Privacy encryption method in archive record tracing based on block chain

Abstract

The invention discloses a privacy encryption method in archive record tracing based on a block chain, and the method comprises the steps: collecting archive record data under archive record tracing, and carrying out the preprocessing of the archive record data; classifying and grading the archive record data according to the importance degree to obtain sub-control data, and constructing an encryption strategy based on the sub-control data; performing hierarchical encryption on the archive record data according to the encryption strategy to obtain encrypted data, and constructing an archive record tracing privacy encryption model according to the encrypted data; and optimizing the archive record tracing privacy encryption model according to the encryption error, inputting to-be-encrypted data into the archive record tracing privacy encryption model, and outputting a privacy encryption result. The method not only can improve the accuracy of privacy encryption, but also has better interpretability, and can be directly applied to a privacy encryption system.

Description

Technical Field

[0001] The present invention relates to the field of privacy encryption, and particularly to a privacy encryption method in file record traceability based on blockchain. Background Art

[0002] With the rapid development of information technology, the digital management of file records has become increasingly important. However, the privacy protection and data security issues of file records have also become increasingly prominent. In the traditional file management system, risks such as data leakage, tampering, and unauthorized access are faced during data sharing and transmission. To address these challenges, blockchain technology has been introduced into file record management, providing a new solution for the traceability and privacy protection of file records by virtue of its decentralized, immutable, and highly secure characteristics.

[0003] Although blockchain technology itself has relatively high security performance, it is still difficult to fully meet the privacy protection requirements of file record data only relying on its own characteristics. In addition, although traditional encryption methods can encrypt and protect data, when facing a large amount of file record data, there are often problems such as low encryption efficiency, complex key management, and it is difficult to perform flexible classification and grading encryption according to the importance of the data, and accurate privacy protection cannot be achieved.

[0004] Although blockchain technology has many advantages in file management, it also faces some challenges in practical applications: how to seamlessly connect the existing file management system with the blockchain platform is a key issue. Since each new record added to the blockchain requires verification by all network nodes, there may be delays when processing a large amount of high-frequency file data. Although the blockchain itself has a high level of security, improper design may also lead to the leakage of sensitive information.

[0005] Therefore, there is an urgent need to invent a new privacy encryption method to improve the security, efficiency, and reliability of privacy encryption. Summary of the Invention

[0006] The object of the present invention is to provide a privacy encryption method in file record traceability based on blockchain.

[0007] To achieve the above object, the present invention is implemented according to the following technical solution: The present invention includes the following steps: Collect file record data under file record traceability, and preprocess the file record data; In the actual evaluation, the file record data of XXX is used as the research object, which includes record A, record B, and record C; Classify and grade the file record data according to the importance to obtain classified control data, and construct an encryption strategy based on the classified control data; including: Construct the Euclidean distance matrix through the archival record data, determine the set of K nearest neighbors, and calculate the local density of the archival record data: , where the local density of the x-th archival record data is , the c-th archival record data is , the x-th archival record data is , the archival record data and the archival record data The Euclidean distance is , the number of elements in the nearest neighbor set of the archival record data is , the nearest neighbor set of the archival record data is , the adjustment factor is , the set of archival record data is B, and the probability of the archival record data appearing is ; For the local archival record data with less than 3 samples, the Gaussian kernel function is used to calculate the sparse local density: , where the sparse local density of the x-th archival record data is , and the truncation distance of the c-th archival record data is ; Obtain the classification clusters according to the local density, and calculate the optimized mean shift of the archival record data: , where the optimized mean shift of the archival record data is , the bandwidth parameter is , the dimension The bandwidth parameter of is , the number of archival record data is , and the kernel density gradient estimate is ; Take the archival record data with the largest optimized mean shift as the cluster center of the classification cluster, extract the feature information of the archival record data within the classification cluster, and calculate the importance of the feature information: , where the probability of the x-th feature information appearing in the y-th classification cluster is , the number of classification clusters is , the adjustment factor of the x-th feature information is , the correlation degree of the x-th feature information in the y-th classification cluster is , and the importance of the x-th feature information is ; Sort the feature information in descending order according to the importance level to obtain the sub-control data. Among them, the importance level of feature information less than 1 and greater than or equal to 0.752 is the first level, the importance level of feature information greater than or equal to 0.479 and less than 0.752 is the second level, the importance level of feature information greater than or equal to 0.283 and less than 0.479 is the third level, and the importance level of feature information greater than or equal to 0 and less than 0.283 is the fourth level; In the actual evaluation, the importance level of the feature information of record A is the first level, the importance level of the feature information of record B is the third level, and the importance level of the feature information of record C is the second level; Record A embeds a timestamp at the middle end, record B embeds timestamps at the start end and the middle end respectively, and record C embeds timestamps at the start end and the end end respectively; Record A: Only accessible to top-level permission personnel; Record B: Accessible to personnel with second-level permissions and above; Record C: Accessible to personnel with third-level permissions and above; Perform hierarchical encryption on the archival record data according to the encryption policy to obtain encrypted data, and construct an archival record traceability privacy encryption model based on the encrypted data; In the actual evaluation, record A: Embed the timestamp 2023-10-01T12:00:00Z at the middle end of the data; Record B: Embed the timestamp 2023-10-01T12:00:00Z at the start end and embed the timestamp 2023-10-01T12:02:30Z at the middle end; Record C: Embed the timestamp 2023-10-01T12:00:00Z at the start end and embed the timestamp 2023-10-01T12:05:00Z at the end end; Optimize the archival record traceability privacy encryption model according to the encryption error, input the data to be encrypted into the archival record traceability privacy encryption model, and output the privacy encryption result.

