Operating personnel safety portrait data sharing method and system based on block chain technology

Abstract

The invention belongs to the technical field of data processing and sharing, and particularly relates to an operator safety portrait data sharing method and system based on the block chain technology, and the method comprises the steps: obtaining the safety behavior data of an operator, training a weighted score card model, obtaining safety score distribution, and constructing a dynamic safety portrait. Performing verification in combination with zero-knowledge proof and polynomial commitment, and generating a digital identity certificate; an improved block chain network is utilized to construct an associated data chain, IPFS distributed storage is combined to generate an on-chain feature map, a cross-chain consensus mechanism and an intelligent contract are fused, and through a multi-node weight distribution mechanism, a high-risk operation key area is positioned, a behavior abnormal mode is analyzed, and a risk evolution trend is output; the comprehensive safety degree is quantitatively scored through a distributed random forest model, the risk level is identified, a visual map is generated, high-risk personnel are marked, and meanwhile data sharing is carried out. Therefore, the problems of missing detection of key features, misjudgment of risk areas, incomplete portraits and the like in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the field of data processing and sharing technology, and specifically relates to a method and system for sharing operator safety portrait data based on blockchain technology. Background Art

[0002] With the accelerated digital transformation of industry, the sharing and application of worker safety profile data has become a core element in ensuring production safety. Accurate safety profiles, by integrating multiple sources of data such as worker behavior, environmental parameters, and training records, can provide critical support for risk warnings and emergency decision-making. However, current safety profile data sharing relies primarily on a traditional centralized architecture, with data stored on a single server. This not only poses the risk of data leakage and tampering due to hacker attacks, but also creates "data silos" in cross-departmental and cross-enterprise data flows due to a lack of trust mechanisms, severely hindering the efficiency of collaborative safety management. Furthermore, feature extraction methods based on manual rules struggle to dynamically capture safety hazards in complex operational scenarios, resulting in insufficient safety profile accuracy and an inability to meet the demands of intelligent safety management.

[0003] However, existing technologies have significant flaws: fixed feature extraction algorithms are difficult to adapt to changing operational scenarios and can easily miss key features; regional positioning is subject to interference from equipment and the environment, making it easy to misjudge risk areas; models are poorly robust to environmental changes, resulting in low data collection consistency; and they rely solely on two-dimensional data, failing to integrate multimodal information, resulting in incomplete portraits. Therefore, a highly secure and adaptable intelligent personnel portrait data sharing method is urgently needed to achieve precise safety management. Summary of the Invention

[0004] This application provides a method and system for sharing operator safety portrait data based on blockchain technology to solve problems such as missed key features, misjudgment of risk areas, and incomplete portraits in existing technologies.

[0005] The first embodiment of the present application provides a method for sharing operator safety portrait data based on blockchain technology, comprising the following steps: obtaining operator safety behavior data; training a safety portrait generation model based on the safety behavior data to obtain a safety score distribution, constructing a dynamic safety portrait based on the safety score distribution, combining zero-knowledge proof and polynomial commitment for verification, and generating a digital identity credential; based on the digital identity credential, using an improved blockchain network to construct an associated data chain, combining the IPFS distributed storage mechanism to generate an on-chain feature graph, based on the on-chain feature graph, integrating a cross-chain consensus mechanism and a smart contract, locating key areas of high-risk operations through a multi-node weight distribution mechanism, and synchronously analyzing abnormal behavior patterns, and outputting a risk evolution trend based on the abnormal behavior patterns; based on the risk evolution trend, quantitatively scoring the comprehensive safety degree through a distributed random forest model, identifying the risk level, generating a visual map and marking high-risk operators, and at the same time, sharing data.

[0006] Preferably, the digital identity credential is generated by verification through zero-knowledge proof and polynomial commitment, including: constructing a zk-SNARK zero-knowledge proof algorithm; analyzing the security behavior data according to the zk-SNARK algorithm, generating a privacy credential based on the polynomial commitment, and extracting the polynomial commitment value; based on the polynomial commitment value, generating the polynomial commitment root value binding data, and verifying the node identity through the Schnorr signature; verifying the on-chain data according to the polynomial commitment root value and the open proof, and generating the digital identity credential.

[0007] Preferably, the zk-SNARK zero-knowledge proof algorithm formula is: ; in, For concise non-interactive proofs; is the arithmetic circuit relationship; For public input; Witness for privacy; To prove the generating function; For the verification function.

[0008] Preferably, based on the security behavior data, a security portrait generation model is trained to obtain a security score distribution, including: constructing a risk assessment model; analyzing operational compliance, device interaction records, and environmental adaptability data based on the risk assessment model; based on the analyzed data, combined with a Bayesian dynamic update mechanism, generating a real-time security probability map, and obtaining security score distribution data based on the security probability map.

[0009] Preferably, the risk assessment model formula is: ; in, Score security risks; For input data; is the weight coefficient; is the feature mapping function; is the i-th dimension safety index; is the Sigmoid activation function; For risk scoring model; is the total number of features.

[0010] Preferably, a visual map is generated for sharing, and at the same time, high-risk workers are marked, including: building an on-chain data traceability mechanism; according to the traceability mechanism, calculating the gradient of the block hash to the transaction record, performing spatiotemporal aggregation, and generating a risk thermal map; superimposing the risk thermal map with the three-dimensional model of the operation scene, marking the distribution of high-risk personnel and the boundaries of abnormal behavior through color gradients, and at the same time, sharing data.

[0011] Preferably, a distributed random forest model is used to quantitatively score the comprehensive safety level and identify the risk level, including: When the safety score is ≥90 points, the risk level is low and full-authority operations are allowed; when the score is 70-89 points, the risk level is medium and supervision needs to be strengthened; when the score is 50-69 points, the risk level is high and high-risk operations are restricted; when the score is <50 points, the risk level is extremely high and on-site operations are prohibited.

