Digital bond risk assessment method and system based on block chain and privacy calculation, electronic equipment and storage medium

Abstract

The invention discloses a digital bond risk assessment method and system based on a block chain and privacy calculation, electronic equipment and a storage medium, and the method achieves the innovation of digital bond risk assessment, and has the core effect of enhancing the data security and privacy protection in the assessment process. And meanwhile, the integrity and non-tampering property of the data are ensured. According to the method, the homomorphic encryption technology is utilized, the encryption state of the data in the processing process can be ensured even if calculation is carried out at the cloud, and data leakage and unauthorized access are effectively prevented. Besides, the evaluation system provided by the invention greatly improves the transparency and credibility of evaluation, so that investors can more accurately grasp the risk condition of the digital bond, thereby promoting the healthy development of the digital financial market and the efficient configuration of capital. Through the intelligent evaluation process, the evaluation efficiency is remarkably improved, the decision-making period is shortened, and the capacity of quickly responding to market changes is provided for issuers and investors.

Description

Technical Field

[0001] The present invention relates to the field of blockchain and digital bond technology, and in particular, to a digital bond risk assessment method, system, electronic device, and storage medium based on blockchain and privacy computing. Background Art

[0002] Digital bonds are financial instruments issued to fund environmental and sustainable development projects, and the market is developing rapidly. Traditional risk assessment methods involve analyzing a company's core operating data (such as production data, fixed asset data, tax data, carbon emissions data, etc.) to determine whether the company meets the issuance criteria for digital bonds. During the risk assessment process, a company's core operating data needs to be shared among multiple parties for comprehensive analysis. The opacity of the assessment process makes it difficult for investors to fully understand the true risk profile of the bond, and there is a lack of effective technical means to ensure the objectivity and authenticity of the assessment process.

[0003] The traditional risk assessment method for digital bonds has the following problems:

[0004] 1. Inefficiency: Traditional risk assessment methods rely on manual processes and centralized databases, resulting in slow processing of large amounts of data and an inability to meet the demands of high-concurrency business. Data processing may involve multiple intermediaries, increasing processing time and reducing overall efficiency, making it difficult to quickly respond to market changes.

[0005] 2. Information opacity: The risk assessment process lacks transparency, making it difficult for investors and other stakeholders to verify the authenticity and fairness of assessment results, resulting in low investor trust in the results. The lack of a real-time data sharing and update mechanism leads to information lags, making it difficult for investors to make timely decisions.

[0006] 3. Susceptibility to tampering: Core business data is shared among multiple parties, creating the risk of data tampering. Existing systems may lack effective mechanisms to prevent data tampering, which could affect the accuracy of assessment results. There is also a lack of effective audit tracking mechanisms to monitor data change history.

[0007] 4. Data privacy leakage: During the data sharing process, the core operating data of an enterprise may face the risk of privacy leakage.

[0008] 5. Lack of Technical Support: The lack of effective technical means to ensure the objectivity and authenticity of the assessment process affects the accuracy and fairness of the assessment results. Existing technologies may not fully utilize the latest scientific and technological achievements, such as blockchain, cloud computing, and artificial intelligence, to improve the efficiency and accuracy of risk assessments. Existing systems lack flexibility and scalability, making it difficult to adapt to market changes and new demands.

[0009] 6. Inadequate Information Disclosure: Issuers may fail to disclose key operating information in a timely or sufficient manner, preventing investors and other market participants from making informed decisions. The format and content of information disclosed may be inconsistent and lack standardization, making comparison and analysis difficult. Summary of the Invention

[0010] In response to the above technical problems, this application provides a digital bond risk assessment method based on blockchain and privacy computing.

[0011] This application is implemented through the following scheme:

[0012] A digital bond risk assessment method based on blockchain and privacy computing, comprising the following steps:

[0013] Step S1: The enterprise entities participating in the assessment complete dual identity verification by integrating distributed digital identity (DID) and biometric authentication to ensure that the identity cannot be tampered with and is unique. The system collects enterprise-related data, homomorphically encrypts it, and stores it in shards on the private cloud. At the same time, a composite hash value is generated for on-chain storage, and zero-knowledge proof technology is introduced to construct data fingerprints to verify the availability of encrypted data. Smart contracts automatically anchor the spatiotemporal attributes of data to ensure that the data is traceable throughout its life cycle.

[0014] Step S2: The assessment and certification agency, together with financial institutions and regulators, collaboratively trains the risk assessment model based on secure multi-party computation (MPC). The risk assessment model parameters are encrypted and stored in a sharded manner using threshold homomorphic encryption (TFHE) technology. During the risk assessment model deployment phase, a trusted execution environment (TEE) is built in the cloud to implement closed computation from confidential data input to encryption model inference, and generate proof of the correctness of the computation process through zero-knowledge proof.

[0015] Step S3: The assessment results trigger a blockchain smart contract to automatically execute a risk classification response, and the entire assessment process data is stored cross-chain in judicial and regulatory nodes to support multi-party audits and inspections;

[0016] Step S4: Panoramic Monitoring and Collaborative Governance During the bond's lifespan, continuous monitoring is achieved across three dimensions, with the disposal process automatically triggered based on the type of abnormal data. All operation records are uploaded to the blockchain in real time, forming a closed-loop collaborative governance system involving regulators, companies, and investors.

[0017] Step S5: The assessment agency verifies the legitimacy of the entity that uploaded the enterprise information through the distributed digital identity (DID), ensuring that the source of the information is consistent with the uploader. The assessment agency can also trace back the information on the chain to prevent information tampering.

[0018] Step S6: Build an automated audit and violation handling process, deploy AI audit robots to implement consistency verification of on-chain hashes and cloud ciphertexts, detect abnormal behavior patterns, and trace data changes based on Merkle trees; when data tampering is discovered, the smart contract automatically triggers a graded response: minor violations will freeze account permissions; serious violations will initiate on-chain asset liquidation and link judicial chain evidence storage, forming a "monitoring-handling-tracing" full-chain risk control.

[0019] Furthermore, the step S1 specifically includes the steps of:

[0020] Step S11: Identity authentication and rights management. This involves participating enterprises, assessment agencies, and regulators completing real-name authentication through a distributed digital identity (DID). The DID is bound to the legal person's biometrics (such as voiceprint / iris) to ensure non-repudiation of identity. The system automatically assigns data operation permissions (for example, production data can only be uploaded by designated personnel of the enterprise). Changes in permissions require multi-party signature confirmation.