[0008] Furthermore, the method for constructing an encryption policy based on the sub-control data includes: When the importance level of the feature information of the sub-control data is the first level, embed a timestamp at the middle end of the archival record data; when the importance level of the feature information of the sub-control data is the second level, embed timestamps at the start end and the end end of the archival record data respectively; when the importance level of the feature information of the sub-control data is the third level, embed timestamps at the start end and the middle end of the archival record data respectively; when the importance level of the feature information of the sub-control data is the fourth level, embed timestamps at the start end, the end end, and the middle end of the archival record data respectively; At the same time, add identity restrictions. When the importance level of the characteristic information of the sub-control data is level one, the identity restriction is for top-level permission personnel; when the importance level of the characteristic information of the sub-control data is level two, the identity restriction can be required for level-two permission personnel and above; when the importance level of the characteristic information of the sub-control data is level three, the identity restriction can be required for level-three permission personnel and above; when the importance level of the characteristic information of the sub-control data is level four, the identity restriction can be required for level-four permission personnel and above. Among them, the top-level permission personnel are engineers, the level-two permission personnel are project leaders, the level-three permission personnel are project executors, and the level-four permission personnel are ordinary employees.

[0009] Furthermore, the method for performing hierarchical encryption on the archival record data according to the encryption policy to obtain encrypted data includes: Extract the characteristic information of the archival record data, use the characteristic information as nodes, and calculate the importance level of the nodes; Calculate the weight coefficient of the nodes: , Among them, the importance level of the w-th node is , the joint distribution of the w-th node and the k-th node is , the weight coefficient of the w-th node is , the marginal distribution of the w-th node is , the marginal distribution of the k-th node is , the importance level of the k-th node is ; Calculate the privacy matching index of the nodes according to the encryption policy: , Among them, the privacy matching index of the w-th node is , the j-th privacy policy is , the average value of the privacy policies is , the number of privacy policies is , the w-th node is , the average value of the nodes is , the regulation parameter is , the balance factor is , the number of privacy policies is ; If , then the encryption level of the node is level four; if , then the encryption level of the node is level three; if , then the encryption level of the node is level two; if , then the encryption level of the node is level one; Perform timestamp embedding on the archival record data using a three-dimensional point cloud model according to the encryption level, and calculate the weight of the bits: , where the weight of node u is , the number of nodes is N, and the bit form of the nodes is ; Embed the timestamp, and the expression is: , , where the coordinates of the vertex are , the x-axis coordinate of the vertex is , the y-axis coordinate of the vertex is , the z-axis coordinate of the vertex is , the timestamp embedding parameter is , the three-dimensional unit vector is , and the error value of the vertex coordinates is ; Convert the archival record data embedded with the timestamp into a byte string and output it as encrypted data.

