Certificate authenticity verification method based on credible block chain big data evaluation

Abstract

The invention discloses a credential authenticity verification method based on credible block chain big data evaluation, and relates to the technical field of credential authenticity verification methods, and the method comprises the following steps: S1, collecting credential data from multiple sources, covering multiple formats and multiple channels, integrating specifications, and enabling the integrity rate to exceed 95%, S2, embedding data into a block chain, carrying out Hash salting encryption, and storing according to a consensus mechanism, s3, carrying out big data feature analysis, mining association, modeling by fusing internal and external features, and carrying out automatic updating optimization; and S4, comprehensively verifying voucher and priori basic information, and comparing the model with the history. According to the method provided by the invention, the verification accuracy is more than 95%, the authenticity of the voucher is accurately identified, block chain encryption ensures data security, tampering-free tracing is realized, big data analysis is combined with multi-source data and internal and external characteristics, comprehensive evaluation is realized, the automatic process is efficient, a user feedback optimization model is realized, the verification reliability is improved, and the use order of the voucher in each field is maintained.

Description

Technical Field

[0001] The present invention relates to the technical field of credential authenticity verification, and in particular to a credential authenticity verification method based on trusted blockchain big data evaluation. Background Art

[0002] In today's digital age, various types of vouchers are widely used in many fields such as commerce, finance, and government affairs, such as invoices, contracts, and certificates. They are important bases for the orderly development of economic activities and social affairs. However, with the rapid development of information technology, the means of forging vouchers are becoming increasingly complex and diverse, and their authenticity verification faces many severe challenges.

[0003] Traditional voucher verification methods often rely on manual review or simple database comparison. Manual review is inefficient, not only consuming a lot of manpower and time, but also easily affected by the subjective factors of the auditors, making it difficult to ensure the accuracy and consistency of the audit results. For example, in the field of financial reimbursement, auditors need to check each invoice information one by one, including invoice code, number, amount, invoicing unit, etc. Faced with a large amount of invoice data, fatigue and negligence are inevitable, thus letting go of some false invoices.

[0004] Although the verification method based on database comparison has improved efficiency to a certain extent, it still has problems such as untimely data updates, limited data sources, and lack of in-depth analysis of the semantics and logical relationships of vouchers. Once the counterfeiter uses information not included in the database or tampers with the content of the voucher to make it conform to the database format requirements, it can easily avoid verification. For example, some fake invoices may use the real invoice format and number, but make false entries in the invoice content, such as fictitious transaction items, exaggerated transaction amounts, etc. It is difficult for traditional database comparison methods to detect such hidden fraud.

[0005] At the same time, with data interaction and sharing becoming increasingly frequent, the cross-platform and cross-institutional circulation of credentials has become the norm. The lack of unified verification standards and trust mechanisms between different platforms and institutions makes it difficult to effectively guarantee the authenticity of credentials throughout the entire circulation chain. This not only provides opportunities for criminals, but also seriously affects market order and social credibility.

[0006] In addition, with the rise of big data technology, although the amount of data has exploded, how to extract valuable information from massive, multi-source, and heterogeneous big data for credential authenticity verification is still a problem that needs to be solved. Moreover, problems such as data noise, data redundancy, and data privacy protection in big data have also brought new challenges to credential verification. For example, when a web crawler collects data related to credentials, it may obtain a large amount of irrelevant or erroneous information, which will not only interfere with the verification process, but also lead to misjudgment.

[0007] The emergence of blockchain technology provides new ideas and possibilities for solving these problems. Its distributed ledger, non-tamperability, and traceability can provide a safe and reliable storage and sharing environment for credential data. However, the current method of effectively combining blockchain technology with big data analysis to verify the authenticity of credentials is not mature enough, and there is a lack of systematic, efficient, and accurate verification systems and methods. Therefore, it is of great practical significance to develop a credential authenticity verification method based on trusted blockchain big data evaluation to cope with the increasingly complex credential counterfeiting environment and ensure the normal operation and healthy development of business activities in various fields. Summary of the invention

[0008] The present invention proposes a credential authenticity verification method based on trusted blockchain big data evaluation to solve the problems mentioned in the above-mentioned prior art.

