Digital archive secure circulation tracking method and system based on dynamic watermark

Abstract

The present invention discloses a method and system for tracking the secure circulation of digital archives based on dynamic watermarks, which relates to the field of digital archive technology. The method comprises the following steps: simultaneously collecting the physical layout features and semantic features of the archives, generating a comprehensive archive feature map, and dynamically adjusting the watermark strength in combination with a rank screening threshold; introducing a dual-index evaluation system of visual fidelity and watermark extraction degree to evaluate the watermark position and obtain substandard and standard labels of the archive carrier sequence; and constructing correction strategy selection rules including position iterative correction or sequence correction by monitoring the watermark survival rate, visual fidelity and circulation error rate, thereby realizing not only the evaluation and dynamic calibration of the watermark embedding position, but also the dynamic selection of the correction strategy.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital archives, and in particular relates to a method and system for secure circulation tracking of digital archives based on dynamic watermarks. Background Art

[0002] Digital archives are increasingly used in modern information management, but their security and protection during circulation have become urgent issues. Traditional archival storage and management methods are unable to cope with the challenges posed by the digital environment, such as security risks such as data leakage and tampering. In addition, archives are easily affected by various factors during circulation, resulting in loss of data integrity and even loss or error of information. Traditional archival protection measures, such as encryption technology and digital signatures, can provide a certain degree of security, but lack effective management of the dynamic changes in archives during transmission and use, and cannot monitor and adjust protection strategies in real time to respond to new threats.

[0003] Based on this, a method and system for secure circulation tracking of digital archives based on dynamic watermarks are proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for tracking the secure circulation of digital archives based on dynamic watermarks.

[0005] A digital archive secure circulation tracking method based on dynamic watermarks includes: collecting the physical layout features and semantic features of digital archive data and generating an archive feature map; constructing each archive carrier sequence based on the rank screening threshold and watermark strength corresponding to each archive feature map; and performing a watermark embedding operation on the sequence to obtain an initial watermark embedding result;

[0006] Based on each archive carrier sequence and its corresponding initial watermark embedding results, the corresponding visual fidelity and watermark extraction degree are obtained through data analysis. The watermark position of each initial watermark embedding result is evaluated to obtain the archive carrier sequence substandard and standard labels;

[0007] Collect labels of each initial watermark embedding result that does not meet the standard, and form a set of substandard archive carrier sequences. Combined with their corresponding visual fidelity and watermark extraction degree, a multi-objective optimization function is constructed and the optimal watermark position is output to obtain the secondary watermark embedding result;

[0008] The circulation of each archive carrier sequence is monitored to obtain the watermark survival rate, visual fidelity, and circulation error rate of each secondary watermark embedding result, and a correction strategy selection rule is constructed. According to the correction strategy selection rule, the corresponding secondary correction strategy is executed; the secondary correction strategy includes iterative correction of the watermark embedding position, correction of each archive carrier sequence, and no correction required.

[0009] As a further solution of the present invention: collecting physical layout features and semantic features of digitized archival data and generating an archival feature map: the physical layout features are text block position coordinates, font size, paragraph spacing, and the semantic features are text keywords, text themes, and text semantic relationships;

[0010] The archive feature map is generated by weighted fusion of physical layout features and semantic features based on the pre-trained convolutional neural network model, and the archive feature map is recorded as , where R represents the real number set of feature data in the archive feature map, n is the number of archives, g and w are the height and width of the feature map, and d is the number of channels of the feature map.

[0011] As a further solution of the present invention: the archive carrier sequence is constructed based on the rank screening threshold and watermark strength corresponding to each archive feature map, specifically:

[0012] For each profile feature map , where i is the identifier of each profile feature map and 1, 2, ..., n; n is the number of files; Combined into the total number of spatial locations N= , and get a two-dimensional matrix , N is the total number of spatial positions;

[0013] For each Perform singular value decomposition to obtain Where, and Represent N-order and d-order matrices respectively, and the superscript T represents the conjugate transpose of the matrix. for The matrix, the main diagonal is composed of Singular values Composition, P is the theoretical maximum rank, the rest of the elements are 0, and satisfy , Each column vector of the matrix The eigenvectors of are mutually orthogonal, called matrices The left singular vector of , similarly, ={ , ,..., Each column vector of} is a matrix The eigenvectors of are mutually orthogonal, called matrices The right singular vectors of ;

[0014] Based on the above decomposition process, the total information of the archive feature map is obtained , where P is the theoretical maximum rank and j is the index variable of P;

[0015] The minimum value of all information in the feature map is defined as the rank screening threshold , and the front The cumulative energy ratio of the singular values is compared with the preset threshold ;

[0016] when , retain the previous The subregion corresponding to the singular value As the feature sub-region, that is, the watermark embedding region;

[0017] when , retain all singular values, and do not process those that have no analytical value;

[0018] Based on preset watermark strength And introduce the rank screening threshold Get the dynamic adjustment strength coefficient , according to the formula ; Where P is the theoretical maximum rank;

[0019] The characteristic sub-regions corresponding to each archive feature map are converted into a one-dimensional carrier sequence that can be embedded with a watermark and recorded as the archive carrier sequence , and combined with the dynamic adjustment intensity coefficient corresponding to each characteristic sub-region , sort and splice to get the global archive vector sequence ;in Indicates the number of archive carrier sequences;

[0020] Perform watermark embedding operation on each archive carrier sequence to obtain the initial watermark embedding result.

