherein the authentication feedback is authentication success, authentication failure, or no authentication.

[0127] The server obtains the current timestamp T2, calculates the hash value H3 of the consultation log and timestamp T2 using the SM3 algorithm, selects 32 bits starting from the 9th bit of the hash value H3 as the dynamic key K2, calls the dynamic key K2 using the ChaCha20 algorithm to encrypt the consultation log into a layer of encrypted data, encrypts the layer of encrypted data, timestamp T2 and hash value H3 into a ciphertext consultation log using the 3DES algorithm, stores the ciphertext consultation log in the IPFS system, calculates the second log fingerprint of the ciphertext consultation log using the SHA3-256 algorithm and uploads it to the blockchain, obtains and stores the second evidence certificate fed back by the blockchain, which carries at least the evidence number, evidence time, evidence subject information, data information, blockchain information and signature information, for subsequent consultation tracing;

[0128] IPFS (InterPlanetary File System) is a peer-to-peer distributed file system designed to create a content-addressable, versioned, peer-to-peer hypermedia transport protocol. Simply put, IPFS attempts to change the way data is stored and transmitted on the internet. Under the traditional HTTP protocol, we obtain network resources primarily by locating servers using domain names and then retrieving data from them. In contrast, the IPFS system locates data using the hash value of the content, and data can be stored across multiple nodes in the network.

[0129] Step S70 specifically includes:

[0130] Step S71: The server concatenates the real-time consultation result and the second certificate of proof into concatenated data, obtains the current timestamp T3, calculates the hash value H4 of the concatenated data and the timestamp T3 using the SM3 algorithm, uses bits 32-70 of the hash value H4 as dynamic key K3, bits 50-186 as dynamic key K4, and bits 164-256 as dynamic key K5, divides the concatenated data into a first data block, a second data block, and a third data block, encrypts the first data block using the dynamic key K3 with the AES algorithm to obtain a first encrypted data block, encrypts the second data block using the dynamic key K4 with the AES algorithm to obtain a second encrypted data block, encrypts the third data block using the dynamic key K5 with the AES algorithm to obtain a third encrypted data block, and encrypts the first encrypted data block, the second encrypted data block, the third encrypted data block, the timestamp T3, and the hash value H4 into a consultation feedback encrypted packet using the session key, and sends the consultation feedback encrypted packet back to the enterprise client in real time via the TLS protocol.

[0131] The enterprise client receives and stores the consultation feedback encrypted package in real time, decrypts and verifies the consultation feedback encrypted package to obtain the real-time consultation result and the second evidence certificate, and displays the real-time consultation result and the second evidence certificate in real time through the consultation interface.

[0132] Step S72: The server monitors the number of consultation logs in real time. When the number of logs reaches a preset threshold, an incremental dataset is constructed based on each consultation log. During the idle period of the certification consultation decision model, the deployed certification consultation decision model is trained using the incremental dataset, and the performance of the trained certification consultation decision model is verified, followed by iterative optimization.

[0133] A preferred embodiment of the blockchain-enabled high-efficiency authentication and consultation system of the present invention includes the following modules:

[0134] An initialization module is used to obtain a large amount of historical certification consultation data and historical certification standard files from the server, preprocess the historical certification consultation data and historical certification standard files, annotate the preprocessed historical certification consultation data to construct a consultation dataset, and construct a decision knowledge graph based on the preprocessed historical certification standard files.

[0135] The model training and graph update module is used by the server to create an authentication consultation decision model that calls the decision knowledge graph to provide authentication consultation services. After performing sample expansion operations on the consultation dataset, it is divided into a training set, a validation set, and a test set. The authentication consultation decision model is trained, validated, and tested sequentially through the training set, validation set, and test set. The authentication consultation decision model that passes the test is deployed to the TEE environment, and a monitoring agent is created to dynamically update the decision knowledge graph.

[0136] A TEE (Trusted Execution Environment) is a secure execution environment that runs in parallel with the device's operating system. Only authorized and reliable applications (trusted applications) can run in this environment. It uses hardware and software security resources to protect the applications and data executed in the TEE.

[0137] The session key negotiation module is used for bidirectional authentication between the enterprise client and the server and to negotiate a shared key. Based on the shared key, a session key is derived, and the consistency of the session key derived by the enterprise client and the server is verified. The server records an authentication log, encrypts the authentication log into an authentication ciphertext log and stores it, calculates the first log fingerprint of the authentication ciphertext log and uploads it to the blockchain, and obtains and stores the first evidence certificate fed back by the blockchain for subsequent authentication tracing.

[0138] The authentication consultation request sending module is used by the enterprise client to obtain the input authentication consultation content, encrypt the authentication consultation content into consultation ciphertext using the session key, record the request time, generate an authentication consultation request based on the consultation ciphertext and the request time, and send the authentication consultation request to the server via the TLS protocol.

[0139] The model reasoning module is used by the server to verify and parse the received certification consultation request to obtain certification consultation content, to de-identify the certification consultation content through the k-anonymization algorithm to obtain de-identified consultation content, to input the de-identified consultation content into the deployed certification consultation decision model for reasoning, to obtain real-time consultation results including compliance suggestion reports and certification execution path diagrams, and to delete the plaintext certification consultation content.

[0140] The consultation log management module is used to record consultation logs in real time on the server, encrypt the consultation logs into ciphertext logs and store them, calculate the second log fingerprint of the ciphertext logs and upload it to the blockchain, obtain and store the second evidence certificate fed back by the blockchain for subsequent consultation tracing.

[0141] The result feedback and model iteration module is used by the server to encrypt the real-time consultation results and the second evidence certificate into a consultation feedback encrypted package using the session key, and to feed the consultation feedback encrypted package back to the enterprise client in real time via the TLS protocol, and to iteratively optimize the deployed authentication consultation decision model based on the consultation log.

[0142] The initialization module is specifically used for:

[0143] The server acquires a large amount of historical certification consultation data and historical certification standard documents; the historical certification consultation data includes at least certification consultation content, compliance recommendation reports, and certification execution path diagrams; the certification consultation content includes at least consultation requests and current enterprise data; the historical certification standard documents include at least core standard documents, supporting documents, certification process documents, certification body documents, and certification standard interpretation documents.

[0144] The enterprise's current status data should include at least the following: a) Basic enterprise information: the enterprise's size, industry sector, business scope, organizational structure, etc. This information helps to understand the overall situation of the enterprise and tailor a management system accordingly. b) Existing management system documents: the enterprise's existing management systems, process documents, operating procedures, etc., used to identify gaps with the target certification standards and provide a basis for system establishment and improvement. c) Current status of management processes: the enterprise's actual management processes, including business connections, information transmission, and decision-making mechanisms between departments, used to identify problems and weaknesses in the processes, and to propose optimization suggestions to make the management system smoother and more efficient. d) Personnel capabilities and responsibilities: the professional skills, work experience, and level of understanding and knowledge of the management system among the enterprise's internal personnel, while clearly defining the allocation of responsibilities for each department and position, so as to reasonably arrange personnel and ensure that all responsibilities are effectively implemented when establishing and operating the management system.

[0145] The core standard document includes at least the standard text and interpretations of the standard clauses. The standard text is the core part of the certification standard, which specifies in detail the specific requirements that enterprises or organizations need to meet, such as ISO 9001 quality management system standard, ISO 14001 environmental management system standard, and ISO 45001 occupational health and safety management system standard. The interpretations of the standard clauses are to help enterprises better understand and apply the standard clauses, and usually include the background, purpose, detailed explanation of the specific requirements, and how to implement these requirements in practice.