[0012] The second aspect of the present application provides a worker safety portrait data sharing system based on blockchain technology, including: an acquisition module for acquiring worker safety behavior data; a verification module for training a safety portrait generation model based on the safety behavior data to obtain a safety score distribution, constructing a dynamic safety portrait based on the safety score distribution, combining zero-knowledge proof and polynomial commitment for verification, and generating a digital identity credential; an analysis module for constructing an associated data chain based on the digital identity credential using an improved blockchain network, combining the IPFS distributed storage mechanism to generate an on-chain feature graph, based on the on-chain feature graph, integrating a cross-chain consensus mechanism and a smart contract, locating key areas of high-risk operations through a multi-node weight distribution mechanism, synchronously analyzing abnormal behavior patterns, and outputting risk evolution trends based on the abnormal behavior patterns; a generation module for quantitatively scoring the comprehensive safety degree based on the risk evolution trend through a distributed random forest model, identifying risk levels, generating a visual map and marking high-risk workers, and at the same time, sharing data.

[0013] The third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and runnable on the processor. The processor executes the program to implement a method for sharing operator safety portrait data based on blockchain technology as in the above embodiment.

[0014] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored, and the program is executed by a processor to implement a method for sharing operator safety portrait data based on blockchain technology as described in the above embodiment.

[0015] Therefore, this application has the following beneficial effects: The embodiments of this application utilize the immutable and encrypted characteristics of blockchain to ensure the security and credibility of security behavior data storage and sharing, and use IPFS to achieve efficient data storage and retrieval; they also use zero-knowledge proofs and polynomial commitments to ensure the reliability of data verification, and use improved blockchain networks and smart contracts to accurately locate high-risk operation areas and analyze abnormal behavior patterns; at the same time, based on federated learning, they quantify safety risks and generate visual maps to assist in decision-making, effectively breaking through the security and efficiency bottlenecks of traditional data sharing, achieving the safe, efficient, and accurate sharing and in-depth application of operator safety profile data, and significantly improving the intelligent level of safety management and risk prevention and control capabilities. As a result, the problems of missing key features, misjudging risk areas, and incomplete profiles in existing technologies are resolved.

[0016] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, wherein:

[0018] Figure 1 This is a flowchart of a method for sharing operator safety portrait data based on blockchain technology according to an embodiment of the present application.

[0019] Figure 2 This is an example diagram of a safety portrait of workers in a construction scene provided according to an embodiment of the present application.

[0020] Figure 3 This is an example diagram of a large manufacturing enterprise using security profiling according to an embodiment of the present application.

[0021] Figure 4 This is an example diagram of risk assessment for a construction company provided according to one embodiment of the present application.

[0022] Figure 5This is an example diagram of a comprehensive safety quantification score for a large chemical park provided according to one embodiment of the present application.

[0023] Figure 6 This is a flowchart of a method for sharing operator safety portrait data based on blockchain technology according to an embodiment of the present application.

[0024] Figure 7 This is a structural diagram of a worker safety portrait data sharing system based on blockchain technology provided according to one embodiment of the present application.

[0025] Figure 8 A schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0027] The following describes the operator safety portrait data sharing method and system based on blockchain technology of the embodiment of the present application with reference to the accompanying drawings. In response to the problem of misjudgment of risk areas mentioned in the above background technology, the present application provides an operator safety portrait data sharing method based on blockchain technology. In this method, the immutability and encryption characteristics of the blockchain are used to ensure the security and credibility of the storage and sharing of safety behavior data, and the efficient storage and retrieval of data are achieved with the help of IPFS; the reliability of data verification is also guaranteed by zero-knowledge proof and polynomial commitment, and the improved blockchain network and smart contracts are used to accurately locate high-risk operation areas and analyze abnormal behavior patterns; at the same time, based on federated learning to quantify safety risks, generate visual maps to assist decision-making, effectively break through the security and efficiency bottlenecks of traditional data sharing, and realize the safe, efficient and accurate sharing and in-depth application of operator safety portrait data, significantly improving the intelligent level of safety management and risk prevention and control capabilities. As a result, the problems of missed key features, misjudgment of risk areas and incomplete portraits in the existing technology are solved.

[0028] Specifically, Figure 1 A flowchart of a method for sharing operator safety portrait data based on blockchain technology provided in an embodiment of the present application.

[0029] like Figure 1 As shown, the operator safety portrait data sharing method based on blockchain technology includes the following steps: In step S101, the safety behavior data of the operator is obtained.

[0030] It can be understood that the embodiments of the present application obtain the safety behavior data of the operating personnel, comprehensively integrate the dynamic information of the personnel's operating behavior, environmental parameters, and training records, ensure that the data covers the entire operation process and multi-dimensional scenarios, and provide basic data for subsequent analysis; dynamically reflect the safety status of the operating personnel, and avoid misjudgment of safety risks due to data missing or lagging.

[0031] In step S102, a weighted scorecard model is trained based on security behavior data to obtain a security score distribution. A dynamic security profile is constructed based on the security score distribution, and verification is performed using zero-knowledge proof and polynomial commitment to generate a digital identity credential.

[0032] Among them, the weighted scorecard model is a quantitative analysis model that assigns different weights to various indicators of the evaluation object and obtains a comprehensive score distribution after weighted calculation to achieve quantitative evaluation and hierarchical management of the target object.

[0033] It can be understood that the embodiment of the present application uses a weighted scoring card model to assign differentiated weights according to the importance of each indicator in the safety behavior data, and generates an accurate safety score distribution through weighted calculation, thereby constructing a dynamic safety portrait to intuitively present the safety status of the operators; combining zero-knowledge proof and polynomial commitment for verification to ensure the credibility and accuracy of the portrait generation process and results, and on the premise of protecting data privacy, generate authoritative and tamper-proof digital identity certificates, providing data basis for subsequent blockchain-based data sharing, risk warning and safety management decisions, and improving the refinement and intelligence level of safety management.

[0034] It should be noted that the weighted scorecard model formula is:

[0035] in, Score safety; is the weight of the i-th feature; is the standardized value of the i-th safety behavior characteristic; is the index variable; is the ending index.

[0036] For example, Figure 2As shown in the figure, in a construction scenario, a large construction company used a weighted scorecard model to construct worker safety profiles. Fifteen indicators were set across four dimensions: work ability, workload, safety penalties, and safety rewards. In the work ability dimension, key indicators included safety regulations exam scores (weighted 20%, with a maximum score of 100 points, 5 points deducted for scores below 80), skill level (15% weighted for senior workers and above, 3 points deducted for intermediate workers, and 5 points deducted for junior workers), and qualifications (15% weighted, 10 points deducted for missing certificates). In the workload dimension, factors such as the number of tasks performed (weighted 10%, 3 points deducted for fewer than 5 tasks per month) and the duration of work (weighted 10%, 5 points added for tasks exceeding 100 hours per month) were considered. In the safety penalties dimension, the "four types of violations" (8 points deducted for each minor violation, 15 points for a more serious violation, and 30 points for a severe violation) and the implementation of corrective actions (10 points deducted for failure to rectify on time). In the safety reward dimension, violation-free work sites are weighted by risk level (low risk +5 points, medium risk +8 points, high risk +12 points). This weighted calculation generates a comprehensive safety score, categorizing personnel into high, medium, and low risk levels. This provides a basis for targeted safety training and task assignments, significantly improving the efficiency and accuracy of safety management.