[0021] As a further solution of the present invention: collect each file carrier sequence and its corresponding initial watermark embedding result, and obtain the corresponding visual fidelity and watermark extraction degree through data analysis. Specifically: each file carrier sequence The original digitized archives are not watermarked;

[0022] The initial watermark embedding result A digital file containing a watermark carrier after watermark embedding operation;

[0023] Based on the sequence of each archive carrier And the initial watermark embedding results Visual fidelity is calculated based on the structural similarity formula ;

[0024] For each initial watermark embedding result Perform watermark extraction operation to obtain the extracted watermark sequence and original watermark sequence corresponding to each initial watermark embedding result, and calculate the watermark extraction degree , according to the following formula: ;in, is the number of files, for Watermark sequence length of digitized archives q is the index of the element in the watermark sequence, for The qth element in the watermark sequence of the digitized archive, for The qth element in the extracted watermark sequence of the digitized archive, The mean of the original watermark sequence of the ith digital file is obtained according to the mean formula, The mean of the watermark sequence used to extract the watermark for the i-th digitized archive.

[0025] As a further solution of the present invention: evaluating the watermark position of each initial watermark embedding result specifically includes: based on each archive carrier sequence And the initial watermark embedding results Corresponding visual fidelity and watermark extraction degree , and the preset visual fidelity and watermark extraction degree standard interval to build a watermark position evaluation model, specifically as shown in the following formula: Where, 、 They refer to the preset visual fidelity and watermark extraction standard intervals respectively. 1 and -1 are evaluation identifiers, which respectively indicate that the watermark position of the initial watermark embedding result is normal or the watermark position state is abnormal.

[0026] As a further solution of the present invention, generating the archive carrier sequence substandard and standard labels includes:

[0027] The visual fidelity obtained will be calculated based on the value of the evaluation flag -1 and watermark extraction degree The corresponding preset visual fidelity and watermark extraction degree range 、 Make comparative judgments;

[0028] When visual fidelity or watermark extraction degree Does not belong to the corresponding standard range 、 , then an abnormal label of the initial watermark embedding result not meeting the standard is generated;

[0029] When visual fidelity And watermark extraction degree Belongs to the corresponding standard range 、 , then the initial watermark embedding result meets the standard label.

[0030] As a further solution of the present invention: constructing a multi-objective optimization function and outputting the optimal watermark position to obtain the secondary watermark embedding result is specifically as follows: and traversing to obtain each initial watermark embedding result non-compliant label and each archive carrier sequence corresponding to each initial watermark embedding result non-compliant label, to form a non-compliant archive carrier sequence set;

[0031] Based on the visual fidelity and watermark extraction index of each archive carrier sequence that does not meet the standard, a visual fidelity sub-function is constructed. and watermark extraction subfunction And introduce the preset weight coefficient to obtain the multi-objective optimization function ;

[0032] Combined with the constraints: the watermark embedding position belongs to the preset archive carrier boundary D, denoted as x ∈ D, and the watermark intensity is less than or equal to the preset maximum watermark intensity, denoted as ;

[0033] Based on the above multi-objective optimization function and constraints, the optimal watermark position is obtained by using the Pareto frontier solution algorithm:

[0034] Using the Pareto frontier solution algorithm, each individual in the population Encoded as watermark embedding position x and watermark strength , using real number encoding and calculating its target sub-function value and ; Compare the dominance relationships among all individuals:

[0035] When individuals Outperforms on all targets , and is better than at least one goal, then Dominate ;

[0036] The population is divided into multiple frontier layers and crowding is calculated. The crowding is calculated for the solutions in the same frontier layer. According to the crowding, a new population is generated through the three basic operations of genetic algorithm: selection, crossover and mutation.

[0037] According to the preset iteration termination condition, i.e. the preset maximum number of iterations, all non-dominated solutions are retained to form a Pareto optimal solution;

[0038] And take the Pareto optimal solution as the optimal watermark position ; Based on the above optimal watermark position Perform watermark embedding operation on the corresponding archive carrier sequence to obtain the secondary watermark embedding result.

[0039] As a further solution of the present invention: constructing the correction strategy selection rule specifically includes: defining the watermark survival rate, visual fidelity, and flow error rate as input variables, and dividing them into different fuzzy sets respectively;

[0040] The correction strategy selection rule is defined as the output variable and divided into fuzzy sets;

[0041] Formulate fuzzy rules to describe the impact of watermark survival rate, visual fidelity, and flow error rate on the correction strategy selection rules;

[0042] Perform fuzzy reasoning based on fuzzy rules to determine the results of the revised strategy selection rules;

[0043] The correction strategy selection rules include iterative correction of watermark embedding position, archive carrier sequence correction and no correction required.