[0010] Furthermore, a method for constructing an archival record traceability privacy encryption model based on the encrypted data includes: The archival record traceability privacy encryption model includes an autoencoder, blockchain technology, and deep learning algorithms; The autoencoder compresses the encrypted data into a low-dimensional representation through the encoder, and then reconstructs the original data through the decoder to learn the essential features of the data and obtain encrypted features; Blockchain technology encrypts the immutability and security of data through hash functions, asymmetric encryption, and consensus mechanisms, and at the same time uses a distributed ledger to achieve decentralized encrypted data storage and verification to obtain privacy encrypted data; The deep learning algorithm combines the encrypted features and the privacy encrypted data to learn the encryption pattern and verification rules of the data during the training process, thereby obtaining encryption skills and enhancing data security.

[0011] Furthermore, a method for optimizing the archival record traceability privacy encryption model according to the encryption error includes: Introduce the particle swarm optimization algorithm, use the error between the predicted encryption result and the actual encryption result as the fitness function, and use the encryption result as the particle; Take the position of the particle with the minimum fitness as the best position and update the position of the particle. The expression is: , where the updated position of the z-th particle in the (t + 1)-th iteration is , the initial position of the z-th particle is , the control coefficient is , the scanning factor is , and the random number from 0 to 1 is , the original sequence of the z-th particle in the t-th iteration is , and the best position is ; Update the position of the particle through the distribution operator to obtain the moving position, and the expression is: , where the moving position of the z-th particle in the (t + 1)-th iteration is , the random number between 0 and 1 is , the random number between -1 and 1 is , and the updated position of the z-th particle in the t-th iteration is ; Update the moving position according to the spiral coefficient to obtain the spiral position, and the expression is: , where the spiral coefficient is , the current iteration number is t, and the maximum iteration number is , the moving position of the z-th particle in the t-th iteration is , the position of the random particle in the t-th iteration is , and the spiral position of the z-th particle in the (t + 1)-th iteration is ; Introduce an inhibition factor, and update and adjust the spiral position according to the inhibition factor to obtain the inhibition position. The expression is: , , where the inhibition factor in the t-th iteration is , and the random numbers between 0 and 1 are respectively 、 , the spiral position of the z-th particle in the t-th iteration is , and the inhibition position of the z-th particle in the (t + 1)-th iteration is ; Iterate continuously until the maximum iteration number is reached, otherwise update the inhibition factor and reselect the optimal solution.

[0012] In a second aspect, an embodiment of the present application further provides an electronic device, including: a processor; and a memory arranged to store computer-executable instructions, where the executable instructions, when executed, cause the processor to execute the method steps described in the first aspect.

[0013] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute the method steps described in the first aspect.

[0014] The beneficial effects of the present invention are as follows: The present invention is a privacy encryption method in the traceability of archive records based on blockchain. Compared with the prior art, the present invention has the following technical effects: Through the steps of preprocessing, classification and grading, constructing an encryption strategy, hierarchical encryption, model construction and model optimization, the present invention can improve the accuracy of privacy encryption in the traceability of archive records, thereby improving the precision of privacy encryption in the traceability of archive records. Optimizing the privacy encryption in the traceability of archive records can greatly save resources, improve work efficiency, and realize intelligent privacy encryption in the traceability of archive records. It can automatically classify and grade and perform hierarchical encryption in real time, which is of great significance for the privacy encryption in the traceability of archive records. It can adapt to the privacy encryption of archive records traceability with different standards and the privacy encryption requirements of different archive records traceability, and has a certain universality. Brief Description of the Drawings

[0015] Figure 1 is a flowchart of the steps of a privacy encryption method for archive record traceability based on blockchain according to the present invention; Figure 2 is a schematic structural diagram of an electronic device in an embodiment of this specification. Detailed Embodiments

[0016] The present invention will be further described below through specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention, but do not limit the present invention.