[0009] In order to achieve the above object, the present invention adopts the following technical solution: a method for verifying the authenticity of a credential based on trusted blockchain big data evaluation, comprising the following steps:

[0010] S1. Multi-source data collection steps: Use web crawler technology to capture public data related to vouchers from the Internet platform, use data interfaces to connect to various databases to extract structured voucher data, use OCR recognition technology to process paper or image format vouchers to obtain text information, and the collected data includes all key elements of the voucher. In addition, data from different sources are integrated and standardized to build a comprehensive and standardized voucher data set;

[0011] S2. Blockchain data embedding step: Perform hash operation on the collected credential data to obtain a hash value of fixed length, and construct transaction information with the hash value and the metadata of the credential, including the credential number, generation time, and source information, in accordance with the protocol specification of the blockchain. The transaction information is broadcast to multiple nodes in the blockchain network. Through the consensus mechanism of the nodes, the transaction information is packaged into blocks and added to the blockchain. The hash operation adopts the formula H=SHA256(data+salt), where H is the hash value, data is the credential data, and salt is a randomly generated salt value, and the length of the salt value is not less than 128 bits;

[0012] S3. Big data feature analysis steps: extract credential data from the blockchain, use data mining algorithms to mine frequent patterns and association rule features in the credential data, and use decision trees and neural network machine learning algorithms to learn and model the authenticity features of the credential; cross-validation technology is used in the model training process, and when constructing the credential authenticity feature model, the feature fusion formula F = ω1×Ⅰ+ω2×E is used, where F is the fused feature vector, I is the internal feature vector of the credential, E is the external environment feature vector, and ω1 and ω2 are weight coefficients;

[0013] S4. Comprehensive verification step: Get the credential to be verified and verify its basic information first; then compare the credential data with the model constructed in the big data feature analysis step, analyze the matching degree between the features of the credential data and the real credential feature model, and compare the historical credential data of the same type on the blockchain horizontally, using the matching degree calculation formula Where M is the matching degree, m i is the matching score of the i-th feature, ranging from 0 to 1, ω i The weight of the ith feature is set according to the feature importance, and a verification report containing the verification basis and difference analysis details is generated;

[0014] S5. User interaction and feedback step: Provide users with an operation interface where they can upload the credentials to be verified and view the verification progress and result report. The interface response time is less than 2 seconds and supports multi-language display. After receiving feedback, the system will incorporate the feedback information as a new data sample into the model training process in the big data feature analysis step.

[0015] Furthermore, in the S1 multi-source data collection step, an intelligent screening algorithm is used for the data collected by the web crawler, and the data highly relevant to the credential authenticity verification is screened out according to the pre-set credential keyword library and data relevance evaluation model. The data relevance evaluation model is set as Where R is the correlation score, k j is the weight of the jth keyword, s j is the frequency of occurrence of the jth keyword in the data. This formula is used to quantify the correlation between the data and the authenticity verification of the credential. At the same time, a reasonable access frequency limit is set for the web crawler. The access frequency limit can be dynamically adjusted according to the traffic carrying capacity of the website.

[0016] Furthermore, in the S2 blockchain data embedding step, salting is used for the hash operation, and the salt value is randomly generated to enhance the security of the hash value and reduce the risk of hash collision. The probability of hash collision is lower than 10 to the power of -60, and when constructing transaction information, the credential data is encrypted and an asymmetric encryption algorithm is used to protect sensitive information. The encryption strength meets industry security standards. The security strength evaluation formula of the encrypted information is assumed to be S=log2(N), where S is the security strength and N is the size of the key space of the encryption algorithm.

[0017] Furthermore, in the S3 big data feature analysis step, when constructing the credential authenticity feature model, in addition to conventional credential data features, external environment data features are also incorporated, including industry policy and regulatory change data related to the credential, macroeconomic data, etc. These external features are combined with the internal features of the credential through feature fusion technology. In the feature extraction process, the time series analysis formula T = α × T is used for the external environment data features. prev +β×E curr Where T is the time series feature value after processing, T prev is the eigenvalue of the previous moment, E curr is the external environment data value at the current moment, and α and β are smoothing coefficients.

[0018] Furthermore, in the S4 comprehensive verification step, when suspicious points are found in the credential to be verified, a traceability algorithm is used to trace back the historical records of the credential data on the blockchain, track the generation, modification and circulation of the credential data, and analyze the abnormalities in its historical trajectory; the traceability credibility evaluation formula is set as Where C is the traceability credibility, V is the number of valid traceability information, and U is the number of invalid traceability information.