[0044] As a further solution of the present invention: the iterative correction of the watermark embedding position specifically includes returning the corresponding archive carrier sequence to step 2 to re-evaluate the optimal position;

[0045] The sequence of each file carrier is modified to modify the sequence of each file carrier, specifically:

[0046] S1: Establish an association model based on the initial construction parameters corresponding to each evaluation index and each archive carrier sequence; the evaluation index is visual fidelity , watermark survival rate , flow error rate The initial construction parameters corresponding to each archive carrier sequence are the initial construction parameters including the rank screening threshold , watermark strength , feature graph node connection density ; Where r represents the number of corresponding vector sequences that need to be corrected;

[0047] S2: Constructing a correlation model between evaluation indicators and construction parameters ;

[0048] S3: Visual fidelity of each evaluation indicator , watermark survival rate , flow error rate The corresponding preset threshold 、 、 Perform difference calculation to obtain the corresponding deviation value 、 、 , the correction coefficient matrix is calculated using linear interpolation according to each deviation value , where Q represents the proportional coefficient of each parameter to be adjusted;

[0049] S4: Based on the correction coefficients corresponding to the construction parameters, the initial construction parameters corresponding to the archive carrier sequences are updated to obtain the updated construction parameters. 、 、 ;

[0050] And based on each updated construction parameter, the corresponding archive carrier sequence is reconstructed to generate a revised carrier sequence.

[0051] The digital archive security circulation tracking system with dynamic watermarks includes an archive initial watermark embedding module, a watermark position initial assessment module, a secondary watermark embedding module, and a circulation monitoring and correction strategy construction module.

[0052] The archive initial watermark embedding module is used to collect the physical layout characteristics and semantic characteristics of digital archive data and generate archive feature maps. Based on the rank screening threshold and watermark strength corresponding to each archive feature map, each archive carrier sequence is constructed and watermark embedding operation is performed on it to obtain the initial watermark embedding result.

[0053] The watermark position initial assessment module is used to evaluate the watermark position of each initial watermark embedding result based on each archive carrier sequence and its corresponding initial watermark embedding result. The module obtains the corresponding visual fidelity and watermark extraction degree through data analysis, and obtains the non-compliant and compliant labels of the archive carrier sequence.

[0054] The secondary watermark embedding module is used to collect the labels of each initial watermark embedding result that does not meet the standards, and form a set of substandard archive carrier sequences, combined with their corresponding visual fidelity and watermark extraction degree, to construct a multi-objective optimization function and output the optimal watermark position to obtain the secondary watermark embedding result;

[0055] The circulation monitoring and correction strategy execution module is used to monitor the circulation of each archive carrier sequence, obtain the watermark survival rate, visual fidelity, and circulation error rate of each corresponding secondary watermark embedding result, and construct correction strategy selection rules. According to the correction strategy selection rules, the corresponding secondary correction strategy is executed.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] (1) This invention generates a comprehensive archive feature map by simultaneously collecting the physical layout features and semantic features of the archive, and dynamically adjusts the watermark strength in combination with the rank screening threshold. It introduces a dual-index evaluation system of visual fidelity and watermark extraction degree, combines label classification with a multi-objective optimization function, and realizes dynamic calibration of the watermark embedding position.

[0058] (2) The present invention constructs correction strategy selection rules including position iteration correction or sequence correction by monitoring watermark survival rate, visual fidelity and transfer error rate; and combines the correlation analysis between watermark survival rate and transfer error rate; it not only realizes dynamic maintenance of watermark throughout its life cycle, but also realizes dynamic selection of correction strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Schematic diagram of the framework structure of the method of the present invention;

[0060] Figure 2 It is a schematic diagram of the system framework structure of the present invention. DETAILED DESCRIPTION

[0061] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0062] Example 1: Please refer to Figure 1 ,This application provides a method for secure circulation tracking of digital archives based on dynamic watermarks, including;

[0063] Step 1: Collect the physical layout features and semantic features of the digitized archival data and generate archival feature maps. Based on the rank screening threshold and watermark strength corresponding to each archival feature map, construct each archival carrier sequence, and perform watermark embedding operations on it to obtain the initial watermark embedding results.

[0064] Specifically, physical layout features refer to the visual structure and spatial distribution attributes of the archive after digitization, including text block position coordinates, font size, and paragraph spacing; semantic features refer to the contextual information carried by the archive content, including text keywords, text themes, and text semantic relationships;

[0065] The principle of generating the archive feature map is as follows: based on the pre-trained convolutional neural network (CNN) model, the physical layout features and semantic features are weighted and fused to obtain the archive feature map denoted as , where R represents the real number set of feature data in the archive feature map, n is the number of archives, g and w are the height and width of the feature map, and d is the number of channels of the feature map; the weights are obtained through training and learning to ensure that the fused feature map can better express the comprehensive features of the archives; the archive feature map can simultaneously contain the physical layout information and semantic information of the archives; the generated archive feature map is normalized to ensure that the feature values are within a reasonable range.

[0066] It should be noted that the above-mentioned method of obtaining the archive feature map based on the convolutional neural network (CNN) model is a prior art and will not be described in detail in this embodiment.

