Enterprise contract privacy encryption method and device, electronic equipment and storage medium

Abstract

The application discloses a kind of privacy encryption method, device, electronic equipment and storage medium of enterprise contract, comprising: obtaining the enterprise contract data corresponding to target enterprise;Contract privacy score corresponding to enterprise contract data is determined by carrying out privacy sensitive analysis to enterprise contract data;High-frequency privacy contract data is determined from enterprise contract data based on contract privacy score, and high-frequency privacy contract data is encrypted based on privacy.The above technical scheme, by privacy sensitive analysis to contract data, the contract privacy score corresponding to it is determined, and then high-frequency privacy contract data is determined and encrypted, the quantitative evaluation of contract privacy is realized, and the high-frequency privacy contract data needing encryption is determined according to the quantitative evaluation result, and the encryption of high-frequency privacy contract.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a privacy encryption method, apparatus, electronic device, and storage medium for enterprise contracts. Background Technology

[0002] Contracts are agreements established between natural persons, legal persons, or other organizations of equal standing, and serve as mechanisms for regulating the transfer of property under market economy conditions. In the course of business operations, it is necessary to manage and encrypt contract data to prevent the leakage of sensitive information and avoid confidentiality breaches.

[0003] However, although existing technologies assess the risk level of contract risk information to provide risk warnings, they cannot analyze the frequency of private words appearing in high-risk contracts, nor can they encrypt high-risk contracts, making it difficult to meet the management needs of enterprises. Summary of the Invention

[0004] This invention provides a privacy encryption method, device, electronic device, and storage medium for enterprise contracts. By performing privacy sensitivity analysis on contract data to determine the corresponding contract privacy score, high-frequency privacy contract data is identified and encrypted, thereby achieving a quantitative evaluation of contract privacy and encryption of high-frequency privacy contracts.

[0005] According to one aspect of the present invention, a privacy encryption method for enterprise contracts is provided, comprising:

[0006] Obtain enterprise contract data corresponding to the target company;

[0007] Conduct privacy sensitivity analysis on enterprise contract data to determine the contract privacy score corresponding to the enterprise contract data;

[0008] High-frequency privacy contracts are identified from enterprise contract data based on contract privacy scores, and these high-frequency privacy contracts are then encrypted for privacy purposes.

[0009] According to another aspect of the present invention, a privacy encryption device for enterprise contracts is provided, comprising:

[0010] The data acquisition module is used to acquire enterprise contract data corresponding to the target enterprise;

[0011] The contract privacy assessment module is used to perform privacy sensitivity analysis on enterprise contract data and determine the contract privacy score corresponding to the enterprise contract data.

[0012] The privacy encryption module is used to identify high-frequency privacy contract data from enterprise contract data based on contract privacy scores, and to encrypt the high-frequency privacy contract data.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory that is communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to execute the privacy encryption method for enterprise contracts according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute a privacy encryption method for enterprise contracts according to any embodiment of the present invention.

[0018] The technical solution of this invention involves acquiring enterprise contract data corresponding to a target enterprise; performing privacy sensitivity analysis on the enterprise contract data to determine a contract privacy score corresponding to the enterprise contract data; identifying high-frequency privacy contract data from the enterprise contract data based on the contract privacy score; and encrypting the high-frequency privacy contract data. Based on the above technical solution, by performing privacy sensitivity analysis on contract data to determine the corresponding contract privacy score, and then identifying and encrypting high-frequency privacy contract data, a quantitative evaluation of contract privacy is achieved. Based on the quantitative evaluation results, the high-frequency privacy contract data that needs to be encrypted is determined and then encrypted.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a privacy encryption method for enterprise contracts provided by an embodiment of the present invention;

[0022] Figure 2 This is a flowchart of a privacy encryption method for enterprise contracts provided by an embodiment of the present invention;

[0023] Figure 3 A schematic diagram of a privacy encryption device for enterprise contracts provided in an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Figure 1 This is a flowchart illustrating a privacy encryption method for enterprise contracts provided in an embodiment of the present invention. This embodiment is applicable to situations where privacy evaluation is performed on contract data within an enterprise to identify high-frequency privacy contract data, and then the high-frequency privacy contract data is encrypted. This method can be executed by an enterprise contract privacy encryption device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method specifically includes the following steps:

[0028] S110. Obtain enterprise contract data corresponding to the target enterprise.