[0037] In an embodiment of the present application, a digital identity credential is generated through verification through zero-knowledge proof and polynomial commitment, including: constructing a zk-SNARK zero-knowledge proof algorithm; analyzing security behavior data according to the zk-SNARK algorithm, generating a privacy credential based on a polynomial commitment, and extracting the polynomial commitment value; based on the polynomial commitment value, generating a polynomial commitment root value binding data, and verifying the node identity through a Schnorr signature; verifying the on-chain data based on the polynomial commitment root value and open proof to generate a digital identity credential.

[0038] The polynomial commitment value is a specific value generated after a cryptographic commitment is made to the polynomial.

[0039] It can be understood that the embodiments of the present application verify the consistency of data and commitment polynomials through a cryptographic proof mechanism to ensure data integrity and correctness; convert complex data verification into a mathematical proof of the commitment value, combined with the zk-SNARK zero-knowledge proof algorithm, which can not only hide the privacy of the original data, but also provide a trusted anchor for the digital identity certificate through the immutability of the commitment value. At the same time, with the help of polynomial commitment root value binding and Schnorr signature, dual verification of the legitimacy of the node identity and the authenticity of the on-chain data is achieved.

[0040] It should be noted that the Schnorr signature is a digital signature scheme based on the discrete logarithm problem. It has the characteristics of signature aggregation and key hiding, and can efficiently merge and verify multiple signatures, improving signature efficiency and privacy protection capabilities in blockchain scenarios.

[0041] For example, in the application of safety profiling for power workers, the company encodes employee safety behavior data, such as the number of illegal operations in the month (3 times), the duration of safety training (16 hours), and the equipment inspection pass rate (85%), into the polynomial P(x) = 2x³ + 3x² + 16x + 85, and calculates the polynomial commitment value C = 98765. The regulatory agency randomly assigns a challenge value r = 2, and the company calculates P(2) = 2×2³ + 3×2² + 16×2 + 85 = 133, and submits P(2), the commitment value C, and related evidence based on zero-knowledge proof to the regulatory agency. By verifying the validity of the commitment value C and the consistency between P(2) and P(x), the regulatory agency confirms the authenticity and accuracy of the employee safety profile scoring results without accessing the original safety behavior data, thus protecting the employee's privacy data and ensuring the reliability and credibility of the safety profile data.

[0042] In the embodiment of the present application, the zk-SNARK zero-knowledge proof algorithm formula is:

[0043] in, For concise non-interactive proofs; is the arithmetic circuit relationship; For public input; Witness for privacy; To prove the generating function; For the verification function.

[0044] It is understandable that the embodiments of the present application can verify the authenticity and integrity of data through a simple and efficient cryptographic proof mechanism without revealing the specific content of the security behavior data by using the zk-SNARK zero-knowledge proof algorithm. The complex security behavior data verification is converted into a lightweight mathematical proof, which greatly reduces the computing resources and communication costs required for verification; combined with polynomial commitments, it can effectively hide data privacy and avoid the leakage of sensitive information; at the same time, the generated proof is verifiable and unforgeable, providing a solid security guarantee for the generation of digital identity credentials, ensuring that the authenticity of node identity and data is quickly confirmed in cross-node data interaction, and improving security and privacy protection capabilities.

[0045] It should be noted that the zk-SNARK zero-knowledge proof algorithm is an algorithm that can prove the authenticity of a statement in a simple and efficient cryptographic way without leaking specific information.

[0046] For example, in a construction scenario, a large construction company with 1,200 workers needs to prove to regulatory authorities that the workers' safety profile data is authentic and reliable while also protecting their privacy. For example, a worker committed six violations in the fourth quarter of 2024, received a total of 40 hours of safety training, and had an 85% compliance rate for safety equipment use. The company uses the zk-SNARK zero-knowledge proof algorithm to convert this data into a specific mathematical problem, generating a concise zero-knowledge proof. After receiving the proof, the regulatory authorities verify it against publicly available parameters. Without requiring access to sensitive information such as the specific circumstances of Wang Qiang's violations, training course content, or equipment usage records, they can confirm that the company's safety profile data truly reflects Wang Qiang's safety status. After verification using this algorithm, the company's security data review efficiency increased by 60%, with no privacy leaks occurring, ensuring efficient and secure security management data interaction.

[0047] In an embodiment of the present application, a security portrait generation model is trained based on security behavior data to obtain a security score distribution, including: constructing a risk assessment model; analyzing operational compliance, device interaction records, and environmental adaptability data based on the risk assessment model; generating a real-time security probability map based on the analyzed data in combination with a Bayesian dynamic update mechanism, and obtaining security score distribution data based on the security probability map.

[0048] Among them, the Bayesian dynamic update mechanism refers to a mechanism based on Bayes' theorem. After obtaining new observation data, the prior probability is updated to the posterior probability through the likelihood function calculation, and this is used as the new prior probability to continue iteratively update, thereby realizing the dynamic correction and optimization of the probability of event occurrence.

[0049] It can be understood that the embodiment of the present application combines prior knowledge with new observation data and uses Bayes' theorem to dynamically adjust the probability distribution of security risk assessment. When new operating behaviors, abnormal device interactions or environmental changes occur, the new data is quickly analyzed and the judgment of security risks is promptly corrected, so that the security score distribution accurately reflects the current actual risk situation, effectively adapts to the dynamic changes in the network security environment, and timely captures new features of security threats, so that the security score distribution is more in line with the actual risk situation, improves the accuracy and timeliness of the security portrait generation model, provides a more reliable and dynamic quantitative basis for network security decision-making, and enhances the adaptive ability and early warning response efficiency of the security protection system.