[0067] The construction of the archive carrier sequence based on the rank screening threshold and watermark strength corresponding to each archive feature graph includes:

[0068] For each profile feature map , where i is the identifier of each profile feature map and 1, 2, ..., n; n is the number of files; Combined into the total number of spatial locations N= , and get a two-dimensional matrix , N is the total number of spatial positions;

[0069] For each Perform singular value decomposition to obtain Where, and Represent N-order and d-order matrices respectively, and the superscript T represents the conjugate transpose of the matrix. for The matrix, the main diagonal is composed of Singular values Composition, P is the theoretical maximum rank, the rest of the elements are 0, and satisfy , Each column vector of the matrix The eigenvectors of are mutually orthogonal, called matrices The left singular vector of , similarly, ={ , ,..., Each column vector of} is a matrix The eigenvectors of are mutually orthogonal, called matrices The right singular vectors of ;

[0070] Based on the above decomposition process, the total information of the archive feature map is obtained , where P is the theoretical maximum rank and j is the index variable of P;

[0071] The minimum value of all information in the feature map is defined as the rank screening threshold , and the front The cumulative energy ratio of the singular values is compared with the preset threshold ;

[0072] when , retain the previous The subregion corresponding to the singular value As the feature sub-region, that is, the watermark embedding region;

[0073] when , retain all singular values, and do not process those that have no analytical value;

[0074] It should be noted that in this example, the case where the rank filtering threshold is greater than the threshold usually represents a part of the feature map with higher information content and importance, while the case where the rank filtering threshold is less than the threshold may increase the computational complexity and time cost. By ignoring these minor parts, the calculation process can be simplified.

[0075] Based on preset watermark strength And introduce the rank screening threshold Get the dynamic adjustment strength coefficient , according to the formula ; Where P is the theoretical maximum rank;

[0076] The characteristic sub-regions corresponding to each archive feature map are converted into a one-dimensional carrier sequence that can be embedded with a watermark and recorded as the archive carrier sequence , and combined with the dynamic adjustment intensity coefficient corresponding to each characteristic sub-region , sort and splice to get the global archive vector sequence ;in Indicates the number of archive carrier sequences;

[0077] Perform watermark embedding operation on each file carrier sequence to obtain the initial watermark embedding result; specifically, the watermark sequence corresponding to each file carrier sequence is based on the preset , and use watermark embedding technology to embed the watermark sequence corresponding to each archive carrier sequence Embedded into the corresponding sub-region of each file carrier sequence Get the initial watermark embedding result;

[0078] It should be noted that the generation of the above-mentioned preset watermark sequence is an existing technology such as formation through spread spectrum technology, and the specific formation process is not described in detail.

[0079] Step 2: Collect each archive carrier sequence and its corresponding initial watermark embedding results, obtain the corresponding visual fidelity and watermark extraction degree through data analysis, evaluate the watermark position of each initial watermark embedding result, and obtain the archive carrier sequence substandard and standard labels;

[0080] The sequence of each file carrier The original digitized archives are not watermarked;

[0081] The initial watermark embedding result After the watermark embedding operation is performed, the archive containing the watermark carrier is recorded as a digital archive;

[0082] Based on the sequence of each archive carrier And the initial watermark embedding results The calculated structural similarity index is defined as the visual fidelity , according to the formula ; Among them, a and b are the sequences of each file carrier and the initial watermark embedding result The archive image block, and are the means of a and b respectively, and are the standard deviations of a and b, is the covariance of a and b, and is the stability coefficient;

[0083] It should be noted that the above stability coefficient can be preset according to the formula: and ,in and is a preset small constant, L is the preset dynamic range of the archive image block pixels;

[0084] For each initial watermark embedding result Perform watermark extraction operation to obtain the extracted watermark sequence and original watermark sequence corresponding to each initial watermark embedding result, and calculate the watermark extraction degree , according to the following formula: ;in, is the number of files, for Watermark sequence length of digitized archives q is the index of the element in the watermark sequence, for The qth element in the watermark sequence of the digitized archive, for The qth element in the extracted watermark sequence of the digitized archive, The mean of the original watermark sequence of the ith digital file is obtained according to the mean formula, The mean of the watermark sequence for extracting the watermark for the i-th digitized archive

[0085] It should be noted that the original watermark sequence is the watermark information initially embedded into the archive, which is usually generated by a watermark generation algorithm and embedded into the archive through embedding. The extracted watermark sequence is the watermark information extracted from the archive.

[0086] Based on the above archive carrier sequences And the initial watermark embedding results Corresponding visual fidelity and watermark extraction degree , and the preset visual fidelity and watermark extraction degree standard interval to build a watermark position evaluation model, specifically as shown in the following formula: Where, 、 Refers to the preset visual fidelity and watermark extraction standard range respectively. The specific values are set by researchers based on experience, and can also be dynamically set based on the mean of historical data plus or minus a certain multiple of the standard deviation;

[0087] The evaluation flag contains a value of 1 or -1, which respectively indicates that the watermark position of the corresponding initial watermark embedding result is normal or the watermark position state is abnormal;

[0088] Generate a prompt indicating that the watermark position of the initial watermark embedding result is normal and the initial watermark embedding result is normal according to the value of 1 in the evaluation identifier, and generate a prompt indicating that the watermark position of the initial watermark embedding result is abnormal and the initial watermark embedding result is abnormal according to the value of -1 in the status identifier;

