Data credibility processing method and system based on block chain

Abstract

The invention discloses a block chain-based data credibility processing method and system, and the method comprises the following steps: obtaining equipment data, verifying the equipment data, generating an encrypted verification signature through trusted execution environment equipment, merging the verification signature with original data, and uploading the merged verification signature and original data to a block chain; on the basis of the equipment data, rule judgment and filtering of data verification are carried out through an intelligent contract, the intelligent contract responds to a preset standard to judge the data, or the quality of uploaded data is predicted and analyzed through machine learning, and the quality of uplink data is determined; according to the method, the data source is encrypted and signed through trusted hardware and is stored on the block chain, so that higher data source credibility is provided, and single-point tampering is prevented. And a multi-verification mechanism is combined with the smart contract, a block chain consensus mechanism and out-of-chain data verification, so that multi-dimensional verification of block chain data is ensured, and the limitation of a single verification mode is avoided.

Description

Technical Field

[0001] The present invention relates to the field of blockchain data technology, and in particular to a blockchain-based data credibility processing method and system. Background Art

[0002] The decentralized, tamper-proof and transparent features of blockchain technology are used to ensure the credibility of data. This method is usually used in scenarios where the source, integrity and security of data need to be guaranteed, such as IoT data, financial data, medical data, etc.

[0003] Existing technical problems:

[0004] Data writing efficiency: The data writing speed of blockchain is slow, especially on the public chain. Each node needs to verify the data, which may lead to high latency and cannot adapt to large-scale data processing.

[0005] Storage costs: Data storage in blockchain networks is distributed. As the amount of data surges over time, storage costs may become unaffordable, especially when data is updated frequently.

[0006] Complexity of data quality verification: The blockchain itself does not directly verify the accuracy of the data, but only guarantees the immutability of the data. How to ensure the quality and reliable source of the data on the chain remains a challenge.

[0007] Privacy protection: For some sensitive data (such as medical and health data), the openness of blockchain may bring the risk of privacy leakage. How to protect user privacy while ensuring transparency is still an urgent problem to be solved.

[0008] Smart contract vulnerabilities: Although smart contracts can automate data verification and processing, vulnerabilities or improper design of smart contracts may lead to security risks in the system and affect the processing effect of data credibility.

[0009] Based on these problems, we propose a data credibility processing method and system based on blockchain. Summary of the invention

[0010] In order to solve one of the above technical problems, a data credibility processing method and system based on blockchain is provided. The current blockchain technology can ensure the immutability and transparency of data, but how to ensure the quality, accuracy and reliability of data sources on the blockchain is still a problem to be solved.

[0011] In order to achieve the above objectives, the technical inventions adopted by the present invention are:

[0012] A first aspect: A data credibility processing method based on blockchain, comprising the following steps:

[0013] Obtain device data, verify the device data, generate an encrypted verification signature through a trusted execution environment device, and merge the verification signature with the original data and upload it to the blockchain;

[0014] The acquisition device data is collected through IoT sensors or smart meters. In the initial stage of data collection, a trusted execution environment device is used for source encryption and a digital signature is generated. The signature is protected by a symmetric encryption algorithm.

[0015] Based on the device data, the smart contract is used for data verification rule judgment and filtering. The smart contract judges the data in response to preset standards, or predicts and analyzes the quality of the uploaded data through machine learning to determine the quality of the data on the chain. The preset standards include the legitimacy of the data, scope verification, format requirements and logical consistency;

[0016] The prediction and analysis of the quality of the uploaded data by machine learning specifically includes:

[0017] Perform a preliminary screening of the data through anomaly detection algorithms in machine learning to find outliers;

[0018] Based on the effective data, the data is cleaned and standardized, and the data quality is determined by the data preprocessing model. The anomaly detection algorithm includes Isolation Forest and One-Class SVM, the data preprocessing model includes Z-score standardization and Min-Max normalization, the machine learning includes Isolation Forest algorithm or One-Class SVM, and the Z-score standardization is specifically calculated as follows:

[0019]

[0020] Among them, X is the original data, μ is the data mean, and σ is the standard deviation;