[0050] It should be noted that the core of the Bayesian dynamic update mechanism is the Bayesian theorem, which is as follows:

[0051] in, is the posterior probability; is the likelihood function; is the marginal likelihood; is the prior probability.

[0052] For example, Figure 3 As shown in the figure, a large manufacturing enterprise achieved significant results in constructing a personnel safety profile using a Bayesian dynamic update mechanism. Initially, data on employee operational compliance over the past year was collected. For example, the average number of operational violations per employee per month was two, and the correctness of operational procedures reached 85%. Regarding equipment interaction records, employees averaged 160 hours of equipment operation per month, with 20% of equipment failure reports due to improper operation. Environmental adaptability data revealed that 20% of employees experienced reduced efficiency when working in high-temperature environments, and 15% experienced increased operational errors in noisy environments. Based on this data, an initial safety probability was set, assuming an initial safety score of 70 out of 100. Over time, new data was generated. By the time the new quarter's data was collected, the number of operational violations had decreased to one per employee per month, while the correctness of operational procedures had increased to 90%. Based on the Bayesian theorem, this new evidence increased the safety probability for operational compliance, which was reflected in the safety profile, increasing the score for the operational compliance dimension from 65 to 75. At the same time, the proportion of equipment failure reports due to improper human operation has dropped to 15%, and the score of the equipment interaction record dimension has increased from 70 points to 78 points. If the company introduces a new production link in the quarter, the complexity of the environment will increase, resulting in an increase in operating errors among 30% of employees when working in the new environment, and the score of the environmental adaptability dimension will drop from 75 points to 65 points. Based on the data of various dimensions and the Bayesian dynamic update mechanism, the employee's safety score is updated to 72 points. After continuous iterative updates, the company can provide timely training for employees with high safety risks based on accurate and real-time personnel safety portraits, reduce the accident rate by 30%, and greatly improve the overall safety production level of the company.

[0053] In the embodiment of the present application, the risk assessment model formula is:

[0054] in, Score security risks; For input data; is the weight coefficient; is the feature mapping function; is the i-th dimension safety index; is the Sigmoid activation function; For risk scoring model; is the total number of features.

[0055] It is understandable that the embodiments of this application quantitatively assess the potential risks of operators in different scenarios by combing through operational compliance, equipment interaction records, and environmental adaptability safety behavior data. Key risk factors are accurately identified from massive data, and the impact of high-risk indicators is highlighted through weight distribution, helping managers quickly locate safety hazards. Combined with the Bayesian dynamic update mechanism, real-time dynamic risk assessment is performed to ensure that the safety score distribution data always fits the actual safety situation, providing a data foundation for enterprise safety management decisions and reducing the probability of safety accidents.

[0056] For example, Figure 4 As shown, a construction company incorporated operational compliance data into its risk assessment model, including the frequency of construction worker violations, which averaged three violations per person per month. Equipment interaction records showed that equipment failures and repairs due to improper operation accounted for 35% of total repairs. Environmental adaptability data also revealed a 20% probability of project delays when working in complex geological environments. Based on this data, the risk assessment model assigned weights of 40%, 30%, and 30%, respectively, to operational compliance, equipment interaction records, and environmental adaptability to calculate an initial risk score. As the project progressed, new data was continuously generated. For example, if the frequency of construction worker violations in a certain area increased to five per person per month, the model would update the risk score in real time based on this new data, indicating that the risk level in that area had increased from "medium" to "high." Using this risk assessment model, the company was able to accurately identify high-risk areas and links, enabling it to implement targeted measures, such as strengthening personnel training, optimizing equipment maintenance procedures, and adjusting construction plans. This resulted in a 40% reduction in the overall project accident rate, effectively ensuring the smooth progress of the project and the safety of its personnel.

[0057] In step S103, based on the digital identity credentials, an improved blockchain network is used to construct an associated data chain, and combined with the IPFS distributed storage mechanism, an on-chain feature map is generated. Based on the on-chain feature map, the cross-chain consensus mechanism and smart contracts are integrated, and a multi-node weight distribution mechanism is used to locate key areas of high-risk operations, and synchronously analyze behavioral abnormality patterns. Based on the behavioral abnormality patterns, the risk evolution trend is output.

[0058] Among them, the improved blockchain network is a new type of distributed ledger network that is based on the core characteristics of traditional blockchain such as decentralization and immutability, and solves performance bottlenecks, reduces energy consumption or expands application scenarios through innovative designs such as optimizing consensus mechanisms, improving scalability, enhancing privacy protection or introducing cross-chain interactions.

[0059] It can be understood that the embodiments of the present application, through the use of an improved blockchain network, can efficiently process large amounts of data in high-risk operation scenarios and quickly build related data chains based on an optimized consensus mechanism and scalability; combine IPFS storage with a cross-chain consensus mechanism to achieve secure data storage and cross-chain interaction, thereby improving data credibility; through smart contracts and multi-node weight distribution, accurately locate high-risk areas, analyze abnormal behaviors, and output risk evolution trends in a timely manner, thereby improving the efficiency, accuracy, and security of risk management while ensuring that data is decentralized and tamper-proof.

[0060] It should be noted that based on the digital identity certificate, an improved blockchain network is used to build an associated data chain, combined with the IPFS distributed storage mechanism to generate an on-chain feature map, using the key information in the digital identity certificate, with the help of the improved blockchain network to sort out data associations, build a structured data chain, and store the data through IPFS distribution. The corresponding hash value is obtained to establish a mapping relationship with the blockchain, and then the decentralized stored data features are aggregated and encoded, and finally an on-chain feature map containing data associations, storage locations and feature information is generated.

[0061] Based on the on-chain feature graph, the cross-chain consensus mechanism and smart contracts are integrated. Through the multi-node weight distribution mechanism, key areas of high-risk operations are located, and abnormal behavior patterns are simultaneously analyzed. According to the abnormal behavior patterns, the risk evolution trend is output. Based on the on-chain feature graph, the cross-chain consensus mechanism is used to realize the collaborative verification of data between different blockchains. Relying on the smart contract to automatically execute the preset rules, combined with the multi-node weight distribution mechanism, different voices are given to nodes according to their importance, and high-risk operation areas are accurately located. At the same time, by analyzing the behavioral data of the operators, abnormal behavior patterns are simultaneously identified, the risk development situation is predicted, and the risk evolution trend is output, providing data support and decision-making basis for safety management.

