A blockchain-based evaluation method and system

Abstract

The present application relates to the technical field of mental health assessment, in particular to a kind of evaluation method and system based on block chain, comprising the following steps: based on Ethereum block chain platform, using SHA-256 encryption algorithm and Merkle tree technology, the construction of block chain network is carried out, and using Solidity programming language deployment smart contract, generate mental health assessment block chain network;In the present application, through multivariate analysis of variance, linear regression and logistic regression analysis, the sensitivity analysis of mental health data and the identification ability of key influence factors are improved, by introducing proof of stake consensus algorithm and distributed hash table technology, the data traceability and the accuracy verification of evaluation result are enhanced, through differential privacy technology and data desensitization method, a balance point between protecting personal privacy and maintaining data effectiveness is found more effectively, by adopting box dimension calculation and multi-scale fractal analysis and other advanced technologies, so that the present application can deeply mine the complex trend of mental health data.

Description

Technical Field

[0001] This invention relates to the field of mental health assessment technology, and in particular to a blockchain-based assessment method and system. Background Technology

[0002] Mental health assessment is used to evaluate an individual's mental state and mental health. Due to work pressure and environmental factors, it is very important to conduct mental health assessments regularly. Existing assessment systems are already able to effectively measure mental health status and have established corresponding mental health norms.

[0003] Among them, blockchain-based assessment methods, particularly psychological assessment methods that incorporate blockchain technology, aim to improve the security and confidentiality of assessment data. The core advantages of blockchain lie in its immutability and high security, making it an ideal choice for storing sensitive information such as mental health data. By encrypting and storing psychological assessment data on the blockchain, it ensures that the data is not accessed or modified by unauthorized third parties, thus protecting the privacy of the test-takers. Simultaneously, due to the transparency of blockchain technology, relevant institutions can effectively access and utilize this data while ensuring data security. In implementation, blockchain-based psychological assessment methods first assess the psychological state of individuals, then encrypt the collected data and store it on the blockchain. This not only enhances the security of data storage but also ensures the authenticity and reliability of the assessment results. Overall, blockchain-based assessment methods provide a secure and reliable data storage and management solution while ensuring the scientific validity and effectiveness of psychological assessments, making them particularly suitable for handling mental health data involving personal privacy and sensitive information.

[0004] While existing blockchain-based mental health assessment methods offer significant improvements in data security and confidentiality, they still have shortcomings in deeper applications and technical details. First, traditional blockchain assessment methods are relatively rudimentary in data processing and analysis, failing to fully utilize the potential of blockchain technology for complex data analysis and process optimization. For example, sensitivity analysis of mental health data, identification of key influencing factors, and optimization of the assessment process have not received sufficient attention in traditional methods. Although traditional methods emphasize secure data storage, they are not comprehensive enough in terms of multi-party verification and auditing, limiting advanced verification of the accuracy of assessment results and enhancement of data traceability. Furthermore, although traditional methods consider data encryption and privacy protection, they have not yet reached an optimal balance in the application of differential privacy technology and data anonymization methods. While ensuring data security, it is also necessary to ensure data validity and usability, especially in the sensitive field of mental health. Finally, existing methods lack advanced data analysis capabilities, making it difficult to reveal the nonlinear characteristics and more complex trends of the data. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing a blockchain-based evaluation method and system.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a blockchain-based evaluation method, comprising the following steps:

[0007] S1: Based on the Ethereum blockchain platform, it uses the SHA-256 encryption algorithm and Merkle tree technology to build a blockchain network, and uses the Solidity programming language to deploy smart contracts to generate a mental health assessment blockchain network.

[0008] S2: Based on the aforementioned mental health assessment blockchain network, an anti-fraud mechanism is implemented using an elliptic curve digital signature algorithm, and assessment data is recorded to generate secure assessment data.

[0009] S3: Based on the evaluation data of the security records, perform sensitivity analysis using multivariate analysis of variance, optimize the evaluation process, and generate an adjusted evaluation process;

[0010] S4: Based on the adjusted evaluation process, a proof-of-stake consensus algorithm is used for multi-party verification, and the accuracy of the evaluation results is checked to generate an evaluation result that has been verified by multiple parties.

[0011] S5: Based on the evaluation results verified by multiple parties, differential privacy technology using the Laplace noise mechanism is used to protect the data and generate privacy-protected evaluation data.

[0012] S6: Based on the privacy-protected assessment data, time series breakpoint analysis is performed using CUMSUM and Bayesian change point detection methods to generate a report on key moments of psychological state change.

[0013] S7: Based on the key moment report of the psychological state change, the box dimension calculation method is used to perform fractal analysis on the data to generate a fractal feature report of the psychological state.

[0014] As a further aspect of the present invention, the mental health assessment blockchain network includes a network architecture consisting of multiple nodes, a blockchain data structure, and smart contracts that automatically execute operations. The securely recorded assessment data specifically includes encrypted user mental health information, assessment questionnaire responses, historical data on user mental health status, and behavioral patterns. The adjusted assessment process specifically refers to optimized assessment steps and methods. The multi-party verified assessment results specifically refer to mental health assessment results confirmed by multiple verification nodes on the blockchain network. The privacy-protected assessment data specifically refers to mental health information processed using differential privacy technology. The critical moment report of changes in mental state includes abrupt changes in mental health status and potential risk warnings. The fractal characteristic report of mental state specifically refers to a data complexity report obtained through box dimension calculation.