[0019] Furthermore, in the S5 user interaction and feedback step, when the user objects to the verification result and provides additional evidence, the system starts the re-verification process, re-collects the additional data related to the voucher, merges the additional data with the original data, and then performs the big data feature analysis and comprehensive verification steps again; the calculation formula of the user feedback influence factor is assumed to be Where I is the user feedback impact factor, Q is the number of valid information in user feedback, and P is the number of invalid information in user feedback.

[0020] Furthermore, in the S1 multi-source data acquisition step, if the access to the data source is limited or the data acquisition fails, the backup data source is automatically switched to or a data recovery mechanism is used. The data recovery mechanism recovers part of the lost or damaged data through local cache data and data repair algorithm. The data recovery effect evaluation formula is: Where E is the data recovery effect, D recis the amount of data recovered, D lost is the amount of data lost.

[0021] Furthermore, in the S4 comprehensive verification step, when the verification result determines that the voucher is false, the system automatically generates early warning information and sends it to relevant regulatory agencies, enterprises or individuals. The early warning information value assessment formula is V=λ×R+μ×I, where V is the value of the early warning information, R is the risk assessment score, I is the importance score of the related party, and λ and μ are weight coefficients.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] In terms of accuracy, through the multi-source data collection step, various types of voucher data are widely collected, and advanced algorithms and models in the big data feature analysis step are used, such as feature fusion technology to combine the internal features of the voucher with the external environment features to build a highly accurate authenticity assessment model. The accuracy of its verification results is not less than 95%, which is a qualitative leap compared to traditional verification methods. It can effectively identify various complex counterfeiting methods and greatly reduce the risk of false vouchers passing through.

[0024] From a security perspective, the blockchain data embedding step uses hash operations and salt processing and asymmetric encryption algorithms. The probability of hash collision is less than 10 to the power of -60, and the encryption strength meets the industry's high standards, ensuring the security of credential data during storage and transmission, and effectively preventing data tampering and leakage. Even in the face of malicious attacks or data theft attempts, it can effectively protect the integrity and confidentiality of credential information, providing a reliable basic guarantee for the authenticity verification of credentials.

[0025] In terms of efficiency improvement, this method realizes an automated verification process. In the user interaction and feedback step, after the user uploads the voucher to be verified, the system can respond quickly, with the interface response time less than 2 seconds, and complete the verification and generate a detailed report in a short time. Compared with traditional manual review or simple database comparison methods, it greatly shortens the verification time and improves business processing efficiency, especially when processing a large amount of voucher data. It can effectively save labor costs and time costs and improve the operational efficiency of enterprises and institutions.

[0026] In addition, the method has good self-optimization capabilities. The effective utilization rate of user feedback information reaches more than 90%. The system can continuously update and optimize the model based on user feedback and new blockchain data, so that it can adapt to the ever-changing means of credential fraud and market environment, and always maintain efficient and accurate verification performance, laying a solid foundation for long-term guarantee of credential authenticity, and promoting the healthy and orderly development of multiple fields such as commercial transactions and government services. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a schematic block diagram of a credential authenticity verification method based on trusted blockchain big data evaluation proposed in the present invention. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0030] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, and it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0031] Reference Figure 1 :A credential authenticity verification method based on trusted blockchain big data evaluation, comprising the following steps:

[0032] S1. Multi-source data collection steps: Use web crawler technology to capture public data related to vouchers from the Internet platform, use data interfaces to connect to various databases to extract structured voucher data, and use OCR recognition technology to process paper or image format vouchers to obtain text information. The collected data covers all key elements of the voucher, and the data collection completeness rate reaches more than 95%. In addition, data from different sources are integrated and standardized, and the format uniformity of the processed data reaches more than 98%, so as to build a comprehensive and standardized voucher data set.

[0033] S2. Blockchain data embedding step: Hash the collected credential data to obtain a fixed-length hash value, and construct transaction information with the hash value and the metadata of the credential, such as the credential number, generation time, source, etc., according to the protocol specification of the blockchain. The transaction information is broadcast to multiple nodes in the blockchain network. Through the consensus mechanism of the nodes, such as proof of work or proof of equity mechanism, the transaction information is packaged into blocks and added to the blockchain to ensure the immutability and traceability of the data. The success rate of nodes participating in the consensus in the blockchain network is not less than 90%. Among them, the hash operation adopts the formula H=SHA256(data+salt), where H is the hash value, data is the credential data, and salt is a randomly generated salt value. The length of the salt value is not less than 128 bits. The probability of hash collision is greatly reduced by adding salt to ensure data security.