[0062] The smart contract's pre-set rules are based on data verification, risk identification, location decision-making, and early warning feedback. Data verification rules include verifying whether digital identity credentials are valid, whether the data in the on-chain feature map is complete and meets format requirements, and whether cross-chain interaction data has been collaboratively verified by different blockchains. Risk identification rules set quantitative standards for abnormal operating behavior, such as the length of time an operator stays in a high-risk area exceeding the normal threshold, the frequency of equipment operation exceeding the safety standard by a multiple, or the number of times the operating sequence deviates from the standard process. Location decision rules combine a multi-node weight distribution mechanism. When more than a certain weight ratio of nodes determines that an area is at risk, the area is designated as a high-risk operation key area. Early warning feedback rules specify that when the duration of an abnormal pattern reaches a set length, or the risk evolution trend reaches the preset risk level boundary, different levels of warnings are automatically triggered, and risk information is synchronized to relevant safety management personnel, providing a reliable basis for safety management.

[0063] The IPFS distributed storage mechanism is a content-addressed, decentralized distributed storage network. By fragmenting files and storing them on multiple nodes and uniquely identifying them with hash values, it achieves a new storage model that allows for efficient data storage, resistance to single-point failures, and distributed retrieval.

[0064] The cross-chain consensus mechanism is a collaborative consensus mechanism that achieves data verification, state synchronization and consensus between different chains through cross-blockchain protocol design, thereby solving the problem of blockchain islands.

[0065] Smart contracts are distributed protocols that are based on the programmable nature of blockchain and pre-define rules in code and are automatically executed.

[0066] For example, in industrial production scenarios, smart contracts can be used to construct personnel safety profiles, enabling accurate assessments of employee safety status. Employees log in daily using digital credentials, and their work data is uploaded to the blockchain in real time. The smart contract pre-sets multiple rules. For example, if an employee works continuously for more than eight hours, a fatigue alert is automatically triggered. For safety training, if an employee fails to complete daily safety training, the smart contract prohibits them from entering high-risk areas. Furthermore, if an employee makes three cumulative operational errors, the smart contract automatically suspends their operational privileges. Once employee behavior data triggers these pre-set conditions, a safety profile tag is automatically generated based on the smart contract. For example, if an employee makes five operational errors and enters a high-risk area twice within a month, the smart contract will flag them as high-risk, issue an alert, restrict their access to specific areas, and recommend targeted safety training courses. In this way, smart contracts enable efficient and accurate assessment and management of personnel safety status, significantly improving safety in production.

[0067] In step S104, based on the risk evolution trend, the comprehensive safety degree is quantitatively scored through the distributed random forest model, the risk level is identified, a visual map is generated, and high-risk workers are marked. At the same time, data sharing is carried out.

[0068] Among them, the distributed random forest model is a machine learning model that implements the random forest algorithm on distributed computing.

[0069] It can be understood that the embodiment of the present application processes massive amounts of data in parallel based on the random forest algorithm, quickly and efficiently quantifies the overall safety level based on the risk evolution trend, accurately identifies the risk level, solves the memory and performance problems of single-machine processing, and improves computing efficiency; combines visual maps to mark high-risk workers, presents risk distribution in an intuitive manner, and provides basic data for decision-making; at the same time, the data sharing function promotes collaboration among multiple departments, exchanges information, and improves the ability of departments to work together.

[0070] It should be noted that the random forest algorithm formula is:

[0071]

[0072] in, is the number of base learners; is the predicted probability of the sample by the i-th base learner; The probability of the i-th base learner predicting an error; Score the final fused continuous value; is the final predicted category label; is the position corresponding to the maximum value of variable k; is the indicator function; is the predicted category of sample x by the i-th base learner; To count the prediction results of all base learners, calculate the number of base models that predict category k.

[0073] For example, Figure 5 As shown, a large chemical park used a distributed random forest model based on historical operational data from over 5,000 workers (including over 10 types of features, such as equipment inspection records, duration of hot work, and safety training participation, totaling 200GB of data) and three years of risk evolution trend data (updated monthly with 20,000 risk events). The model, in parallel, invoked 200 distributed decision trees to quantify the overall safety level. After a five-minute computation (a 70% improvement in efficiency compared to a traditional stand-alone model), the model accurately identified risk levels: 62% (3,100 workers) were classified as low-risk, 25% (1,250 workers) as medium-risk, and 13% (650 workers) as high-risk. Simultaneously, a visual safety risk map was generated, using thermal images to identify 12 high-risk work areas. Combined with worker location, 650 high-risk workers were accurately identified. For example, Zhang San, a hot work worker in a facility area, failed to wear protective gear properly three times in a row, resulting in a safety score of 0.3 and a high-risk rating. Data sharing is achieved through the park's safety management platform, and the safety supervision department, workshop teams, and training center work together. Based on the profiling results, special safety training is completed for high-risk personnel within 48 hours (training coverage rate 100%). A re-evaluation one month later showed that the proportion of high-risk personnel has dropped to 5%, effectively improving the intelligence and refinement of the park's safety management.

[0074] In an embodiment of the present application, a visual map is generated for sharing, and at the same time, high-risk workers are marked, including: building an on-chain data traceability mechanism; according to the traceability mechanism, calculating the gradient of the block hash to the transaction record, performing spatiotemporal aggregation, and generating a risk thermal map; superimposing the risk thermal map with the three-dimensional model of the operation scene, marking the distribution of high-risk personnel and the boundaries of abnormal behavior through color gradients, and at the same time, sharing data.

[0075] Among them, the on-chain data traceability mechanism uses blockchain to record the entire process information such as data generation and modification through blocks, and relies on hash encryption, distributed storage and chain structure to achieve a mechanism that can be checked, verified and traced for data source, flow and operation.

[0076] It can be understood that the embodiment of the present application uses the tamper-proof and traceable characteristics of the blockchain to accurately record the entire process information of security data, provide data for calculating the gradient and spatiotemporal aggregation of block hashes to generate risk thermal maps for transaction records, ensure the authenticity of the data, and enable the risk thermal map to accurately reflect the distribution of operational risks; when subsequently superimposed with the three-dimensional model of the operational scene, the distribution of high-risk personnel and the boundaries of abnormal behavior can be accurately marked through color gradients to clearly present the security risk situation. At the same time, due to the trusted sharing attributes of the data on the chain, data barriers are broken, and efficient circulation of security data in the management link is achieved, helping multiple departments to jointly carry out security supervision and risk disposal, and comprehensively improve the accuracy, visualization effect and sharing and collaboration efficiency of security portraits.

