Trusted Hybrid Marking Index Generation Method Based on Digital Signature

Abstract

The present invention relates to the field of information security technology, and specifically relates to a method for generating a trusted hybrid marking index based on digital signatures. The method includes: collecting electronic contract document data and user identity identification sequences; obtaining the word perception frequency sensitivity coefficients of each Chinese character, and further obtaining the numeral verification coefficients of each Chinese character; calculating the Chinese character frequency sequences of each sentence, and further obtaining the sentence pattern numeral verification sensitivity coefficients of each sentence in the electronic contract document data; obtaining the hybrid marking significance coefficients between each sentence; constructing the intra-paragraph sentence pattern hybrid marking significance matrix of each paragraph; selecting the specified paragraphs in the electronic contract document data and the paragraph comparison blocks of each paragraph, and obtaining the paragraph marking comparison trust index of each paragraph in the electronic contract document data; obtaining the paragraph marking comparison trust sequence, and further obtaining the digital signature of the electronic document user data. The present invention aims to solve the problem that the private key is easily cracked due to using pseudo-random numbers as the private key generation parameters.

Description

Technical Field

[0001] This application relates to the field of information security technology, and particularly to a method for generating a trusted hybrid tag index based on digital signature. Background Art

[0002] Digital signature is a technology that uses asymmetric key encryption to combine specific data (usually a message or a file) with the identity information of the sender to generate a unique identifier, which is called a digital signature. Through the digital signature, the integrity of the data can be verified and the identity information of the sender can be confirmed. The Identity-Based Cryptography (IBC) specification requires that the identity identification technology based on data signature is mainly manifested as the IBE encryption and decryption algorithm group, the IBS signature algorithm group, and the IBKA identity authentication algorithm group. Among them, the IBS signature algorithm group is an algorithm that generates a digital signature by using asymmetric encryption for the data information to be encrypted and the identity identification information of the user, which directly determines the security and reliability of the information.

[0003] The Elliptic Curve Digital Signature Algorithm (ECDSA) has the advantages of a small key size, fast signature, and verification speed, and has become the preferred signature algorithm. In the traditional ECDSA algorithm, the generation of the private key is usually determined by a private key generation parameter d, and d is usually an integer greater than zero. However, the generation of a secure random number is not always easy to implement, and the possibility of generating a pseudo-random number is relatively large. If the random seed of the random number generator is not random enough or the generator is cracked, it may lead to the predictability and derivability of the user's private key, thereby reducing the security of encryption. To solve the above problems, the present invention proposes a method for generating a trusted hybrid tag index based on digital signature, which uses signature data and user information to improve the chaos of the key and the security of the digital signature. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a method for generating a trusted hybrid tag index based on digital signature to solve the existing problems.

[0005] The method for generating a trusted hybrid tag index based on digital signature of the present invention adopts the following technical solutions:

[0006] An embodiment of the present invention provides a method for generating a trusted hybrid tag index based on digital signature, and the method includes the following steps:

[0007] Collect electronic contract document data and user identity identification sequences;

[0008] Obtain the word perception frequency sensitivity coefficient of each Chinese character in the electronic contract document data according to the number of times each Chinese character appears in the electronic contract document; obtain the numeral verification coefficient of each Chinese character in the electronic contract document data according to the preset contract sensitive numeral set; obtain the Chinese character frequency sequence of each sentence according to the frequency of each Chinese character; obtain the sentence pattern numeral verification sensitivity coefficient of each sentence in the electronic contract document data according to the Chinese character frequency sequence, the word perception frequency sensitivity coefficient, and the numeral verification coefficient; obtain the mixed mark significance coefficient between each sentence according to the sentence pattern numeral verification sensitivity coefficient; construct the intra-paragraph sentence pattern mixed mark significance matrix of each paragraph according to the mixed mark significance coefficient;

[0009] Select the paragraph comparison block of each paragraph in the electronic contract document data, and obtain the paragraph mark comparison credibility index of each paragraph in the electronic contract document data according to the intra-paragraph sentence pattern mixed mark significance matrix;

[0010] Obtain the paragraph mark comparison credibility sequence according to the paragraph mark comparison credibility index, and obtain the digital signature of the electronic document user data according to the paragraph mark comparison credibility sequence.