[0089] Automatically perform abnormal retrospective verification on the abnormal watermark position and the initial watermark embedding result generated based on the value of -1 in the state identifier;

[0090] Among them, the visual fidelity obtained will be calculated according to the value of -1 in the state identifier and watermark extraction degree The corresponding preset visual fidelity and watermark extraction degree range 、 Make comparative judgments;

[0091] If visual fidelity or watermark extraction degree Does not belong to the corresponding standard range 、 , then an abnormal label of the initial watermark embedding result not meeting the standard is generated;

[0092] If visual fidelity And watermark extraction degree Belongs to the corresponding standard range 、 , then generate the initial watermark embedding result compliance label;

[0093] Step 3: Collect the labels of each initial watermark embedding result that does not meet the standards, and form a set of substandard archive carrier sequences. Combine their corresponding visual fidelity and watermark extraction degree, construct a multi-objective optimization function and output the optimal watermark position to obtain the secondary watermark embedding result;

[0094] And according to the traversal, each initial watermark embedding result non-compliant label and each file carrier sequence corresponding to each initial watermark embedding result non-compliant label are obtained to form a non-compliant file carrier sequence set;

[0095] Based on the visual fidelity and watermark extraction indexes of each substandard set of archive carrier sequences, a multi-objective optimization function is constructed, specifically:

[0096] Constructing the visual fidelity subfunction and watermark extraction subfunction , according to the formula ,in is the archive carrier sequence of candidate watermark positions, It is the original archive carrier sequence;

[0097] Watermark extraction subfunction ,in is the watermark extracted from the image after watermark embedding, is the original watermark sequence;

[0098] A multi-objective optimization function is constructed based on the above function. The constructed multi-objective optimization function is: Where, and They represent the weight coefficients corresponding to each sub-function, and their specific values are dynamically determined by researchers based on actual needs;

[0099] The watermark embedding position does not exceed the preset archive carrier boundary D, which is recorded as x ∈ D, and the watermark intensity does not exceed the preset maximum watermark intensity, which is recorded as , as a constraint;

[0100] Based on the above multi-objective optimization function and constraints, the optimal watermark position is obtained using the Pareto frontier solution algorithm, specifically including:

[0101] Using the Pareto frontier solution algorithm, a certain number of initial populations B are randomly generated, and each individual in the population is encoded as the watermark embedding position x and the watermark strength , using real number coding, randomly generating positions x at initialization to form the initial population E0, ensuring that the gene value of each chromosome is within the allowed range and meets basic constraints;

[0102] For each individual in the population , calculate the value of its target sub-function and ;

[0103] Compare the dominance relationships among all individuals: If an individual Not inferior to , and is strictly better in at least one objective, then Dominate ;

[0104] Divide the population into multiple frontier layers:

[0105] Level 1: All non-dominated solutions

[0106] Layer 2: Solutions dominated by layer 1 but not dominated by other layers, and so on;

[0107] Crowding calculation: Calculate the crowding degree for the solutions in the same frontier layer to measure the distribution density of the solutions in the target space and avoid selecting overly concentrated solutions;

[0108] Generate new populations through the three basic operations of genetic algorithm: selection, crossover, and mutation;

[0109] According to the preset iterative termination condition, that is, the preset maximum number of iterations, if it is reached, the algorithm is terminated; when the termination condition is met, all non-dominated solutions (first-level frontier) are retained to form the Pareto front;

[0110] And select the multi-objective optimization function from the Pareto front The largest solution is the optimal solution, that is, the optimal watermark position ;

[0111] Based on the above optimal watermark position Perform watermark embedding operation on the corresponding archive carrier sequence to obtain the secondary watermark embedding result;

[0112] It should be noted that the Pareto front-based solution algorithm provides a scientific and efficient solution for the selection of watermark embedding location through multi-objective collaborative optimization, global search and constraint processing.

[0113] Step 4: Based on the circulation of each archive carrier sequence, the watermark survival rate, visual fidelity, and circulation error rate of each corresponding secondary watermark embedding result are collected, and a correction strategy selection rule is constructed. Based on the correction strategy selection rule, the corresponding secondary correction strategy is executed; the secondary correction strategy includes iterative correction of watermark embedding position, correction of archive carrier sequence, and no correction required;

[0114] The visual fidelity, watermark survival rate, and transfer error rate of each secondary watermark embedding result corresponding to each archive carrier sequence during the circulation process are collected; the watermark survival rate is the proportion of watermarks that can still be correctly extracted after circulation, and its acquisition logic is: the ratio of the number of correctly extracted watermarks to the total number of watermarks is calculated; the transfer error rate is the error rate caused by watermark embedding during the circulation of archives, and its acquisition logic is: the ratio of the number of archives with errors to the total number of archives is calculated;

[0115] Visual fidelity of each secondary watermark embedding result corresponding to each archive carrier sequence during the circulation process , watermark survival rate , flow error rate , construct the fuzzy rule table

[0116] For example, “High”, “Low”, and “Medium” for visual fidelity, watermark survival rate, and flow error rate;