[0077] It should be noted that according to the traceability mechanism, the gradient of the block hash to the transaction record is calculated, and spatiotemporal aggregation is performed to generate a risk thermal map. Based on the on-chain data traceability mechanism, by calculating the gradient of the block hash to the transaction record, the sensitivity of data to changes during storage and circulation in the blockchain is quantified, and subtle features of data changes are captured; using the time and space dimensions as clues, transaction records in different time periods and different operating areas are aggregated and analyzed, and risk information is graded according to intensity, and finally a risk thermal map is generated, which intuitively presents the distribution of high-risk operating areas and high-risk periods.

[0078] For example, in the construction of a super-high-rise commercial complex, an on-chain data traceability mechanism ensured comprehensive safety management. During the construction period, approximately 1,200 data items were uploaded daily in real time to the blockchain (including attendance clocks for 800 workers, operating parameters of 300 pieces of machinery, and 100 safety inspection records), forming approximately 200 data blocks. Following a high-altitude work accident, calculations of the gradient of block hashes against transaction records revealed abnormal fluctuations in the load-bearing sensor data of the tower crane in block 4567 within three hours prior to the accident. The hash value fluctuation gradient reached 0.8 (normal range 0.1-0.3), locating key records indicating equipment overload. Based on spatiotemporal aggregation analysis, 23 equipment anomaly records and 18 instances of personnel violations in the same area over the previous 15 days were integrated to generate a risk heat map. The construction area on floors 28-32, where the accident occurred, was highlighted in red. The risk heat map for this area reached 92 points (out of a maximum of 100), far exceeding the average score of 65. The project party shared the complete on-chain traceability data with the safety supervision department, which included 127 tamper-proof operation logs and 28 sets of associated hash values. The accident responsibility was determined in just two days. Based on the thermal mapping results, 8 sets of safety monitoring equipment were added, reducing the high-risk operation accident rate in the subsequent construction phase by 67%.

[0079] In an embodiment of the present application, a distributed random forest model is used to quantify the comprehensive safety level and identify the risk level, including: when the safety score is ≥90 points, the risk level is low and full-authority operations are allowed; the score is 70-89 points, the risk level is medium and supervision needs to be strengthened; the score is 50-69 points, the risk level is high and high-risk operations are restricted; the score is <50 points, the risk level is extremely high and on-site operations are prohibited.

[0080] It can be understood that the embodiment of the present application provides a basis for operation control efficiently and accurately by quantifying the comprehensive safety score and dividing the risk level. When the safety score is ≥90 points, it is judged as low risk, and full authority operations are allowed to fully guarantee production efficiency and avoid excessive control; the medium risk level of 70-89 points triggers enhanced supervision in time to reduce the probability of risk; the high risk level of 50-69 points restricts high-risk operations to avoid major accidents; the extremely high risk level of <50 points directly prohibits on-site operations to eliminate serious safety hazards. The hierarchical control mechanism ensures safe production, flexibly balances production efficiency and safety risks, and resources can be reasonably allocated and efficiently utilized.

[0081] According to the operator safety portrait data sharing method based on blockchain technology proposed in the embodiment of this application, the immutability and encryption characteristics of blockchain are used to ensure the security and credibility of safety behavior data storage and sharing, and IPFS is used to achieve efficient data storage and retrieval; the reliability of data verification is also guaranteed through zero-knowledge proof and polynomial commitment, and an improved blockchain network and smart contracts are used to accurately locate high-risk operation areas and analyze abnormal behavior patterns; at the same time, based on federated learning to quantify safety risks, a visual map is generated to assist decision-making, effectively breaking through the security and efficiency bottlenecks of traditional data sharing, realizing the safe, efficient, and accurate sharing and in-depth application of operator safety portrait data, and significantly improving the intelligent level of safety management and risk prevention and control capabilities. As a result, the problems of missing key features, misjudging risk areas, and incomplete portraits in the existing technology are solved.

[0082] The following will illustrate the operator safety portrait data sharing method based on blockchain technology through a specific embodiment. Figure 6 As shown, including: Within the chemical plant, various devices are used to collect worker safety behavior data. In the reactor production workshop, smart cameras detected the following behaviors by worker Zhang San from October 1 to October 7, 2024: three instances of operating without protective gloves, each lasting approximately five minutes; and one instance of illegal hot work, lasting 10 minutes. Equipment sensors recorded four abnormal startups of the reactor he was operating during that week (startup times exceeded the normal range by ±10 seconds), and three instances of operating temperature settings exceeding the safety threshold, each lasting three to five minutes. Environmental monitoring equipment indicated that the hazardous chlorine concentration in the work area reached 80 ppm (the safety threshold is 50 ppm) between 2:00 PM and 3:00 PM on October 3, and the temperature reached 45°C (normal operating range 20-35°C) at 10:00 AM on October 5. This data was organized into a time series to form a safety behavior dataset containing the worker ID (Zhang San-001), data collection time, and data details.

[0083] Building a risk assessment model: , set the operational compliance weight =0.4, device interaction record weight =0.3, environmental fitness weight =0.3. The specific penalty rules are as follows: Operational compliance: 8 points will be deducted for each failure to wear protective gloves, 15 points for each violation of hot work regulations, 10 points for each violation of equipment operation procedures, 12 points for each violation of high-risk operations without wearing goggles, 20 points for each violation of bringing a fire source into a fire-prohibited area, 18 points for each violation of smoking in the work area, and 12 points for each violation of leaving the post without permission. Equipment interaction records: 5 points will be deducted for each abnormal equipment startup, 7 points for each operation parameter exceeding the threshold, 9 points for each abnormal vibration alarm of an equipment component, and 6 points for each abnormal valve opening and closing. Environmental adaptability: 0.5 points will be deducted for each minute that the harmful gas concentration exceeds the standard, 1 point for each 1°C temperature abnormality, and 0.4 points for each minute that the dust concentration exceeds the standard. Incorporating a Bayesian dynamic update mechanism, the model parameters are continuously updated based on newly collected data, generating a real-time safety probability map. Ultimately, Zhang San's safety score for that week was determined to be in the high-risk range (50-69 points), while Li Si and Wang Wu's safety scores were in the medium-risk range (70-89 points).