[0034] S3. Big data feature analysis steps: extract credential data from the blockchain, use data mining algorithms to mine frequent patterns, association rules and other features in the credential data, for example, analyze the association between specific fields in different types of credentials, and use machine learning algorithms, such as decision trees and neural networks, to learn and model the authenticity features of the credentials. Cross-validation technology is used in the model training process, and the training accuracy rate reaches more than 90%. The model can be automatically updated and optimized according to new blockchain data, and the update cycle can be set to 1 to 7 days according to the frequency of data changes. When constructing the credential authenticity feature model, the feature fusion formula F = ω1×Ⅰ+ω2×E is used, where F is the fused feature vector, I is the internal feature vector of the credential, and E is the external environment feature vector (such as industry policy and regulation change data, macroeconomic data and other feature vectors). ω1 and ω2 are weight coefficients, which can be determined according to the importance of the data and the model training effect. After incorporating external features, the comprehensive evaluation accuracy of the model is increased by more than 10%.

[0035] S4. Comprehensive verification step: Get the credential to be verified, first verify its basic information, such as checking whether the credential format conforms to the standard format template, whether the digital signature is verifiable, etc. The accuracy of basic information verification reaches more than 98%; then compare the credential data with the model constructed in the big data feature analysis step, analyze the matching degree between the features of the credential data and the real credential feature model, and combine the historical credential data of the same type on the blockchain for horizontal comparison, such as comparing the distribution of key data of the same period and the same type of credentials, and comprehensively judge the authenticity of the credential from multiple dimensions. Use the matching degree calculation formula Where M is the matching degree, m i is the matching score of the i-th feature, ranging from 0 to 1, ω i is the weight of the ith feature, which is set according to the feature importance. The accuracy of the final verification result is not less than 95%, and a verification report containing detailed contents such as verification basis and difference analysis is generated.

[0036] S5. User interaction and feedback step: Provide users with an operation interface where they can upload the credentials to be verified and view the verification progress and result report. The interface response time is less than 2 seconds and supports multi-language display. Users can evaluate and provide feedback on the verification results. After receiving the feedback, the system will incorporate the feedback information as a new data sample into the model training process in the big data feature analysis step to continuously improve the accuracy of the model and the reliability of the verification method. The effective utilization rate of user feedback information reaches more than 90%.

[0037] In the multi-source data collection step S1 of the present invention, an intelligent screening algorithm is used for the data collected by the web crawler, and the data highly relevant to the credential authenticity verification is screened out according to the pre-set credential keyword library and data relevance evaluation model, and the screening accuracy reaches more than 95%. Assume that the data relevance evaluation model is Where R is the correlation score, k j is the weight of the jth keyword, s j is the frequency of occurrence of the jth keyword in the data. This formula is used to quantify the correlation between the data and the authenticity verification of the credential. At the same time, a reasonable access frequency limit is set for the web crawler to avoid excessive access pressure on the target website. The access frequency limit can be dynamically adjusted according to the traffic carrying capacity of the website.

[0038] In the S2 blockchain data embedding step described in the present invention, salting is used for hash operations. The salt value is randomly generated and has sufficient length and complexity to enhance the security of the hash value and reduce the risk of hash collision. The probability of hash collision is less than 10 to the power of -60. When constructing transaction information, the credential data is encrypted and an asymmetric encryption algorithm is used to protect sensitive information. The encryption strength meets industry security standards. Suppose the security strength evaluation formula of encrypted information is S=log2(N), where S is the security strength and N is the key space size of the encryption algorithm. The security of encrypted information is evaluated by this formula to ensure the security of data during storage and transmission, and prevent data leakage and tampering.