[0015] As a further aspect of this invention, based on the Ethereum blockchain platform, the blockchain network is constructed using the SHA-256 encryption algorithm and Merkle tree technology, and smart contracts are deployed using the Solidity programming language to generate a mental health assessment blockchain network. The specific steps are as follows:

[0016] S101: Based on the Ethereum blockchain platform, it uses the SHA-256 encryption algorithm to encrypt data blocks and create blockchain data blocks to generate encrypted blockchain data.

[0017] S102: Based on the encrypted blockchain data, a tree structure is constructed using Merkle tree technology, and data integrity is verified to generate the Merkle tree structure;

[0018] S103: Based on the Merkle tree structure, deploy smart contracts on the Ethereum blockchain platform using the Solidity programming language, write mental health assessment logic, and generate a mental health assessment blockchain network.

[0019] As a further aspect of the present invention, based on the aforementioned mental health assessment blockchain network, an anti-fraud mechanism is implemented using an elliptic curve digital signature algorithm, and assessment data is recorded to generate secure assessment data. The specific steps are as follows:

[0020] S201: Based on the aforementioned mental health assessment blockchain network, an elliptic curve digital signature algorithm is used to digitally sign the data and generate a blockchain network for signature authentication;

[0021] S202: Based on the blockchain network of the aforementioned signature authentication, a distributed ledger technology is adopted to deploy anti-fraud strategies, record and verify the authenticity of the evaluation data, and generate anti-fraud verification data records;

[0022] S203: Based on the data records of the anti-fraud verification, the AES encryption algorithm is used to store the mental health assessment data and generate assessment data for the security record.

[0023] As a further aspect of the present invention, based on the evaluation data of the security records, a multivariate analysis of variance is used to perform sensitivity analysis, and the evaluation process is optimized to generate the adjusted evaluation process. The specific steps are as follows:

[0024] S301: Based on the evaluation data of the security records, linear regression analysis and logistic regression analysis are used for data analysis to select key evaluation indicators and generate key evaluation indicator data;

[0025] S302: Based on the key evaluation index data, perform sensitivity analysis using multivariate analysis of variance, identify key influencing factors, and generate data impact factor analysis results;

[0026] S303: Based on the data impact factor analysis results, Six Sigma process improvement and lean management techniques are used to adjust and optimize the evaluation process, and generate the adjusted evaluation process.

[0027] As a further aspect of the present invention, based on the adjusted evaluation process, the steps of using a proof-of-stake consensus algorithm for multi-party verification and checking the accuracy of the evaluation results to generate a multi-party verified evaluation result are as follows:

[0028] S401: Based on the adjusted evaluation process, a distributed hash table is used to record data, index and manage the evaluation data, and generate traceable data records;

[0029] S402: Based on the traceable data records, a proof-of-stake consensus algorithm is used to perform multi-party collaborative verification and generate data that has been verified by multiple parties.

[0030] S403: Based on the data that has been verified by multiple parties, a hash chain algorithm is used to conduct a final data audit and generate an evaluation result that has been verified by multiple parties.

[0031] As a further aspect of the present invention, based on the multi-verified evaluation results, differential privacy technology using the Laplace noise mechanism is employed to protect the data, and the specific steps for generating privacy-protected evaluation data are as follows:

[0032] S501: Based on the evaluation results verified by multiple parties, the evaluation data is encrypted using RSA encryption technology to generate encrypted evaluation data;

[0033] S502: Based on the evaluation data of the encryption process, differential privacy processing is performed using the Laplace noise mechanism to generate differential privacy-processed data;

[0034] S503: Based on the data that has undergone differential privacy processing, a data anonymization and desensitization method is used to conduct a final privacy audit and generate privacy-protected evaluation data.

[0035] As a further aspect of the present invention, based on the privacy-protected assessment data, the steps of performing time series breakpoint analysis using CUMSUM and Bayesian change point detection methods to generate a report on key moments of psychological state change are as follows:

[0036] S601: Based on the privacy-protected assessment data, time series analysis technology is used to identify key time points and trends, and time point analysis results are generated;

[0037] S602: Based on the time point analysis results, the CUMSUM method is used to perform change point detection and generate change point detection results;

[0038] S603: Based on the change point detection results, the Bayesian change point detection method is used to analyze changes in psychological state and generate a report on key moments of psychological state changes.