[0021] Step S12: The system collects six core data sets covering production data (real-time monitoring of industrial IoT equipment), supply chain resilience data (blockchain oracle to obtain customs logistics status), ESG three-dimensional data (satellite remote sensing carbon emissions and IoT water resources monitoring), dynamic financial data (direct connection to the central bank's credit reporting system), market sentiment index (NLP sentiment analysis of social media texts), and carbon trading records (on-chain synchronized exchange data);

[0022] Step S13: The enterprise entity cleans and normalizes the raw data and automatically marks the sensitivity level through the data classification engine: Level 1 data (such as financial data): uses homomorphic encryption + zero-knowledge verification; Level 2 data (such as production data): uses national secret algorithm encryption; Level 3 data (such as ESG reports): only hashes are stored on the chain, and the encryption strategy is dynamically adjusted through smart contracts to ensure a balance between compliance and security;

[0023] Step S14: Trusted storage and cross-chain evidence storage, including encrypted data sharding and storage in a private cloud, while generating a composite hash chain and uploading it to a multi-chain network and introducing zero-knowledge proof technology to construct a data fingerprint to verify the availability of confidential data. The multi-chain network includes a regulatory chain and a judicial chain.

[0024] Step S15: Dynamic audit and traceability verification, including deploying automated audit robots, scanning blockchain hash values ​​and cloud ciphertext consistency daily, triggering smart contract alarms under abnormal conditions, and enterprises using DID keys to trace historical data in time and space to ensure that the data is traceable throughout its life cycle.

[0025] Furthermore, the step S2 specifically includes the steps of:

[0026] Step S21: Collaborative development of a federated model: The assessment and certification agency, together with financial institutions and regulators, collaboratively trains the risk assessment model through secure multi-party computing (MPC). The model architecture adopts a heterogeneous federated learning framework:

[0027] Data side: Keep encrypted data locally and output homomorphically encrypted gradients.

[0028] Computational side: aggregate gradients and update the global model,

[0029] Supervisors: monitor model deviations and trigger retraining thresholds.

[0030] Step S22, model encryption: Model parameters are encrypted and stored in a sharded manner using threshold homomorphic encryption (TFHE) technology. Three-fifths of the participants must jointly decrypt the model during deployment.

[0031] Step S23, trusted model deployment: During the model deployment phase, a trusted execution environment (TEE) is built in the cloud to implement closed computing of the entire process of "data input-encrypted calculation-result output", and generate trusted evidence through SGX remote attestation.

[0032] Furthermore, the step S3 specifically includes the steps of:

[0033] Step S31: Automated risk assessment: After receiving the encrypted data and risk assessment model, the cloud platform performs a secret calculation in the Trusted Execution Environment (TEE) to generate a risk level label. The calculation result is encrypted and returned with a joint signature from 3 / 5 institutions, and the signing process is recorded in the blockchain.

[0034] Step S32: Deploy a hierarchical response smart contract based on the smart contract response mechanism to automatically execute risk hierarchical response, including levels 1-10, where:

[0035] Levels 1-3 are low risk: digital bond issuance certificates are automatically issued and synchronized to the custody chain and exchanges;

[0036] Level 4-7 Medium Risk: The company is required to provide additional collateral or disclose supplementary data, and the assessment will be re-evaluated after verification by the oracle.

[0037] Levels 8-10 are high risk: issuance is suspended and the insurance hedging mechanism is triggered. The DeFi platform on the linked chain freezes related assets, triggering CDS insurance payouts. This includes obtaining market prices through oracles and automatically liquidating collateral.

[0038] Step S33, cross-chain evidence storage and audit, evaluate the entire process data (including input, model, and results) and anchor it to the judicial evidence chain (Supreme Court node), the central bank supervision chain, and the international ESG chain, and support regulators to conduct penetrating audits through DID keys.

[0039] Furthermore, the step S4 comprises the steps of:

[0040] Step S41: Panoramic monitoring and collaborative governance During the bond's lifespan, a visual monitoring system is constructed through three dimensions to achieve continuous monitoring and upload monitoring records to the blockchain:

[0041] Credit Dimension: Using LSTM to track corporate financial data and market ratings, predict the probability of corporate default over the next 12 months, updated daily.

[0042] Environmental dimension: Using satellite remote sensing carbon emission heat maps to analyze carbon emission data in real time and compare it with industry benchmark values;

[0043] Market dimension: Implied volatility surface, calibrated based on the SABR model, updated hourly

[0044] Step S42: Automatically trigger the handling process based on the type of abnormal data and upload the handling record to the blockchain:

[0045] Carbon emissions exceed the limit: mandatory purchase of quotas from the on-chain carbon market, with prices obtained through oracles before purchase;

[0046] Liquidity crisis: When liquidity is insufficient, funds will be injected from the DAO governance reserve pool, which must be approved by a vote of 2 / 3 of the nodes before the injection;

[0047] Public opinion risk: Launch an AI-generated automatic roadshow robot that can issue clarification announcements, monitor public opinion fluctuations and liquidity indicators, and warn of potential sell-off risks.

[0048] Furthermore, the step S5 specifically includes the steps of:

[0049] Step S51: The assessment agency verifies the entity that uploaded the enterprise information through the distributed digital identity DID. After the enterprise passes the distributed digital identity DID authentication, it regularly uploads its business data to the on-chain data cabin. The data cabin adopts a dual storage structure, including:

[0050] Plain text summary: publicly searchable desensitized data, including total carbon emissions data,

[0051] Full ciphertext: detailed homomorphically encrypted data, including data that can only be decrypted by authorized parties;

[0052] Step S52: The enterprise is responsible for the completeness and accuracy of the disclosed information and accepts supervision and inquiries from assessment and certification agencies and market participants to ensure that the source of the information is consistent with the uploader. The information of relevant personnel will also be tracked;

[0053] Step S53: The enterprise discloses information through a transparent information disclosure mechanism to enhance investors' confidence in the enterprise's operating conditions and digital bonds, and promote the stable development of the digital financial market.

[0054] Furthermore, the step S6 specifically includes the steps of:

[0055] Step S61: Intelligent audit and tracing, including deploying AI audit robots to automatically execute:

[0056] Data integrity verification: Compare the consistency between the hash on the chain and the ciphertext on the cloud;

[0057] Behavioral pattern analysis: Detecting abnormal data upload behavior, including frequent modifications during non-business hours;

[0058] Historical tracing: Quickly locate data change records through Merkle Patricia Trie;

[0059] Step S62: Violation handling, including automatic execution of the smart contract upon discovery of tampering:

[0060] Minor violations: freeze the enterprise or individual DID permissions for 72 hours;

[0061] Serious violations: triggering forced redemption of bonds, including liquidation of collateral through DeFi protocols;

[0062] Judicial intervention: Encrypt the evidence package and transmit it to the chain of custody, initiate legal proceedings, and form a full-chain risk control of "monitoring-handling-traceability".