[0029] The target company can be any entity that requires intelligent contract review and privacy protection. Enterprise contract data can be understood as a collection of textual data of various business contracts within the target company, including commercial, procurement, and legal contracts.

[0030] Specifically, this involves acquiring enterprise contract data corresponding to the target company. For example, internal systems such as enterprise document management systems and legal management platforms can be used to collect contract text data of all types and lifecycles from the target company in batches, and complete the data formatting and storage.

[0031] S120. Conduct privacy sensitivity analysis on enterprise contract data to determine the contract privacy score corresponding to the enterprise contract data.

[0032] Privacy sensitivity analysis can be understood as an analytical process that assesses the risk level of privacy leakage in contract data based on text semantics and keyword features. The contract privacy score is a numerical value used to quantify the degree of privacy sensitivity of contract data; a higher score indicates a greater privacy risk.

[0033] Specifically, privacy sensitivity analysis is performed on enterprise contract data to determine the contract privacy score corresponding to the enterprise contract data. For example, the contract type corresponding to the enterprise contract data can be identified first, a dedicated privacy bag-of-words model can be built, and then corresponding contract cases can be matched and privacy word sequences can be extracted. The weight and trigger frequency of privacy words can be counted, and the privacy coefficient of each word can be calculated. The contract privacy score is obtained by summing all privacy coefficients.

[0034] S130. Based on the contract privacy score, identify high-frequency privacy contract data from enterprise contract data and encrypt the high-frequency privacy contract data for privacy.

[0035] High-frequency privacy contract data can be defined as contract data with a privacy score higher than the threshold, containing a large amount of sensitive information, and requiring strong encryption protection. Low-frequency privacy contract data can be understood as contract data with a privacy score lower than the threshold, containing less sensitive information, and not requiring strong encryption. Privacy encryption is a multi-level encryption process used to perform slicing, matrix transformation, and random embedding on contracts with high privacy risks.

[0036] Specifically, high-frequency privacy contract data is identified from enterprise contract data based on contract privacy scores, and privacy encryption is applied to high-frequency privacy contract data. For example, historical classification standard thresholds can be retrieved from the database, and the contract privacy scores can be compared with the thresholds to distinguish between high-frequency and low-frequency privacy contract data. Only high-frequency privacy contract data undergoes full-process privacy encryption processing, including slice encryption, matrix transformation, augmentation obfuscation, and embedding hiding.

[0037] Based on the above technical solution, high-frequency privacy contract data is determined from enterprise contract data based on contract privacy scores, including: obtaining classification standard thresholds and comparing the contract privacy scores with the classification standard thresholds; if the contract privacy scores are greater than or equal to the classification standard thresholds, the corresponding contract data is determined to be high-frequency privacy contract data; if the contract privacy scores are less than the classification standard thresholds, the corresponding contract data is determined to be low-frequency privacy contract data.

[0038] Specifically, the system can automatically retrieve historical classification standards and parse them to obtain classification standard thresholds. The privacy score of each contract is compared with the threshold; contracts with a score greater than or equal to the threshold are marked as high-frequency privacy contracts, while those with a score less than the threshold are marked as low-frequency privacy contracts. For example, historical classification standards are retrieved from the database; these standards are analyzed to obtain classification standard thresholds; the contract privacy score is compared with the classification standard threshold; if the contract privacy score is greater than or equal to the classification standard threshold, the contract is determined to be a high-frequency privacy contract; if the contract privacy score is less than the classification standard threshold, the contract is determined to be a low-frequency privacy contract.

[0039] The technical solution of this invention achieves automatic contract classification through standardized threshold comparison, without manual intervention. The classification rules are clear and traceable, improving the efficiency and consistency of contract classification processing.

[0040] Based on the above technical solution, encryption processing is performed on high-frequency privacy contract data, including: dividing the high-frequency privacy contract data into data slices of fixed length and encrypting the data slices to obtain encrypted slices; obtaining an encryption matrix based on the encrypted slices and performing an affine transformation on the encryption matrix to obtain an affine matrix; concatenating the affine matrix with a random augmented matrix to obtain a preprocessing matrix, and embedding the preprocessing matrix into a random transmission confidentiality matrix to determine the encrypted transmission matrix.

[0041] Specifically, high-frequency privacy contracts can be sliced ​​into fixed-length segments, with special characters added if the length is insufficient. The segments are then asymmetrically encrypted to obtain encrypted segments. An encryption matrix is ​​constructed based on the number of segments and filled in. Row, column, and hybrid transformations are then performed sequentially to obtain an affine matrix. The affine matrix is ​​then concatenated with a random augmented matrix and embedded as a whole into a larger random transmission confidentiality matrix to form the final encrypted transmission matrix.