[0039] In the S3 big data feature analysis step of the present invention, when constructing the credential authenticity feature model, in addition to the conventional credential data features, external environment data features are also included, such as industry policy and regulation change data related to the credential, macroeconomic data, etc. These external features are combined with the internal features of the credential through feature fusion technology, so that the model can more comprehensively evaluate the authenticity of the credential. After incorporating external features, the comprehensive evaluation accuracy of the model is increased by more than 10%. In the feature extraction process, the time series analysis formula T = α × T is used for the external environment data features. prev +β×E curr Where T is the time series feature value after processing, T prev is the eigenvalue of the previous moment, E curr is the external environment data value at the current moment, α and β are smoothing coefficients, which can be determined according to the volatility and importance of the data, so as to better capture the impact of the changing trend of external environment data on the authenticity of the voucher.

[0040] In the S4 comprehensive verification step of the present invention, when suspicious points are found in the credential to be verified, a traceability algorithm is used to trace back the historical records of the credential data on the blockchain, track the generation, modification and circulation of the credential data, and further determine the authenticity of the credential by analyzing the abnormalities in its historical trajectory. The information completeness of the traceability query reaches more than 90%, and the traceability result is included in the final verification report as an important basis. Suppose the traceability credibility evaluation formula is Among them, C is the traceability credibility, V is the number of valid traceability information, and U is the number of invalid traceability information. This formula is used to evaluate the credibility of the traceability results, providing a more reliable basis for comprehensively judging the authenticity of the voucher.

[0041] In the S5 user interaction and feedback step of the present invention, when the user raises an objection to the verification result and provides supplementary evidence, the system starts the re-verification process, re-collects the supplementary data related to the voucher, merges the supplementary data with the original data, and then performs big data feature analysis and comprehensive verification steps again. The accuracy of the re-verification result is not less than 95%, and the system records the user's objection and re-verification process to provide a reference case for subsequent model optimization. Assume that the calculation formula for the user feedback impact factor is Among them, I is the user feedback impact factor, Q is the number of valid information in user feedback, and P is the number of invalid information in user feedback. This formula is used to quantify the influence of user feedback on model optimization, so as to better utilize user feedback information to improve system performance.

[0042] In the S1 multi-source data acquisition step of the present invention, if the access to the data source is restricted or the data acquisition fails, the system automatically switches to the backup data source or uses the data recovery mechanism. The switching success rate of the backup data source reaches more than 90%. The data recovery mechanism recovers some lost or damaged data through local cache data and data repair algorithm. The data recovery rate reaches more than 80%, ensuring the continuity and stability of the data acquisition process. Suppose the data recovery effect evaluation formula is Where E is the data recovery effect, D rec is the amount of data recovered, D lost is the amount of lost data, and this formula is used to evaluate the effectiveness of the data recovery mechanism to ensure the integrity of data collection.

[0043] In the S4 comprehensive verification step of the present invention, when the verification result determines that the voucher is false, the system automatically generates an early warning message and sends it to the relevant regulatory agency, enterprise or individual. The early warning information includes the false details of the voucher, the scope and degree of the risk involved, possible related parties, etc. The accuracy of sending the early warning information reaches more than 98%, and the sending method includes multiple channels such as e-mail, text message, and system message push, so that the relevant parties can take timely countermeasures to reduce the risks and losses caused by false vouchers. Suppose the early warning information value evaluation formula is V=λ×R+μ×I, where V is the value of the early warning information, R is the risk assessment score, which is determined according to the size of the risk that the false voucher may bring, I is the importance score of the related party, which is determined according to the importance of the related parties involved, λ and μ are weight coefficients, which can be adjusted according to actual needs. The value of the early warning information is evaluated by this formula so that the relevant parties can better pay attention to and handle the early warning information.

[0044] This credential authenticity verification method based on trusted blockchain big data evaluation operates collaboratively through a series of closely connected links.

[0045] In the multi-source data collection stage, we give full play to the advantages of web crawler technology to accurately locate and capture public data related to vouchers in the huge and complex Internet environment, such as obtaining industry standard information from authoritative official websites and transaction data from professional business platforms. Through data interfaces, we establish stable connections with various databases and deeply extract structured voucher data such as internal financial data and business transaction data of the enterprise. For vouchers in paper or image formats, we use OCR recognition technology to convert them into text information that can be analyzed, covering the core elements of the voucher in all aspects. In this process, the intelligent screening algorithm uses the preset voucher keyword library and the accurate data correlation evaluation model to efficiently screen out data that is highly consistent with the authenticity verification of the voucher, effectively ensuring the quality and effectiveness of the data and laying a solid foundation for subsequent analysis and verification.