[0011] Furthermore, the obtaining of the word perception frequency sensitivity coefficient of each Chinese character in the electronic contract document data includes:

[0012] For each Chinese character in each sentence in the electronic contract document data, calculate the probability that each Chinese character and its previous adjacent Chinese character appear in the electronic contract document data simultaneously as the first probability, calculate the probability that each Chinese character and its next adjacent Chinese character appear in the electronic contract document data simultaneously as the second probability, and calculate the sum value of the first probability and the second probability;

[0013] Calculate the probability that each Chinese character appears in the electronic contract document as the third probability, calculate the calculation result of the exponential function with base 10 and the third probability as the exponent, and take the ratio of the negative value of the calculation result to the sum value as the word perception frequency sensitivity coefficient of each Chinese character in the electronic contract document data.

[0014] Furthermore, the obtaining of the numeral verification coefficient of each Chinese character in the electronic contract document data includes:

[0015] For each Chinese character in each sentence in the electronic contract document data, if the Chinese character belongs to the preset contract sensitive numeral set, take the first preset numeral adjustment factor as the numeral verification coefficient of the Chinese character; otherwise, take the second preset numeral adjustment factor as the numeral verification coefficient of the Chinese character, where the first preset numeral adjustment factor is greater than the second preset numeral adjustment factor.

[0016] Furthermore, the obtaining of the Chinese character frequency sequence of each sentence includes:

[0017] For each sentence in the electronic contract document, calculate the frequency of each Chinese character in the sentence in the electronic contract document data, and arrange the frequencies of each Chinese character in the order of appearance in the sentence to construct the Chinese character frequency sequence of each sentence.

[0018] Further, the obtaining of the syntactic numeral verification sensitivity coefficient of each sentence in the electronic contract document data includes:

[0019] For each sentence in the electronic contract document data, calculate the calculation result of the logarithmic function with the natural constant as the base and the numeral verification coefficient of each Chinese character as the true number, calculate the product of the calculation result and the word perception frequency sensitivity coefficient of each Chinese character, calculate the mean value of the products in the sentence, and take the product of the mean value and the information entropy of the Chinese character frequency sequence of each sentence as the syntactic numeral verification sensitivity coefficient of each sentence in the electronic contract document data.

[0020] Further, the obtaining of the mixed mark significance coefficient between each sentence includes:

[0021] For each paragraph in the electronic contract document data, calculate the DTW distance between the i-th sentence and the j-th sentence in the paragraph, calculate the calculation result of the exponential function with the natural constant as the base and the sum value of the syntactic numeral verification sensitivity coefficients of the i-th sentence and the j-th sentence as the exponent, and take the product of the DTW distance and the calculation result as the mixed mark significance coefficient between the i-th sentence and the j-th sentence.

[0022] Further, the constructing of the intra-paragraph syntactic mixed mark significance matrix of each paragraph includes:

[0023] Take the mixed mark significance coefficient between the i-th sentence and the j-th sentence in each paragraph as the element in the i-th row and j-th column of the intra-paragraph syntactic mixed mark significance matrix of the paragraph, and form the intra-paragraph syntactic mixed mark significance matrix of each paragraph.

[0024] Further, the selecting of the paragraph comparison block of each paragraph in the electronic contract document data includes:

[0025] Centering on each paragraph in the electronic contract document data, select a total of paragraphs in the front and back directions as the paragraph comparison block of the current paragraph, where is the preset number of paragraphs.