[0042] For example, high-frequency privacy contract data is segmented into at least one data slice, with a preset slice length. If the length of the high-frequency privacy contract data is not divisible by the preset length, special characters are appended to the end of the high-frequency privacy contract data until the length is divisible by the preset length. If the length of the high-frequency privacy contract data is divisible by the preset length, data segmentation is performed, the data slices are encrypted to obtain encrypted slices, and the encryption algorithm is stored in the real key. At least one encrypted slice is sequentially placed into an encryption matrix, where the number of columns is a fixed value (a preset number of columns), and the number of rows varies according to the number of encrypted slices. The encryption matrix filled with encrypted slices... Affine transformation is performed on the matrix to obtain an affine matrix, which is then stored in the real key. An augmented matrix is ​​obtained, with its elements generated by reading and writing random numbers. The affine matrix and the augmented matrix are concatenated and merged to form a preprocessed matrix, which is then stored in the real key. A transmission confidentiality matrix is ​​generated, with its elements generated by reading and writing random numbers. An embedding offset for the preprocessed matrix is ​​generated and embedded into the transmission confidentiality matrix to obtain the final transmission matrix. Random prime numbers are generated, with a minimum number of bits. The embedding offset is multiplied by the random prime number to obtain an encryption embedding offset. The encryption embedding offset is mapped one-to-one with the final transmission matrix and stored in the real key.

[0043] The technical solution of this invention significantly increases the difficulty of data cracking through a four-fold encryption structure of slicing, matrix transformation, augmented obfuscation, and deep embedding, thus ensuring the security of sensitive contracts during storage and transmission.

[0044] Based on the above technical solution, the data slice is encrypted to obtain an encrypted slice, including: determining the target cryptogenic prime number and calculating the product and Euler's totient function; generating a coprime public key and a private key based on the Euler's totient function; storing the private key in a key store; and performing encryption operations on the data slice based on the public key to obtain an encrypted slice corresponding to the data slice.

[0045] The target cryptographic prime number can be a randomly selected, very large prime number used to construct an asymmetric encryption key pair. Euler's totient function can be understood as a number-theoretic function used to calculate key associations. The public key is a publicly available encryption key used for data encryption; correspondingly, the private key is a confidential decryption key stored in a key store.

[0046] Specifically, two very large and unequal prime numbers can be randomly selected, their product and corresponding Euler's totient function can be calculated, a prime number coprime to Euler's totient function can be selected as the public key, the private key can be obtained through counting iteration and stored securely, and then the public key can be used to perform modulo exponentiation on the data slice to obtain the corresponding encrypted slice.

[0047] For example, by using a random number algorithm, arbitrarily select two numbers greater than... Let the prime numbers be denoted as the first encryption index p and the second encryption index q, respectively, where p ≠ q; calculate the product of the first encryption index p and the second encryption index q to obtain the third encryption index n; construct the Euler totient function of n based on the first encryption index p and the second encryption index q. , Using a random number algorithm, obtain a prime number greater than the first encryption index p and the second encryption index q, denoted as the encryption key r. r and... Coprime; Define a counting index k, starting from 1 and increasing by 1 at intervals of 1. When the key r is first divided by the key count index k, the value of the record count index k is the dark key count index. Based on dark key counting index The dark key d is calculated. Publicly store the third encryption index n and the encryption key r, and save the hidden key d into the real key; obtain the data slice a, encrypt the data slice a, and obtain... The remainder b obtained by dividing by n is used as an encrypted slice, and the encrypted slice is matched one-to-one with the data slice.

[0048] The technical solution of this invention adopts a high-strength asymmetric encryption algorithm, with public key encryption and private key decryption, and key separation and storage, which effectively prevents the sliced ​​content from being cracked and ensures the underlying encryption security of the data.

[0049] Based on the above technical solution, an encryption matrix is ​​obtained from the encryption slices, and an affine matrix is ​​obtained by performing an affine transformation on the encryption matrix, including: determining the row and column size of the encryption matrix according to the number of encryption slices and filling the encryption slices; performing matrix transformations on the encryption matrix in sequence to obtain the transformation matrix, and determining the inverse matrix corresponding to each transformation matrix; determining the affine matrix based on the transformation matrix, and storing the inverse matrix in the key library.