[0021] Based on the credibility and accuracy of the data on the chain, each piece of data is independently verified before being uploaded to the chain through a multiple verification mechanism or blockchain consensus mechanism. The multiple verification mechanism includes:

[0022] Step 301: First level verification - hardware encryption signature verification, which compares the encrypted signature generated by the trusted hardware device with the original data on the blockchain to determine whether the uploaded data is consistent with the data signature generated by the trusted hardware;

[0023] Step 302, second layer verification - data validity check, based on smart contract verification data to determine whether it complies with the rules;

[0024] Step 304: The third layer verification - blockchain network consensus verification, which performs secondary confirmation on the data based on the blockchain consensus mechanism, wherein the blockchain consensus mechanism includes PoW or PoS;

[0025] Construct an off-chain data quality monitoring model, and regularly perform back-testing of the on-chain data according to the off-chain data quality monitoring model, and regularly interact with external systems to check and verify the consistency of on-chain data with the original data. The external system includes a database and an IoT platform. The consistency of the on-chain data with the original data is checked by comparing the encrypted hash value. The specific expression is:

[0026] Hash Blockchain (Data)=Hash External Source (Data);

[0027] According to the off-chain data quality monitoring model, combined with the event listener and Al anomaly detection algorithm on the blockchain, the on-chain data is continuously monitored to verify the results; if the data quality is abnormal or there is a risk of tampering, the early warning mechanism is automatically triggered;

[0028] Based on the verification results, the credibility score of the generated data is determined.

[0029] Preferably, the step of determining and generating a data credibility score based on the verification result specifically includes:

[0030] Based on the AI ​​model, several quality indicators of the data are converted into specific scoring values;

[0031] Provides a real-time data monitoring panel to display the source, verification results, and quality score information of each data point;

[0032] Among them, AI models include regression analysis and classification models.

[0033] Aspect 2: A data credibility processing system based on blockchain, comprising:

[0034] A data acquisition module is used to acquire device data, verify the device data, generate an encrypted verification signature through a trusted execution environment device, and merge the verification signature with the original data and upload it to the blockchain;

[0035] A data verification quality module, used to determine and filter the rules for data verification through smart contracts based on the device data. The smart contracts judge the data in response to preset standards, or predict and analyze the quality of the uploaded data through machine learning to determine the quality of the on-chain data;

[0036] Independent verification module, based on the credibility and accuracy of the data on the chain, through multiple verification mechanisms or blockchain consensus mechanisms, each piece of data is independently verified before being uploaded to the chain.

[0037] The off-chain data quality monitoring module is used to build an off-chain data quality monitoring model, and regularly back-verify the on-chain data according to the off-chain data quality monitoring model, and regularly interact with external systems to check and verify the consistency of on-chain data with the original data.

[0038] The trigger warning module is used to continuously monitor the on-chain data according to the off-chain data quality monitoring model combined with the event listener and Al anomaly detection algorithm on the blockchain to verify the results; if the data quality is abnormal or there is a risk of tampering, the warning mechanism is automatically triggered;

[0039] The credibility scoring module is used to determine the credibility score of the generated data based on the verification results.

[0040] A third aspect: A computer device comprising:

[0041] processor;

[0042] A memory for storing executable instructions;

[0043] Among them, the processor is used to read the executable instructions from the memory and execute the executable instructions to implement the blockchain-based data credibility processing method.

[0044] A fourth aspect: A computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the blockchain-based data credibility processing method.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] 1. The present invention proposes to encrypt and sign the data source through trusted hardware (such as TEE) and store it on the blockchain, providing higher credibility of the data source and preventing single point tampering.

[0047] 2. Multiple verification mechanism: Combining smart contracts, blockchain consensus mechanism and off-chain data verification, it ensures multi-dimensional verification of blockchain data and avoids the limitations of a single verification method.

[0048] 3. AI-driven quality assessment: Using AI (especially machine learning algorithms) to dynamically analyze and predict data quality can intelligently identify potential problems and anomalies, thereby improving the automation level of data credibility monitoring.