[0146] The supporting documents include at least application guidelines, industry-specific requirements, and technical specifications. The application guidelines provide guidance for the specific application of the standard, helping companies better implement the standard in different industries or specific situations. For example, the application guidelines for ISO 9001 may provide specific implementation suggestions for different industries such as manufacturing and services. The industry-specific requirements supplement or refine general standards for specific industries. For example, the automotive industry has the IATF 16949 standard, which is a more detailed quality management system standard for the automotive industry based on ISO 9001. The technical specifications provide technical details and specifications related to the standard, ensuring that companies can meet the technical requirements during implementation. For example, environmental management system standards may involve emission standards for specific pollutants, environmental monitoring technical specifications, etc.

[0147] The certification process documents include at least a certification application guide, audit process documents, and a certification certificate sample. The certification application guide details how companies can apply for certification, including application requirements, required documents and materials, and the application process, helping companies understand the entry requirements and initial steps. The audit process documents include an audit plan, audit checklist, and audit report template. These documents standardize the certification audit process, ensuring the fairness, objectivity, and consistency of the audit. The audit plan clarifies the audit timeline, scope, and focus. The audit checklist lists the specific clauses and contents to be checked during the audit. The audit report template specifies the format and content requirements for the audit report. The certification certificate sample demonstrates the style and content of the certification certificate, including the company name, certification scope, certificate number, issuing authority, and validity period, helping companies correctly use and display the certification certificate after obtaining it.

[0148] The certification body documents include at least the certification body rules and procedures, and certification body qualification certificates. The certification body rules and procedures are the certification body's own operating rules and procedures, including the certification body's qualification requirements, certification process, auditor qualification management, certification decision-making procedures, appeal and complaint handling mechanisms, etc., to ensure that the certification body's operation complies with regulations. The certification body qualification certificates are the certification body's qualification certificates, accreditation certificates, and other documents, proving that it has the legal qualifications and capabilities to carry out specific certification business.

[0149] The certification standard interpretation documents include at least a standard clarification document and a frequently asked questions (FAQs). The standard clarification document is used to further explain and clarify controversial or easily misunderstood clauses to ensure the correct understanding and application of the standard. The frequently asked questions are answers to questions that enterprises often encounter during the implementation of certification standards, providing a way to quickly resolve problems and improve the efficiency and accuracy of certification implementation.

[0150] The historical certified consultation data shall undergo preprocessing including at least data cleaning, data formatting, data classification, and tagging; the data cleaning shall at least include removing duplicate data, handling missing values, and correcting erroneous data; the data formatting shall at least include unifying text format and standardizing data structure; the data classification and tagging shall at least include consultation type classification and adding tags.

[0151] The process of removing duplicate data involves checking for duplicate records in certification consultation content, compliance recommendation reports, and certification execution path diagrams. For example, the same consultation case might be recorded repeatedly due to data entry errors or multiple backups. Duplicates can be identified and deleted by comparing key data fields. Handling missing values ​​involves taking corresponding measures when certain key information in the consultation request (such as the specific type of consultation issue) or enterprise status data (such as some financial indicators) is missing. If the missing data significantly impacts the analysis and cannot be completed, the data entry can be deleted. If the missing information is minor, interpolation or filling with default values ​​can be used. Correcting erroneous data involves checking for errors in the data, such as incorrect consultation date formats or numerical errors in enterprise status data (such as incorrect sales unit). Standardizing text format involves standardizing the font, font size, and other formats for text data such as certification consultation content and compliance recommendation reports. Simultaneously, the text is segmented to ensure a clear structure. The standardized data structure standardizes the data structure of the certification execution path diagram. If the certification execution path diagram is stored in image form, it can be converted into a graphical data structure, such as nodes and edges. Each node represents a certification stage, and the edges represent the transformation relationship between stages. Corresponding attributes are added to each node and edge. The consultation type classification divides historical certification consultation data into different consultation categories based on the content of the consultation request. For example, it can be divided into quality management system certification consultation, environmental management system certification consultation, etc. Adding tags involves adding tags to the data, such as consultation result tags (certification successful, certification failed, not certified, etc.) and compliance recommendation severity tags (high risk, medium risk, low risk), etc.

[0152] The historical authentication standard documents are preprocessed in at least the following ways: document organization and classification, text content extraction and cleaning, and key information annotation and association. The document organization and classification includes at least physical organization and index creation. The text content extraction and cleaning includes at least text extraction and text format cleaning. The key information annotation and association includes at least annotation of key information and establishment of document associations.

[0153] The physical organization involves classifying and storing core standard documents, supporting documents, certification process documents, certification body documents, and certification standard interpretation documents separately. In practice, this can be done by file type (e.g., Word document, PDF document) or subject (e.g., quality certification, environmental certification). Indexing involves creating an index for each file, including file name, file type, file category, and file version, facilitating quick file retrieval and management. Text extraction involves using PDF parsing tools to extract text content from PDF files and directly reading text from Word documents. During extraction, the integrity of the text must be ensured to avoid garbled characters. Text formatting removal involves removing redundant formatting elements such as headers, footers, and page numbers. Tables in the text can be converted to structured data formats such as CSV files. Marking key information involves marking key clauses and keywords in core standard documents, certification standard interpretation documents, etc. For example, in quality management system certification standard documents, key concepts such as "quality policy" and "quality objectives" are marked. Establishing file associations involves analyzing the relationships between files, such as the reference relationship between core standard documents and supporting documents, and the matching relationship between certification process documents and certification body documents.

[0154] In the preprocessed historical certification consultation data, the certification consultation content, compliance suggestion report, and certification execution path diagram are associated and labeled with consultation result tags. Based on the labeled historical certification consultation data, a consultation dataset is constructed. The enterprise information carried by the enterprise status data in the consultation dataset is anonymized and desensitized using the k-anonymization algorithm. The consultation result tags are certification successful, certification failed, or not certified.

[0155] Entities are extracted from the pre-processed historical certification standard documents using a pre-trained BiLSTM-CRF model. Relationships between these entities are inferred using the TransE algorithm. A decision knowledge graph is then constructed based on these entities and their relationships. The entities include at least standard-related entities, supporting document entities, certification process document entities, certification body document entities, and enterprise-related entities. The relationships include at least standard-related relationships, supporting document relationships, certification process document relationships, certification body document relationships, enterprise-standard relationships, and internal enterprise relationships.

[0156] The LSTM (Long Short-Term Memory) network in the BiLSTM-CRF model is a special type of recurrent neural network (RNN). By introducing input gates, forget gates, and output gates, it solves the gradient vanishing or exploding problems that traditional RNNs often encounter when processing long sequences of data, and can better capture long-term dependencies in the sequence. BILSTM (Bidirectional Long Short-Term Memory) is an improvement on LSTM, containing two LSTM layers: a forward LSTM layer that processes data sequentially from the beginning to the end of the sequence, and a backward LSTM layer that processes data sequentially from the end to the beginning of the sequence. This allows for the simultaneous acquisition of information from both directions in the sequence. This bidirectional information is crucial for many natural language processing tasks, such as named entity recognition. In sequence labeling tasks, whether a word is part of an entity depends not only on the words preceding it but also on the words following it. CRF (Conditional Random Field) is a discriminative model used to model a given observation sequence labeled with another entity. In sequence labeling tasks, there are often certain relationships between the labels of a labeled sequence. For example, in named entity recognition tasks, the start label of an entity (such as "B-PER" indicating the beginning of a person's name) is usually followed by an intermediate label (such as "I-PER") or an end label (such as "E-PER"), and it will not jump directly to other types of labels. CRF can model this transition relationship between labels very well. It calculates the probability of a certain labeled sequence under a given observation sequence by defining a conditional probability distribution, so as to maximize the probability that the labeled sequence conforms to the labeling rules.