[0050] The encryption matrix can be a two-dimensional data structure consisting of encrypted slices arranged with a fixed number of columns and a dynamic number of rows. The affine transformation can be understood as a matrix scrambling operation that includes elementary row transformations, column transformations, and mixed row transformations. The inverse matrix is ​​the decryption matrix used to restore the original matrix transformation and is stored in the keystore.

[0051] Specifically, the number of matrix rows can be calculated based on the total number of encrypted slices and the preset number of columns, an encrypted matrix can be constructed and filled in order, with special characters filling empty spaces; row swapping, column swapping, and row superposition hybrid transformations can be performed on the matrix in sequence to obtain an affine matrix; the inverse matrix of each transformation step can be recorded synchronously and stored in the key library for decryption.

[0052] For example, affine transformations consist of elementary row transformations, elementary column transformations, and elementary row-column mixed transformations. The encryption matrix undergoes elementary row transformations, which involves swapping the elements of the encryption matrix row by row. Each elementary row transformation is equivalent to multiplying the encryption matrix by a row transformation matrix, where the row transformation matrix is ​​the identity matrix that has undergone the same elementary row transformation. All row transformation matrices are recorded in order, and the inverses of all row transformation matrices are calculated. The inverses of all row transformation matrices are then multiplied in order to obtain the row transformation decryption matrix. Similarly, the encryption matrix undergoes elementary column transformations, which involve swapping the elements of the encryption matrix column by column. Each elementary column transformation is equivalent to multiplying the encryption matrix by a column transformation matrix, where the column transformation matrix is ​​the identity matrix that has undergone the same elementary column transformation. All column transformation matrices are recorded in order. Find the inverses of all column transformation matrices, and multiply them in order to obtain the column transformation decryption matrix. Perform elementary row mixing transformations on the encryption matrix, that is, superimpose the elements of the encryption matrix according to the row mixing. Each elementary row mixing transformation is equivalent to multiplying the encryption matrix by the row mixing transformation matrix. The row mixing transformation matrix is ​​the identity matrix that has undergone the same elementary row mixing transformation. Record all row mixing transformation matrices in order, find the inverses of all row mixing transformation matrices, and multiply them in order to obtain the row mixing transformation decryption matrix. After elementary row transformations, elementary column transformations, and elementary row mixing transformations, the encryption matrix is ​​transformed into an affine matrix. The number of rows and columns of the affine matrix is ​​consistent with that of the encryption matrix.

[0053] Then, obtain the number of columns of the augmented matrix; obtain the number of rows of the affine matrix, and expand the affine matrix row by row. During expansion, add a preset number of elements to the end of each row of the affine matrix, all of which are empty. The preset number is equal to the number of columns of the augmented matrix; according to the element arrangement order in the augmented matrix, copy and replace the elements in the empty parts of the expanded affine matrix to obtain the preprocessed matrix; generate the embedding offset of the preprocessed matrix, and embed the preprocessed matrix into the transmission confidentiality matrix, including the following steps: obtain the horizontal coordinate using a random number algorithm. The offset e and the vertical coordinate offset f are combined to form the embedding offset (e, f). For any matrix element in the preprocessing matrix, the matrix element located in the i-th row and j-th column is mapped to the unit element in the (i+e)-th row and (j+f)-th column of the transmission confidentiality matrix during embedding. The unit element in the (i+e)-th row and (j+f)-th column of the transmission confidentiality matrix is ​​replaced with the matrix element in the i-th row and (j)-th column of the preprocessing matrix. When the matrix elements traverse the preprocessing matrix, the final transmission matrix is ​​obtained.

[0054] The technical solution of this invention scrambles the original data structure through multi-layer matrix affine transformation, further increasing the encryption complexity. Only by possessing the complete set of inverse matrices can the data be correctly restored, thus enhancing the data's resistance to attacks.

[0055] The technical solution of this invention involves acquiring enterprise contract data corresponding to a target enterprise; performing privacy sensitivity analysis on the enterprise contract data to determine a contract privacy score corresponding to the enterprise contract data; identifying high-frequency privacy contract data from the enterprise contract data based on the contract privacy score; and encrypting the high-frequency privacy contract data. Based on the above technical solution, by performing privacy sensitivity analysis on contract data to determine the corresponding contract privacy score, and then identifying and encrypting high-frequency privacy contract data, a quantitative evaluation of contract privacy is achieved. Based on the quantitative evaluation results, the high-frequency privacy contract data that needs to be encrypted is determined and then encrypted.