[0039] As a further aspect of the present invention, based on the key moment reports of changes in psychological state, the steps of performing fractal analysis on the data using the box dimension calculation method to generate a fractal feature report of the psychological state are as follows:

[0040] S701: Based on the key moment report of the psychological state change, time series decomposition technology is used to separate the data into trend, seasonal and random components to generate decomposed time series data;

[0041] S702: Based on the decomposed time series data, multi-scale fractal analysis technology is used to explore the nonlinear characteristics of the data through box dimension calculation and generate intermediate fractal analysis results;

[0042] S703: Based on the intermediate results of the fractal analysis, linear regression and nonlinear regression modeling techniques are used to comprehensively analyze the data characteristics, complete the comprehensive fractal characteristic analysis of the psychological state, and generate a fractal characteristic report of the psychological state.

[0043] A blockchain-based evaluation system is provided, which is used to execute the aforementioned blockchain-based evaluation method. The system includes a data encryption processing module, a Merkle tree construction module, a smart contract deployment module, a digital signature and anti-fraud module, a sensitivity analysis and optimization module, a multi-party verification and data auditing module, a privacy protection and data security module, and a change point detection and fractal analysis module.

[0044] The data encryption processing module is based on the Ethereum blockchain platform. It uses the SHA-256 encryption algorithm to encrypt data blocks and create blockchain data blocks to generate encrypted blockchain data.

[0045] The Merkle tree construction module is based on blockchain encrypted data, uses Merkle tree technology to construct a tree structure, performs data integrity verification, and generates a Merkle tree structure.

[0046] The smart contract deployment module is based on a Merkle tree structure and uses the Solidity programming language to deploy smart contracts on the Ethereum blockchain platform, write mental health assessment logic, and generate a mental health assessment blockchain network.

[0047] The digital signature and anti-fraud module is based on a mental health assessment blockchain network. It uses elliptic curve digital signature algorithm and distributed ledger technology to implement an anti-fraud mechanism, and records assessment data to generate anti-fraud verification data records.

[0048] The sensitivity analysis and optimization module uses data records from anti-fraud verification to conduct sensitivity analysis using multivariate analysis of variance, linear regression analysis, and logistic regression analysis. It selects key evaluation indicators, identifies key influencing factors, and uses Six Sigma process improvement and lean management techniques to adjust and optimize the evaluation process, generating the adjusted evaluation process.

[0049] The multi-party verification and data auditing module is based on the adjusted evaluation process. It uses a distributed hash table to record data and a proof-of-stake consensus algorithm for multi-party verification, and a hash chain algorithm for data auditing to generate an evaluation result that has been verified by multiple parties.

[0050] The privacy protection and data security module is based on the evaluation results verified by multiple parties. It uses RSA encryption technology and Laplace noise mechanism differential privacy technology to protect the data. At the same time, it uses data desensitization and anonymization processing methods to perform privacy auditing and generate privacy-protected evaluation data.

[0051] The variable point detection and fractal analysis module uses privacy-protected assessment data, employs time series analysis technology, CUMSUM and Bayesian variable point detection methods to perform time series breakpoint analysis, and uses box dimension calculation methods to perform fractal analysis, generating a fractal feature report of psychological state.

[0052] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0053] This invention employs more sophisticated data processing and analysis techniques, such as multivariate analysis of variance, linear regression, and logistic regression, to effectively enhance the sensitivity analysis of mental health data and the identification of key influencing factors. This makes the assessment process more refined and personalized, thus more accurately reflecting and addressing the mental health status of high-stress occupational groups. Regarding multi-party verification and data auditing, this invention introduces a proof-of-stake consensus algorithm and distributed hash table technology to enhance data traceability and the accuracy of assessment results. This not only improves the transparency of data processing but also provides stronger credibility to the assessment results. Furthermore, through differential privacy technology and data anonymization methods, this invention more effectively strikes a balance between protecting personal privacy and maintaining data validity. This not only protects the privacy of those being assessed but also ensures that the collected data, while maintaining high security, can still be used for further research and analysis. Finally, by employing advanced techniques such as box-dimensionality calculation and multi-scale fractal analysis, this invention can deeply explore the nonlinear characteristics and complex trends of mental health data. This advanced analytical capability can reveal deeper changes in psychological states, providing a more accurate basis for the prediction and intervention of mental health. Attached Figure Description

[0054] Figure 1 This is a schematic diagram of the workflow of the present invention;

[0055] Figure 2 This is a detailed flowchart of step S1 of the present invention;

[0056] Figure 3 This is a detailed flowchart of step S2 of the present invention;

[0057] Figure 4 This is a detailed flowchart of step S3 of the present invention;

[0058] Figure 5 This is a detailed flowchart of step S4 of the present invention;

[0059] Figure 6 This is a detailed flowchart of step S5 of the present invention;

[0060] Figure 7 This is a detailed flowchart of step S6 of the present invention;

[0061] Figure 8 This is a detailed flowchart of step S7 of the present invention;

[0062] Figure 9 This is a system flowchart of the present invention. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0064] In the description of this invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, in the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0065] Example 1

[0066] Please see Figure 1 This invention provides a technical solution: a blockchain-based evaluation method, comprising the following steps:

[0067] S1: Based on the Ethereum blockchain platform, it uses the SHA-256 encryption algorithm and Merkle tree technology to build a blockchain network, and uses the Solidity programming language to deploy smart contracts to generate a mental health assessment blockchain network.