[0157] TransE (Translating Embedding) is an algorithm for embedding knowledge graphs. The TransE algorithm maps entities and relations to a vector space, so that pairs of entities that satisfy the relations satisfy certain geometric relationships in the vector space. This allows the TransE algorithm to be used to predict missing triples in a knowledge graph, that is, to infer the relationships between entities.

[0158] The model training and graph update module specifically includes:

[0159] The certification consultation decision model creation unit is used by the server to create an certification consultation decision model based on the input parsing layer, knowledge graph retrieval layer, feature fusion layer, decision generation layer and output transformation layer, and to set the loss function of the certification consultation decision model.

[0160] The input parsing layer is constructed based on a bidirectional LSTM module, an enterprise status encoding module, and a vector concatenation module. The bidirectional LSTM module is used to extract text feature vectors from consultation requests; the enterprise status encoding module is used to extract numerical feature vectors from enterprise status data through a fully connected layer (with ReLU activation); and the vector concatenation module is used to concatenate the text feature vectors and numerical feature vectors into a preliminary feature vector.

[0161] The input parsing layer is used to parse and standardize the input authentication consultation content, encoding the consultation request into a text feature vector and the enterprise status data into a structured numerical feature vector for easier subsequent processing. In specific implementation, an adaptive length mechanism is adopted to handle variable-length consultation requests and missing enterprise data; dropout regularization is used to reduce the risk of overfitting and ensure robustness across various enterprise sizes.

[0162] The knowledge graph retrieval layer is constructed based on a graph embedding module and a graph attention retrieval module; the graph embedding module is used to encode the decision knowledge graph into node embeddings through a graph convolutional network (GCN); the graph attention retrieval module is used to retrieve enhanced feature vectors related to the initial feature vectors from each of the node embeddings through a multi-head attention mechanism.

[0163] The knowledge graph retrieval layer dynamically accesses the decision knowledge graph, retrieves contextual features related to the input (preliminary feature vector), such as compliance standards and industry best practices, and outputs enhanced feature vectors (knowledge-driven features). These enhanced feature vectors include entity embeddings and relation weights. In practice, a caching mechanism can be used to improve retrieval efficiency; and an error-tolerant module can be added to handle noise or missing data in the decision knowledge graph, ensuring decision reliability.

[0164] The feature fusion layer is constructed based on a feature concatenation module and a self-attention fusion module. The feature concatenation module is used to concatenate the initial feature vector and the enhanced feature vector into a unified feature vector. The self-attention fusion module is used to perform weighted fusion of key features in the unified feature vector through a transformer-based self-attention mechanism to obtain fused features.

[0165] The feature fusion layer is used to unify features from different sources (preliminary feature vectors and enhanced feature vectors), capture the dependencies between features (such as the correlation between the current state of the enterprise and the consulting needs), and output high-dimensional fused features to support subsequent decision-making. In specific implementation, a gating mechanism (such as GRU units) is introduced to prioritize the fusion of enhanced feature vectors from the decision knowledge graph to emphasize compliance knowledge; feature normalization is added to balance the scale differences between textual and numerical features and improve decision robustness.

[0166] The decision generation layer is constructed based on a suggestion generation module and a path graph generation module. The suggestion generation module is used to infer compliance suggestion reports by using a seq2seq model (encoder-decoder structure, mainly LSTM) to the fused features. The path graph generation module is used to decode the fused features by a first graph neural network (GNN) to obtain an authentication execution path graph.

[0167] The decision generation layer generates structured output based on fusion features; the suggestion generation module outputs a text sequence report (compliance suggestion report), and the path graph generation module outputs a directed graph (certification execution path graph). In specific implementation, the suggestion generation module integrates rule constraint decoding to ensure that the compliance suggestion report conforms to industry standards; the path graph generation module adds a dynamic path optimization sublayer (based on a reinforcement learning reward mechanism) to generate the shortest or lowest-risk execution path, adapting to the diversity of enterprises.

[0168] The output conversion layer is built upon a text formatting module and a graph rendering module; the text formatting module is used to convert compliance recommendation reports into formal report formats through a softmax layer and a template engine; the graph rendering module is used to convert the certification execution path graph into a visual graph representation through a tree decoder.

[0169] The output conversion layer is used for formatting compliance recommendation reports and certification execution path diagrams, generating the final consultation results.

[0170] The formula for the loss function is:

[0171] L total =α·L report +β·L path +γ·L reg ;

[0172] Among them, L total L represents the loss value of the loss function; report The sequence loss for compliance recommendation reports is represented by cross-entropy loss, which is suitable for text generation tasks; L path The graph structure loss representing the authentication execution path graph is represented by the graph edit distance loss, which measures the deviation between the generated path and the ideal path; L reg α represents the regularization term, including L2 regularization (weight decay) and dropout noise regularization; α, β, and γ all represent weight coefficients;

[0173] The certification consultation decision model training unit is used by the server to perform sample expansion operations on the consultation dataset based on the consultation category, and then divide the consultation dataset into a training set, a validation set, and a test set in a ratio of 7:2:1. The certification consultation decision model is trained using the training set and a loss function. During the training process, the hyperparameters of the certification consultation decision model are continuously optimized, including at least the learning rate, learning warm-up rate, learning decay rate, random dropout rate, batch size, and number of hidden layers, until the loss value of the loss function is less than a preset loss threshold, or a preset early stopping condition is reached (e.g., the training time or number of iterations reaches the upper limit, or the model parameters change too little).

[0174] The training set is used to calculate the accuracy of consultation results, inference latency, completeness of compliance recommendation report content, completeness of certification execution path rendering, and retrieval relevance of decision knowledge graph to validate the trained certification consultation decision model. If the validation fails, the training set is expanded and training continues; if the validation passes, then:

[0175] The test set is used to calculate task completion efficiency, actual path deviation rate, noise tolerance, resource consumption, and maximum processing request rate to test the verified certification consultation decision model. If the test fails, the training set is expanded and training continues; if the test passes, training ends and the verified certification consultation decision model is deployed to the TEE environment.

[0176] The decision knowledge graph update unit is used by the server to create a monitoring agent, set the monitoring parameters of the monitoring agent, monitor the latest authentication standard files through the monitoring agent, preprocess the monitored latest authentication standard files, and then integrate the latest authentication standard files into the decision knowledge graph through a second graph neural network (updating or adding entities and relationships in the decision knowledge graph) to dynamically update the decision knowledge graph; the monitoring parameters include at least the monitoring period, monitoring source, and access permissions;

[0177] The server dynamically caches the decision knowledge graph based on the retrieval records.