[0017] A privacy encryption method for archive record traceability based on blockchain according to the present invention includes the following steps: As Figure 1 shown, in this embodiment, it includes the following steps: Collect archive record data under archive record traceability, and preprocess the archive record data; Classify and grade the archive record data according to the importance to obtain sub-control data, and construct an encryption strategy based on the sub-control data; including: Construct an Euclidean distance matrix through archive record data, determine the K-nearest neighbor set, and calculate the local density of the archive record data: , where the local density of the xth archive record data is , the cth archive record data is , the xth archive record data is , the archive record data and the archive record data The Euclidean distance of is , the archival record data The number of elements in the neighbor set of , the archival record data The neighbor set of , the adjustment factor is , the set of archival record data is B, the archival record data The probability of occurrence is ; For local archival record data with less than 3 samples, the Gaussian kernel function is used to calculate the sparse local density: , Among them, the sparse local density of the x-th archival record data is , the truncation distance of the c-th archival record data is ; Obtain classification clusters according to the local density, and calculate the optimized mean shift of the archival record data: , Among them, the archival record data The optimized mean shift of is , the bandwidth parameter is , dimension The bandwidth parameter of is , the number of archival record data is , the kernel density gradient estimate is ; Take the archival record data with the largest optimized mean shift as the cluster center of the classification cluster, extract the feature information of the archival record data within the classification cluster, and calculate the importance of the feature information: , Among them, the probability of the x-th feature information appearing in the y-th classification cluster is , the number of classification clusters is , the adjustment factor of the x-th feature information is , the correlation degree of the x-th feature information in the y-th classification cluster is , the importance of the x-th feature information is ; Sort the feature information in descending order according to the importance to obtain the control data; among them, the importance of the feature information less than 1 and greater than or equal to 0.752 is the first level, the importance of the feature information greater than or equal to 0.479 and less than 0.752 is the second level, the importance of the feature information greater than or equal to 0.283 and less than 0.479 is the third level, and the importance of the feature information greater than or equal to 0 and less than 0.283 is the fourth level; Perform hierarchical encryption on the archival record data according to the encryption strategy to obtain encrypted data, and construct an archival record traceability privacy encryption model according to the encrypted data; Optimize the archival record traceability privacy encryption model according to the encryption error, input the data to be encrypted into the archival record traceability privacy encryption model, and output the privacy encryption result.

[0018] In this embodiment, the method for constructing an encryption policy based on the sub-control data includes: When the importance level of the feature information of the sub-control data is level one, embed a timestamp at the middle end of the archival record data; when the importance level of the feature information of the sub-control data is level two, embed timestamps at the start end and the end of the archival record data respectively; when the importance level of the feature information of the sub-control data is level three, embed timestamps at the start end and the middle end of the archival record data respectively; when the importance level of the feature information of the sub-control data is level four, embed timestamps at the start end, the end, and the middle end of the archival record data respectively; At the same time, add identity restrictions. When the importance level of the feature information of the sub-control data is level one, the identity restriction is top-level permission personnel; when the importance level of the feature information of the sub-control data is level two, the identity restriction can be required to be level-two permission personnel and above; when the importance level of the feature information of the sub-control data is level three, the identity restriction can be required to be level-three permission personnel and above; when the importance level of the feature information of the sub-control data is level four, the identity restriction can be required to be level-four permission personnel and above; Among them, the top-level permission personnel are engineers, the level-two permission personnel are project leaders, the level-three permission personnel are project executors, and the level-four permission personnel are ordinary employees.