[0117] Formulate a set of fuzzy rules to describe the impact of different input variables on the output variable. The definition of rules can be based on professional knowledge or obtained through data analysis and experiments. For example:

[0118] Mark visual fidelity as , the watermark survival rate is marked as , the flow error rate is marked as , the correction strategy selection rule is marked as Rfcs, including the location of watermark embedding, iterative correction is marked as , each archive carrier sequence is corrected as , no correction is required to mark

[0119] Then we can define:

[0120] Rule 1: IF ( is Low) AND ( is Low)AND( is High) THEN (Rfcs is )

[0121] Rule 2: IF (U is High) AND (U is High) AND ( is Low) THEN (Rfcs is )

[0122] Rule 3: IF (U is Low) AND (U is Medium) AND ( is Low) THEN (Rfcsis )

[0123] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although this embodiment takes three fuzzy sets as an example, in fact, visual fidelity, watermark survival rate, and flow error rate can be divided into more than three sets to facilitate better selection of correction strategies.

[0124] Furthermore, for the judgment of visual fidelity, watermark survival rate, and flow error rate, thresholds can be set according to actual conditions. For example, when the visual fidelity value exceeds 45%, it is marked as "High", when the watermark survival rate value is less than 75%, it is marked as "Low", and when the flow error rate is between 10% and 35%, it is marked as "Medium", and so on. I will not go into details here.

[0125] Statistics are" " The correction strategy selection rule is used to iteratively correct the watermark embedding position by returning the corresponding archive carrier sequence to step 2 for re-evaluation of the optimal position;

[0126] Statistics are" " The correction strategy selection rules for correcting the sequence of each archive carrier are specifically as follows:

[0127] S1: Establish an association model based on the initial construction parameters corresponding to each evaluation index and each archive carrier sequence; the evaluation index is visual fidelity , watermark survival rate , flow error rate The initial construction parameters corresponding to each archive carrier sequence are the initial construction parameters including the rank screening threshold , watermark strength , feature graph node connection density ; Where r represents the number of corresponding vector sequences that need to be corrected;

[0128] S2: Constructing a correlation model between evaluation indicators and construction parameters ;

[0129] S3: Visual fidelity of each evaluation indicator , watermark survival rate , flow error rate The corresponding preset threshold 、 、 The difference is calculated to get the corresponding deviation value 、 、 , the correction coefficient matrix is calculated based on each deviation value , where Q represents the proportional coefficient of each parameter to be adjusted;

[0130] It should be noted that the above correction coefficient can be calculated using a variety of methods, such as linear interpolation, nonlinear function, etc., to form a simple linear interpolation;

[0131] S4: Based on the correction coefficients corresponding to the construction parameters, the initial construction parameters corresponding to the archive carrier sequences are updated to obtain the updated construction parameters. 、 、 ;

[0132] and reconstructing the corresponding archive carrier sequences based on each updated construction parameter, thereby generating a revised carrier sequence;

[0133] It should be noted that the specific implementation steps of reconstructing the corresponding archive carrier sequences based on the updated construction parameters to generate the modified carrier sequences have been described in detail in step 1 of this embodiment and will not be repeated here.

[0134] In this embodiment, a comprehensive archive feature map is generated by simultaneously collecting the physical layout features and semantic features of the archive, and the watermark strength is dynamically adjusted in combination with the rank screening threshold; a dual-index evaluation system of visual fidelity and watermark extraction degree is introduced, combined with label classification and multi-objective optimization function; dynamic calibration of the watermark embedding position is achieved; by monitoring the watermark survival rate, visual fidelity and flow error rate, correction strategy selection rules are constructed, including position iterative correction or sequence correction; and combined with the correlation analysis of the watermark survival rate and the flow error rate; not only the dynamic maintenance of the watermark throughout its life cycle is achieved, but also the precise positioning of the leakage node is achieved.

[0135] Example 2: Please refer to Figure 2 ,The digital archive security circulation tracking system with dynamic watermarks ,includes an archive initial watermark embedding module, a watermark position initial ,assessment module, a secondary watermark embedding module, and a circulation ,monitoring and correction strategy building module;

[0136] The archive initial watermark embedding module is used to collect the physical layout characteristics and semantic characteristics of digital archive data and generate archive feature maps. Based on the rank screening threshold and watermark strength corresponding to each archive feature map, each archive carrier sequence is constructed and watermark embedding operation is performed on it to obtain the initial watermark embedding result.

[0137] The watermark position initial assessment module is used to evaluate the watermark position of each initial watermark embedding result based on each archive carrier sequence and its corresponding initial watermark embedding result. The module obtains the corresponding visual fidelity and watermark extraction degree through data analysis, and obtains the non-compliant and compliant labels of the archive carrier sequence.

[0138] The secondary watermark embedding module is used to collect the labels of each initial watermark embedding result that does not meet the standards, and form a set of substandard archive carrier sequences, combined with their corresponding visual fidelity and watermark extraction degree, to construct a multi-objective optimization function and output the optimal watermark position to obtain the secondary watermark embedding result;

[0139] The circulation monitoring and correction strategy execution module is used to monitor the circulation of each archive carrier sequence, obtain the watermark survival rate, visual fidelity, and circulation error rate of each corresponding secondary watermark embedding result, and construct correction strategy selection rules. According to the correction strategy selection rules, the corresponding secondary correction strategy is executed.