[0056] In one possible implementation of the present invention Figure 2 This is a flowchart illustrating a privacy encryption method for enterprise contracts provided by an embodiment of the present invention. The embodiment further describes a technical solution for performing privacy sensitivity analysis on enterprise contract data to determine a contract privacy score corresponding to the enterprise contract data, such as... Figure 2 As shown, the method includes:

[0057] S210. Determine the contract type corresponding to the enterprise contract data, and construct a privacy bag-of-words model based on the contract type.

[0058] Contract type can be understood as the business classification of enterprise contracts, such as procurement, sales, labor, and technology agreements. The privacy bag-of-words model can be understood as a set of privacy keywords customized according to contract type.

[0059] Specifically, the contract types corresponding to the enterprise contract data are identified, and a privacy bag-of-words model is constructed based on the contract types. For example, text classification and recognition can be performed on the enterprise contract data to determine the business type to which the contract belongs; according to the privacy expression characteristics of different contract types, a privacy bag-of-words model containing corresponding sensitive keywords and proprietary expressions is constructed.

[0060] The technical solution of this invention improves the accuracy of privacy vocabulary recognition by customizing the bag-of-words model according to contract type, and avoids misjudgments and omissions caused by general vocabulary.

[0061] S220. Determine the contract case information corresponding to the enterprise contract data based on the contract type, and determine the privacy vocabulary sequence based on the contract case information and the privacy bag-of-words model.

[0062] The contract case information can be historical contract text data of the same type. The privacy term sequence can be understood as a continuous combination of keywords in the contract that hit the privacy term bag, and is used for subsequent statistical analysis.

[0063] Specifically, contract case information corresponding to enterprise contract data is determined based on contract type, and a privacy word sequence is determined based on contract case information and privacy bag-of-words model. For example, similar contract cases can be matched from the case library based on contract type; the case text is input into the privacy bag-of-words model for keyword matching, all matched privacy keywords are extracted, and a privacy word sequence is generated in the order of appearance.

[0064] The technical solution of this invention combines case matching and bag-of-words matching to comprehensively extract contract privacy features, providing a complete and accurate lexical basis for subsequent coefficient calculation.

[0065] S230. Determine the privacy vocabulary set based on the privacy vocabulary sequence, and determine the privacy coefficient corresponding to each privacy vocabulary in the privacy vocabulary set.

[0066] The privacy vocabulary set can be understood as a summary of all privacy keywords after deduplication. The privacy coefficient can be the contribution of a single keyword to the overall privacy score, obtained by combining weight and trigger frequency.

[0067] Specifically, a privacy vocabulary set is determined based on the privacy vocabulary sequence, and a privacy coefficient is determined for each privacy vocabulary in the privacy vocabulary set. For example, all privacy vocabulary sequences can be deduplicated and summarized to form a privacy vocabulary set; a privacy weight is assigned to each vocabulary, its trigger frequency in the sequence is counted, high-frequency sensitive sequences are filtered and their proportion is calculated; the privacy coefficient of each vocabulary is obtained by combining the weight and the proportion.

[0068] The technical solution of this invention calculates the privacy coefficient through a two-dimensional approach of weight and frequency, accurately reflecting the sensitivity of different words and significantly improving the rationality and discriminativeness of the privacy score.

[0069] Based on the above technical solution, the privacy coefficient corresponding to each privacy term in the privacy term set is determined, including: assigning weights to each privacy term in the privacy term set and determining the privacy weight corresponding to the privacy term; determining the trigger frequency of the privacy term in the privacy term sequence and filtering out sensitive privacy term sequences based on the trigger frequency parameter; determining the proportion of sensitive privacy term sequences to the total number of privacy term sequences, and determining the privacy coefficient based on the proportion and privacy weight.

[0070] Specifically, normalized weights can be assigned to each word in the privacy vocabulary set according to its sensitivity level; the trigger frequency of each word can be counted by traversing the word sequence, and sequences that exceed the frequency threshold can be selected as sensitive sequences; the proportion of sensitive sequences to the total number of sequences can be calculated; and the privacy weight can be multiplied by the proportion to obtain the privacy coefficient of the word.

[0071] The technical solution of this invention combines weighting and frequency statistics to objectively quantify the actual risk contribution of each privacy term, making the privacy coefficient more closely reflect the real risk of leakage.