[0019] In this embodiment, the method for performing hierarchical encryption on the archival record data according to the encryption policy to obtain encrypted data includes: Extract the feature information of the archival record data, use the feature information as nodes, and calculate the importance level of the nodes; Calculate the weight coefficient of the nodes: , Among them, the importance level of the w-th node is , the joint distribution of the w-th node and the k-th node is , the weight coefficient of the w-th node is , the marginal distribution of the w-th node is , the marginal distribution of the k-th node is , and the importance level of the k-th node is ; Calculate the privacy matching index of the nodes according to the encryption policy: , Among them, the privacy matching index of the w-th node is , the j-th privacy policy is , the average value of the privacy policies is , and the number of privacy policies is , the w-th node is , the average value of the nodes is , the regulation parameter is , the balance factor is , the number of privacy policies is ; If , then the encryption level of the node is level four; if , then the encryption level of the node is level three; if , then the encryption level of the node is level two; if , then the encryption level of the node is level one; According to the encryption level, a 3D point cloud model is used to embed timestamps into the archival record data, and the weight of the bits is calculated: , where the weight of the bit of node u is , the number of nodes is N, and the bit form of the node is ; Embed the timestamp, and the expression is: , , where the coordinates of the vertex are , the x-axis coordinate of the vertex is , the y-axis coordinate of the vertex is , the z-axis coordinate of the vertex is , the timestamp embedding parameter is , the 3D unit vector is , the error value of the vertex coordinates is ; Convert the archival record data with the embedded timestamp into a byte string and output it as encrypted data.

[0020] In this embodiment, the method for constructing an archival record traceability privacy encryption model based on the encrypted data includes: The archival record traceability privacy encryption model includes an autoencoder, blockchain technology, and a deep learning algorithm; The autoencoder compresses the encrypted data into a low-dimensional representation through an encoder, and then reconstructs the original data through a decoder to learn the essential features of the data and obtain encrypted features; Blockchain technology encrypts the immutability and security of the data through a hash function, asymmetric encryption, and a consensus mechanism, and at the same time uses a distributed ledger to achieve decentralized encrypted data storage and verification to obtain privacy-encrypted data; The deep learning algorithm combines the encrypted features and the privacy-encrypted data to learn the encryption pattern and verification rules of the data during the training process, thereby obtaining encryption skills and enhancing data security.

[0021] In this embodiment, the method for optimizing the privacy encryption model of file record tracing according to encryption error includes: Introduce the particle swarm optimization algorithm, take the error between the predicted encryption result and the actual encryption result as the fitness function, and take the encryption result as the particle; Take the position of the particle with the minimum fitness as the best position, and update the position of the particle. The expression is: , where the updated position of the z-th particle in the (t + 1)-th iteration is , the initial position of the z-th particle is , the control coefficient is , the scanning factor is , the random number from 0 to 1 is , the original sequence of the z-th particle in the t-th iteration is , and the best position is ; Update the position of the particle through the distribution operator to obtain the moving position. The expression is: , where the moving position of the z-th particle in the (t + 1)-th iteration is , the random number between 0 and 1 is , the random number from -1 to 1 is , the updated position of the z-th particle in the t-th iteration is ; Update the moving position according to the spiral coefficient to obtain the spiral position. The expression is: , where the spiral coefficient is , the current iteration number is t, the maximum iteration number is , the moving position of the z-th particle in the t-th iteration is , the position of the random particle in the t-th iteration is , and the spiral position of the z-th particle in the (t + 1)-th iteration is ; Introduce the suppression factor, and update and adjust the spiral position according to the suppression factor to obtain the suppression position. The expression is: , , where the suppression factor in the t-th iteration is , the random numbers from 0 to 1 are respectively 、 , the spiral position of the z-th particle in the t-th iteration is , and the suppression position of the z-th particle in the (t + 1)-th iteration is ; Iterate continuously until the maximum number of iterations is reached, otherwise update the suppression factor and reselect the optimal solution.

[0022] Figure 2 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 2 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0023] The processor, network interface, and memory can be interconnected through an internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 2 only uses a bidirectional arrow to represent it in , but it does not mean that there is only one bus or one type of bus.

[0024] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0025] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a privacy encryption device in the traceability of blockchain-based archival records at the logical level. The processor executes the program stored in the memory and is specifically used to execute any one of the foregoing privacy encryption methods in the traceability of blockchain-based archival records.

[0026] The above as in the present application Figure 1A privacy encryption method in blockchain-based archival record traceability disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor or instructions in software form. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0027] The electronic device can also execute Figure 1 a privacy encryption method in blockchain-based archival record traceability, and implement Figure 1 the functions of the illustrated embodiment, which will not be elaborated herein in the embodiments of the present application.