[0049] 4. Data quality prediction through machine learning can perform quality screening before data is uploaded and make prediction decisions based on the historical patterns of the data, thereby reducing human intervention and operational errors and significantly improving the accuracy of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flowchart of the blockchain-based data credibility processing method of the present invention;

[0051] Figure 2 This is a module diagram of the blockchain-based data credibility processing system of the present invention.

[0052] Figure 3 It is a schematic diagram of the structure of the computer device of the present invention;

[0053] In the figure, 10 is a computer device; 1002 is a processor; 1004 is a memory; and 1006 is a transmission device. DETAILED DESCRIPTION

[0054] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0055] Embodiment 1:

[0056] In order to effectively solve the complexity of data quality verification, the present invention proposes the following technical invention based on trusted hardware and multiple verification mechanisms. This invention makes full use of the advantages of blockchain and combines the latest hardware trust technology and multiple verification mechanisms to enhance the quality and credibility verification capabilities of data.

[0057] Reference Figure 1 As shown, a data credibility processing method based on blockchain includes the following steps:

[0058] Step 10: Obtain device data, verify the device data, generate an encrypted verification signature through the trusted execution environment device, and merge the verification signature with the original data and upload it to the blockchain;

[0059] In the data generation or collection stage, this application uses the Trusted Execution Environment (TEE) technology to verify the external data source. Trusted hardware (such as Intel's SGX) ensures the confidentiality and integrity of the computing process at the hardware level, ensuring that the data generation process cannot be tampered with.

[0060] The verification process includes:

[0061] Verification Signature=HMAC SHA-256 (Data, Secret Key);

[0062] Among them, Data is the collected data, and Secret Key is the security key provided by the hardware device. The generated Verification Signature is stored in the blockchain to ensure the credibility of the data source and data content;

[0063] Step 20: Based on the device data, the smart contract is used for data verification rule judgment and filtering. The smart contract judges the data in response to the preset standard, or predicts and analyzes the quality of the uploaded data through machine learning to determine the quality of the on-chain data;

[0064] Preset verification rules: In smart contracts, first set the rules for data quality verification, such as the legal scope of data, format requirements, logical consistency, etc.

[0065] For example, assuming that the collected data should be in the range of [0,100], the smart contract will verify whether the incoming data meets this rule.

[0066] Verification logic:

[0067] if(Data≥MinandData≤Max)thenValid,elseInvalid;

[0068] Data is the incoming collected data, Min and Max are the minimum and maximum values ​​of the data respectively;

[0069] Step 30: Based on the credibility and accuracy of the data on the chain, each piece of data is independently verified before being uploaded to the chain through a multiple verification mechanism or a blockchain consensus mechanism. The multiple verification mechanism includes:

[0070] Step 301: First level verification - hardware encryption signature verification, which compares the encrypted signature generated by the trusted hardware device with the original data on the blockchain to determine whether the uploaded data is consistent with the data signature generated by the trusted hardware;

[0071] Step 302, second layer verification - data validity check, based on smart contract verification data to determine whether it complies with the rules;

[0072] Step 304: The third layer verification - blockchain network consensus verification, which performs secondary confirmation on the data based on the blockchain consensus mechanism, wherein the blockchain consensus mechanism includes PoW or PoS;

[0073] In order to enhance the credibility and accuracy of the data, a multiple verification mechanism is introduced to ensure that each piece of data can undergo multiple independent verification steps before being uploaded to the chain.

[0074] The first layer of verification - hardware encryption signature verification: Use the encrypted signature generated by a trusted hardware device to compare with the original data on the blockchain.

[0075] Verification formula:

[0076] HMAC SHA-256 (Data, Secret Key)=Signature from TEE;

[0077] Ensure that the uploaded data is consistent with the data signature generated by the trusted hardware.

[0078] The second layer of verification - data validity check: Use smart contracts to verify whether the data complies with the rules, such as data format and range.

[0079] Third-layer verification - blockchain network consensus verification: Use blockchain consensus mechanisms (such as PoW or PoS) to double-confirm data to ensure that multiple nodes in the network reach consensus and avoid single point failure or tampering;

[0080] Step 40: Build an off-chain data quality monitoring model, regularly back-check and verify the on-chain data according to the off-chain data quality monitoring model, and regularly interact with external systems (such as databases or IoT platforms) to check and verify the consistency of on-chain data with original data;

[0081] In order to ensure the continued credibility of the on-chain data, an off-chain data quality monitoring model is set up to regularly back-check and verify the on-chain data to ensure data consistency.