[0072] S240. Determine the contract privacy score corresponding to the enterprise contract data based on the privacy coefficient corresponding to each privacy term.

[0073] Specifically, the privacy coefficients corresponding to all words in the privacy vocabulary set can be summed up, and the resulting total value can be used as the contract privacy score for the enterprise contract data.

[0074] For example, a privacy bag-of-words model is constructed based on contract type information; contract case information is matched based on contract type information, and privacy words are matched on the contract case information based on the privacy bag-of-words model to generate multiple privacy word sequences; multiple privacy word sequences are traversed to obtain a privacy word matching set; the privacy coefficient is evaluated by traversing the privacy word matching set to generate multiple privacy coefficients; the multiple privacy coefficients are summed to obtain a contract privacy score.

[0075] Understandably, a privacy bag-of-words model is constructed based on contract type information, serving as an auxiliary analysis tool for identifying and extracting privacy-related terms from contract information. This involves configuring the model's identification and matching mechanisms, such as semantic extraction and keyword recognition. Big data research is conducted based on contract type information to match relevant contract case information—the information carriers to be evaluated. This information is then input into the privacy bag-of-words model for identification and matching. Privacy-related terms within the matched contract case information—expressions with information confidentiality and deployment security requirements—are identified and serialized, generating multiple privacy-related term sequences. These sequences are then further iterated through, and the terms are aggregated and integrated, removing terms with identical expressions to determine a single-frequency privacy-related term set, which serves as the privacy-related term matching set. Finally, the privacy-related term matching set is iterated through, and a privacy coefficient is evaluated for each term.

[0076] The process of traversing the privacy-preserving vocabulary matching set to evaluate privacy coefficients and generate multiple privacy coefficients includes: traversing the privacy-preserving vocabulary matching set to perform privacy weight distribution and obtain privacy weight distribution results, where the sum of the privacy weight distribution results equals 1; extracting the nth privacy-preserving vocabulary from the privacy-preserving vocabulary matching set; traversing multiple privacy-preserving vocabulary sequences based on the nth privacy-preserving vocabulary to obtain multiple word trigger frequency parameters; filtering multiple privacy-preserving vocabulary sequences that meet the word trigger frequency threshold based on the multiple word trigger frequency parameters and designating them as sensitive privacy-preserving vocabulary sequences; calculating the sequence quantity ratio information based on the sensitive privacy-preserving vocabulary sequences; and performing weighted calculations based on the privacy weight distribution results and sequence quantity ratio information to generate the privacy coefficient of the nth privacy-preserving vocabulary, which is then added to the multiple privacy coefficients.

[0077] Understandably, this can be achieved using a pre-defined privacy word weight distribution table. This table can be a weight distribution database built by multiple peer companies based on blockchain technology. The privacy word matching set is weighted, generating privacy weight distribution results, the sum of which is 1. Based on the privacy word matching set, a privacy word is randomly extracted as the nth privacy word. Multiple privacy word sequences are traversed, and the frequency of the nth privacy word is counted as its trigger frequency parameter. Frequency identification and statistics are performed on the privacy word matching set to obtain multiple word trigger frequency parameters, where n is the same as the number of words covered in the privacy word matching set. A word trigger frequency threshold is set, i.e., a critical value for limiting word sensitivity. Using this threshold as a screening criterion, multiple privacy word sequences with trigger frequency parameters greater than the specified trigger frequency are extracted and designated as sensitive privacy word sequences. Sensitive privacy word sequences have a higher semantic weight. The proportion calculation method is determined as the number of sensitive privacy word sequences / the total number of multiple privacy word sequences. The proportion of sequences is calculated based on the sensitive privacy word sequences. Further, based on the privacy weight distribution results and the sequence quantity proportion information, a weighted multiplication is performed. The privacy weight distribution results and the sequence quantity proportion information have a positive feedback to the word privacy coefficient. The privacy coefficients of each word in the privacy word matching set are determined and added to multiple privacy coefficients. By conducting a comprehensive evaluation of word privacy, the accuracy of multiple privacy coefficients can be effectively improved.

[0078] This invention constructs a privacy bag-of-words model to examine and analyze contracts. If a contract contains a large proportion of privacy words, it indicates that the contract is a high-frequency privacy contract and needs to be encrypted to prevent leakage due to network attacks. The high-frequency privacy contract data is divided into multiple data slices, and after the data slices are encrypted, a matrix is ​​generated. The matrix is ​​then shuffled and subjected to row mixing transformation. At the same time, the transformed matrix is ​​augmented and data for obfuscation is added. The high encryption complexity ensures the confidentiality performance of the encrypted data.