[0028] The embodiments of the present application also propose a computer-readable storage medium that stores one or more programs. The one or more programs include instructions that, when executed by an electronic device including multiple application programs, execute any of the aforementioned privacy encryption methods in blockchain-based archival record traceability.

[0029] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0030] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0031] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0032] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0033] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0034] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of computer-readable media.

[0035] A computer-readable medium includes permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0036] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0037] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0038] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A privacy encryption method for archival record tracing based on blockchain, characterized in that: The following steps are involved: Collecting archival record data under archival record tracing, and preprocessing the archival record data; Classifying and grading the archive record data according to their importance to obtain sub-control data, and constructing an encryption strategy based on the sub-control data; comprising: Construct a Euclidean distance matrix through archival record data, determine the K nearest neighbor set, and calculate the local density of archival record data: ， The local density of the x-th archive record data is , the cth file record data is , the xth file record data is , archival record data and archival records The Euclidean distance is , archival record data The number of elements in the neighbor set of , archival record data The neighbor set of , the adjustment factor is , the archive record data set is B, the archive record data The probability of occurrence is ; For local archive record data with less than 3 samples, the Gaussian kernel function is used to calculate the sparse local density: ， The sparse local density of the x-th archive record data is , the cutoff distance of the cth archive record data is ; Obtain classification clusters based on local density and calculate the optimized mean shift for archival record data: ， The archive records data The optimized mean shift of , the bandwidth parameter is , dimension The bandwidth parameter is , the number of archive record data is , the kernel density gradient is estimated as ; The archive record data with the largest optimized mean shift is used as the cluster center of the classification cluster, the feature information of the archive record data in the classification cluster is extracted, and the importance of the feature information is calculated: ， The probability of the xth feature information appearing in the yth classification cluster is , the number of classification clusters is , the adjustment factor of the xth feature information is , the correlation degree of the xth feature information in the yth classification cluster is , the importance of the xth feature information is ; The characteristic information is sorted in descending order according to the importance to obtain the sub-control data; the characteristic information with a value less than 1 and greater than or equal to 0.752 is of the first level of importance, the characteristic information with a value greater than or equal to 0.479 and less than 0.752 is of the second level of importance, the characteristic information with a value greater than or equal to 0.283 and less than 0.479 is of the third level of importance, and the characteristic information with a value greater than or equal to 0 and less than 0.283 is of the fourth level of importance; Performing hierarchical encryption on the archive record data according to the encryption strategy to obtain encrypted data, and constructing an archive record traceability privacy encryption model according to the encrypted data; The archive record tracing privacy encryption model is optimized according to the encryption error, the data to be encrypted is input into the archive record tracing privacy encryption model, and the privacy encryption result is output.

2. According to the privacy encryption method in archival record tracing based on blockchain according to claim 1, it is characterized in that: The method for constructing an encryption strategy based on the distributed control data includes: When the importance of the characteristic information of the sub-control data is level one, a timestamp is embedded in the middle end of the archive record data; when the importance of the characteristic information of the sub-control data is level two, a timestamp is embedded in the starting end and the terminal end of the archive record data; when the importance of the characteristic information of the sub-control data is level three, a timestamp is embedded in the starting end and the middle end of the archive record data; when the importance of the characteristic information of the sub-control data is level four, a timestamp is embedded in the starting end, the terminal end, and the middle end of the archive record data; At the same time, identity restrictions are added. When the importance of the characteristic information of the sub-control data is level one, the identity restriction is the top-level authority personnel; when the importance of the characteristic information of the sub-control data is level two, the identity restriction can be required to be level two authority personnel and above; when the importance of the characteristic information of the sub-control data is level three, the identity restriction can be required to be level three authority personnel and above; when the importance of the characteristic information of the sub-control data is level four, the identity restriction can be required to be level four authority personnel and above; Among them, the top-level authority personnel are engineers, the second-level authority personnel are project leaders, the third-level authority personnel are project executors, and the fourth-level authority personnel are ordinary employees.