[0082] Regular backtracking verification: The system will automatically backtrack historical data through the off-chain monitoring system on a regular basis and perform secondary verification through trusted hardware.

[0083] Data consistency check: Regularly interact with external systems (such as databases or IoT platforms) to verify whether the on-chain data is consistent with the original data to ensure that it has not been tampered with.

[0084] For example, cryptographic hash (SHA-256) values ​​are used to compare and check data consistency.

[0085] Hash Blockchain (Data)=Hash External Source (Data);

[0086] Step 50: Continuously monitor the on-chain data according to the off-chain data quality monitoring model combined with the event listener and the Al anomaly detection algorithm on the blockchain to verify the results; if data quality anomalies or risks of tampering are found, the early warning mechanism is automatically triggered;

[0087] Smart contracts automatically repair data according to preset rules (such as deleting unqualified data and replacing abnormal data). The rules for repairing data are executed through smart contracts to ensure that the repair process is transparent and traceable.

[0088] Historical backtracking and verification: Every once in a while, the system will use the blockchain's historical data and external verification mechanism to conduct a full backtracking to ensure that the data always meets quality requirements.

[0089] Step 60: Based on the verification result, determine and generate a data credibility score.

[0090] Specifically: Based on the verification results, the generated data credibility score is determined, specifically including:

[0091] Based on the AI ​​model, several quality indicators of the data are converted into specific scoring values;

[0092] Provides a real-time data monitoring panel to display the source, verification results, and quality score information of each data point;

[0093] Among them, AI models include regression analysis and classification models.

[0094] Based on the verification results of each link, the data credibility score is automatically generated. Through AI models (such as regression analysis and classification models), the quality indicators of the data are converted into specific scoring values, and the credibility of the data is demonstrated based on this.

[0095] Provides a real-time data monitoring panel that displays information such as the source, verification results, and quality score of each data point, helping users understand the credibility status of the data in real time.

[0096] Specifically, the present invention ensures the integrity, accuracy and source credibility of data through hardware, smart contracts, multiple verifications and risk assessments.

[0097] Traditional blockchain data verification usually focuses on preventing data from being tampered with, while the present invention combines the mechanisms of hardware and smart contracts to comprehensively enhance the integrity, validity and transparency of data.

[0098] This invention enables off-chain monitoring and verification, ensuring that historical data will not be distorted by external factors, thus avoiding the risk of data losing credibility over time.

[0099] Embodiment 2

[0100] To solve the above technical problems, based on the first embodiment, another technical solution adopted by the present application is: a data credibility processing method based on blockchain, comprising the following steps:

[0101] Step 1: Data is collected through various sensors or devices (IoT, smart meters, etc.). In the initial stage of data collection, a trusted execution environment (TEE) (such as Intel SGX or AMD SEV) is used for source encryption.

[0102] A digital signature is generated through TEE and protected using a symmetric encryption algorithm (such as HMAC).

[0103] The signature format is:

[0104] Signature Data =HMAC-SHA 256 (Data, Secret Key);

[0105] Among them, Data is the collected original data, and Secret Key is the security key of the hardware device.

[0106] Submit the data and digital signature to the blockchain, and store the signature and data together through smart contracts.

[0107] Examples of storage structures for data and signatures in blockchain include:

[0108] TransactionData = {Data, SignatureData, Timestamp, HashData}, where Data refers to the actual data involved in the transaction, such as the amount, information about the two parties to the transaction, etc.

[0109] SignatureData: This is usually used to verify the authenticity and integrity of the transaction, ensuring that the transaction has not been tampered with.

[0110] Timestamp: This is a mark that records the time when a transaction occurs and is used to determine the order and time of transactions.

[0111] HashData: Hash data is usually used to ensure the integrity of data. The data is converted into a hash value of fixed length through a hash function to facilitate verification of whether the data has been tampered with.