[0079] Figure 3 This is a schematic diagram of a privacy encryption device for enterprise contracts provided in an embodiment of the present invention. Figure 3 As shown, the device includes: a data acquisition module 310, a contract privacy evaluation module 320, and a privacy encryption module 330.

[0080] Data acquisition module 310 is used to acquire enterprise contract data corresponding to the target enterprise;

[0081] The Contract Privacy Assessment Module 320 is used to perform privacy sensitivity analysis on enterprise contract data and determine the contract privacy score corresponding to the enterprise contract data.

[0082] The privacy encryption module 330 is used to identify high-frequency privacy contract data from enterprise contract data based on contract privacy scores, and to encrypt the high-frequency privacy contract data for privacy purposes.

[0083] Based on the above technical solution, the contract privacy evaluation module is used to determine the contract type corresponding to the enterprise contract data, and construct a privacy bag-of-words model based on the contract type; determine the contract case information corresponding to the enterprise contract data according to the contract type, and determine the privacy word sequence according to the contract case information and the privacy word sequence; determine the privacy word set based on the privacy word sequence, and determine the privacy coefficient corresponding to each privacy word in the privacy word set; and determine the contract privacy score corresponding to the enterprise contract data based on the privacy coefficient corresponding to each privacy word.

[0084] Based on the above technical solution, the contract privacy evaluation module is used to assign weights to each privacy term in the privacy term set, determine the privacy weight corresponding to the privacy term; determine the trigger frequency of the privacy term in the privacy term sequence, and filter out the sensitive privacy term sequence based on the trigger frequency parameter; determine the proportion of the number of sensitive privacy term sequences to the total number of privacy term sequences, and determine the privacy coefficient based on the proportion of the number and the privacy weight.

[0085] Based on the above technical solution, the privacy encryption module is used to obtain the classification standard threshold and compare the contract privacy score with the classification standard threshold. If the contract privacy score is greater than or equal to the classification standard threshold, the corresponding contract data is determined to be high-frequency privacy contract data; if the contract privacy score is less than the classification standard threshold, the corresponding contract data is determined to be low-frequency privacy contract data.

[0086] Based on the above technical solution, the privacy encryption module is used to divide high-frequency privacy contract data into data slices of fixed length and encrypt the data slices to obtain encrypted slices; based on the encrypted slices, an encryption matrix is ​​obtained, and an affine transformation is performed on the encryption matrix to obtain an affine matrix; the affine matrix is ​​concatenated with a random augmented matrix to obtain a preprocessing matrix, and the preprocessing matrix is ​​embedded into a random transmission confidentiality matrix to determine the encrypted transmission matrix.

[0087] Based on the above technical solution, the privacy encryption module is used to determine the target cryptogenic prime number and calculate the product and Euler's totient function, generate a coprime public key and a private key based on the Euler's totient function, store the private key in the key store, and perform encryption operations on the data slice based on the public key to obtain the encrypted slice corresponding to the data slice.

[0088] Based on the above technical solution, the privacy encryption module is used to determine the row and column size of the encryption matrix according to the number of encryption slices and fill the encryption slices; perform matrix transformations on the encryption matrix in sequence to obtain the transformation matrix, and determine the inverse matrix corresponding to each transformation matrix; determine the affine matrix based on the transformation matrix, and store the inverse matrix in the key library.

[0089] The technical solution of this invention involves acquiring enterprise contract data corresponding to a target enterprise; performing privacy sensitivity analysis on the enterprise contract data to determine a contract privacy score corresponding to the enterprise contract data; identifying high-frequency privacy contract data from the enterprise contract data based on the contract privacy score; and encrypting the high-frequency privacy contract data. Based on the above technical solution, by performing privacy sensitivity analysis on contract data to determine the corresponding contract privacy score, and then identifying and encrypting high-frequency privacy contract data, a quantitative evaluation of contract privacy is achieved, as well as the encryption of high-frequency privacy contracts.

[0090] The privacy encryption device for enterprise contracts provided in the embodiments of the present invention can execute the privacy encryption method for enterprise contracts provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0091] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0092] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0093] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0094] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as privacy encryption methods for enterprise contracts.