[0026] Further, the obtaining of the paragraph mark comparison credibility index of each paragraph in the electronic contract document data includes:

[0027] For the electronic contract document data, calculate the absolute value of the difference between the paragraph order of each paragraph in the paragraph comparison block of the C-th paragraph in the electronic contract document and the paragraph order of the C-th paragraph in the electronic contract document, calculate the sum value of the preset parameter adjustment factor and the absolute value of the difference, and calculate the calculation result of the logarithmic function with the natural constant as the base and the sum value as the true number;

[0028] Calculate the absolute value of the difference between the F norms of the intra-paragraph sentence pattern mixing mark significant matrices of the C-th paragraph and each paragraph in the paragraph comparison block of the C-th paragraph as the first absolute value of the difference, calculate the ratio of the first absolute value of the difference to the calculation result, and use the sum value of the ratios of the C-th paragraph and all paragraphs in the paragraph comparison block of the C-th paragraph as the paragraph mark comparison credibility index of each paragraph in the electronic contract document data.

[0029] Further, the obtaining of the paragraph mark comparison credibility sequence and the obtaining of the digital signature of the electronic document user data according to the paragraph mark comparison credibility sequence include:

[0030] Form the paragraph mark comparison credibility sequence of the electronic contract document data by arranging the paragraph mark comparison credibility indexes of each paragraph in the order in which the corresponding paragraphs appear in the electronic contract document data, form the mark index private key generation sequence by combining the paragraph mark comparison credibility sequence with the user identity identification sequence, and process the mark index private key generation sequence using UTF-8 encoding to obtain the binary encoding sequence;

[0031] Use the binary encoding sequence as the input of the hash function, the output of the hash function is the hash value, use the hash value as the digital signature security factor of the electronic document user data, use the electronic contract document data and the digital signature security factor as the input of the ECDSA digital signature algorithm, and the output of the ECDSA digital signature algorithm is the private key, public key and digital signature of the electronic document user data.

[0032] The present invention has at least the following beneficial effects:

[0033] In order to improve the sensitivity to some Chinese characters in the electronic contract, the present invention constructs a contract-sensitive numeral set, obtains the sentence pattern numeral verification sensitivity coefficient by combining the frequency of Chinese characters appearing in the sentences in the contract and the relevance of Chinese characters, obtains the intra-paragraph sentence pattern mixing mark significant matrix by combining the Chinese character information of the sentences within the paragraph, divides the paragraph comparison block in order to measure the influence degree of the paragraph on the contract, obtains the paragraph mark comparison credibility index by comparing with the paragraph, and finally generates the digital signature security factor. It solves the problem that the private key is easily cracked due to using pseudo-random numbers as the private key generation parameters, combines the paragraph information and user information of the electronic contract document data to generate the digital signature security factor, and improves the sensitivity of the digital signature to the contract content. Description of the Drawings

[0034] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 A flowchart of a method for generating a trusted hybrid tag index based on digital signature provided by the present invention;

[0036] Figure 2 Flowchart for obtaining a mixed labeling saliency matrix for intra-segment sentences. DETAILED DESCRIPTION

[0037] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, features and effects of the trusted hybrid tag index generation method based on digital signature proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0038] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0039] The specific scheme of the method for generating a trusted hybrid tag index based on digital signature provided by the present invention is described in detail below with reference to the accompanying drawings.

[0040] An embodiment of the present invention provides a method for generating a trusted hybrid tag index based on a digital signature. Specifically, the following method for generating a trusted hybrid tag index based on a digital signature is provided. Figure 1 , the method comprises the following steps:

[0041] Step S001, obtaining text information to be signed and user identity information.

[0042] With the advent of the paperless era, more and more business transactions are handled in the form of electronic contracts. Therefore, this embodiment uses a signed electronic contract as an example scenario. A contract data is obtained. This embodiment uses a regular matching algorithm to remove meaningless characters in the electronic contract, such as punctuation marks, etc. The input of the regular matching algorithm is the electronic contract document data, and the output of the regular matching algorithm is the electronic contract document data after data cleaning. The regular matching algorithm is a well-known technology and will not be described in detail in this embodiment.

[0043] For the electronic contract document data, taking the paragraph delimiter as the separator, each paragraph in the electronic contract document data is obtained; taking the full stop as the separator, each sentence in the electronic contract document is obtained, and using W k (i) represents the i-th Chinese character in the k-th sentence of the contract data. Further, the identity identification information of the signing user is obtained, including the name, IP address, and signing time, which form the user identity identification sequence U.