3. According to the privacy encryption method in archival record tracing based on blockchain according to claim 1, it is characterized in that: The method of hierarchically encrypting the archive record data according to the encryption strategy to obtain encrypted data includes: Extract the characteristic information of the archive record data, use the characteristic information as nodes, and calculate the importance of the nodes; Calculate the node weight coefficient: ， The importance of the wth node is , the joint distribution of the wth node and the kth node is , the weight coefficient of the wth node is , the edge distribution of the w-th node is , the edge distribution of the kth node is , the importance of the kth node is ; Calculate the privacy matching index of the node according to the encryption strategy: ， The privacy matching index of the wth node is , the jth privacy policy is , the average value of privacy policy is , the number of privacy policies is , the wth node is The average value of the node is , the control parameters are , the balance factor is , the number of privacy policies is ; like , then the encryption level of the node is level 4; if , then the encryption level of the node is level three; if , then the encryption level of the node is level 2; if , then the encryption level of the node is level one; The three-dimensional point cloud model is used to embed the timestamp of the archive record data according to the encryption level, and the weight of the bit is calculated: ， The weight of node u is , the number of nodes is N, and the bit form of the node is ; Embed timestamp, the expression is: ， ， The coordinates of the vertices are , the x-axis coordinate of the vertex is , the y-axis coordinate of the vertex is , the coordinate of the vertex on the z axis is , the timestamp embedding parameters are , the three-dimensional unit vector is , the error value of the vertex coordinates is ; The archive record data with embedded timestamp is converted into a byte string and output as encrypted data.

4. According to the privacy encryption method in archival record tracing based on blockchain according to claim 1, it is characterized in that: The method for constructing an archive record tracing privacy encryption model based on the encrypted data includes: Archival record traceability privacy encryption models include autoencoders, blockchain technology, and deep learning algorithms; The autoencoder compresses the encrypted data into a low-dimensional representation through the encoder, and then reconstructs the original data through the decoder to learn the essential characteristics of the data and obtain the encrypted features; Blockchain technology uses hash functions, asymmetric encryption and consensus mechanisms to encrypt data and ensure its immutability and security. It also uses distributed ledgers to achieve decentralized encrypted data storage and verification, and obtain private encrypted data. Deep learning algorithms acquire encryption skills and enhance data security by combining encryption features and privacy-encrypted data, learning the encryption patterns and verification rules of data during training.

5. According to the privacy encryption method in archival record tracing based on blockchain according to claim 1, it is characterized in that: The method for optimizing the archive record tracing privacy encryption model according to the encryption error includes: The particle swarm optimization algorithm is introduced, the error between the predicted encryption result and the actual encryption result is used as the fitness function, and the encryption result is used as a particle; The particle position with the smallest fitness is taken as the optimal position, and the particle position is updated. The expression is: ， The updated position of the zth particle in the t+1th iteration is , the initial position of the zth particle is , the control coefficient is , the scan factor is , a random number from 0 to 1 is , the original sequence of the zth particle in the tth iteration is , the best position is ; The particle position is updated through the distribution operator to obtain the motion position. The expression is: ， The motion position of the zth particle in the t+1th iteration is , a random number between 0 and 1 is , a random number between -1 and 1 is , the updated position of the zth particle at the tth iteration is ; Update the motion position according to the spiral coefficient to obtain the spiral position. The expression is: ， The spiral coefficient is , the current number of iterations is t, and the maximum number of iterations is , the motion position of the zth particle in the tth iteration is , the position of the random particle at the tth iteration is , the spiral position of the zth particle in the t+1th iteration is ; The inhibition factor is introduced, and the spiral position is updated and adjusted according to the inhibition factor to obtain the inhibition position. The expression is: ， ， The suppression factor for the tth iteration is , the random numbers from 0 to 1 are , , the spiral position of the zth particle at the tth iteration is , the suppression position of the zth particle in the t+1th iteration is ; Continue to iterate until the maximum number of iterations is reached, otherwise update the inhibition factor and re-select the optimal solution.

6. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which, when executed, cause the processor to perform the method according to any one of claims 1 to 5.

7. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, enables the electronic device to execute the method according to any one of claims 1 to 5.

Images