[0178] The session key negotiation module specifically includes:

[0179] The authentication unit is used for bidirectional authentication between the enterprise client and the server and to negotiate a shared key. Each session key is derived based on the shared key. The enterprise client calculates the first key fingerprint of the session key using the SHA3-256 algorithm and sends it to the server. The server calculates the second key fingerprint of the session key using the SHA3-256 algorithm and sends it to the enterprise client. The enterprise client and the server verify the consistency of the session key using the first key fingerprint and the second key fingerprint.

[0180] The authentication log management unit is used by the server to record authentication logs in real time. After authentication, it obtains the current timestamp T1, calculates the hash value H1 of the authentication log and timestamp T1 using the BLAKE2 algorithm, selects the first 64 bits of the hash value H1 as the dynamic key K1, calls the dynamic key K1 using the ChaCha20 algorithm to encrypt the authentication log into first-level encrypted data, encrypts the first-level encrypted data, timestamp T1 and hash value H1 into authentication ciphertext log using the AES256 algorithm, stores the authentication ciphertext log in the IPFS system, calculates the first log fingerprint of the authentication ciphertext log using the SHA3-256 algorithm and uploads it to the blockchain, obtains and stores the first evidence certificate fed back by the blockchain, which carries at least the evidence number, evidence time, evidence subject information, data information, blockchain information and signature information, for subsequent authentication and traceability.

[0181] The authentication unit specifically includes:

[0182] The certificate initialization subunit is used by the enterprise client to preset a certificate Cert_C carrying a long-term public key PublicKey_C, a long-term private key PrivateKey_C matching the long-term public key PublicKey_C, and a CA root certificate through the CA center.

[0183] The server pre-sets a certificate Cert_S carrying a long-term public key PublicKey_S, a long-term private key PrivateKey_S matching the long-term public key PublicKey_S, and a CA root certificate through the CA center.

[0184] The CA root certificate is used to verify the validity of certificates Cert_C and Cert_S;

[0185] The first authentication request sending subunit is used by the enterprise client to generate a random number Nonce_C, generate a first authentication request based on the list of cipher suites supported by the local machine and the random number Nonce_C, and send it to the server.

[0186] The second authentication request sending subunit is used by the server to parse the received first authentication request to obtain a list of cipher suites and a random number Nonce_C, select a cipher suite from the list of cipher suites, generate a random number Nonce_S, create a pair of temporary public keys EphemeralPublicKey_S and temporary private keys EphemeralPrivateKey_S based on the ECDHE algorithm in the cipher suite, and sign the random number Nonce_C, the random number Nonce_S, and the temporary public key EphemeralPublicKey_S with the long-term private key PrivateKey_S to obtain the server signature Sig_S;

[0187] The server generates a second authentication request based on the cipher suite, the random number Nonce_S, the certificate Cert_S, the temporary public key EphemeralPublicKey_S, and the server signature Sig_S, and sends it to the enterprise client.

[0188] The third authentication request sending subunit is used by the enterprise client to parse the received second authentication request to obtain the cipher suite, random number Nonce_S, certificate Cert_S, temporary public key EphemeralPublicKey_S, and server signature Sig_S;

[0189] The enterprise client verifies the certificate Cert_S using the CA root certificate, and verifies the server signature Sig_S using the long-term public key PublicKey_S carried by the certificate Cert_S. Upon successful verification:

[0190] The enterprise client creates a pair of temporary public keys EphemeralPublicKey_C and temporary private keys EphemeralPrivateKey_C based on the ECDHE algorithm in the cryptographic suite. The client then uses the long-term private key PrivateKey_C to sign the random number Nonce_C, the random number Nonce_S, and the temporary public key EphemeralPublicKey_C to obtain the client signature Sig_C.

[0191] The enterprise client generates a third authentication request based on the certificate Cert_C, the temporary public key EphemeralPublicKey_C, and the client signature Sig_C, and sends it to the server.

[0192] The verification result sending subunit is used by the server to parse the received third authentication request to obtain the certificate Cert_C, the temporary public key EphemeralPublicKey_C, and the client signature Sig_C;

[0193] The server verifies the certificate Cert_C using the CA root certificate, verifies the client signature Sig_C using the public key PublicKey_C carried by the certificate Cert_C, and sends a verification result to the enterprise client indicating whether the verification was successful or failed.

[0194] The session key derivation subunit is used to terminate the process when the verification result is a verification failure; when the verification result is a verification success, the enterprise client uses the ECDHE algorithm to call the temporary private key EphemeralPrivateKey_C and the temporary public key EphemeralPublicKey_S to calculate the shared key SharedSecret_C; the server uses the ECDHE algorithm to call the temporary private key EphemeralPrivateKey_S and the temporary public key EphemeralPublicKey_C to calculate the shared key SharedSecret_S, where the shared key SharedSecret_C and the shared key SharedSecret_S are the same key;

[0195] The ECDHE algorithm is a key negotiation algorithm based on elliptic curve cryptography. It allows two communicating parties to negotiate a shared key over an insecure channel without sharing any secret information beforehand. Its core idea is to leverage the one-way nature of dot product operations on elliptic curves, ensuring that even if an attacker intercepts the public keys of both parties, they cannot compute the shared key.

[0196] The enterprise client derives a session key from the shared key SharedSecret_C, the random number Nonce_C, and the random number Nonce_S using KDF functions; the server derives a session key from the shared key SharedSecret_S, the random number Nonce_C, and the random number Nonce_S using KDF functions.

[0197] The consistency verification subunit is used by the enterprise client to calculate the first key fingerprint of the session key using the SHA3-256 algorithm and send it to the server, and the server to calculate the second key fingerprint of the session key using the SHA3-256 algorithm and send it to the enterprise client. The enterprise client and the server verify the consistency of the session key using the first key fingerprint and the second key fingerprint.

[0198] The authentication inquiry request sending module is specifically used for:

[0199] The enterprise client obtains the input authentication consultation content, uses the IDEA algorithm to call the session key to encrypt the authentication consultation content into consultation ciphertext, records the request time, calculates the hash value H2 of the consultation ciphertext and the request time using the BLAKE2 algorithm, encrypts the consultation ciphertext, the request time and the hash value H2 into an encrypted string using the RC6 algorithm, generates an authentication consultation request based on the encrypted string, and sends the authentication consultation request to the server via the TLS protocol.

[0200] The model inference module is specifically used for:

[0201] The server receives the authentication consultation request in real time, parses the request to obtain an encrypted string, decrypts the encrypted string using the RC6 algorithm to obtain the consultation ciphertext, request time, and hash value H2, performs integrity verification on the consultation ciphertext and request time using the hash value H2, performs timeliness verification using the request time, and then uses the IDEA algorithm to call the session key to decrypt the consultation ciphertext to obtain the authentication consultation content. The rule engine calls preset data detection rules to verify the data completeness of the authentication consultation content, that is, to determine whether the enterprise status data corresponding to the consultation request is missing. If the content is missing, feedback is given to the enterprise client to avoid invalid reasoning.

[0202] The server uses the k-anonymization algorithm to de-identify the certification consultation content to obtain de-identified consultation content. The de-identified consultation content is then input into the deployed certification consultation decision model. The certification consultation decision model performs inference based on hardware acceleration technology to obtain real-time consultation results, including compliance recommendation reports and certification execution path diagrams, and simultaneously deletes the plaintext certification consultation content.

[0203] The consultation log management module is specifically used for:

[0204] The server records in real time a consultation log that includes at least authentication consultation requests, real-time consultation results, client information, and authentication feedback, wherein the authentication feedback is authentication success, authentication failure, or no authentication.