[0084] Constructing zk-SNARK zero-knowledge proof algorithm: , the security behavior data of Zhang San, Li Si and Wang Wu are analyzed respectively, and the privacy credentials based on polynomial commitment are generated. The polynomial commitment values ​​are extracted as follows: =1234567890, =9876543210, =5678901234. Based on these commitment values, polynomial commitment root values ​​are generated for binding data, and Schnorr signatures are used to verify node identity. Finally, based on the polynomial commitment root values ​​and open proofs, on-chain data is verified and respective digital identity credentials are generated, ensuring data privacy and authenticity.

[0085] Based on the digital identity credentials of Zhang San, Li Si, and Wang Wu, and leveraging an improved blockchain network and the IPFS distributed storage mechanism, the safety behavior data of the three individuals, including records of illegal operations, equipment interaction data, and environmental data, was stored on the IPFS network. These hash values ​​were recorded on the blockchain, generating an on-chain feature map. By integrating a cross-chain consensus mechanism with smart contracts, a multi-node weight distribution mechanism was employed for analysis. Within a week, monitoring of the reactor operation area revealed that eight operators, including Zhang San, Li Si, and Wang Wu, all had safety scores below 80. There were also 35 records of abnormal equipment operation in this area, with hazardous gas concentrations exceeding the standard for a total of 5 hours and dust concentrations exceeding the standard for a total of 4 hours. Based on this data, the reactor operation area was identified as a critical high-risk area for operations. Further analysis of Zhang San's illegal debugging and unauthorized leaving of post, Li Si's failure to follow procedures, and Wang Wu's illegal carrying of fire and smoking, combined with historical data, predicts that if these behaviors continue, Zhang San will have an 85% probability of causing equipment failure and a 30% probability of causing serious accidents such as explosions in the next month; Li Si will have a 70% probability of causing equipment damage and a 25% probability of causing production interruptions; Wang Wu will have a 60% probability of causing fire and a 15% probability of causing casualties.

[0086] A distributed random forest model was used to quantify the comprehensive safety scores of Zhang San, Li Si, and Wang Wu. Zhang San ultimately scored 58, placing him at a high risk level; Li Si scored 75, placing him at a medium risk level; and Wang Wu scored 72, placing him at a medium risk level. Zhang San was subsequently restricted from performing high-risk operations such as working with flames and working at heights, and a risk warning was issued. Daily supervision of Li Si and Wang Wu was also strengthened, requiring them to participate in safety training. An on-chain data traceability mechanism was established, calculating the gradient of block hashes with respect to transaction records and performing spatiotemporal aggregation to generate a risk thermal map. In a three-dimensional operational scenario model of a chemical plant, high-risk reactor operating areas were marked in red, and surrounding areas with medium risk were marked in orange. This clearly marked the distribution of high- and medium-risk individuals, including Zhang San, Li Si, and Wang Wu, as well as the boundaries of abnormal behavior. This visual map, along with relevant data such as the three individuals' specific violation records and risk prediction results, was shared with safety management and operational personnel. Based on this, safety management personnel formulated targeted supervision measures, such as adding inspection robots to the reactor area to conduct inspections once an hour, and organizing safety warning training for all operators; after Zhang San, Li Si and Wang Wu reviewed their own safety portraits, they realized the seriousness of the problem, took the initiative to learn safe operating procedures, and actively improved their operating behaviors.

[0087] In summary, the present invention collects the safety behavior data of operators through the collaborative collection of multiple devices, combines the risk assessment model with the Bayesian dynamic update mechanism, can accurately quantify safety risks, and quickly locate high-risk personnel such as Zhang San and medium-risk personnel such as Li Si and Wang Wu; uses the zk-SNARK zero-knowledge proof algorithm and IPFS distributed storage to ensure data privacy and security, and achieve efficient storage and trusted sharing; the associated data chain built based on blockchain and multi-mechanism collaborative analysis can accurately lock high-risk operation areas such as reactor operation areas, and scientifically predict risk evolution trends; finally, quantitative scoring and visual data sharing help safety management personnel quickly formulate and implement targeted supervision measures, and operators can also intuitively understand their own safety status, actively standardize operating behaviors, effectively reduce the probability of accidents, and comprehensively improve the level and efficiency of chemical plant operation safety management, building a solid line of defense for safe production.

[0088] Next, the operator safety portrait data sharing system based on blockchain technology proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0089] Figure 7 It is a block diagram of the operator safety portrait data sharing system based on blockchain technology in an embodiment of the present application.

[0090] like Figure 7 As shown, the operator safety portrait data sharing system 10 based on blockchain technology includes: an acquisition module 100, a verification module 200, an analysis module 300, and a generation module 400.

[0091] Among them, the acquisition module 100 is used to obtain the safety behavior data of the operating personnel; the verification module 200 is used to train the safety portrait generation model based on the safety behavior data, obtain the safety score distribution, build a dynamic safety portrait based on the safety score distribution, combine zero-knowledge proof and polynomial commitment for verification, and generate a digital identity certificate; the analysis module 300 is used to use the improved blockchain network to build an associated data chain based on the digital identity certificate, combine the IPFS distributed storage mechanism to generate an on-chain feature map, based on the on-chain feature map, integrate the cross-chain consensus mechanism and smart contracts, and locate the key areas of high-risk operations through a multi-node weight distribution mechanism, and simultaneously analyze the abnormal behavior patterns. According to the abnormal behavior patterns, the risk evolution trend is output; the generation module 400 is used to quantify the comprehensive safety degree based on the risk evolution trend through a distributed random forest model, identify the risk level, generate a visual map and mark high-risk operating personnel, and at the same time, share data.

[0092] It should be noted that the above explanation of the embodiment of the operator safety portrait data sharing method based on blockchain technology is also applicable to the operator safety portrait data sharing system based on blockchain technology in this embodiment, and will not be repeated here.