[0068] S2: Based on a mental health assessment blockchain network, an anti-fraud mechanism is implemented using an elliptic curve digital signature algorithm, and assessment data is recorded to generate secure assessment data.

[0069] S3: Based on the safety record assessment data, a multivariate analysis of variance is used to conduct sensitivity analysis, and the assessment process is optimized to generate an adjusted assessment process;

[0070] S4: Based on the adjusted evaluation process, the Proof-of-Stake consensus algorithm is used for multi-party verification, and the accuracy of the evaluation results is checked to generate an evaluation result that has been verified by multiple parties.

[0071] S5: Based on the evaluation results verified by multiple parties, differential privacy technology using the Laplace noise mechanism is used to protect the data and generate privacy-protected evaluation data;

[0072] S6: Based on privacy-protected assessment data, time series breakpoint analysis is performed using CUMSUM and Bayesian change point detection methods to generate reports on key moments of psychological state changes.

[0073] S7: Based on the critical moment report of psychological state changes, the box dimension calculation method is used to perform fractal analysis on the data to generate a fractal characteristic report of psychological state.

[0074] The mental health assessment blockchain network includes a network architecture consisting of multiple nodes, a blockchain data structure, smart contracts that automatically execute operations, and securely recorded assessment data, specifically encrypted user mental health information, assessment questionnaire responses, historical data on user mental health status, and behavioral patterns. The adjusted assessment process refers to optimized assessment steps and methods. The multi-party verified assessment results are mental health assessment results confirmed by multiple verification nodes on the blockchain network. The privacy-protected assessment data is mental health information processed using differential privacy technology. The critical moment report on changes in mental state includes abrupt changes in mental health status and potential risk warnings. The fractal characteristic report of mental state is a data complexity report obtained through box dimension calculation methods.

[0075] By building a mental health assessment blockchain network on the Ethereum blockchain platform, and employing the SHA-256 encryption algorithm and Merkle tree technology to ensure data integrity and security, this provides a solid foundation for the secure storage and transmission of mental health data. At the same time, the use of the Solidity programming language to deploy smart contracts ensures the automated execution of the assessment process, thereby reducing operational risks and minimizing potential errors.

[0076] Employing elliptic curve digital signature algorithms to implement anti-fraud mechanisms helps ensure the authenticity and credibility of assessment data. Digital signatures on the blockchain ensure the traceability of data sources, reduce the possibility of fraud, and provide credibility and transparency to the healthcare system.

[0077] The application of multivariate analysis of variance makes the evaluation process more robust and interpretable. Through sensitivity analysis, the system can identify and eliminate possible confounding factors, improving the accuracy of the evaluation results. At the same time, the optimization of the evaluation process makes the evaluation more efficient and objective, helping to save time and resources.

[0078] The Proof-of-Stake consensus algorithm ensures the accuracy of multi-party verification evaluation results. Multi-party verification enhances the credibility and reliability of the evaluation results, helps eliminate uncertainty, and provides a solid basis for decision-making.

[0079] Using differential privacy technology to protect assessment data is crucial to ensuring that user privacy is not compromised, as mental health assessment data often contains sensitive information. Differential privacy technology allows for effective data analysis while protecting privacy, providing a high level of protection for data privacy and security.

[0080] Time series breakpoint analysis and fractal analysis have enabled a deeper understanding of the trends and characteristics of changes in psychological states. This not only helps to detect mental health problems early, but also provides more personalized and precise intervention and treatment recommendations.

[0081] Please see Figure 2 Based on the Ethereum blockchain platform, using the SHA-256 encryption algorithm and Merkle tree technology, a blockchain network is built, and smart contracts are deployed using the Solidity programming language to generate a mental health assessment blockchain network. The specific steps are as follows:

[0082] S101: Based on the Ethereum blockchain platform, it uses the SHA-256 encryption algorithm to encrypt data blocks and create blockchain data blocks to generate encrypted blockchain data.

[0083] S102: Based on blockchain encrypted data, a tree structure is constructed using Merkle tree technology, and data integrity is verified to generate the Merkle tree structure;

[0084] S103: Based on the Merkle tree structure, using the Solidity programming language, deploy smart contracts on the Ethereum blockchain platform, write mental health assessment logic, and generate a mental health assessment blockchain network.

[0085] In step S101, based on the Ethereum blockchain platform, the data block is encrypted using the SHA-256 encryption algorithm to create a blockchain data block. This ensures the security and immutability of the data, forming an encrypted blockchain data structure.

[0086] In step S102, Merkle tree technology is used to construct a tree structure for the encrypted blockchain data and to perform data integrity verification. Merkle trees improve the efficiency and reliability of data verification, providing an efficient verification mechanism for blockchain networks.

[0087] In step S103, based on the Merkle tree structure, a smart contract is deployed on the Ethereum blockchain platform using the Solidity programming language, and the logic for the mental health assessment is written. This automates the mental health assessment process while maintaining transparency and security on the blockchain network.