[0063] The other party to this application also provides a digital bond risk assessment system based on blockchain and privacy computing, including:

[0064] The identity verification module is used by participating enterprise entities to complete dual identity verification by integrating distributed digital identity (DID) and biometric authentication to ensure that the identity cannot be tampered with and is unique. The system collects enterprise-related data, homomorphically encrypts it, and stores it in shards on the private cloud. It also generates a composite hash value for on-chain evidence storage and introduces zero-knowledge proof technology to construct a data fingerprint to verify the availability of encrypted data. Smart contracts automatically anchor the spatiotemporal attributes of data to ensure traceability throughout the data lifecycle.

[0065] The model training and deployment module is used by assessment and certification bodies, financial institutions, and regulators to collaboratively train risk assessment models based on secure multi-party computation (MPC). The risk assessment model parameters are encrypted and stored in a sharded manner using threshold homomorphic encryption (TFHE) technology. During the risk assessment model deployment phase, a trusted execution environment (TEE) is built in the cloud to implement closed computation from confidential data input to encryption model inference, and evidence of the correctness of the computation process is generated through zero-knowledge proof.

[0066] Smart contract trigger module, used to trigger blockchain smart contracts based on assessment results, automatically execute risk-level responses, and store cross-chain evidence of the entire assessment process in judicial and regulatory nodes, supporting multi-party audits and inspections;

[0067] The continuous monitoring and disposal module is used for comprehensive monitoring and collaborative governance during the bond's lifespan. It implements continuous monitoring across three dimensions and automatically triggers the disposal process based on the type of abnormal data. All operation records are uploaded to the blockchain in real time, forming a closed-loop collaborative governance system among regulators, companies, and investors.

[0068] The information upload subject verification module is used by the assessment agency to verify the legitimacy of the uploader of corporate information through the distributed digital identity DID, ensuring that the source of the information is consistent with the uploader, and can be traced back through on-chain information to prevent information tampering;

[0069] The audit and violation handling module is used to build an automated audit and violation handling process, deploy AI audit robots to implement consistency verification of on-chain hashes and cloud ciphertexts, detect abnormal behavior patterns, and trace data changes based on Merkle trees. When data tampering is discovered, the smart contract automatically triggers a graded response: minor violations will freeze account permissions; serious violations will initiate on-chain asset liquidation and link judicial chain evidence storage, forming a "monitoring-handling-tracing" full-chain risk control.

[0070] On the other hand, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the steps of the digital bond risk assessment method based on blockchain and privacy computing are implemented.

[0071] On the other hand, the present application also provides a storage medium, which includes a stored program, and when the program is running, controls the device where the storage medium is located to execute the steps of the digital bond risk assessment method based on blockchain and privacy computing.

[0072] Compared with the existing technology, this application has the following beneficial effects:

[0073] 1. Improve the efficiency and accuracy of risk assessment:

[0074] This application leverages the high-performance computing resources of cloud computing platforms and homomorphic encryption technology to achieve direct calculations on encrypted data, significantly improving the efficiency of risk assessment. Simultaneously, the automated assessment process reduces human error and improves the accuracy of assessment results.

[0075] 2. Strengthen data security and privacy protection:

[0076] This application ensures that data is processed in an encrypted state through homomorphic encryption, and combines blockchain technology to ensure the integrity and immutability of data, greatly enhancing data security and privacy protection, and reducing the risk of data leakage and tampering.

[0077] 3. Enhance the transparency and credibility of the assessment process:

[0078] This application utilizes the decentralized and open and transparent characteristics of blockchain, as well as real-time data update and disclosure mechanisms, to improve the transparency of the evaluation process, enabling investors and other stakeholders to verify the authenticity of the evaluation results and enhancing market trust in the evaluation results.

[0079] 4. Protect intellectual property rights and promote technological innovation:

[0080] The application of homomorphic encryption technology in this application not only protects the privacy of enterprise data, but also protects the intellectual property rights of artificial intelligence evaluation models, prevents illegal copying and tampering of models, and encourages more technological innovation and intellectual property protection.

[0081] 5. This application promotes the stability and development of the digital financial market:

[0082] This application's efficient, secure, and transparent risk assessment system enhances investors' confidence in the digital bond market, promotes market stability and sustainable development, and provides more reliable financial support for digital financial projects.

[0083] In addition to the above-described purposes, features and advantages, the present application also has other purposes, features and advantages. The present application will be further described in detail below with reference to the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] The drawings constituting a part of this application are used to provide a further understanding of the application. The illustrative embodiments of the application and their descriptions are used to explain the application and do not constitute an improper limitation of the application. In the drawings:

[0085] Figure 1 This is a flowchart of a digital bond risk assessment method based on blockchain and privacy computing in a preferred embodiment of the present application;

[0086] Figure 2 This is a schematic flow chart of the sub-steps of step S1 of the preferred embodiment of the present application;

[0087] Figure 3 This is a schematic flow chart of the sub-steps of step S2 of the preferred embodiment of the present application;

[0088] Figure 4 This is a schematic flow chart of the sub-steps of step S3 of the preferred embodiment of the present application;

[0089] Figure 5 This is a schematic flow chart of the sub-steps of step S4 of the preferred embodiment of the present application;

[0090] Figure 6 This is a schematic flow chart of the sub-steps of step S5 of the preferred embodiment of the present application;

[0091] Figure 7 This is a schematic flow chart of the sub-steps of step S6 in a preferred embodiment of the present application;

[0092] Figure 8 This is a schematic diagram of the overall data processing flow of the digital bond risk assessment system based on blockchain and privacy computing in the preferred embodiment of the present application;

[0093] Figure 9 This is a schematic diagram of the functional architecture of a digital bond risk assessment system based on blockchain and privacy computing according to an embodiment of the present invention;

[0094] Figure 10 This is a module diagram of a digital bond risk assessment system based on blockchain and privacy computing in a preferred embodiment of the present application;

[0095] Figure 11 This is a schematic block diagram of an electronic device according to a preferred embodiment of the present application;

[0096] Figure 12 It is a diagram of the internal structure of a computer device according to a preferred embodiment of the present application. DETAILED DESCRIPTION

[0097] The embodiments of the present application are described in detail below with reference to the accompanying drawings, but the present application can be implemented in a variety of different ways defined and covered below.

[0098] Technical term explanation

[0099] Homomorphic encryption technology: used to encrypt an enterprise's core operating data, allowing calculations to be performed directly on the encrypted data, and obtaining correct calculation results without decryption, thereby protecting data privacy.

[0100] Blockchain technology refers to an emerging technology that uses a peer-to-peer distributed network of computers to jointly maintain a complete distributed database. Blockchain technology boasts decentralization, transparency, and data resistance to tampering and loss, making it widely applicable in numerous fields. It stores hash values ​​for data, ensuring its integrity and immutability. The decentralized nature of blockchain provides data consistency and traceability.

[0101] Distributed digital identity: Distributed digital identity is an identity management framework built using blockchain or distributed ledger technology, which allows individuals or entities to own and fully control their own digital identity information.