[0112] Verification: Blockchain nodes can verify the matching of data and hardware signatures through smart contracts to ensure that the data has not been tampered with:

[0113] HMAC-SHA256(Data, SecretKey)=SignatureData

[0114] Data:

[0115] This is the data to be processed. In practical applications, this can be any data that needs to be verified and authenticated for integrity, such as user login information, transaction data, etc.

[0116] Secret Key:

[0117] This is a key that only a party with this key can generate and verify signatures. The confidentiality of the key is crucial because if the key is leaked, the security of the data will be compromised.

[0118] Signature Data:

[0119] This is the signature data obtained by processing the Data and Secret Key through the HMAC-SHA256 algorithm. This signature data can be used to verify the integrity and source of the data.

[0120] If there is a match, it indicates that the data came from a trusted source.

[0121] Step 2: Use machine learning (ML) to predict and analyze the quality of uploaded data.

[0122] Design a quality prediction model based on supervised learning, train it on historical data, and learn various data patterns (such as volatility of sensor collected data, data noise, etc.).

[0123] Data processing: Anomaly detection: Preliminary screening of data to find outliers is performed through anomaly detection algorithms in machine learning (such as IsolationForest, One-ClassSVM). The algorithm is based on specific thresholds, deviations, or the prediction results of other algorithms (such as regression models) for analysis.

[0124] Data standardization and cleaning: Clean and standardize valid data. Standardize data through data preprocessing models (such as Z-score standardization or Min-Max normalization) to ensure data quality.

[0125] Suppose we use Z-score for normalization:

[0126]

[0127] Among them, X is the original data, μ is the data mean, and σ is the standard deviation.

[0128] Quality Assessment:

[0129] Evaluate data accuracy by comparing it to external data sources (e.g., National Meteorological Service, known standard datasets, etc.).

[0130] Use time series-based algorithms to verify the validity of data collection and submission time to ensure that the data is not outdated or lost.

[0131] Smart contracts automatically execute the data quality verification process in the blockchain. When the data quality is judged to be abnormal, the smart contract will refuse to allow the data to enter the blockchain or perform early warning processing.

[0132] Automated data quality verification is achieved through smart contracts. The conditional logic in the smart contract will determine whether the data meets the quality requirements (such as accuracy, timeliness, etc.).

[0133] Smart contract code (Solidity) example:

[0134] functionvalidateData(uint256timestamp, uint256accuracy) publicreturns(bool){

[0135] if(timestamp>now-1hours&&accuracy>90){

[0136] returntrue;

[0137] }else{

[0138] revert("Data is not valid.");

[0139] }

[0140] }

[0141] This code checks whether the timeliness (whether it is within the past hour) and accuracy (whether it is more than 90%) of the data meet the requirements. If not, the data will be rejected from entering the blockchain.

[0142] Step 3: Blockchain data verification: In addition to the hardware-level signature of the data and basic verification of the smart contract, a multi-verification mechanism will periodically adopt a consensus mechanism to further confirm the credibility of the data.

[0143] When data is uploaded to the chain, in addition to automatic verification by smart contracts, nodes perform secondary confirmation based on the blockchain consensus mechanism (such as PoW or PoS). Each node performs a weighted average calculation of the verification value of the data to ensure that multiple nodes verify the data in a consistent manner:

[0144]

[0145] Among them, V i is the verification value of the i-th node, w i is the node weight (such as reputation, computing power, etc.), Vfinal This is the final verification result.

[0146] Introduce cross-chain technology or Oracles to connect other blockchains and traditional databases to verify the authenticity of off-chain data. For example, through the oracle to verify the external environment (such as weather data, currency exchange rates, etc.) to ensure that the data on the chain is consistent with the actual situation.

[0147] Step 4: All requests to access blockchain data must pass multi-layer authentication and authorization, including passwords, hardware authentication, fingerprint recognition, etc. Combined with the "read-only" nature of blockchain data and multi-factor authentication, ensure that every data access request must pass authentication and permission review to prevent malicious data tampering.

[0148] Use multi-factor authentication including hardware keys (such as USB keys), biometrics (such as fingerprints, facial recognition) and dynamic tokens to further ensure that data access and update processes are protected from unauthorized attacks.