[0046] The blockchain data embedding process is crucial. The collected credential data is hashed to generate a unique and highly secure hash value. At the same time, the metadata of the credential and the hash value are integrated to construct transaction information, which is then widely disseminated in the blockchain network. Many nodes verify and package the transaction information with the help of consensus mechanisms such as proof of work or proof of equity, and finally form blocks to be added to the blockchain. In this process, the salting of hash operations and advanced asymmetric encryption algorithms work together to create an indestructible security protection for credential data, ensuring that data is free of tampering and leakage risks during storage and transmission. In addition, with the traceability of blockchain, any data changes can be clearly traced, providing a reliable trust basis for credential authenticity verification.

[0047] In the big data feature analysis phase, after accurately extracting the credential data from the blockchain, a powerful data mining algorithm is used to deeply explore the frequent patterns and association rules therein, such as deeply analyzing the internal logical connections between credential data in different business scenarios. With the help of machine learning algorithms, a feature model specifically for credential authenticity is constructed, which cleverly integrates the internal features of the credential with the external environmental features. The external environmental features include the dynamic changes in industry policies and regulations, the fluctuations in the macroeconomic situation, etc., and are accurately captured through specific time series analysis technology. The model is repeatedly trained and optimized using cross-validation technology, so that it can keenly identify the key features of credential authenticity, and realize self-optimization and upgrading based on the continuously updated blockchain data, always maintaining high accuracy and adaptability for credential authenticity verification.

[0048] In the comprehensive verification phase, after obtaining the certificate to be verified, its basic information is first carefully verified, including key aspects such as the standardization of the format and the validity of the digital signature. Then, the certificate data is comprehensively compared with the precise model constructed in the early stage, and multi-dimensional factors are comprehensively considered. Combined with the rich historical data of similar certificates on the blockchain, a horizontal comparative analysis is conducted to deeply judge the authenticity of the certificate from multiple angles, and a detailed and professional verification report is generated. The report covers core contents such as precise verification basis and in-depth difference analysis. If suspicious points are detected during the verification process, the traceability algorithm is immediately activated to conduct a deep backtracking query on the historical records of the certificate data on the blockchain. Through a rigorous traceability credibility assessment system, the true status of the certificate is further determined to ensure that the entire verification process is rigorous, comprehensive, and efficient, providing a solid and reliable guarantee for the authenticity of certificates in various fields, and effectively maintaining the normal order and good environment in many aspects such as commercial transactions and government services.

[0049] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for verifying the authenticity of a credential based on trusted blockchain big data evaluation, characterized in that: The following steps are involved: S1. Multi-source data collection steps: Use web crawler technology to capture public data related to vouchers from the Internet platform, use data interfaces to connect to various databases to extract structured voucher data, use OCR recognition technology to process paper or image format vouchers to obtain text information, and the collected data includes all key elements of the voucher. In addition, data from different sources are integrated and standardized to build a comprehensive and standardized voucher data set; S2. Blockchain data embedding step: Perform hash operation on the collected credential data to obtain a hash value of fixed length, and construct transaction information with the hash value and the metadata of the credential, including the credential number, generation time, and source information, in accordance with the protocol specification of the blockchain. The transaction information is broadcast to multiple nodes in the blockchain network. Through the consensus mechanism of the nodes, the transaction information is packaged into blocks and added to the blockchain. The hash operation adopts the formula H=SHA256(data+salt), where H is the hash value, data is the credential data, and salt is a randomly generated salt value, and the length of the salt value is not less than 128 bits; S3. Big data feature analysis steps: extract credential data from the blockchain, use data mining algorithms to mine frequent patterns and association rule features in the credential data, and use decision trees and neural network machine learning algorithms to learn and model the authenticity features of the credential; cross-validation technology is used in the model training process, and when constructing the credential authenticity feature model, the feature fusion formula F = ω1×I+ω2×E is used, where F is the fused feature vector, I is the internal feature vector of the credential, E is the external environment feature vector, and ω1 and ω2 are weight coefficients; S4. Comprehensive verification step: Get the credential to be verified and verify its basic information first; then compare the credential data with the model constructed in the big data feature analysis step, analyze the matching degree between the features of the credential data and the real credential feature model, and compare the historical credential data of the same type on the blockchain horizontally, using the matching degree calculation formula Where M is the matching degree, m i is the matching score of the i-th feature, ranging from 0 to 1, ω i The weight of the ith feature is set according to the feature importance, and a verification report containing the verification basis and difference analysis details is generated; S5. User interaction and feedback step: Provide users with an operation interface where they can upload the credentials to be verified and view the verification progress and result report. The interface response time is less than 2 seconds and supports multi-language display. After receiving feedback, the system will incorporate the feedback information as a new data sample into the model training process in the big data feature analysis step.