[0044] Thus far, the electronic contract document data and the user identity identification sequence are obtained.

[0045] Step S002: According to the document information in the electronic contract, the sentences are divided. The word perception frequency sensitivity coefficient is obtained by using the occurrence frequency of Chinese characters and the correlation between Chinese characters. In order to improve the sensitivity of the contract to numerals, a contract-sensitive numeral set is constructed to obtain the sentence pattern numeral verification sensitivity coefficient. Combining the numeral differences of the sentences within the paragraph, the within-paragraph sentence pattern mixed marking significant matrix is obtained. The paragraph marking comparison credibility index is obtained by dividing the paragraph comparison block. Finally, the digital signature security factor is generated in combination with the user information.

[0046] The selection of the private key has an important impact on the security and input results of the ECDSA signature algorithm. The private key must have privacy to prevent attackers from cracking the digital signature by guessing and predicting the private key. In addition, the private key cannot be spread externally. Since the private key carries the user's identity representation, once the private key is leaked, attackers can forge digital signatures, thereby destroying the reliability of the digital signature. Among them, the private key generation parameter d in the ECDSA signature algorithm directly affects the generation of the private key and the result of the algorithm. Using a larger d value can improve the security of the algorithm, but it will increase the computational complexity of the algorithm; using a smaller d value can speed up the generation speed of the signature and reduce the security of the algorithm. Therefore, it is necessary to jointly determine the size of the private key generation parameter d in combination with the text information of the electronic contract and the user identity identification data.

[0047] The electronic contract document data often contains a large number of Chinese characters. The electronic contract has certain legal effects. If a defaulter tampers with a small part of the Chinese characters, it is usually not easily detected. However, the impact of different Chinese character modifications on the electronic contract is different. Therefore, combining the text information in the electronic contract document data, the sensitivity of Chinese characters is measured. The word perception frequency sensitivity coefficient is constructed, and the formula is:

[0048]

[0049] In the formula, represents the word perception frequency sensitivity coefficient of the i-th Chinese character in the k-th sentence of the electronic contract document data, W k (i) represents the i-th Chinese character in the k-th sentence of the electronic contract document data, PT (W k (i)) represents the probability that the i-th Chinese character in the k-th sentence of the electronic contract document data appears in the electronic contract document data, log 10 () represents the logarithmic function with base 10, W k (i - 1) and W k (i + 1) respectively represent the (i - 1)-th and (i + 1)-th Chinese characters in the k-th sentence of the electronic contract document data, count(W k (i - 1), W k (i)) is the number of times that the i-th Chinese character and the previous adjacent Chinese character appear together in the electronic contract document data, count(W k (i), W k (i + 1)) is the number of times that the i-th Chinese character and the next adjacent Chinese character appear together in the electronic contract document data. If the i-th Chinese character is the starting Chinese character of the sentence, only the number of times it appears together with the next Chinese character is counted. exp() represents the exponential function with base e, the natural constant.

[0050] Word Perception Frequency Sensitivity Coefficient Reflects the degree to which the current Chinese character should be concerned. For Chinese characters that appear frequently in the text, if they are modified, it is easy to attract visual attention. For Chinese characters that appear less frequently, if they are modified, it is not easy to attract attention. Therefore, it is necessary to measure the sensitivity of Chinese characters that appear less frequently through the Word Perception Frequency Sensitivity Coefficient α. If the i-th Chinese character in the current group represents the main content of the electronic contract, the frequency of this Chinese character appearing in the electronic contract document data is relatively high. Thus, calculating -log 10 (P T (W k (i))) is relatively small. In addition, since this Chinese character reflects the main content of the electronic contract, the number of times this Chinese character appears together with the surrounding characters is relatively large, that is, count(W k (i - 1), W k (i)) and count(W k (i), W k (i + 1)) have relatively large values. Eventually, the value of the Word Perception Frequency Sensitivity Coefficient is relatively small. On the contrary, if the current Chinese character represents the differential information in the contract, the frequency of this Chinese character appearing is relatively low, and the degree of association with the surrounding Chinese characters is relatively low. Eventually, the value of increases.