[0149] Step 5: When it is found that the data does not meet the quality standards or there is a risk of tampering, the repair process is automatically triggered to ensure that the credibility of the data is not affected.

[0150] Data update operations are triggered through smart contracts to replace invalid or problematic data records.

[0151] The system will issue alerts to all nodes to warn of possible problems and intervene.

[0152] Innovation and breakthrough of the solution:

[0153] Introduction of trusted hardware: Combined with the hardware-level trusted execution environment (TEE), the hardware encryption signature provides source credibility verification for the data. This not only ensures that the data cannot be tampered with, but also ensures the reliability of the data source, breaking through the limitations of the current verification mechanism that relies on the blockchain itself.

[0154] Multiple verification mechanisms: Through multiple verification methods such as data generation, smart contracts, and consensus mechanisms, data can undergo strict multi-layer verification before being uploaded to the chain, which improves the credibility of the data and reduces the potential loopholes of a single verification method.

[0155] Off-chain monitoring and continuous verification: Through regular off-chain backtracking verification, the consistency of historical data is ensured, avoiding possible changes and distortions in data over time.

[0156] Smart contracts and risk assessment: Combining the automated verification and risk assessment mechanisms of smart contracts improves the automation of data management, reduces the risk of human operations, and improves the transparency of the entire system.

[0157] Step 6: Further improve the transparency and credibility of data processing by introducing data visualization and risk assessment modules.

[0158] Data visualization: Help users understand the credibility of data by analyzing and displaying each data source, verification status, and data flow in the blockchain.

[0159] Risk assessment: Generate a risk report on data credibility based on historical data verification results and retrospective inspection results, and provide an early warning mechanism to promptly identify potential risks.

[0160] Embodiment three:

[0161] In order to solve the above technical problems, based on the second embodiment, another technical solution adopted by this application is: a data credibility processing method based on blockchain, comprising the following steps:

[0162] Step 4: Zero Trust Architecture and Multi-Factor Authentication:

[0163] Step 4.1 Zero Trust Architecture:

[0164] Goal: Ensure that every request for data access must be strictly authenticated, without relying on traditional trust models, to prevent unauthorized access and data tampering.

[0165] Adopting the core principles of Zero Trust architecture, any request (whether internal or external) is not trusted by default, but goes through multiple layers of authentication.

[0166] All access requests are subject to multi-factor authentication, such as: hardware authentication (such as USB keys, physical authentication devices); biometrics (such as fingerprints, facial recognition).

[0167] Step 4.2:

[0168] Goal: Ensure data access security by adding an authentication layer.

[0169] Use multiple authentication methods such as hardware keys (such as USB Key), biometrics (fingerprint, facial recognition) and dynamic tokens (such as Google Authenticator, SMS verification code, etc.) to ensure that each access request is verified.

[0170] The user enters a username and password.

[0171] The system sends a verification code to the user's registered mobile phone or email address.

[0172] Users perform secondary authentication using a hardware key or biometrics.

[0173] After the system verification is passed, the user is authorized to access data or perform operations.

[0174] Specific:

[0175] Intelligent data quality screening automates data quality processing through machine learning and achieves automated quality control through smart contracts.

[0176] A multiple verification mechanism (combining internal and external blockchain) is adopted to enhance the credibility of data and the transparency of the system through consensus mechanism and external data source verification.

[0177] The security of data access is enhanced through zero-trust architecture and multi-factor authentication to ensure that data is not maliciously tampered with or illegally accessed. Compared with the prior art, the present invention can handle data credibility issues more efficiently, more intelligently, and more securely, and has stronger practicality and innovation.

[0178] Embodiment 4:

[0179] like Figure 2 As shown, a data credibility processing system based on blockchain includes:

[0180] A data acquisition module is used to acquire device data, verify the device data, generate an encrypted verification signature through a trusted execution environment device, and merge the verification signature with the original data and upload it to the blockchain;

[0181] A data verification quality module, used to determine and filter the rules for data verification through smart contracts based on the device data. The smart contracts judge the data in response to preset standards, or predict and analyze the quality of the uploaded data through machine learning to determine the quality of the on-chain data;

[0182] Independent verification module, based on the credibility and accuracy of the data on the chain, through multiple verification mechanisms or blockchain consensus mechanisms, each piece of data is independently verified before being uploaded to the chain.