[0088] Please see Figure 3Based on a blockchain network for mental health assessment, an anti-fraud mechanism is implemented using the elliptic curve digital signature algorithm, and assessment data is recorded. The specific steps for generating secure assessment data are as follows:

[0089] S201: Based on the mental health assessment blockchain network, the elliptic curve digital signature algorithm is used to digitally sign the data and generate a blockchain network for signature authentication.

[0090] S202: A blockchain network based on signature authentication, employing distributed ledger technology, deploying anti-fraud strategies, recording and verifying the authenticity of evaluation data, and generating anti-fraud verification data records;

[0091] S203: Data records based on anti-fraud verification, using AES encryption algorithm, store mental health assessment data, and generate assessment data for secure records.

[0092] In step S201, based on the mental health assessment blockchain network, the data is signed using the elliptic curve digital signature algorithm to ensure the integrity and non-repudiation of the data, thereby generating a blockchain network with signature authentication.

[0093] In step S202, an anti-fraud strategy is deployed on a signature-authenticated blockchain network using distributed ledger technology to record and verify the authenticity of the evaluation data, thereby generating data records with anti-fraud verification to ensure the accuracy and tamper-proof nature of the evaluation data.

[0094] In step S203, the stored mental health assessment data is encrypted using the AES encryption algorithm to ensure the security of the data during storage and transmission, and to generate assessment data with secure records.

[0095] Please see Figure 4 Based on the safety record assessment data, a sensitivity analysis was conducted using multivariate analysis of variance, and the assessment process was optimized. The specific steps of the adjusted assessment process are as follows:

[0096] S301: Based on the safety record assessment data, linear regression analysis and logistic regression analysis are used for data analysis to select key assessment indicators and generate key assessment indicator data;

[0097] S302: Based on the key evaluation indicator data, use multivariate analysis of variance to conduct sensitivity analysis, identify key influencing factors, and generate data impact factor analysis results;

[0098] S303: Based on the data impact factor analysis results, Six Sigma process improvement and lean management techniques are used to adjust and optimize the assessment process, and generate the adjusted assessment process.

[0099] In step S301, based on the assessment data from the security records, key assessment indicators for mental health assessment are determined through linear regression and logistic regression analysis to ensure the relevance and accuracy of the assessment process.

[0100] In step S302, the sensitivity analysis of key evaluation indicators is performed using multivariate analysis of variance to identify key factors affecting the evaluation results, thereby generating data impact factor analysis results and providing in-depth insights to improve the evaluation standards.

[0101] In step S303, based on the data impact factor analysis results, the evaluation process is adjusted and optimized using Six Sigma process improvement and lean management techniques to generate an adjusted, efficient, and accurate evaluation process.

[0102] Please see Figure 5 Based on the adjusted evaluation process, the steps for generating a multi-party verified evaluation result by using the Proof-of-Stake consensus algorithm and verifying the accuracy of the evaluation results are as follows:

[0103] S401: Based on the adjusted evaluation process, a distributed hash table is used to record data, index and manage the evaluation data, and generate traceable data records;

[0104] S402: Based on traceable data records, a proof-of-stake consensus algorithm is used to perform multi-party collaborative verification and generate data that has been verified by multiple parties.

[0105] S403: Based on data that has been verified by multiple parties, a hash chain algorithm is used to conduct a final data audit and generate an evaluation result that has been verified by multiple parties.

[0106] In step S401, based on the adjusted evaluation process, distributed hash table technology is used to perform detailed indexing and management of the evaluation data. This step ensures that all evaluation data can be accurately tracked and retrieved by creating an efficient data recording method, thereby forming a complete and traceable data framework.

[0107] In step S402, a Proof-of-Stake consensus algorithm is introduced to perform multi-party verification of the indexed evaluation data. This process confirms the validity of the data through the collaboration of multiple nodes in the network, enhancing the transparency and security of the data processing and ensuring the authenticity and consistency of the data.

[0108] In step S403, a hash chain algorithm is applied to perform a final audit of the data that has been verified through multi-party collaboration. This step increases the integrity check of the data by creating an immutable, continuous data chain, ensuring the accuracy of the evaluation results, generating evaluation results that have been rigorously audited and confirmed by multiple parties, and improving the reliability of the entire evaluation process.

[0109] Please see Figure 6 Based on the evaluation results verified by multiple parties, differential privacy technology using the Laplace noise mechanism is employed to protect the data. The specific steps for generating privacy-preserving evaluation data are as follows:

[0110] S501: Based on the evaluation results verified by multiple parties, the evaluation data is encrypted using RSA encryption technology to generate encrypted evaluation data;

[0111] S502: Based on the encrypted evaluation data, a Laplace noise mechanism is used to perform differential privacy processing to generate differential privacy-processed data;

[0112] S503: Based on the data that has undergone differential privacy processing, data anonymization and desensitization methods are used to conduct a final privacy audit and generate privacy-protected assessment data.

[0113] In step S501, based on the evaluation results verified by multiple parties, the evaluation data is encrypted using RSA encryption technology to ensure the security of the data during transmission and storage, thereby generating encrypted evaluation data.