[0205] The server obtains the current timestamp T2, calculates the hash value H3 of the consultation log and timestamp T2 using the SM3 algorithm, selects 32 bits starting from the 9th bit of the hash value H3 as the dynamic key K2, calls the dynamic key K2 using the ChaCha20 algorithm to encrypt the consultation log into a layer of encrypted data, encrypts the layer of encrypted data, timestamp T2 and hash value H3 into a ciphertext consultation log using the 3DES algorithm, stores the ciphertext consultation log in the IPFS system, calculates the second log fingerprint of the ciphertext consultation log using the SHA3-256 algorithm and uploads it to the blockchain, obtains and stores the second evidence certificate fed back by the blockchain, which carries at least the evidence number, evidence time, evidence subject information, data information, blockchain information and signature information, for subsequent consultation tracing;

[0206] IPFS (InterPlanetary File System) is a peer-to-peer distributed file system designed to create a content-addressable, versioned, peer-to-peer hypermedia transport protocol. Simply put, IPFS attempts to change the way data is stored and transmitted on the internet. Under the traditional HTTP protocol, we obtain network resources primarily by locating servers using domain names and then retrieving data from them. In contrast, the IPFS system locates data using the hash value of the content, and data can be stored across multiple nodes in the network.

[0207] The result feedback and model iteration module specifically includes:

[0208] The reasoning result feedback unit is used by the server to concatenate the real-time consultation result and the second evidence certificate into concatenated data, obtain the current timestamp T3, calculate the hash value H4 of the concatenated data and the timestamp T3 using the SM3 algorithm, use the 32-70 bits of the hash value H4 as the dynamic key K3, the 50-186 bits as the dynamic key K4, and the 164-256 bits as the dynamic key K5, divide the concatenated data into a first data block, a second data block, and a third data block, encrypt the first data block using the dynamic key K3 through the AES algorithm to obtain a first encrypted data block, encrypt the second data block using the dynamic key K4 through the AES algorithm to obtain a second encrypted data block, encrypt the third data block using the dynamic key K5 through the AES algorithm to obtain a third encrypted data block, encrypt the first encrypted data block, the second encrypted data block, the third encrypted data block, the timestamp T3, and the hash value H4 into a consultation feedback encrypted packet using the session key, and feed the consultation feedback encrypted packet back to the enterprise client in real time via the TLS protocol;

[0209] The enterprise client receives and stores the consultation feedback encrypted package in real time, decrypts and verifies the consultation feedback encrypted package to obtain the real-time consultation result and the second evidence certificate, and displays the real-time consultation result and the second evidence certificate in real time through the consultation interface.

[0210] The certification consultation decision model optimization unit is used to monitor the number of consultation logs in real time on the server. When the number of logs reaches a preset threshold, an incremental dataset is constructed based on each consultation log. During the idle period of the certification consultation decision model, the deployed certification consultation decision model is trained using the incremental dataset, and the performance of the trained certification consultation decision model is verified, and then iterative optimization is performed.

[0211] While specific embodiments of the present invention have been described above, those skilled in the art should understand that the specific embodiments described are merely illustrative and not intended to limit the scope of the present invention. Equivalent modifications and variations made by those skilled in the art in accordance with the spirit of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A blockchain-enabled, highly efficient authentication and consultation method, characterized in that: Includes the following steps: Step S10: The server obtains historical authentication consultation data and historical authentication standard files, preprocesses each of the historical authentication consultation data and historical authentication standard files, annotates each of the preprocessed historical authentication consultation data and constructs a consultation dataset, and constructs a decision knowledge graph based on each of the preprocessed historical authentication standard files. Step S20: The server creates an authentication consultation decision model that calls the decision knowledge graph to provide authentication consultation services. After performing sample expansion operations on the consultation dataset, it divides it into a training set, a validation set, and a test set. The authentication consultation decision model is trained, validated, and tested sequentially through the training set, validation set, and test set. The authentication consultation decision model that passes the test is deployed to the TEE environment, and a monitoring agent is created to dynamically update the decision knowledge graph. Step S30: The enterprise client and the server perform bidirectional authentication and negotiate a shared key. A session key is derived based on the shared key, and the consistency of the session key derived by the enterprise client and the server is verified. The server records authentication logs, encrypts the authentication logs into ciphertext authentication logs and stores them, calculates the first log fingerprint of the ciphertext authentication logs and uploads it to the blockchain, obtains and stores the first evidence certificate fed back by the blockchain, and uses it for subsequent authentication and traceability. Step S40: The enterprise client obtains the input authentication consultation content, uses the IDEA algorithm to call the session key to encrypt the authentication consultation content into consultation ciphertext, records the request time, calculates the hash value H2 of the consultation ciphertext and the request time using the BLAKE2 algorithm, encrypts the consultation ciphertext, the request time and the hash value H2 into an encrypted string using the RC6 algorithm, generates an authentication consultation request based on the encrypted string, and sends the authentication consultation request to the server via the TLS protocol. Step S50: The server verifies and parses the received authentication consultation request to obtain authentication consultation content. The authentication consultation content is de-identified using the k-anonymization algorithm to obtain de-identified consultation content. The de-identified consultation content is input into the deployed authentication consultation decision model for reasoning to obtain real-time consultation results including compliance suggestion reports and authentication execution path diagrams. The plaintext authentication consultation content is then deleted. Step S60: The server records consultation logs in real time, encrypts the consultation logs into ciphertext logs and stores them, calculates the second log fingerprint of the ciphertext logs and uploads it to the blockchain, obtains and stores the second evidence certificate fed back by the blockchain, and uses it for subsequent consultation tracing. Step S70: The server encrypts the real-time consultation results and the second evidence certificate into a consultation feedback encrypted package using the session key, and sends the consultation feedback encrypted package back to the enterprise client in real time via the TLS protocol. Based on the consultation log, the server iteratively optimizes the deployed authentication consultation decision model.

2. The blockchain-enabled efficient authentication and consultation method as described in claim 1, characterized in that: Step S10 specifically involves: The server acquires historical certification consultation data and historical certification standard documents; the historical certification consultation data includes at least certification consultation content, compliance recommendation reports, and certification execution path diagrams; the certification consultation content includes at least consultation requests and current enterprise data; the historical certification standard documents include at least core standard documents, supporting documents, certification process documents, certification body documents, and certification standard interpretation documents. The historical certified consultation data shall undergo preprocessing including at least data cleaning, data formatting, data classification, and tagging; the data cleaning shall at least include removing duplicate data, handling missing values, and correcting erroneous data; the data formatting shall at least include unifying text format and standardizing data structure; the data classification and tagging shall at least include consultation type classification and adding tags. The historical authentication standard documents are preprocessed in at least the following ways: document organization and classification, text content extraction and cleaning, and key information annotation and association. The document organization and classification includes at least physical organization and index creation. The text content extraction and cleaning includes at least text extraction and text format cleaning. The key information annotation and association includes at least annotation of key information and establishment of document associations. In the preprocessed historical certification consultation data, the certification consultation content, compliance suggestion report and certification execution path diagram are associated and labeled with consultation result tags. Based on the labeled historical certification consultation data, a consultation dataset is constructed. The enterprise information carried by the enterprise status data in the consultation dataset is anonymized and desensitized using the k-anonymization algorithm. The consultation result is tagged as successful authentication, failed authentication, or unauthenticated. Entities are extracted from the pre-processed historical authentication standard files using a pre-trained BiLSTM-CRF model. Relationships between the entities are inferred using the TransE algorithm. A decision knowledge graph is then constructed based on the entities and their relationships.