[0183] The off-chain data quality monitoring module is used to build an off-chain data quality monitoring model, and regularly back-verify the on-chain data according to the off-chain data quality monitoring model, and regularly interact with external systems to check and verify the consistency of on-chain data with the original data.

[0184] The trigger warning module is used to continuously monitor the on-chain data according to the off-chain data quality monitoring model combined with the event listener and Al anomaly detection algorithm on the blockchain to verify the results; if the data quality is abnormal or there is a risk of tampering, the warning mechanism is automatically triggered;

[0185] The credibility scoring module is used to determine and generate a data credibility score based on the verification results. A blockchain-based data credibility processing system includes:

[0186] A task acquisition module is used to acquire historical data during the vehicle journey, perform edge computing and data preprocessing on the historical data, and obtain target data;

[0187] A feature extraction module, used for extracting features from the target data to obtain input features of the target data, wherein the feature extraction includes time series feature extraction, environmental feature extraction, and behavior pattern extraction;

[0188] A dynamic risk assessment module is used to construct a dynamic risk assessment model, and train the dynamic risk assessment model according to the input characteristics of the target data, wherein the dynamic risk assessment model predicts dynamic risks using an ARIMA model and an LSTM network model;

[0189] A risk scoring module, used to generate a risk score according to the risk value output by the dynamic risk assessment model, set a threshold according to the risk score, trigger a real-time warning when the threshold is exceeded, and evaluate the safety level of the current driving state;

[0190] The driving strategy optimization module is used to adjust the model warning parameters according to real-time data and risk assessment results, and optimize the driver's behavior pattern through the Q-learning algorithm.

[0191] The foregoing Figure 1 The various variations and specific examples of a blockchain-based data credibility processing method in Example 1 are also applicable to a blockchain-based data credibility processing system in this embodiment. Through the above detailed description of a blockchain-based data credibility processing method, those skilled in the art can clearly understand the implementation method of a blockchain-based data credibility processing system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0192] Embodiment 5

[0193] An embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a blockchain-based data credibility processing method provided in the above method embodiment.

[0194] Figure 3 A schematic diagram of the hardware structure of a device for implementing a blockchain-based data credibility processing method provided in an embodiment of the present application is shown. The device may participate in or include the apparatus or system provided in an embodiment of the present application. Figure 3As shown, the computer device 10 may include one or more processors 1002 (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations shown.

[0195] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer device 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0196] The memory 1004 can be used to store software programs and modules of application software, such as a program instruction / data storage device corresponding to a data credibility processing method based on blockchain in an embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, that is, implementing the above-mentioned method. The memory 1004 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0197] The transmission device 1006 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer device 10. In one example, the transmission device 1006 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 1006 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0198] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer device 10 (or mobile device).

[0199] Embodiment 6

[0200] An embodiment of the present application also provides a computer-readable storage medium, which can be set in a server to store at least one instruction or at least one program related to a blockchain-based data credibility processing method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement a blockchain-based data credibility processing method provided in the above method embodiment.

[0201] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0202] Embodiment 7

[0203] The embodiment of the present invention also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes a data credibility processing method based on blockchain provided in the above various optional embodiments.

[0204] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0205] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0206] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0207] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

[0208] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A data credibility processing method based on blockchain, characterized in that: The following steps are involved: Obtain device data, verify the device data, generate an encrypted verification signature through a trusted execution environment device, and merge the verification signature with the original data and upload it to the blockchain; Based on the device data, the smart contract is used for data verification rule judgment and filtering. The smart contract judges the data in response to the preset standards, or predicts and analyzes the quality of the uploaded data through machine learning to determine the quality of the data on the chain; Based on the credibility and accuracy of the data on the chain, each piece of data is independently verified before being uploaded to the chain through a multiple verification mechanism or blockchain consensus mechanism. The multiple verification mechanism includes: Step 301, first layer verification - hardware encryption signature verification; Step 302, second level verification - data validity check; Step 304, third layer verification - blockchain network consensus verification; Construct an off-chain data quality monitoring model, regularly back-verify the on-chain data according to the off-chain data quality monitoring model, and regularly interact with external systems to check and verify the consistency of on-chain data with original data; According to the off-chain data quality monitoring model, combined with the event listener and Al anomaly detection algorithm on the blockchain, the on-chain data is continuously monitored to verify the results; if the data quality is abnormal or there is a risk of tampering, the early warning mechanism is automatically triggered; Based on the verification results, the credibility score of the generated data is determined.