[0114] In step S502, the Laplace noise mechanism is applied to perform differential privacy processing on the evaluation data of the encryption process, which effectively protects the data content, prevents the leakage of sensitive information, and generates data that has undergone differential privacy processing.

[0115] In step S503, the data that has undergone differential privacy processing is anonymized and desensitized, and a final privacy audit is performed to ensure that the evaluation data maintains the highest level of privacy protection when used and shared, thereby generating privacy-protected evaluation data.

[0116] Please see Figure 7 Based on privacy-protected assessment data, the steps for generating a report on key moments of psychological state change using CUMSUM and Bayesian change point detection methods for time series breakpoint analysis are as follows:

[0117] S601: Based on privacy-protected assessment data, time series analysis technology is used to identify key time points and trends, and generate time point analysis results;

[0118] S602: Based on the time point analysis results, the CUMSUM method is used to detect change points and generate change point detection results;

[0119] S603: Based on the change point detection results, the Bayesian change point detection method is used to analyze changes in psychological state and generate a report on key moments of psychological state changes.

[0120] In step S601, based on the privacy-preserving assessment data, time series analysis techniques are used to identify key time points and trends in the assessment data, generating time point analysis results. This step aims to understand the significant changes and patterns in the assessment data.

[0121] In step S602, the CUMSUM method is used to detect change points in the time-point analysis results, identifying significant changes in the data and generating change point detection results. The CUMSUM method effectively detects abrupt changes in the data through accumulation and other techniques.

[0122] In step S603, based on the change point detection results, the Bayesian change point detection method is used to further analyze changes in psychological state and generate a report on key moments of psychological state change. This method combines a probabilistic model to provide in-depth insights into changes in psychological state.

[0123] Please see Figure 8 Based on key moment reports of psychological state changes, the specific steps for generating fractal characteristic reports of psychological states by using box dimension calculation to perform fractal analysis on the data are as follows:

[0124] S701: Report on key moments based on changes in psychological state, using time series decomposition technology to separate data into trend, seasonal and random components, generating decomposed time series data;

[0125] S702: Based on the decomposed time series data, multi-scale fractal analysis technology is used to explore the nonlinear characteristics of the data through box dimension calculation and generate intermediate fractal analysis results.

[0126] S703: Based on the intermediate results of fractal analysis, linear regression and nonlinear regression modeling techniques are used to comprehensively analyze data characteristics, complete the comprehensive fractal characteristic analysis of psychological state, and generate a fractal characteristic report of psychological state.

[0127] In step S701, based on the key moment reports of psychological state changes, time series decomposition techniques are applied to separate the data into trend, seasonal, and random components, generating decomposed time series data. This step aims to extract the basic structure and patterns from the psychological state data.

[0128] In step S702, multi-scale fractal analysis techniques are used, and the nonlinear characteristics of the data are explored through box-dimensional calculation, generating intermediate fractal analysis results. This process reveals the complexity and hidden features of the data.

[0129] In step S703, based on the intermediate results of fractal analysis, linear regression and nonlinear regression modeling techniques are used to comprehensively analyze data characteristics, complete the comprehensive fractal characteristic analysis of psychological states, and generate a fractal characteristic report of psychological states. This step deeply analyzes the intrinsic characteristics of psychological state data and provides a comprehensive mental health assessment.

[0130] Please see Figure 9 A blockchain-based evaluation system is used to execute the aforementioned blockchain-based evaluation method. The system includes a data encryption processing module, a Merkle tree construction module, a smart contract deployment module, a digital signature and anti-fraud module, a sensitivity analysis and optimization module, a multi-party verification and data auditing module, a privacy protection and data security module, and a change point detection and fractal analysis module.

[0131] The data encryption processing module is based on the Ethereum blockchain platform. It uses the SHA-256 encryption algorithm to encrypt data blocks and create blockchain data blocks to generate encrypted blockchain data.

[0132] The Merkle tree building module is based on blockchain encrypted data, uses Merkle tree technology to build a tree structure, performs data integrity verification, and generates a Merkle tree structure.

[0133] The smart contract deployment module is based on a Merkle tree structure and uses the Solidity programming language to deploy smart contracts on the Ethereum blockchain platform, and writes mental health assessment logic to generate a mental health assessment blockchain network.

[0134] The digital signature and anti-fraud module is based on a mental health assessment blockchain network. It uses elliptic curve digital signature algorithm and distributed ledger technology to implement an anti-fraud mechanism, record assessment data, and generate anti-fraud verification data records.

[0135] The sensitivity analysis and optimization module uses data records from anti-fraud verification to conduct sensitivity analysis using multivariate analysis of variance, linear regression analysis, and logistic regression analysis. It selects key evaluation indicators, identifies key influencing factors, and uses Six Sigma process improvement and lean management techniques to adjust and optimize the evaluation process, generating the adjusted evaluation process.

[0136] The multi-party verification and data auditing module is based on the adjusted evaluation process. It uses a distributed hash table to record data and a proof-of-stake consensus algorithm for multi-party verification, and a hash chain algorithm for data auditing to generate evaluation results that have been verified by multiple parties.