3. The efficient authentication and consultation method powered by blockchain as described in claim 1, characterized in that: Step S20 specifically includes: Step S21: The server creates an authentication consultation decision model based on the input parsing layer, knowledge graph retrieval layer, feature fusion layer, decision generation layer, and output transformation layer, and sets the loss function of the authentication consultation decision model; The input parsing layer is constructed based on a bidirectional LSTM module, an enterprise status encoding module, and a vector concatenation module. The bidirectional LSTM module is used to extract text feature vectors from consultation requests; the enterprise status encoding module is used to extract numerical feature vectors from enterprise status data through a fully connected layer; and the vector concatenation module is used to concatenate the text feature vectors and numerical feature vectors into a preliminary feature vector. The knowledge graph retrieval layer is constructed based on a graph embedding module and a graph attention retrieval module; the graph embedding module is used to encode the decision knowledge graph into node embeddings through a graph convolutional network; the graph attention retrieval module is used to retrieve enhanced feature vectors related to the initial feature vectors from each of the node embeddings through a multi-head attention mechanism; The feature fusion layer is constructed based on a feature concatenation module and a self-attention fusion module. The feature concatenation module is used to concatenate the initial feature vector and the enhanced feature vector into a unified feature vector. The self-attention fusion module is used to perform weighted fusion of key features in the unified feature vector through a transformer-based self-attention mechanism to obtain fused features. The decision generation layer is constructed based on a suggestion generation module and a path graph generation module; the suggestion generation module is used to infer compliance suggestion reports by using a seq2seq model to analyze the fused features; the path graph generation module is used to decode the fused features by using a first graph neural network to obtain an authentication execution path graph. The output conversion layer is built upon a text formatting module and a graph rendering module; the text formatting module is used to convert compliance recommendation reports into formal report formats through a softmax layer and a template engine; the graph rendering module is used to convert the certification execution path graph into a visual graph representation through a tree decoder. The formula for the loss function is: ; in, This represents the loss value of the loss function; The sequence loss of the compliance recommendation report is represented by cross-entropy loss; The graph structure loss representing the authentication execution path graph is represented by graph edit distance loss; Represents regularization terms, including L2 regularization and dropout noise regularization; All represent weighting coefficients; Step S22: After the server performs sample augmentation on the consultation dataset based on the consultation category, it divides the consultation dataset into a training set, a validation set, and a test set in a ratio of 7:2:

1. The certification consultation decision model is trained using the training set and the loss function. During the training process, the certification consultation decision model is continuously optimized, including at least the hyperparameters such as learning rate, learning warm-up rate, learning decay rate, random dropout rate, batch size, and number of hidden layers, until the loss value of the loss function is less than the preset loss threshold or the preset early stopping condition is met. The training set is used to calculate the accuracy of consultation results, inference latency, completeness of compliance recommendation report content, completeness of certification execution path rendering, and retrieval relevance of decision knowledge graph to validate the trained certification consultation decision model. If the validation fails, the training set is expanded and training continues; if the validation passes, then: The test set is used to calculate task completion efficiency, actual path deviation rate, noise tolerance, resource consumption, and maximum processing request rate to test the verified certification consultation decision model. If the test fails, the training set is expanded and training continues; if the test passes, training ends and the verified certification consultation decision model is deployed to the TEE environment. Step S23: The server creates a monitoring agent, sets the monitoring parameters of the monitoring agent, monitors the latest certification standard file through the monitoring agent, preprocesses the monitored latest certification standard file, and then integrates the latest certification standard file into the decision knowledge graph through a second graph neural network to dynamically update the decision knowledge graph; the monitoring parameters include at least the monitoring period, monitoring source, and access permissions; The server dynamically caches the decision knowledge graph based on the retrieval records.

4. The efficient authentication and consultation method powered by blockchain as described in claim 1, characterized in that: Step S30 specifically includes: Step S31: The enterprise client and the server perform bidirectional authentication and negotiate a shared key. Based on the shared key, they derive session keys. The enterprise client calculates the first key fingerprint of the session key using the SHA3-256 algorithm and sends it to the server. The server calculates the second key fingerprint of the session key using the SHA3-256 algorithm and sends it to the enterprise client. The enterprise client and the server verify the consistency of the session key using the first key fingerprint and the second key fingerprint. Step S32: The server records the authentication log in real time. After authentication, it obtains the current timestamp T1, calculates the hash value H1 of the authentication log and timestamp T1 using the BLAKE2 algorithm, selects the first 64 bits of the hash value H1 as the dynamic key K1, and uses the ChaCha20 algorithm to call the dynamic key K1 to encrypt the authentication log into first-level encrypted data. It then uses the AES256 algorithm to encrypt the first-level encrypted data, timestamp T1, and hash value H1 into an authentication ciphertext log, stores the authentication ciphertext log in the IPFS system, calculates the first log fingerprint of the authentication ciphertext log using the SHA3-256 algorithm, uploads it to the blockchain, and obtains and stores the first evidence certificate fed back by the blockchain, which carries at least the evidence number, evidence time, evidence subject information, data information, blockchain information, and signature information for subsequent authentication and traceability.

5. The blockchain-enabled efficient authentication and consultation method as described in claim 1, characterized in that: Step S50 specifically involves: The server receives the authentication consultation request in real time, parses the authentication consultation request to obtain an encrypted string, decrypts the encrypted string using the RC6 algorithm to obtain the consultation ciphertext, request time, and hash value H2, performs integrity verification on the consultation ciphertext and request time using the hash value H2, performs timeliness verification using the request time, and then uses the IDEA algorithm to call the session key to decrypt the consultation ciphertext to obtain the authentication consultation content. Finally, the server uses the rule engine to call preset data detection rules to verify the data completeness of the authentication consultation content. The server uses the k-anonymization algorithm to de-identify the certification consultation content to obtain de-identified consultation content. The de-identified consultation content is then input into the deployed certification consultation decision model. The certification consultation decision model performs inference based on hardware acceleration technology to obtain real-time consultation results, including compliance recommendation reports and certification execution path diagrams, and simultaneously deletes the plaintext certification consultation content. Step S60 specifically involves: The server records in real time a consultation log that includes at least authentication consultation requests, real-time consultation results, client information, and authentication feedback, wherein the authentication feedback is authentication success, authentication failure, or no authentication. The server obtains the current timestamp T2, calculates the hash value H3 of the consultation log and timestamp T2 using the SM3 algorithm, selects 32 bits starting from the 9th bit of the hash value H3 as the dynamic key K2, calls the dynamic key K2 using the ChaCha20 algorithm to encrypt the consultation log into a layer of encrypted data, encrypts the layer of encrypted data, timestamp T2 and hash value H3 into a ciphertext consultation log using the 3DES algorithm, stores the ciphertext consultation log in the IPFS system, calculates the second log fingerprint of the ciphertext consultation log using the SHA3-256 algorithm and uploads it to the blockchain, obtains and stores the second evidence certificate fed back by the blockchain, which carries at least the evidence number, evidence time, evidence subject information, data information, blockchain information and signature information, for subsequent consultation tracing; Step S70 specifically includes: Step S71: The server concatenates the real-time consultation result and the second certificate of proof into concatenated data, obtains the current timestamp T3, calculates the hash value H4 of the concatenated data and the timestamp T3 using the SM3 algorithm, uses bits 32-70 of the hash value H4 as dynamic key K3, bits 50-186 as dynamic key K4, and bits 164-256 as dynamic key K5, divides the concatenated data into a first data block, a second data block, and a third data block, encrypts the first data block using the dynamic key K3 with the AES algorithm to obtain a first encrypted data block, encrypts the second data block using the dynamic key K4 with the AES algorithm to obtain a second encrypted data block, encrypts the third data block using the dynamic key K5 with the AES algorithm to obtain a third encrypted data block, and encrypts the first encrypted data block, the second encrypted data block, the third encrypted data block, the timestamp T3, and the hash value H4 into a consultation feedback encrypted packet using the session key, and sends the consultation feedback encrypted packet back to the enterprise client in real time via the TLS protocol. The enterprise client receives and stores the consultation feedback encrypted package in real time, decrypts and verifies the consultation feedback encrypted package to obtain the real-time consultation result and the second evidence certificate, and displays the real-time consultation result and the second evidence certificate in real time through the consultation interface. Step S72: The server monitors the number of consultation logs in real time. When the number of logs reaches a preset threshold, an incremental dataset is constructed based on each consultation log. During the idle period of the certification consultation decision model, the deployed certification consultation decision model is trained using the incremental dataset, and the performance of the trained certification consultation decision model is verified, followed by iterative optimization.