2. The method for verifying the authenticity of a credential based on trusted blockchain big data evaluation according to claim 1 is characterized in that: In the S1 multi-source data collection step, an intelligent screening algorithm is used for the data collected by the web crawler, and the data highly relevant to the credential authenticity verification is screened out according to the pre-set credential keyword library and data relevance evaluation model. The data relevance evaluation model is set as Where R is the correlation score, k j is the weight of the jth keyword, s j is the frequency of occurrence of the jth keyword in the data. This formula is used to quantify the correlation between the data and the authenticity verification of the credential. At the same time, a reasonable access frequency limit is set for the web crawler. The access frequency limit can be dynamically adjusted according to the traffic carrying capacity of the website.

3. The method for verifying the authenticity of a credential based on trusted blockchain big data evaluation according to claim 1 is characterized in that: In the S2 blockchain data embedding step, salting is used for the hash operation, and the salt value is randomly generated to enhance the security of the hash value and reduce the risk of hash collision. The probability of hash collision is lower than 10 to the power of -60. When constructing transaction information, the credential data is encrypted and an asymmetric encryption algorithm is used to protect sensitive information. The encryption strength meets industry security standards. The security strength evaluation formula of the encrypted information is assumed to be S=log2(N), where S is the security strength and N is the size of the key space of the encryption algorithm.

4. The method for verifying the authenticity of a credential based on trusted blockchain big data evaluation according to claim 1 is characterized in that: In the S3 big data feature analysis step, when constructing the credential authenticity feature model, in addition to the conventional credential data features, external environment data features are also included, including industry policy and regulation change data related to the credential, macroeconomic data, etc. These external features are combined with the internal features of the credential through feature fusion technology. In the feature extraction process, the time series analysis formula T = α × T is used for the external environment data features. prev +β×E curr , where T is the time series feature value after processing, T prev is the eigenvalue of the previous moment, E curr is the external environment data value at the current moment, and α and β are smoothing coefficients.

5. The method for verifying the authenticity of a credential based on trusted blockchain big data evaluation according to claim 1 is characterized in that: In the S4 comprehensive verification step, when suspicious points are found in the credential to be verified, the traceability algorithm is used to trace back the historical records of the credential data on the blockchain, track the generation, modification and circulation of the credential data, and analyze the abnormalities in its historical trajectory; the traceability credibility evaluation formula is set as Where C is the traceability credibility, V is the number of valid traceability information, and U is the number of invalid traceability information.

6. The method for verifying the authenticity of a credential based on trusted blockchain big data evaluation according to claim 1 is characterized in that: In the S5 user interaction and feedback step, when the user objects to the verification result and provides additional evidence, the system starts the re-verification process, re-collects the additional data related to the voucher, merges the additional data with the original data, and then performs the big data feature analysis and comprehensive verification steps again; the calculation formula of the user feedback influence factor is: Where I is the user feedback impact factor, Q is the number of valid information in user feedback, and P is the number of invalid information in user feedback.

7. According to the method for verifying the authenticity of a credential based on trusted blockchain big data evaluation in claim 1, in the S1 multi-source data collection step, if access to the data source is restricted or data acquisition fails, the data source is automatically switched to an alternative data source or a data recovery mechanism is used. The data recovery mechanism uses local cache data and a data repair algorithm to recover part of the lost or damaged data. The data recovery effect evaluation formula is: Where E is the data recovery effect, D rec is the amount of data recovered, D lost is the amount of data lost.

8. The method for verifying the authenticity of a credential based on trusted blockchain big data evaluation according to claim 1 is characterized in that: In the S4 comprehensive verification step, when the verification result determines that the voucher is false, the system automatically generates early warning information and sends it to the relevant regulatory agency, enterprise or individual. The early warning information value assessment formula is V=λ×R+μ×I, where V is the value of the early warning information, R is the risk assessment score, I is the importance score of the related party, and λ and μ are weight coefficients.

Images