[0102] Cloud computing technology: provides powerful computing resources for processing homomorphically encrypted data and evaluation models, executing risk assessment algorithms, and calculating encrypted risk assessment results.

[0103] Artificial Intelligence (AI) Assessment Models: These models are used to comprehensively analyze a company's core operating data and assess the risks of its digital bond issuance. These models are encrypted using homomorphic encryption technology to protect intellectual property.

[0104] Data storage and processing technology: involves data screening, preprocessing, encrypted storage and hash value generation, as well as real-time updating and disclosure of data.

[0105] Information audit and integrity verification technology: used to verify the integrity and authenticity of business information disclosed by enterprises and prevent information tampering.

[0106] Result decryption technology: used to decrypt confidential assessment results obtained through cloud computing so that assessment and certification bodies can obtain and use these results.

[0107] Logging and monitoring technology: used to record and monitor the entire computing process to facilitate post-audit and verification of the compliance of the computing process.

[0108] High-performance computing technology: The cloud platform uses its high-performance computing capabilities to handle complex data analysis and model operations.

[0109] Distributed storage systems: Hardware and software components are distributed across different computers, communicating and coordinating with each other over a network. This system provides storage services in a state imperceptible to users, while ensuring system performance and fault tolerance. These systems involve components such as reverse proxies, application server clusters, cache pools, data processing modules, and message queue clusters to improve overall system performance and reliability.

[0110] ESG: The full name is Environmental, Social and Governance. It is the three core elements for measuring a company's performance in sustainable development and social responsibility. It is an important criterion for investors to evaluate a company's long-term value and risk management capabilities.

[0111] SGX (Intel Software Guard Extensions) is a security technology developed by Intel that allows applications to create a secure, isolated area within the CPU called an "enclave." Code and data running within this enclave are highly protected, preventing the disclosure of sensitive information even if the operating system or hypervisor is compromised. It is widely used in privacy-preserving computing, blockchain, and trusted execution environments.

[0112] DAO: Decentralized Autonomous Organization, is a new organizational form based on blockchain technology. Its rules are written into the blockchain in the form of smart contracts, and organizational decisions are made through member voting without the need for a traditional central management agency.

[0113] Merkle Patricia Trie: A data structure that combines a Merkle tree and a Patricia Trie. It is primarily used for efficiently storing and verifying large amounts of key-value pairs. It is widely used in Ethereum to enable efficient querying and hash digest generation for state storage, transactions, receipts, and other data.

[0114] like Figure 1 As shown, the preferred embodiment of the present application provides a digital bond risk assessment method based on blockchain and privacy computing, comprising the following steps:

[0115] Step S1: The enterprise entities participating in the assessment complete dual identity verification by integrating distributed digital identity (DID) and biometric authentication to ensure that the identity cannot be tampered with and is unique; the system collects enterprise-related data, encrypts it homomorphically, and stores it in shards on the private cloud. At the same time, it generates a composite hash value for on-chain evidence storage, and introduces zero-knowledge proof technology to construct data fingerprints to verify the availability of encrypted data; the smart contract automatically anchors the data's spatiotemporal attributes to ensure that the data is traceable throughout its life cycle, and the smart contract automatically anchors the data's spatiotemporal attributes (such as the carbon trading record timestamp error <1ms) to ensure that the data is traceable throughout its life cycle;

[0116] Step S2: The assessment and certification agency, together with financial institutions and regulators, jointly trains the risk assessment model based on secure multi-party computing (MPC). The risk assessment model parameters are encrypted and stored in a sharded manner using threshold homomorphic encryption (TFHE) technology. During the risk assessment model deployment phase, a trusted execution environment (TEE) is built in the cloud to implement closed computing from confidential data input to encryption model reasoning. Evidence of the correctness of the computing process is generated through zero-knowledge proof. The model supports hourly dynamic optimization driven by federated learning and utilizes a gradient aggregation mechanism protected by differential privacy to achieve parameter updates under the condition of "available but invisible" data, ensuring that risk prediction indicators evolve in real time with the market environment.

[0117] Step S3: The assessment results trigger a blockchain smart contract to automatically execute a risk grading response. The entire assessment process data (including calculation logic and results) is stored cross-chain in judicial and regulatory nodes, supporting multi-party audits and inspections.

[0118] Step S4: Panoramic Monitoring and Collaborative Governance During the bond's lifespan, continuous monitoring is achieved across three dimensions, with the disposal process automatically triggered based on the type of abnormal data. All operation records are uploaded to the blockchain in real time, forming a closed-loop collaborative governance system involving regulators, companies, and investors.

[0119] Step S5: The assessment agency verifies the legitimacy of the entity that uploaded the enterprise information through the distributed digital identity (DID), ensuring that the source of the information is consistent with the uploader. The assessment agency can also trace back the information on the chain to prevent information tampering.

[0120] Step S6: Build an automated audit and violation handling process, deploy AI audit robots to implement consistency verification of on-chain hashes and cloud ciphertexts, detect abnormal behavior patterns, and trace data changes based on Merkle trees; when data tampering is discovered, the smart contract automatically triggers a graded response: minor violations will freeze account permissions; serious violations will initiate on-chain asset liquidation and link judicial chain evidence storage, forming a "monitoring-handling-traceability" full-chain risk control. By continuously verifying data integrity and solidifying on-chain evidence, the immutability of the assessment system and the credibility of supervision are ensured, and ultimately a collaborative governance mechanism with self-healing risks and clear rights and responsibilities is established.

[0121] The digital bond risk assessment method based on blockchain and privacy computing provided in this embodiment has the following key features:

[0122] (1) Application of Homomorphic Encryption Technology: In this embodiment, homomorphic encryption technology is used to process the core business data of an enterprise without decryption. This means that the encrypted data can be directly used for risk assessment calculations, and the calculation results are consistent with the results of the same calculation performed on the original data after decryption. The application of this technology ensures the privacy and security of the data during the assessment process, while allowing necessary data analysis.

[0123] (2) Integration of blockchain technology: Blockchain technology is used in this application to store the hash value of the data, ensuring the integrity and immutability of the data. The hash value of the data is recorded on the blockchain, and any changes to the data will change its hash value and be detected by the system. This mechanism improves the transparency and credibility of the evaluation process.

[0124] (3) Combining cloud computing with AI: Cloud platforms provide the necessary computing resources to run homomorphically encrypted AI assessment models. These models are able to process encrypted data and output risk assessment results without decrypting the data. This combination leverages the elasticity and scalability of cloud computing, improving the efficiency and accuracy of the assessment process.

[0125] (4) Fully automated risk assessment system: This embodiment automates the entire process from data encryption, blockchain evidence storage, cloud computing, to result decryption. The automated process reduces human intervention, lowers the error rate, and improves the speed and consistency of assessments.