[0095] In some embodiments, the privacy encryption method for enterprise contracts may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the privacy encryption method for enterprise contracts described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the privacy encryption method for enterprise contracts by any other suitable means (e.g., by means of firmware).

[0096] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0097] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0098] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0099] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0100] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0101] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0102] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0103] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A privacy encryption method for enterprise contracts, characterized in that, include: Obtain enterprise contract data corresponding to the target company; Perform privacy sensitivity analysis on the enterprise contract data to determine the contract privacy score corresponding to the enterprise contract data; Based on the contract privacy score, high-frequency privacy contract data is identified from the enterprise contract data, and the high-frequency privacy contract data is encrypted for privacy.

2. The method according to claim 1, characterized in that, The step of performing privacy sensitivity analysis on the enterprise contract data to determine the contract privacy score corresponding to the enterprise contract data includes: Determine the contract type corresponding to the enterprise contract data, and construct a privacy bag-of-words model based on the contract type; Based on the contract type, determine the contract case information corresponding to the enterprise contract data, and determine the privacy vocabulary sequence based on the contract case information and the privacy bag-of-words model; A privacy vocabulary set is determined based on the privacy vocabulary sequence, and a privacy coefficient corresponding to each privacy vocabulary in the privacy vocabulary set is determined. A contract privacy score is determined based on the privacy coefficient corresponding to each privacy term and the enterprise contract data.

3. The method according to claim 2, characterized in that, The determination of the privacy coefficient corresponding to each privacy term in the privacy terminology set includes: Each privacy term in the privacy term set is assigned a weight, and a privacy weight corresponding to the privacy term is determined. Determine the trigger frequency of the privacy words in the privacy word sequence, and filter the sensitive privacy word sequence based on the trigger frequency parameter; Determine the proportion of the number of the sensitive privacy word sequence and the privacy word sequence, and determine the privacy coefficient based on the proportion of the number and the privacy weight.

4. The method according to claim 1, characterized in that, The process of determining high-frequency privacy contract data from the enterprise contract data based on the contract privacy score includes: Obtain the classification standard threshold and compare the contract privacy score with the classification standard threshold; If the contract privacy score is greater than or equal to the classification standard threshold, the corresponding contract data is identified as high-frequency privacy contract data; If the contract privacy score is less than the classification standard threshold, the corresponding contract data is identified as low-frequency privacy contract data.

5. The method according to claim 1, characterized in that, The encryption process performed on the high-frequency privacy contract data includes: High-frequency privacy contract data is divided into fixed-length data slices, and the data slices are encrypted to obtain encrypted slices; An encryption matrix is ​​obtained based on the encryption slice, and an affine transformation is performed on the encryption matrix to obtain an affine matrix; The affine matrix and the random augmented matrix are concatenated to obtain the preprocessed matrix, and the preprocessed matrix is ​​embedded into the random transmission confidentiality matrix to determine the encrypted transmission matrix.

6. The method according to claim 5, characterized in that, The process of encrypting the data slice to obtain an encrypted slice includes: Determine the target cryptoprime number and calculate its product and Euler's totient function. Generate a coprime public key and a private key based on the Euler's totient function. The private key is stored in a key store, and the data slice is encrypted based on the public key to obtain an encrypted slice corresponding to the data slice.

7. The method according to claim 5, characterized in that, The step of obtaining an encryption matrix based on the encryption slice and performing an affine transformation on the encryption matrix to obtain an affine matrix includes: The row and column dimensions of the encryption matrix are determined based on the number of encryption slices, and the encryption slices are then filled. The encryption matrix is ​​transformed sequentially by performing matrix transformations to obtain the transformation matrix, and the inverse matrix corresponding to each transformation matrix is ​​determined. The affine matrix is ​​determined based on the transformation matrix, and the inverse matrix is ​​stored in the key store.

8. A privacy encryption device for enterprise contracts, characterized in that, include: The data acquisition module is used to acquire enterprise contract data corresponding to the target enterprise; The contract privacy evaluation module is used to perform privacy sensitivity analysis on the enterprise contract data and determine the contract privacy score corresponding to the enterprise contract data. A privacy encryption module is used to determine high-frequency privacy contract data from the enterprise contract data based on the contract privacy score, and to encrypt the high-frequency privacy contract data for privacy purposes.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the privacy encryption method for the enterprise contract according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the privacy encryption method for the enterprise contract according to any one of claims 1-7.

Images