[0137] The privacy protection and data security module is based on evaluation results verified by multiple parties. It uses RSA encryption and Laplace noise mechanism differential privacy technology to protect the data, and uses data desensitization and anonymization methods to conduct privacy audits, generating privacy-protected evaluation data.

[0138] The change point detection and fractal analysis module uses privacy-protected assessment data, employs time series analysis techniques, CUMSUM and Bayesian change point detection methods to perform time series breakpoint analysis, and utilizes box dimension calculation methods to perform fractal analysis, generating a fractal feature report of psychological states.

[0139] The data encryption and Merkle tree construction modules ensure data security and integrity; the smart contract deployment module automates the assessment logic; the digital signature and anti-fraud module improves data authenticity and security; the sensitivity analysis and optimization module enhances the accuracy and efficiency of the assessment process; the multi-party verification and data auditing module guarantees the credibility of the assessment results; the privacy protection and data security module protects personal privacy; and the change point detection and fractal analysis module provides in-depth analysis of mental health status. This provides users and professionals with a comprehensive, accurate, and secure assessment tool, helping to improve the accuracy and timeliness of mental health assessments.

[0140] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention in any other way. Any person skilled in the art may make changes or modifications to the above-disclosed technical content to create equivalent embodiments that can be applied to other fields. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A blockchain-based evaluation method, characterized in that, Includes the following steps: Based on the Ethereum blockchain platform, the blockchain network is built using the SHA-256 encryption algorithm and Merkle tree technology, and smart contracts are deployed using the Solidity programming language to generate a mental health assessment blockchain network. Based on the aforementioned mental health assessment blockchain network, an anti-fraud mechanism is implemented using an elliptic curve digital signature algorithm, and assessment data is recorded to generate secure assessment data. Based on the evaluation data of the security records, a multivariate analysis of variance was used to conduct sensitivity analysis, and the evaluation process was optimized to generate an adjusted evaluation process. The adjusted evaluation process specifically refers to the optimized evaluation steps and methods; The specific steps for generating the adjusted evaluation process are as follows: Based on the evaluation data of the security records, linear regression analysis and logistic regression analysis are used for data analysis, key evaluation indicators are selected, and key evaluation indicator data are generated. Based on the key evaluation index data, a sensitivity analysis was conducted using multivariate analysis of variance to identify key influencing factors and generate data impact factor analysis results. Based on the data impact factor analysis results, Six Sigma process improvement and lean management techniques were used to adjust and optimize the evaluation process, and an adjusted evaluation process was generated. Based on the adjusted evaluation process, a proof-of-stake consensus algorithm is used for multi-party verification, and the accuracy of the evaluation results is checked to generate an evaluation result that has been verified by multiple parties. Based on the evaluation results verified by multiple parties, differential privacy technology using the Laplace noise mechanism is employed to protect the data, generating privacy-protected evaluation data. Based on the privacy-protected assessment data, time series breakpoint analysis is performed using CUMSUM and Bayesian change point detection methods to generate a report on key moments of psychological state change. The report on key moments of change in mental state includes abrupt changes in mental health status and warnings of potential risks; The specific steps for generating the key moment report of the psychological state change are as follows: Based on the privacy-protected assessment data, time series analysis technology is used to identify key time points and trends, and time point analysis results are generated. Based on the time point analysis results, the CUMSUM method is used to detect change points and generate change point detection results. Based on the change point detection results, the Bayesian change point detection method is used to analyze changes in psychological state and generate a report on key moments of psychological state changes. Based on the key moment reports of the changes in the psychological state, the box dimension calculation method is used to perform fractal analysis on the data to generate a fractal feature report of the psychological state.

2. The blockchain-based evaluation method according to claim 1, characterized in that: The mental health assessment blockchain network includes a network architecture consisting of multiple nodes, a blockchain data structure, and smart contracts that automatically execute operations. The securely recorded assessment data specifically includes encrypted user mental health information, assessment questionnaire responses, historical data on user mental health status, and behavioral patterns. The multi-party verified assessment results specifically refer to mental health assessment results confirmed by multiple verification nodes on the blockchain network. The privacy-protected assessment data specifically refers to mental health information processed using differential privacy technology. The fractal feature report of mental state specifically refers to a data complexity report obtained through box dimension calculation methods.

3. The blockchain-based evaluation method according to claim 1, characterized in that: Based on the Ethereum blockchain platform, using the SHA-256 encryption algorithm and Merkle tree technology, a blockchain network is built, and smart contracts are deployed using the Solidity programming language to generate a mental health assessment blockchain network. The specific steps are as follows: Based on the Ethereum blockchain platform, the SHA-256 encryption algorithm is used to encrypt data blocks and create blockchain data blocks to generate encrypted blockchain data. Based on the encrypted blockchain data, a tree structure is constructed using Merkle tree technology, and data integrity is verified to generate the Merkle tree structure. Based on the Merkle tree structure, smart contracts are deployed on the Ethereum blockchain platform using the Solidity programming language, and mental health assessment logic is written to generate a mental health assessment blockchain network.