[0140] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0141] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for tracking the secure circulation of digital archives based on dynamic watermarks, characterized in that: include: The physical layout features and semantic features of digital archival data are collected and archival feature maps are generated. Based on the rank screening threshold and watermark strength corresponding to each archival feature map, each archival carrier sequence is constructed, and a watermark embedding operation is performed on it to obtain the initial watermark embedding result. Based on each archive carrier sequence and its corresponding initial watermark embedding results, the corresponding visual fidelity and watermark extraction degree are obtained through data analysis. The watermark position of each initial watermark embedding result is evaluated to obtain the substandard and qualified labels of the archive carrier sequence; Collect labels of each initial watermark embedding result that does not meet the standard, and form a set of substandard archive carrier sequences. Combined with their corresponding visual fidelity and watermark extraction degree, a multi-objective optimization function is constructed and the optimal watermark position is output to obtain the secondary watermark embedding result; Monitor the circulation of each archive carrier sequence, obtain the watermark survival rate, visual fidelity, and circulation error rate of each corresponding secondary watermark embedding result, and construct correction strategy selection rules. According to the correction strategy selection rules, the corresponding secondary correction strategy is executed; The secondary correction strategy includes iterative correction of the watermark embedding position, correction of each file carrier sequence and no correction required.

2. The method for secure circulation and tracking of digital archives based on dynamic watermarks according to claim 1 is characterized in that: The method includes collecting physical layout features and semantic features of digitized archival data and generating an archival feature map: the physical layout features are text block position coordinates, font size, paragraph spacing, and the semantic features are text keywords, text themes, and text semantic relationships; The file feature map is generated by weighted fusion of physical layout features and semantic features based on the pre-trained convolutional neural network model, and the obtained file feature map is denoted as M and , where R represents the real number set of feature data in the archive feature map, n is the number of archives, g and w are the height and width of the feature map, and d is the number of channels of the feature map.

3. The method for secure circulation and tracking of digital archives based on dynamic watermarks according to claim 1 is characterized in that: The file carrier sequence is constructed based on the rank screening threshold and watermark strength corresponding to each file feature map, specifically: For each profile feature map , where i is the identifier of each profile feature map and 1, 2, ..., n; n is the number of files; Combined into the total number of spatial locations N= , and get a two-dimensional matrix , N is the total number of spatial positions; For each Perform singular value decomposition to obtain Where, and Represent N-order and d-order matrices respectively, and the superscript T represents the conjugate transpose of the matrix. for The matrix, the main diagonal is composed of Singular values Composition, P is the theoretical maximum rank, the rest of the elements are 0, and satisfy , Each column vector of the matrix The eigenvectors of are mutually orthogonal, called matrices The left singular vector of , similarly, ={ ... Each column vector of} is a matrix The eigenvectors of are mutually orthogonal, called matrices The right singular vectors of ; Based on the above decomposition process, the total information of the archive feature map is obtained , where P is the theoretical maximum rank and j is the index variable of P; The minimum value of all information in the feature map is defined as the rank screening threshold , and the front The cumulative energy ratio of the singular values is compared with the preset threshold ; when , retain the previous The subregion corresponding to the singular value As the feature sub-region, that is, the watermark embedding region; when , retain all singular values, and do not process those that have no analytical value; Based on preset watermark strength And introduce the rank screening threshold Get the dynamic adjustment strength coefficient , according to the formula ; Where P is the theoretical maximum rank; The characteristic sub-regions corresponding to each archive feature map are converted into a one-dimensional carrier sequence that can be embedded with a watermark, which is recorded as the archive carrier sequence. , and combined with the dynamic adjustment intensity coefficient corresponding to each characteristic sub-region , sort and splice to get the global archive vector sequence ;in Indicates the number of archive carrier sequences; Perform watermark embedding operation on each archive carrier sequence to obtain the initial watermark embedding result.

4. The method for secure circulation and tracking of digital archives based on dynamic watermarks according to claim 1 is characterized in that: Collect each file carrier sequence and its corresponding initial watermark embedding result, and obtain the corresponding visual fidelity and watermark extraction degree through data analysis. Specifically: each file carrier sequence The original digitized archives are not watermarked; The initial watermark embedding result After the watermark embedding operation is performed, the archive containing the watermark carrier is recorded as a digital archive; Based on the sequence of each archive carrier And the initial watermark embedding results Visual fidelity is calculated based on the structural similarity formula ; For each initial watermark embedding result Perform watermark extraction operation to obtain the extracted watermark sequence and original watermark sequence corresponding to each initial watermark embedding result, and calculate the watermark extraction degree , calculated according to the following formula: ; where n is the number of files, is the length of the watermark sequence of the i-th digitized file, q is the index of the element in the watermark sequence, is the qth element in the watermark sequence of the i-th digitized file, is the qth element in the watermark sequence extracted from the i-th digitized file, is the mean of the original watermark sequence of the i-th digital archive, The mean of the watermark sequence used to extract the watermark for the i-th digitized archive.