[0126] (5) Real-time data monitoring and transparent disclosure mechanism: Issuers must continuously monitor their business activities and update and disclose key information in real time. This information is submitted to the assessment and certification agency through secure channels and verified and stored using blockchain technology, ensuring the authenticity and timeliness of the information.

[0127] like Figure 2 As shown, in a preferred embodiment of the present application, step S1 specifically includes the following steps:

[0128] Step S11: Identity authentication and rights management. This involves participating enterprises, assessment agencies, and regulators completing real-name authentication through a distributed digital identity (DID). The DID is bound to the legal person's biometrics (such as voiceprint / iris) to ensure non-repudiation of identity. The system automatically assigns data operation permissions (for example, production data can only be uploaded by designated personnel of the enterprise). Changes in permissions require multi-party signature confirmation.

[0129] Step S12: The system collects six core data sets covering production data (real-time monitoring of industrial IoT equipment), supply chain resilience data (blockchain oracle to obtain customs logistics status), ESG three-dimensional data (satellite remote sensing carbon emissions and IoT water resources monitoring), dynamic financial data (direct connection to the central bank's credit reporting system), market sentiment index (NLP sentiment analysis of social media texts), and carbon trading records (on-chain synchronized exchange data);

[0130] Step S13: The enterprise entity cleans and normalizes the raw data and automatically marks the sensitivity level through the data classification engine: Level 1 data (such as financial data): uses homomorphic encryption + zero-knowledge verification; Level 2 data (such as production data): uses national secret algorithm encryption; Level 3 data (such as ESG reports): only hashes are stored on the chain, and the encryption strategy is dynamically adjusted through smart contracts to ensure a balance between compliance and security;

[0131] Step S14: Trusted storage and cross-chain evidence storage, including encrypted data sharding and storage in a private cloud, while generating a composite hash chain and uploading it to a multi-chain network and introducing zero-knowledge proof technology to construct a data fingerprint to verify the availability of confidential data. The multi-chain network includes a regulatory chain and a judicial chain, and hash value synchronization is achieved through a cross-chain protocol to ensure that data tampering on any chain can be detected by other chains (error tolerance rate <0.001%).

[0132] Step S15: Dynamic audit and traceability verification, including deploying automated audit robots, scanning blockchain hash values ​​and cloud ciphertext consistency daily, triggering smart contract alarms under abnormal conditions, and enterprises using DID keys to trace historical data in time and space to ensure that the data is traceable throughout its life cycle (such as verifying whether the timestamp error of a carbon trading record is <1ms).

[0133] The advantages of this implementation include building a secure, trustworthy, and traceable data governance system, encompassing identity authentication, multi-source data collection, encrypted hierarchical processing, cross-chain evidence storage, and dynamic auditing. This system enables full data lifecycle management, ensuring data authenticity, integrity, and security from source authentication to storage, use, and auditing. This provides high-quality, structured, and compliant data foundation for subsequent model training and risk assessment.

[0134] like Figure 3 As shown, in a preferred embodiment of the present application, step S2 specifically includes the following steps:

[0135] Step S21: Collaborative development of a federated model: The assessment and certification agency, together with financial institutions and regulators, collaboratively trains the risk assessment model through secure multi-party computing (MPC). The model architecture adopts a heterogeneous federated learning framework:

[0136] Data side: Keep encrypted data locally and output homomorphically encrypted gradients.

[0137] Computational side: aggregate gradients and update the global model,

[0138] Supervisors: monitor model deviations and trigger retraining thresholds.

[0139] Step S22, model encryption: Model parameters are encrypted and stored in a sharded manner using threshold homomorphic encryption (TFHE) technology. Three-fifths of the participants must jointly decrypt the model during deployment.

[0140] Step S23, trusted model deployment: During the model deployment phase, a trusted execution environment (TEE) is built in the cloud to implement closed computing of the entire process of "data input-encrypted calculation-result output", and generate trusted evidence through SGX remote attestation.

[0141] The advantages of this embodiment include enabling multi-party collaborative modeling while protecting data privacy, breaking through the limitations of traditional data silos. It utilizes a combination of secure multi-party computing, federated learning, homomorphic encryption, and a trusted execution environment (TEE) to balance model performance and data security. The model encryption and deployment mechanism ensures the security and tamper-proofing of the AI ​​model, meeting financial regulatory requirements.

[0142] like Figure 4 As shown, in a preferred embodiment of the present application, step S3 specifically includes the following steps:

[0143] Step S31: Automated risk assessment: After receiving the encrypted data and risk assessment model, the cloud platform performs a secret calculation in the Trusted Execution Environment (TEE) to generate a risk level label (level 1-10). The calculation result is encrypted and returned with the joint signature of 3 / 5 institutions, and the signing process is recorded in the blockchain.

[0144] Step S32: Deploy a hierarchical response smart contract based on the smart contract response mechanism to automatically execute risk hierarchical response, including levels 1-10, where:

[0145] Levels 1-3 are low risk: digital bond issuance certificates are automatically issued and synchronized to the custody chain and exchanges;

[0146] Level 4-7 Medium Risk: The company is required to provide additional collateral or disclose supplementary data, and the assessment will be reassessed after verification by the oracle (the smart contract will freeze the on-chain assets until the standards are met);

[0147] Levels 8-10 are high risk: issuance is suspended and the insurance hedging mechanism is triggered. The DeFi platform on the linked chain freezes related assets, triggering CDS insurance payouts. This includes obtaining market prices through oracles and automatically liquidating collateral.

[0148] Step S33, cross-chain evidence storage and audit, evaluate the entire process data (including input, model, and results) and anchor it to the judicial evidence chain (Supreme Court node), the central bank supervision chain, and the international ESG chain, and support regulators to conduct penetrating audits through DID keys.

[0149] The advantages of this implementation include: It incorporates trusted computing into the risk assessment process, enabling automated risk rating in a confidential state and ensuring the confidentiality of sensitive information. Risk response mechanisms are automatically triggered through smart contracts, improving the efficiency and standardization of risk management. All assessment processes and results are stored on-chain, enabling penetrating oversight and full process auditability, enhancing system transparency and credibility.

[0150] like Figure 5 As shown, in a preferred embodiment of the present application, step S4 comprises the following steps:

[0151] Step S41: Panoramic monitoring and collaborative governance During the bond's lifespan, a visual monitoring system is constructed through three dimensions to achieve continuous monitoring and upload monitoring records to the chain (three-dimensional monitoring dashboard):

[0152] Credit Dimension: Using LSTM to track corporate financial data and market ratings, predict the probability of corporate default over the next 12 months, updated daily.