4. The blockchain-based evaluation method according to claim 3, characterized in that: Based on the aforementioned mental health assessment blockchain network, the steps for implementing an anti-fraud mechanism using the elliptic curve digital signature algorithm, recording assessment data, and generating secure assessment data are as follows: Based on the aforementioned mental health assessment blockchain network, an elliptic curve digital signature algorithm is used to digitally sign the data and generate a blockchain network for signature authentication. Based on the blockchain network with the aforementioned signature authentication, distributed ledger technology is used to deploy anti-fraud strategies, record and verify the authenticity of the evaluation data, and generate anti-fraud verification data records. Based on the data records obtained from the anti-fraud verification, the AES encryption algorithm is used to store mental health assessment data and generate assessment data for security records.

5. The blockchain-based evaluation method according to claim 1, characterized in that: Based on the adjusted evaluation process, the steps for using the Proof-of-Stake consensus algorithm for multi-party verification and checking the accuracy of the evaluation results to generate a multi-party verified evaluation result are as follows: Based on the adjusted evaluation process, a distributed hash table is used to record data, index and manage the evaluation data, and generate traceable data records. Based on the traceable data records, a proof-of-stake consensus algorithm is used to perform multi-party collaborative verification and generate data that has been verified by multiple parties. Based on the data that has been verified by multiple parties, a hash chain algorithm is used to conduct a final data audit and generate an evaluation result that has been verified by multiple parties.

6. The blockchain-based evaluation method according to claim 5, characterized in that: Based on the evaluation results verified by multiple parties, differential privacy technology using the Laplace noise mechanism is employed to protect the data. The specific steps for generating privacy-preserving evaluation data are as follows: Based on the evaluation results that have been verified by multiple parties, the evaluation data is encrypted using RSA encryption technology to generate encrypted evaluation data. Based on the evaluation data obtained from the encryption process, a Laplace noise mechanism is used to perform differential privacy processing, generating data that has undergone differential privacy processing. Based on the differential privacy-processed data, data anonymization and desensitization methods are used to conduct a final privacy audit, generating privacy-protected evaluation data.

7. The blockchain-based evaluation method according to claim 1, characterized in that: Based on the key moment reports of changes in psychological state, the specific steps for generating a fractal feature report of psychological state by performing fractal analysis on the data using the box dimension calculation method are as follows: Based on the key moment reports of the changes in the psychological state, time series decomposition technology is used to separate the data into trend, seasonal and random components to generate decomposed time series data. Based on the decomposed time series data, multi-scale fractal analysis technology is used to explore the nonlinear characteristics of the data through box dimension calculation and generate intermediate fractal analysis results. Based on the intermediate results of the fractal analysis, linear regression and nonlinear regression modeling techniques are used to comprehensively analyze the data characteristics, complete the comprehensive fractal characteristic analysis of psychological state, and generate a fractal characteristic report of psychological state.

8. A blockchain-based evaluation system, characterized in that: According to any one of claims 1-7, the blockchain-based evaluation method, the system includes a data encryption processing module, a Merkle tree construction module, a smart contract deployment module, a digital signature and anti-fraud module, a sensitivity analysis and optimization module, a multi-party verification and data auditing module, a privacy protection and data security module, and a change point detection and fractal analysis module. The data encryption processing module is based on the Ethereum blockchain platform. It uses the SHA-256 encryption algorithm to encrypt data blocks and create blockchain data blocks to generate encrypted blockchain data. The Merkle tree construction module is based on blockchain encrypted data, uses Merkle tree technology to construct a tree structure, performs data integrity verification, and generates a Merkle tree structure. The smart contract deployment module is based on a Merkle tree structure and uses the Solidity programming language to deploy smart contracts on the Ethereum blockchain platform, write mental health assessment logic, and generate a mental health assessment blockchain network. The digital signature and anti-fraud module is based on a mental health assessment blockchain network. It uses elliptic curve digital signature algorithm and distributed ledger technology to implement an anti-fraud mechanism, and records assessment data to generate anti-fraud verification data records. The sensitivity analysis and optimization module uses data records from anti-fraud verification to conduct sensitivity analysis using multivariate analysis of variance, linear regression analysis, and logistic regression analysis. It selects key evaluation indicators, identifies key influencing factors, and uses Six Sigma process improvement and lean management techniques to adjust and optimize the evaluation process, generating the adjusted evaluation process. The multi-party verification and data auditing module is based on the adjusted evaluation process. It uses a distributed hash table to record data and a proof-of-stake consensus algorithm for multi-party verification, and a hash chain algorithm for data auditing to generate evaluation results that have been verified by multiple parties. The privacy protection and data security module is based on the evaluation results verified by multiple parties. It uses RSA encryption technology and Laplace noise mechanism differential privacy technology to protect the data. At the same time, it uses data desensitization and anonymization processing methods to conduct privacy audits and generate privacy-protected evaluation data. The variable point detection and fractal analysis module uses privacy-protected assessment data, employs time series analysis technology, CUMSUM and Bayesian variable point detection methods to perform time series breakpoint analysis, and uses box dimension calculation methods to perform fractal analysis, generating a fractal feature report of psychological state.

Images