[0093] According to the operator safety portrait data sharing system based on blockchain technology proposed in the embodiment of this application, the immutable and encrypted characteristics of blockchain are used to ensure the security and credibility of safety behavior data storage and sharing, and IPFS is used to achieve efficient data storage and retrieval; the reliability of data verification is also guaranteed through zero-knowledge proof and polynomial commitment, and an improved blockchain network and smart contracts are used to accurately locate high-risk operation areas and analyze abnormal behavior patterns; at the same time, based on federated learning to quantify safety risks and generate visual maps to assist decision-making, it effectively breaks through the security and efficiency bottlenecks of traditional data sharing, realizes the safe, efficient, and accurate sharing and in-depth application of operator safety portrait data, and significantly improves the intelligent level of safety management and risk prevention and control capabilities. As a result, the problems of missing key features, misjudging risk areas, and incomplete portraits in the existing technology are solved.

[0094] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include: A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0095] When the processor 802 executes the program, the operator safety portrait data sharing method based on blockchain technology provided in the above embodiment is implemented.

[0096] Furthermore, the electronic device further includes: The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0097] The memory 801 is used to store computer programs that can be run on the processor 802.

[0098] The memory 801 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0099] If the memory 801, processor 802, and communication interface 803 are implemented independently, the communication interface 803, memory 801, and processor 802 can be connected to each other via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0100] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0101] The processor 802 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0102] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it implements the above-mentioned method for sharing operator safety portrait data based on blockchain technology.

[0103] In addition, an embodiment of the present application also provides a computer program product, including a computer program or instructions. When the computer program or instructions are executed, the above-mentioned method for sharing operator safety portrait data based on blockchain technology is implemented.

[0104] In the description of this specification, reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless they are mutually inconsistent.

[0105] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0106] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0107] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0108] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above-mentioned embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0109] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for sharing operator safety portrait data based on blockchain technology, characterized in that: include: Obtain safety behavior data of operators; Based on the security behavior data, a weighted scorecard model is trained to obtain a security score distribution. A dynamic security profile is constructed based on the security score distribution, and verification is performed using zero-knowledge proof and polynomial commitment to generate a digital identity credential. Based on the digital identity credentials, an improved blockchain network is used to construct a related data chain, combined with the IPFS distributed storage mechanism to generate an on-chain feature map. Based on the on-chain feature map, a cross-chain consensus mechanism and smart contracts are integrated, and a multi-node weight distribution mechanism is used to locate key areas of high-risk operations, simultaneously analyze abnormal behavior patterns, and output risk evolution trends based on the abnormal behavior patterns; Based on the risk evolution trend, a distributed random forest model is used to quantify the comprehensive safety level, identify the risk level, generate a visual map, and mark high-risk workers. At the same time, data sharing is carried out.

2. The method for sharing operator safety portrait data based on blockchain technology according to claim 1 is characterized in that: Verification is performed through zero-knowledge proof and polynomial commitment to generate digital identity credentials, including: Build zk-SNARK zero-knowledge proof algorithm; Analyze the security behavior data according to the zk-SNARK algorithm, generate a privacy credential based on the polynomial commitment, and extract the polynomial commitment value; Based on the polynomial commitment value, generate polynomial commitment root value binding data, and verify the node identity through Schnorr signature; Based on the polynomial commitment root value and open proof, the on-chain data is verified and a digital identity certificate is generated.

3. The method for sharing operator safety portrait data based on blockchain technology according to claim 2 is characterized in that: The zk-SNARK zero-knowledge proof algorithm formula: ； in, For concise non-interactive proofs; is the arithmetic circuit relationship; For public input; Witness for privacy; To prove the generating function; For the verification function.

4. The method for sharing operator safety portrait data based on blockchain technology according to claim 1 is characterized in that: Based on the safety behavior data, a weighted scorecard model is trained to obtain a safety score distribution, including: Build risk assessment models; Analyze operational compliance, equipment interaction records, and environmental adaptability data based on the risk assessment model; Based on the analyzed data, combined with the Bayesian dynamic update mechanism, a real-time safety probability map is generated, and based on the safety probability map, safety score distribution data is obtained.

5. The method for sharing operator safety portrait data based on blockchain technology according to claim 4 is characterized in that: The risk assessment model formula: ； in, Score security risks; For input data; is the weight coefficient; is the feature mapping function; is the i-th dimension safety index; is the Sigmoid activation function; For risk scoring model; is the total number of features.

6. The method for sharing operator safety portrait data based on blockchain technology according to claim 1 is characterized in that: Generate a visual map for sharing and mark high-risk workers, including: Build an on-chain data traceability mechanism; According to the traceability mechanism, the gradient of the block hash to the transaction record is calculated, and spatiotemporal aggregation is performed to generate a risk heat map; The risk thermal map is superimposed on the three-dimensional model of the operation scene, and the distribution of high-risk personnel and the boundaries of abnormal behavior are marked by color gradients. At the same time, data sharing is carried out.

7. The method for sharing operator safety portrait data based on blockchain technology according to claim 1 is characterized in that: A distributed random forest model is used to quantify the overall safety level and identify risk levels, including: When the safety score is ≥90 points, the risk level is low and full-authority operations are allowed; when the score is 70-89 points, the risk level is medium and supervision needs to be strengthened; when the score is 50-69 points, the risk level is high and high-risk operations are restricted; when the score is <50 points, the risk level is extremely high and on-site operations are prohibited.

8. A worker safety portrait data sharing system based on blockchain technology, characterized in that: include: An acquisition module is used to obtain the safety behavior data of operators; A verification module is used to train a security profile generation model based on the security behavior data to obtain a security score distribution, construct a dynamic security profile based on the security score distribution, and perform verification using zero-knowledge proof and polynomial commitment to generate a digital identity credential; An analysis module is used to construct a related data chain based on the digital identity certificate using an improved blockchain network, and generate an on-chain feature graph in combination with the IPFS distributed storage mechanism. Based on the on-chain feature graph, the module integrates the cross-chain consensus mechanism and smart contracts, locates key areas of high-risk operations through a multi-node weight distribution mechanism, and simultaneously analyzes abnormal behavior patterns. Based on the abnormal behavior patterns, the module outputs risk evolution trends; A generation module is used to quantitatively score the comprehensive safety level based on the risk evolution trend through a distributed random forest model, identify the risk level, generate a visual map and mark high-risk operators, and at the same time, share data.

9. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and runnable on the processor. The processor executes the program to implement the operator safety portrait data sharing method based on blockchain technology of claims 1-7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instructions are executed, the method for sharing operator safety portrait data based on blockchain technology of claims 1-7 is implemented.

Images