[0051] Through the Word Perception Frequency Sensitivity Coefficient It can be calculated based on the frequency of occurrence of Chinese characters and the degree of correlation between the previous and next Chinese characters. Electronic contracts contain many Chinese characters, and it is somewhat one-sided to measure the sensitivity of Chinese characters only by the frequency of occurrence of Chinese characters. Different Chinese characters represent different meanings, and tampering with different Chinese characters will have different impacts on the contract.

[0052] In electronic contract documents, the sensitivity to numerals is high, especially Chinese characters related to money and time, which have a great impact on the importance of the contract. This embodiment constructs a contract sensitive numeral set O, where O = {one, two, three, four, five, six, seven, eight, nine, ten, hundred, thousand, ten thousand, hundred million, yuan, jiao, fen, zero, year, month, day}. Combined with the contract sensitive numeral set O, the word perception frequency sensitivity coefficient α is verified to obtain the sentence numeral verification sensitivity coefficient:

[0053]

[0054]

[0055] In the formula, γ k represents the sentence numeral check sensitivity coefficient of the kth sentence in the electronic contract document data, W k represents the kth sentence in the electronic contract document data, P T (W k ) is a Chinese character frequency sequence composed of the frequencies of the Chinese characters in the k-th sentence in the electronic contract document data according to their order in the sentence, ΔH() represents the information entropy of the Chinese character frequency sequence in the k-th sentence, wherein the calculation of information entropy is a well-known technology and will not be elaborated here; N k represents the number of Chinese characters in the kth sentence in the electronic contract document data, β i represents the numeral check coefficient of the i-th Chinese character in the sentence, ln() represents the logarithmic function with the natural constant e as the base, represents the word perception frequency sensitivity coefficient of the i-th Chinese character in the k-th sentence in the electronic contract document data, t1 and t2 represent the numeral adjustment factors respectively, and the implementer can set the value of the numeral adjustment factor by himself, and this embodiment does not impose any special restrictions. In this embodiment, t1=5, t2=2, where t1>t2, W k (i) represents the i-th Chinese character in the k-th sentence in the electronic contract document data, and O represents the set of contract sensitive numerals.

[0056] Thus, the sensitivity coefficient of word perception frequency in the sentence is verified through the contract-sensitive numeral set O, and the sensitivity coefficient of sentence numeral verification is obtained to reflect the sensitivity of the current sentence when generating the mixed mark of the digital signature. If there are more numerals in the current sentence, it indicates that the current sentence often reflects information such as the amount and expiration date of the contract signing. Although the frequency of occurrence in the full text is low, the content is relatively important. Therefore, a numeral verification coefficient β is set for adjustment. If the Chinese character belongs to the contract numeral sensitive set, a higher weight is assigned to the Chinese character; otherwise, a lower weight is assigned. If the current Chinese character belongs to the contract-sensitive numeral set O, the calculated ln(β) is greater than 1, and the sensitivity coefficient α of word perception frequency is amplified. If the current Chinese character does not belong to O, the sensitivity coefficient α of word perception frequency is appropriately reduced, and finally, the sensitivity coefficient γ of sentence numeral verification of the current sentence is obtained k If there are more numerals in the current sentence, the sensitivity coefficient γ of sentence numeral verification obtained k has a larger value. If the current sentence only expresses the contract information that appears repeatedly in the contract, γ k has a smaller value.