5. The method for secure circulation and tracking of digital archives based on dynamic watermarks according to claim 1 is characterized in that: The watermark position evaluation of each initial watermark embedding result specifically includes: based on each file carrier sequence And the initial watermark embedding results Corresponding visual fidelity and watermark extraction degree , and the preset visual fidelity and watermark extraction degree standard interval to build a watermark position evaluation model, which is specifically calculated as shown in the following formula: Where, They refer to the preset visual fidelity and watermark extraction standard intervals respectively. 1 and -1 are evaluation indicators, which respectively indicate that the watermark position of the initial watermark embedding result is normal or the watermark position state is abnormal.

6. The method for secure circulation and tracking of digital archives based on dynamic watermarks according to claim 5 is characterized in that: The archive carrier sequence substandard and standard labels include: The visual fidelity obtained will be calculated based on the value of the evaluation flag -1 and watermark extraction degree The corresponding preset visual fidelity and watermark extraction degree range Make comparative judgments; When visual fidelity or watermark extraction degree Does not belong to the corresponding standard range , then an abnormal label of the initial watermark embedding result not meeting the standard is generated; When visual fidelity And watermark extraction degree Belongs to the corresponding standard range 、 , then the initial watermark embedding result meets the standard label.

7. The method for secure circulation and tracking of digital archives based on dynamic watermarks according to claim 1 is characterized in that: Constructing a multi-objective optimization function and outputting the optimal watermark position to obtain a secondary watermark embedding result includes: traversing to obtain each initial watermark embedding result non-compliant label and each file carrier sequence corresponding to each initial watermark embedding result non-compliant label, to form a non-compliant file carrier sequence set; Based on the visual fidelity and watermark extraction degree of each archive carrier sequence that does not meet the standard, a visual fidelity sub-function is constructed and watermark extraction subfunction And introduce the preset weight coefficient to obtain the multi-objective optimization function ; Combined with the constraints: the watermark embedding position does not exceed the preset archive carrier boundary D, denoted as x ∈ D, and the watermark intensity does not exceed the preset maximum watermark intensity, denoted as ; Based on the above multi-objective optimization function and constraints, the optimal watermark position is obtained by using the Pareto frontier solution algorithm: Using the Pareto frontier solution algorithm, each individual in the population Encoded as watermark embedding position x and watermark strength , using real number encoding and calculating its target sub-function value and ; Compare the dominance relationships among all individuals: When individuals Outperforms on all targets ,but Dominate ; The population is divided into multiple frontier layers and crowding is calculated. The crowding is calculated for the solutions in the same frontier layer. According to the crowding, a new population is generated through the three basic operations of genetic algorithm: selection, crossover and mutation. According to the preset iteration termination condition, i.e. the preset maximum number of iterations, all non-dominated solutions are retained to form a Pareto optimal solution; And take the Pareto optimal solution as the optimal watermark position ; Based on the above optimal watermark position Perform watermark embedding operation on the corresponding archive carrier sequence to obtain the secondary watermark embedding result.

8. The method for secure circulation and tracking of digital archives based on dynamic watermarks according to claim 1 is characterized in that: The specific construction of the correction strategy selection rule is as follows: watermark survival rate, visual fidelity, and flow error rate are defined as input variables, and they are divided into different fuzzy sets respectively; The correction strategy selection rule is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the impact of watermark survival rate, visual fidelity, and flow error rate on the correction strategy selection rules; Perform fuzzy reasoning based on fuzzy rules to determine the results of the revised strategy selection rules; The correction strategy selection rules include iterative correction of watermark embedding position, archive carrier sequence correction and no correction required.

9. A system for tracking the secure circulation of digital archives with dynamic watermarks, for implementing the method for tracking the secure circulation of digital archives with dynamic watermarks as described in any one of claims 1 to 8, characterized in that: Archive initial watermark embedding module, watermark position initial assessment module, secondary watermark embedding module, circulation monitoring and correction strategy construction module; The archive initial watermark embedding module is used to collect the physical layout characteristics and semantic characteristics of digital archive data and generate archive feature maps. Based on the rank screening threshold and watermark strength corresponding to each archive feature map, each archive carrier sequence is constructed and watermark embedding operation is performed on it to obtain the initial watermark embedding result. The watermark position initial assessment module is used to evaluate the watermark position of each initial watermark embedding result based on each archive carrier sequence and its corresponding initial watermark embedding result. The module obtains the corresponding visual fidelity and watermark extraction degree through data analysis, and obtains the non-compliant and compliant labels of the archive carrier sequence. The secondary watermark embedding module is used to collect the labels of each initial watermark embedding result that does not meet the standards, and form a set of substandard archive carrier sequences, combined with their corresponding visual fidelity and watermark extraction degree, to construct a multi-objective optimization function and output the optimal watermark position to obtain the secondary watermark embedding result; The circulation monitoring and correction strategy execution module is used to monitor the circulation of each archive carrier sequence, obtain the watermark survival rate, visual fidelity, and circulation error rate of each corresponding secondary watermark embedding result, and construct correction strategy selection rules. According to the correction strategy selection rules, the corresponding secondary correction strategy is executed.

Images