[0153] Environmental dimension: Using satellite remote sensing carbon emission heat maps to analyze carbon emission data in real time and compare it with industry benchmark values;

[0154] Market dimension: Implied volatility surface, calibrated based on the SABR model, updated hourly;

[0155] Step S42: Automatically trigger the handling process based on the type of abnormal data and upload the handling record to the chain (self-healing risk control mechanism):

[0156] Carbon emissions exceed the limit: mandatory purchase of quotas from the on-chain carbon market, with prices obtained through oracles before purchase;

[0157] Liquidity crisis: When liquidity is insufficient, funds will be injected from the DAO governance reserve pool, which must be approved by a vote of 2 / 3 of the nodes before the injection;

[0158] Public opinion risk: Launch an AI-generated automatic roadshow robot that can issue clarification announcements, monitor public opinion fluctuations and liquidity indicators, and warn of potential sell-off risks.

[0159] The advantages of this implementation include: A multi-dimensional, frequently updated continuous monitoring system covering the three core risk areas of credit, environment, and market risk. A self-healing risk control mechanism automatically identifies and implements countermeasures when anomalies occur, such as carbon quota purchases, liquidity injections, and public opinion intervention, reducing the cost of manual intervention. All monitoring and handling actions are recorded on-chain, forming a closed-loop risk control chain and enhancing post-issuance management capabilities for digital bonds.

[0160] like Figure 6 As shown, in a preferred embodiment of the present application, step S5 specifically includes the following steps:

[0161] Step S51, continuous data disclosure: The assessment agency verifies the entity that uploads the enterprise information through the distributed digital identity DID. After the enterprise passes the distributed digital identity DID authentication, it regularly uploads its business data to the on-chain data cabin to achieve continuous data disclosure. The data cabin adopts a dual storage structure, including:

[0162] Plain text summary: publicly searchable desensitized data, including total carbon emissions data,

[0163] Full ciphertext: detailed homomorphically encrypted data, including data that can only be decrypted by authorized parties;

[0164] Step S52: The enterprise is responsible for the completeness and accuracy of the disclosed information and accepts supervision and inquiries from assessment and certification agencies and market participants to ensure that the source of the information is consistent with the uploader. The information of relevant personnel will also be tracked;

[0165] Step S53: The enterprise discloses information through a transparent information disclosure mechanism to enhance investors' confidence in the enterprise's operating conditions and digital bonds, and promote the stable development of the digital financial market.

[0166] The advantages of this implementation include institutionalizing, automating, and verifying corporate information disclosure, enhancing market transparency. Using DID to verify the identity of the uploader, combined with a dual storage structure (plaintext digest + ciphertext full data), it balances transparency with privacy protection. This enhances investor confidence in corporate operations and promotes the healthy development and compliant operation of the digital bond market.

[0167] like Figure 7 As shown, in a preferred embodiment of the present application, step S6 specifically includes the following steps:

[0168] Step S61: Intelligent audit and tracing, including deploying AI audit robots to automatically execute:

[0169] Data integrity verification: Compare the consistency between the hash on the chain and the ciphertext on the cloud;

[0170] Behavioral pattern analysis: Detecting abnormal data upload behavior, including frequent modifications during non-business hours;

[0171] Historical tracing: Quickly locate data change records through Merkle Patricia Trie;

[0172] Step S62: Violation handling, including automatic execution of the smart contract upon discovery of tampering:

[0173] Minor violations: freeze the enterprise or individual DID permissions for 72 hours;

[0174] Serious violations: triggering forced redemption of bonds, including liquidation of collateral through DeFi protocols;

[0175] Judicial intervention: Encrypt the evidence package and transmit it to the chain of custody, initiate legal proceedings, and form a full-chain risk control of "monitoring-handling-traceability".

[0176] Steps S61-S62 of this embodiment maintain the authority and reliability of the digital bond risk assessment system through continuous information integrity verification and backtracking mechanisms and assessment agencies.

[0177] In the above embodiment, the enterprise entity, the assessment and certification agency, the cloud server, the blockchain network, and the regulatory agency nodes cooperate to implement the digital bond risk assessment method based on blockchain and privacy computing. Figure 8 shown.

[0178] Figure 9 This is a functional architecture hierarchy diagram of the digital bond risk assessment system based on blockchain and privacy computing in an embodiment of the present invention, showing the system's five-layer structure from underlying data support to upper-layer user services, including: data layer, network layer, management layer, consensus layer, and application layer. Each layer assumes specific system functions and jointly supports digital bond risk assessment. Figure 9 The hierarchical structure design shown in the figure realizes the innovation of digital bond risk assessment in the present invention. Its core effect is to enhance the data security and privacy protection during the evaluation process, while ensuring the integrity and non-tamperability of the data. By using homomorphic encryption technology, even if the calculation is carried out in the cloud, the encryption state of the data during the processing can be ensured, effectively preventing data leakage and unauthorized access. In addition, the evaluation system of the present application greatly improves the transparency and credibility of the evaluation, allowing investors to more accurately grasp the risk status of digital bonds, thereby promoting the healthy development of the digital financial market and the efficient allocation of capital. Through the intelligent evaluation process, the present application also significantly improves the evaluation efficiency, shortens the decision-making cycle, and provides issuers and investors with the ability to quickly respond to market changes.

[0179] like Figure 10 As shown, the other party of this application also provides a digital bond risk assessment system based on blockchain and privacy computing, including:

[0180] The identity verification module is used by participating enterprise entities to complete dual identity verification by integrating distributed digital identity (DID) and biometric authentication to ensure that the identity cannot be tampered with and is unique. The system collects enterprise-related data, homomorphically encrypts it, and stores it in shards on the private cloud. It also generates a composite hash value for on-chain evidence storage and introduces zero-knowledge proof technology to construct a data fingerprint to verify the availability of encrypted data. Smart contracts automatically anchor the spatiotemporal attributes of data to ensure traceability throughout the data lifecycle.

[0181] The model training and deployment module is used by assessment and certification bodies, financial institutions, and regulators to collaboratively train risk assessment models based on secure multi-party computation (MPC). The risk assessment model parameters are encrypted and stored in a sharded manner using threshold homomorphic encryption (TFHE) technology. During the risk assessment model deployment phase, a trusted execution environment (TEE) is built in the cloud to implement closed computation from confidential data input to encryption model inference, and evidence of the correctness of the computation process is generated through zero-knowledge proof.

[0182] Smart contract trigger module, used to trigger blockchain smart contracts based on assessment results, automatically execute risk-level responses, and store cross-chain evidence of the entire assessment process in judicial and regulatory nodes, supporting multi-party audits and inspections;

[0183] The continuous monitoring and disposal module is used for comprehensive monitoring and collaborative governance during the bond's lifespan. It implements continuous monitoring across three dimensions and automatically triggers the disposal process based on the type of abnormal data. All operation records are uploaded to the blockchain in real time, forming a closed-loop collaborative governance system among regulators, companies, and investors.