6. A blockchain-enabled high-efficiency authentication and consultation system, characterized in that: Includes the following modules: An initialization module is used for the server to obtain historical authentication consultation data and historical authentication standard files, preprocess the historical authentication consultation data and historical authentication standard files, annotate the preprocessed historical authentication consultation data to construct a consultation dataset, and construct a decision knowledge graph based on the preprocessed historical authentication standard files. The model training and graph update module is used by the server to create an authentication consultation decision model that calls the decision knowledge graph to provide authentication consultation services. After performing sample expansion operations on the consultation dataset, it is divided into a training set, a validation set, and a test set. The authentication consultation decision model is trained, validated, and tested sequentially through the training set, validation set, and test set. The authentication consultation decision model that passes the test is deployed to the TEE environment, and a monitoring agent is created to dynamically update the decision knowledge graph. The session key negotiation module is used for bidirectional authentication between the enterprise client and the server and to negotiate a shared key. Based on the shared key, a session key is derived, and the consistency of the session key derived by the enterprise client and the server is verified. The server records authentication logs, encrypts the authentication logs into ciphertext authentication logs and stores them, calculates the first log fingerprint of the ciphertext authentication logs and uploads it to the blockchain, obtains and stores the first evidence certificate fed back by the blockchain, and uses it for subsequent authentication and traceability. The authentication consultation request sending module is used by the enterprise client to obtain the input authentication consultation content, encrypt the authentication consultation content into consultation ciphertext by calling the session key through the IDEA algorithm, record the request time, calculate the hash value H2 of the consultation ciphertext and the request time through the BLAKE2 algorithm, encrypt the consultation ciphertext, the request time and the hash value H2 into an encrypted string through the RC6 algorithm, generate an authentication consultation request based on the encrypted string, and send the authentication consultation request to the server through the TLS protocol. The model reasoning module is used by the server to verify and parse the received certification consultation request to obtain certification consultation content, to de-identify the certification consultation content through the k-anonymization algorithm to obtain de-identified consultation content, to input the de-identified consultation content into the deployed certification consultation decision model for reasoning, to obtain real-time consultation results including compliance suggestion reports and certification execution path diagrams, and to delete the plaintext certification consultation content. The consultation log management module is used to record consultation logs in real time on the server, encrypt the consultation logs into ciphertext logs and store them, calculate the second log fingerprint of the ciphertext logs and upload it to the blockchain, obtain and store the second evidence certificate fed back by the blockchain for subsequent consultation tracing. The result feedback and model iteration module is used by the server to encrypt the real-time consultation results and the second evidence certificate into a consultation feedback encrypted package using the session key, and to feed the consultation feedback encrypted package back to the enterprise client in real time via the TLS protocol, and to iteratively optimize the deployed authentication consultation decision model based on the consultation log.

7. The blockchain-enabled high-efficiency authentication and consultation system as described in claim 6, characterized in that: The initialization module is specifically used for: The server acquires historical certification consultation data and historical certification standard documents; the historical certification consultation data includes at least certification consultation content, compliance recommendation reports, and certification execution path diagrams; the certification consultation content includes at least consultation requests and current enterprise data; the historical certification standard documents include at least core standard documents, supporting documents, certification process documents, certification body documents, and certification standard interpretation documents. The historical certified consultation data shall undergo preprocessing including at least data cleaning, data formatting, data classification, and tagging; the data cleaning shall at least include removing duplicate data, handling missing values, and correcting erroneous data; the data formatting shall at least include unifying text format and standardizing data structure; the data classification and tagging shall at least include consultation type classification and adding tags. The historical authentication standard documents are preprocessed in at least the following ways: document organization and classification, text content extraction and cleaning, and key information annotation and association. The document organization and classification includes at least physical organization and index creation. The text content extraction and cleaning includes at least text extraction and text format cleaning. The key information annotation and association includes at least annotation of key information and establishment of document associations. In the preprocessed historical certification consultation data, the certification consultation content, compliance suggestion report and certification execution path diagram are associated and labeled with consultation result tags. Based on the labeled historical certification consultation data, a consultation dataset is constructed. The enterprise information carried by the enterprise status data in the consultation dataset is anonymized and desensitized using the k-anonymization algorithm. The consultation result is tagged as successful authentication, failed authentication, or unauthenticated. Entities are extracted from the pre-processed historical authentication standard files using a pre-trained BiLSTM-CRF model. Relationships between the entities are inferred using the TransE algorithm. A decision knowledge graph is then constructed based on the entities and their relationships.