2. The method according to claim 1, characterized in that: The device data is collected through IoT sensors or smart meters. In the initial stage of data collection, a trusted execution environment device is used to perform source encryption and generate a digital signature, which is protected by a symmetric encryption algorithm.

3. The method according to claim 1, characterized in that: The preset standards include data legitimacy, scope verification, format requirements and logical consistency; The prediction and analysis of the quality of the uploaded data by machine learning specifically includes: Perform a preliminary screening of the data through anomaly detection algorithms in machine learning to find outliers; Based on the effective data, the data is cleaned and standardized, and the data quality is determined by standardizing the data through a data preprocessing model, wherein the anomaly detection algorithm includes Isolation Forest and One-Class SVM, and the data preprocessing model includes Z-score standardization and Min-Max normalization.

4. The method according to claim 1, characterized in that: The multiple verification mechanism includes: Step 301: First level verification - hardware encryption signature verification, which compares the encrypted signature generated by the trusted hardware device with the original data on the blockchain to determine whether the uploaded data is consistent with the data signature generated by the trusted hardware; Step 302, second layer verification - data validity check, based on smart contract verification data to determine whether it complies with the rules; Step 304: The third layer verification - blockchain network consensus verification, performs secondary confirmation on the data based on the blockchain consensus mechanism, wherein the blockchain consensus mechanism includes PoW or PoS.

5. The method according to claim 1, characterized in that: The external system includes a database and an IoT platform. The consistency between the on-chain data and the original data is checked and verified by comparing the encrypted hash values. The specific expression is: Hash Blockchain (Data)=Hash ExternalSource (Data)。 6. The method according to claim 3, characterized in that: The machine learning includes an isolation forest algorithm or a One-Class SVM, and the Z-score is standardized. The specific calculation formula is: Among them, X is the original data, μ is the data mean, and σ is the standard deviation.

7. The method according to claim 1, characterized in that: The step of determining the generated data credibility score based on the verification result specifically includes: Based on the AI ​​model, several quality indicators of the data will be converted into specific scoring values; Provides a real-time data monitoring panel to display the source, verification results, and quality score information of each data point; Among them, AI models include regression analysis and classification models.

8. A data credibility processing system based on blockchain, applied to the data credibility processing method based on blockchain as claimed in any one of claims 1 to 7, characterized in that: include: A data acquisition module is used to acquire device data, verify the device data, generate an encrypted verification signature through a trusted execution environment device, and merge the verification signature with the original data and upload it to the blockchain; A data verification quality module, used to determine and filter the rules for data verification through smart contracts based on the device data. The smart contracts judge the data in response to preset standards, or predict and analyze the quality of the uploaded data through machine learning to determine the quality of the on-chain data; Independent verification module, based on the credibility and accuracy of the data on the chain, through multiple verification mechanisms or blockchain consensus mechanisms, each piece of data is independently verified before being uploaded to the chain. The off-chain data quality monitoring module is used to build an off-chain data quality monitoring model, and regularly back-verify the on-chain data according to the off-chain data quality monitoring model, and regularly interact with external systems to check and verify the consistency of on-chain data with the original data. Triggering an early warning module, which is used to continuously monitor the on-chain data according to the off-chain data quality monitoring model combined with the event listener and Al anomaly detection algorithm on the blockchain to verify the results; If data quality abnormalities or risks of tampering are found, the early warning mechanism will be automatically triggered; The credibility scoring module is used to determine the credibility score of the generated data based on the verification results.

9. A computer device, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the blockchain-based data credibility processing method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the blockchain-based data credibility processing method as described in any one of claims 1 to 7.

Images