[0184] The information upload subject verification module is used by the assessment agency to verify the legitimacy of the uploader of corporate information through the distributed digital identity DID, ensuring that the source of the information is consistent with the uploader, and can be traced back through on-chain information to prevent information tampering;

[0185] The audit and violation handling module is used to build an automated audit and violation handling process, deploy AI audit robots to implement consistency verification of on-chain hashes and cloud ciphertexts, detect abnormal behavior patterns, and trace data changes based on Merkle trees. When data tampering is discovered, the smart contract automatically triggers a graded response: minor violations will freeze account permissions; serious violations will initiate on-chain asset liquidation and link judicial chain evidence storage, forming a "monitoring-handling-tracing" full-chain risk control.

[0186] like Figure 11 As shown, a preferred embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the digital bond risk assessment method based on blockchain and privacy computing in the above embodiment are implemented.

[0187] like Figure 12 As shown, the preferred embodiment of the present application further provides a computer device, which can be a terminal or a liveness detection server, and its internal structure diagram can be as shown in FIG. Figure 12As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with other external computer devices via a network connection. When executed by the processor, the computer program implements the steps of the above-mentioned digital bond risk assessment method based on blockchain and privacy computing.

[0188] Those skilled in the art will understand that Figure 12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0189] A preferred embodiment of the present application also provides a storage medium, which includes a stored program, and when the program is running, controls the device where the storage medium is located to execute the steps of the digital bond risk assessment method based on blockchain and privacy computing in the above embodiment.

[0190] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0191] If the functions described in the method of this embodiment are implemented in the form of a software functional unit and sold or used as an independent product, they can be stored in a storage medium readable by one or more computing devices. Based on this understanding, the part of the embodiment of the present application that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computing device (which can be a personal computer, server, mobile computing device or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0192] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiment of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal translation scripting language JavaScript, etc.

[0193] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0194] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system that is implemented in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0195] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0196] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0197] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A digital bond risk assessment method based on blockchain and privacy computing, characterized in that: The following steps are involved: Step S1: The enterprise entities participating in the assessment complete dual identity verification by integrating distributed digital identity (DID) and biometric authentication to ensure that the identity cannot be tampered with and is unique. The system collects enterprise-related data, homomorphically encrypts it, and stores it in shards on the private cloud. At the same time, a composite hash value is generated for on-chain storage, and zero-knowledge proof technology is introduced to construct data fingerprints to verify the availability of encrypted data. Smart contracts automatically anchor the spatiotemporal attributes of data to ensure that the data is traceable throughout its life cycle. Step S2: The assessment and certification authority, in collaboration with financial institutions and regulators, jointly trains the risk assessment model based on secure multi-party computing. The risk assessment model parameters are encrypted and stored in a sharded manner using threshold homomorphic encryption technology. During the risk assessment model deployment phase, a trusted execution environment is built in the cloud to implement closed computation from confidential data input to encryption model inference, and evidence of the correctness of the computation process is generated through zero-knowledge proof. Step S3: The assessment results trigger a blockchain smart contract to automatically execute a risk classification response, and the entire assessment process data is stored cross-chain in judicial and regulatory nodes to support multi-party audits and inspections; Step S4: Panoramic Monitoring and Collaborative Governance During the bond's lifespan, continuous monitoring is achieved across three dimensions, with the disposal process automatically triggered based on the type of abnormal data. All operation records are uploaded to the blockchain in real time, forming a closed-loop collaborative governance system involving regulators, companies, and investors. Step S5: The assessment agency verifies the legitimacy of the entity that uploaded the enterprise information through the distributed digital identity (DID), ensuring that the source of the information is consistent with the uploader. The assessment agency can also trace back the information on the chain to prevent information tampering. Step S6: Build an automated audit and violation handling process, deploy AI audit robots to implement consistency verification of on-chain hashes and cloud ciphertexts, detect abnormal behavior patterns, and trace data changes based on Merkle trees; when data tampering is discovered, the smart contract automatically triggers a graded response: minor violations will freeze account permissions; serious violations will initiate on-chain asset liquidation and link judicial chain evidence storage, forming a "monitoring-handling-tracing" full-chain risk control.

2. The digital bond risk assessment system based on blockchain and privacy computing as claimed in claim 1, characterized in that: The step S1 specifically includes the following steps: Step S11: Identity authentication and rights management. This involves participating enterprises, assessment agencies, and regulators completing real-name authentication through a distributed digital identity (DID). The DID is bound to the legal person's biometrics to ensure non-repudiation of identity. The system automatically assigns data operation permissions, and changes in permissions require multi-party signature confirmation. Step S12: The system collects a six-dimensional core data set covering production data, supply chain resilience data, ESG three-dimensional data, dynamic financial data, market sentiment index, and carbon trading records; Step S13: The enterprise entity cleans and normalizes the raw data and automatically marks the sensitivity level through the data classification engine: Level 1 data: uses homomorphic encryption + zero-knowledge verification; Level 2 data: uses the national secret algorithm for encryption; Level 3 data: only hashes are stored on the chain, and the encryption strategy is dynamically adjusted through smart contracts to ensure a balance between compliance and security; Step S14: Trusted storage and cross-chain evidence storage, including encrypted data sharding and storage in a private cloud, while generating a composite hash chain and uploading it to a multi-chain network and introducing zero-knowledge proof technology to construct a data fingerprint to verify the availability of confidential data. The multi-chain network includes a regulatory chain and a judicial chain. Step S15: Dynamic audit and traceability verification, including deploying automated audit robots, scanning blockchain hash values ​​and cloud ciphertext consistency daily, triggering smart contract alarms under abnormal conditions, and enterprises using DID keys to trace historical data in time and space to ensure that the data is traceable throughout its life cycle.

3. The digital bond risk assessment system based on blockchain and privacy computing as claimed in claim 1, characterized in that: The step S2 specifically includes the following steps: Step S21: Collaborative development of federated models: The assessment and certification bodies, together with financial institutions and regulators, collaboratively train risk assessment models through secure multi-party computing. The model architecture adopts a heterogeneous federated learning framework: Data side: Keep encrypted data locally and output homomorphically encrypted gradients. Computational side: Aggregate gradients and update the global model, Regulators: monitor model deviations and trigger retraining thresholds; Step S22, model encryption: Model parameters are encrypted and stored in a sharded manner using threshold homomorphic encryption technology. Joint decryption by 3 / 5 participants is required during deployment. Step S23, trusted model deployment: During the model deployment phase, a trusted execution environment is built in the cloud to implement closed computing of the entire process of "data input - encrypted calculation - result output", and to generate trusted evidence through SGX remote attestation.