8. The blockchain-enabled high-efficiency authentication and consultation system as described in claim 6, characterized in that: The model training and graph update module specifically includes: The certification consultation decision model creation unit is used by the server to create an certification consultation decision model based on the input parsing layer, knowledge graph retrieval layer, feature fusion layer, decision generation layer and output transformation layer, and to set the loss function of the certification consultation decision model. The input parsing layer is constructed based on a bidirectional LSTM module, an enterprise status encoding module, and a vector concatenation module. The bidirectional LSTM module is used to extract text feature vectors from consultation requests; the enterprise status encoding module is used to extract numerical feature vectors from enterprise status data through a fully connected layer; and the vector concatenation module is used to concatenate the text feature vectors and numerical feature vectors into a preliminary feature vector. The knowledge graph retrieval layer is constructed based on a graph embedding module and a graph attention retrieval module; the graph embedding module is used to encode the decision knowledge graph into node embeddings through a graph convolutional network; the graph attention retrieval module is used to retrieve enhanced feature vectors related to the initial feature vectors from each of the node embeddings through a multi-head attention mechanism; The feature fusion layer is constructed based on a feature concatenation module and a self-attention fusion module. The feature concatenation module is used to concatenate the initial feature vector and the enhanced feature vector into a unified feature vector. The self-attention fusion module is used to perform weighted fusion of key features in the unified feature vector through a transformer-based self-attention mechanism to obtain fused features. The decision generation layer is constructed based on a suggestion generation module and a path graph generation module; the suggestion generation module is used to infer compliance suggestion reports by using a seq2seq model to analyze the fused features; the path graph generation module is used to decode the fused features by using a first graph neural network to obtain an authentication execution path graph. The output conversion layer is built upon a text formatting module and a graph rendering module; the text formatting module is used to convert compliance recommendation reports into formal report formats through a softmax layer and a template engine; the graph rendering module is used to convert the certification execution path graph into a visual graph representation through a tree decoder. The formula for the loss function is: ; in, This represents the loss value of the loss function; The sequence loss of the compliance recommendation report is represented by cross-entropy loss; The graph structure loss representing the authentication execution path graph is represented by graph edit distance loss; Represents regularization terms, including L2 regularization and dropout noise regularization; All represent weighting coefficients; The certification consultation decision model training unit is used to divide the consultation dataset into a training set, a validation set, and a test set in a 7:2:1 ratio after the server performs sample expansion operations on the consultation dataset based on the consultation category. The training set and loss function are used to train the certification consultation decision model. During the training process, the certification consultation decision model is continuously optimized, including at least the hyperparameters such as learning rate, learning warm-up rate, learning decay rate, random dropout rate, batch size, and number of hidden layers, until the loss value of the loss function is less than a preset loss threshold or a preset early stopping condition is met. The training set is used to calculate the accuracy of consultation results, inference latency, completeness of compliance recommendation report content, completeness of certification execution path rendering, and retrieval relevance of decision knowledge graph to validate the trained certification consultation decision model. If the validation fails, the training set is expanded and training continues; if the validation passes, then: The test set is used to calculate task completion efficiency, actual path deviation rate, noise tolerance, resource consumption, and maximum processing request rate to test the verified certification consultation decision model. If the test fails, the training set is expanded and training continues; if the test passes, training ends and the verified certification consultation decision model is deployed to the TEE environment. The decision knowledge graph update unit is used by the server to create a monitoring agent, set the monitoring parameters of the monitoring agent, monitor the latest certification standard file through the monitoring agent, preprocess the latest certification standard file, and then integrate the latest certification standard file into the decision knowledge graph through a second graph neural network to dynamically update the decision knowledge graph; the monitoring parameters include at least the monitoring period, monitoring source, and access permissions; The server dynamically caches the decision knowledge graph based on the retrieval records.

9. The blockchain-enabled high-efficiency authentication and consultation system as described in claim 6, characterized in that: The session key negotiation module specifically includes: The authentication unit is used for bidirectional authentication between the enterprise client and the server and to negotiate a shared key. Each session key is derived based on the shared key. The enterprise client calculates the first key fingerprint of the session key using the SHA3-256 algorithm and sends it to the server. The server calculates the second key fingerprint of the session key using the SHA3-256 algorithm and sends it to the enterprise client. The enterprise client and the server verify the consistency of the session key using the first key fingerprint and the second key fingerprint. The authentication log management unit is used by the server to record authentication logs in real time. After authentication, it obtains the current timestamp T1, calculates the hash value H1 of the authentication log and timestamp T1 using the BLAKE2 algorithm, selects the first 64 bits of the hash value H1 as the dynamic key K1, calls the dynamic key K1 using the ChaCha20 algorithm to encrypt the authentication log into first-level encrypted data, encrypts the first-level encrypted data, timestamp T1, and hash value H1 into authentication ciphertext log using the AES256 algorithm, stores the authentication ciphertext log in the IPFS system, calculates the first log fingerprint of the authentication ciphertext log using the SHA3-256 algorithm and uploads it to the blockchain, obtains and stores the first evidence certificate fed back by the blockchain, which carries at least the evidence number, evidence time, evidence subject information, data information, blockchain information, and signature information, for subsequent authentication and traceability.

10. The blockchain-enabled high-efficiency authentication and consultation system as described in claim 6, characterized in that: The model inference module is specifically used for: The server receives the authentication consultation request in real time, parses the authentication consultation request to obtain an encrypted string, decrypts the encrypted string using the RC6 algorithm to obtain the consultation ciphertext, request time, and hash value H2, performs integrity verification on the consultation ciphertext and request time using the hash value H2, performs timeliness verification using the request time, and then uses the IDEA algorithm to call the session key to decrypt the consultation ciphertext to obtain the authentication consultation content. Finally, the server uses the rule engine to call preset data detection rules to verify the data completeness of the authentication consultation content. The server uses the k-anonymization algorithm to de-identify the certification consultation content to obtain de-identified consultation content. The de-identified consultation content is then input into the deployed certification consultation decision model. The certification consultation decision model performs inference based on hardware acceleration technology to obtain real-time consultation results, including compliance recommendation reports and certification execution path diagrams, and simultaneously deletes the plaintext certification consultation content. The consultation log management module is specifically used for: The server records in real time a consultation log that includes at least authentication consultation requests, real-time consultation results, client information, and authentication feedback, wherein the authentication feedback is authentication success, authentication failure, or no authentication. The server obtains the current timestamp T2, calculates the hash value H3 of the consultation log and timestamp T2 using the SM3 algorithm, selects 32 bits starting from the 9th bit of the hash value H3 as the dynamic key K2, calls the dynamic key K2 using the ChaCha20 algorithm to encrypt the consultation log into a layer of encrypted data, encrypts the layer of encrypted data, timestamp T2 and hash value H3 into a ciphertext consultation log using the 3DES algorithm, stores the ciphertext consultation log in the IPFS system, calculates the second log fingerprint of the ciphertext consultation log using the SHA3-256 algorithm and uploads it to the blockchain, obtains and stores the second evidence certificate fed back by the blockchain, which carries at least the evidence number, evidence time, evidence subject information, data information, blockchain information and signature information, for subsequent consultation tracing; The result feedback and model iteration module specifically includes: The reasoning result feedback unit is used by the server to concatenate the real-time consultation result and the second evidence certificate into concatenated data, obtain the current timestamp T3, calculate the hash value H4 of the concatenated data and the timestamp T3 using the SM3 algorithm, use the 32-70 bits of the hash value H4 as the dynamic key K3, the 50-186 bits as the dynamic key K4, and the 164-256 bits as the dynamic key K5, divide the concatenated data into a first data block, a second data block, and a third data block, encrypt the first data block using the dynamic key K3 through the AES algorithm to obtain a first encrypted data block, encrypt the second data block using the dynamic key K4 through the AES algorithm to obtain a second encrypted data block, encrypt the third data block using the dynamic key K5 through the AES algorithm to obtain a third encrypted data block, encrypt the first encrypted data block, the second encrypted data block, the third encrypted data block, the timestamp T3, and the hash value H4 into a consultation feedback encrypted packet using the session key, and feed the consultation feedback encrypted packet back to the enterprise client in real time via the TLS protocol; The enterprise client receives and stores the consultation feedback encrypted package in real time, decrypts and verifies the consultation feedback encrypted package to obtain the real-time consultation result and the second evidence certificate, and displays the real-time consultation result and the second evidence certificate in real time through the consultation interface. The certification consultation decision model optimization unit is used to monitor the number of consultation logs in real time on the server. When the number of logs reaches a preset threshold, an incremental dataset is constructed based on each consultation log. During the idle period of the certification consultation decision model, the deployed certification consultation decision model is trained using the incremental dataset, and the performance of the trained certification consultation decision model is verified, and then iterative optimization is performed.

Images