4. The digital bond risk assessment system based on blockchain and privacy computing as claimed in claim 1, characterized in that: Described step S3 specifically comprises the steps: Step S31: Automated risk assessment: After receiving the encrypted data and risk assessment model, the cloud platform performs a secret calculation in a trusted execution environment to generate a risk level label. The calculation result is encrypted and returned with a joint signature from 3 / 5 institutions, and the signing process is recorded in the blockchain. Step S32: Deploy a hierarchical response smart contract based on the smart contract response mechanism to automatically execute risk hierarchical response, including levels 1-10, where: Levels 1-3 are low risk: digital bond issuance certificates are automatically issued and synchronized to the custody chain and exchanges; Level 4-7 Medium Risk: The company is required to provide additional collateral or disclose supplementary data, and the assessment will be re-evaluated after verification by the oracle. Levels 8-10 are high risk: issuance is suspended and the insurance hedging mechanism is triggered. The DeFi platform on the linked chain freezes related assets, triggering CDS insurance payouts. This includes obtaining market prices through oracles and automatically liquidating collateral. Step S33: Cross-chain evidence storage and auditing, evaluate the entire process data anchored to the judicial evidence chain, central bank supervision chain, and international ESG chain, and support regulators to conduct penetrating audits through DID keys.

5. The digital bond risk assessment system based on blockchain and privacy computing as claimed in claim 1 is characterized in that: The step S4 comprises the following steps: Step S41: Panoramic monitoring and collaborative governance During the bond's lifespan, a visual monitoring system is constructed through three dimensions to achieve continuous monitoring and upload monitoring records to the blockchain: Credit Dimension: Using LSTM to track corporate financial data and market ratings, predict the probability of corporate default over the next 12 months, updated daily. Environmental dimension: Using satellite remote sensing carbon emission heat maps to analyze carbon emission data in real time and compare it with industry benchmark values; Market dimension: Implied volatility surface, calibrated based on the SABR model, updated hourly; Step S42: Automatically trigger the handling process based on the type of abnormal data and upload the handling record to the blockchain: Carbon emissions exceed the limit: mandatory purchase of quotas from the on-chain carbon market, with prices obtained through oracles before purchase; Liquidity crisis: When liquidity is insufficient, funds will be injected from the DAO governance reserve pool, which must be approved by a vote of 2 / 3 of the nodes before the injection; Public opinion risk: Launch an AI-generated automatic roadshow robot that can issue clarification announcements, monitor public opinion fluctuations and liquidity indicators, and warn of potential sell-off risks.

6. The digital bond risk assessment system based on blockchain and privacy computing as claimed in claim 1, characterized in that: The step S5 specifically includes the following steps: Step S51: The assessment agency verifies the entity that uploaded the enterprise information through the distributed digital identity DID. After the enterprise passes the distributed digital identity DID authentication, it regularly uploads its business data to the on-chain data cabin. The data cabin adopts a dual storage structure, including: Plain text summary: publicly searchable desensitized data, including total carbon emissions data, Full ciphertext: detailed homomorphically encrypted data, including data that can only be decrypted by authorized parties; Step S52: The enterprise is responsible for the completeness and accuracy of the disclosed information and accepts supervision and inquiries from assessment and certification agencies and market participants to ensure that the source of the information is consistent with the uploader. The information of relevant personnel will also be tracked; Step S53: The enterprise discloses information through a transparent information disclosure mechanism to enhance investors' confidence in the enterprise's operating conditions and digital bonds, and promote the stable development of the digital financial market.

7. The digital bond risk assessment system based on blockchain and privacy computing as claimed in claim 1 is characterized in that , the step S6 specifically includes the steps of: Step S61: Intelligent audit and tracing, including deploying AI audit robots to automatically execute: Data integrity verification: Compare the consistency between the hash on the chain and the ciphertext on the cloud; Behavioral pattern analysis: Detecting abnormal data upload behavior, including frequent modifications during non-business hours; Historical tracing: Quickly locate data change records through Merkle Patricia Trie; Step S62: Violation handling, including automatic execution of the smart contract upon discovery of tampering: Minor violations: freeze the enterprise or individual DID permissions for 72 hours; Serious violations: triggering forced redemption of bonds, including liquidation of collateral through DeFi protocols; Judicial intervention: Encrypt the evidence package and transmit it to the chain of custody, initiate legal proceedings, and form a full-chain risk control system of "monitoring-handling-traceability".

8. A digital bond risk assessment system based on blockchain and privacy computing, characterized by: include: The identity verification module is used by participating corporate entities to complete dual identity verification by integrating distributed digital identity (DID) and biometric authentication to ensure that the identity cannot be tampered with and is unique; The system collects enterprise-related data, encrypts it homomorphically, and then stores it in shards on a private cloud. It also generates a composite hash value for on-chain evidence storage and introduces zero-knowledge proof technology to construct a data fingerprint to verify the availability of encrypted data. Smart contracts automatically anchor the spatiotemporal attributes of data to ensure traceability throughout its lifecycle. The model training and deployment module is used by assessment and certification bodies, financial institutions, and regulators to collaboratively train risk assessment models based on secure multi-party computing. The risk assessment model parameters are encrypted and stored in a sharded manner using threshold homomorphic encryption technology. During the risk assessment model deployment phase, a trusted execution environment is built in the cloud to implement closed computation from confidential data input to encryption model inference, and evidence of the correctness of the computation process is generated through zero-knowledge proof. Smart contract trigger module, used to trigger blockchain smart contracts based on assessment results, automatically execute risk-level responses, and store cross-chain evidence of the entire assessment process in judicial and regulatory nodes, supporting multi-party audits and inspections; The continuous monitoring and disposal module is used for comprehensive monitoring and collaborative governance during the bond's lifespan. It implements continuous monitoring across three dimensions and automatically triggers the disposal process based on the type of abnormal data. All operation records are uploaded to the blockchain in real time, forming a closed-loop collaborative governance system among regulators, companies, and investors. The information upload subject verification module is used by the assessment agency to verify the legitimacy of the uploader of corporate information through the distributed digital identity DID, ensuring that the source of the information is consistent with the uploader, and can be traced back through on-chain information to prevent information tampering; The audit and violation handling module is used to build an automated audit and violation handling process, deploy AI audit robots to implement consistency verification of on-chain hashes and cloud ciphertexts, detect abnormal behavior patterns, and trace data changes based on Merkle trees. When data tampering is discovered, the smart contract automatically triggers a graded response: minor violations will freeze account permissions; serious violations will initiate on-chain asset liquidation and link to judicial chain evidence storage, forming a "monitoring-handling-tracing" full-chain risk control.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the digital bond risk assessment method based on blockchain and privacy computing as described in any one of claims 1 to 7 are implemented.

10. A storage medium comprising a stored program, which, when the program is executed, controls the device where the storage medium is located to execute the steps of the digital bond risk assessment method based on blockchain and privacy computing as described in any one of claims 1 to 7.

Images