[0057] So far, the sensitivity coefficients of sentence numeral verification for each sentence are obtained, and the sensitivity coefficients of sentence numeral verification only reflect the importance of Chinese characters within the group. There are many sentences in a single electronic contract, and different sentences together form a paragraph. Each paragraph reflects part of the contract information, and the contract information reflected by different paragraphs is different. To measure the important difference degree of sentences within the paragraph, a significant matrix of intra-paragraph sentence mixed marks is constructed. Each element in the matrix is calculated as follows:

[0058]

[0059] In the formula represents the significant coefficient of the mixed mark in the i-th row and j-th column of the significant matrix G of intra-paragraph sentence mixed marks constructed for the C-th paragraph in the electronic contract document data C in, W i and W j respectively represent the i-th and j-th sentences in the current paragraph in the electronic contract document data. P T (W i ) and P T (W j ) respectively represent the Chinese character frequency sequences composed of the frequencies of occurrence of each Chinese character in the i-th and j-th sentences in the current paragraph in the electronic contract document data. DTW() represents the DTW distance between two Chinese character frequency sequences. DTW(P T (W i ), P T (W j)) represents calculating the DTW distance of the Chinese character frequency sequences formed by the frequencies of each Chinese character in the \(i\)-th and \(j\)-th sentences within the current paragraph in the electronic contract document data, \(\gamma\). i and \(\gamma\) j respectively represent the sensitive coefficients of the sentence pattern numeral verification in the \(i\)-th and \(j\)-th sentences within the current paragraph in the electronic contract document data, \(N\) C represents the number of sentences in the \(C\)-th paragraph in the electronic contract document data.

[0060] By traversing each sentence within the current paragraph, the intra-paragraph sentence pattern mixed marking significance matrix \(G\) is obtained. C , and the flowchart for obtaining the intra-paragraph sentence pattern mixed marking significance matrix is as Figure 2 shown, reflecting the influence degree of the sentences within the paragraph on the electronic contract. If the current paragraph represents information such as the limited time or transaction amount in the electronic contract, the frequency of each Chinese character appearing in the sentence is relatively small, and the frequencies of Chinese characters appearing are uneven, resulting in a relatively large DTW distance of the Chinese character frequency sequences between sentences. In addition, there are many numbers belonging to the contract-sensitive numeral set within the sentence, resulting in a relatively large value of the sensitive coefficient of the sentence pattern numeral verification, and finally leading to relatively large values of each element in the intra-paragraph sentence pattern mixed marking significance matrix \(G\). C On the contrary, if the current paragraph represents the ordinary content of the electronic contract, the frequency of Chinese characters appearing between each sentence within the paragraph is relatively high, and the value of the sensitive coefficient of the sentence pattern numeral verification is relatively small, and finally leading to a decrease in the values of each element in the intra-paragraph sentence pattern mixed marking significance matrix \(G\). C

[0061] Since the limited contract time period and transaction amount are sensitive information in the electronic contract, that is, the numbers in the electronic contract are relatively sensitive, the paragraphs in the electronic contract document data where numbers appear are used as the limited paragraphs, and the other paragraphs except the limited paragraphs are used as ordinary paragraphs. Among all the paragraphs in the electronic contract document data, the limited paragraphs are relatively few, and most paragraphs are ordinary paragraphs. Therefore, in order to highlight the importance degree of the limited paragraphs, taking each paragraph in the electronic contract document data as the center, a total of paragraphs are selected as the paragraph comparison block of the current paragraph in the front and back two directions, comparing the differences between the current paragraph and the paragraphs within the comparison block. If the front and back directions of the current paragraph cannot meet when there are paragraphs, only all the paragraphs within the

[0062]

[0063] In the formula, \(q\) C represents the paragraph marking comparison credibility index of the \(C\)-th paragraph in the electronic contract document data. represents the number of paragraphs within the paragraph comparison block centered around the C-th paragraph in the electronic contract document data. In this embodiment takes a value of 4, G C and G m respectively represent the within-paragraph sentence pattern mixing mark significance matrices of the C-th paragraph and the m-th paragraph within the paragraph comparison block of the C-th paragraph in the electronic contract document data. m' represents the paragraph order of the m-th paragraph within the paragraph comparison block of the C-th paragraph among all paragraphs in the electronic contract document data. ‖G m ‖ F represents calculating the F-norm of matrix G m ; ‖G C ‖ F represents calculating the F-norm of matrix G C . ε represents a parameter adjustment factor, and ε = 1 is set according to experience. ln() represents the logarithmic function with the natural constant e as the base.

[0064] If the C-th paragraph corresponds to a restricted paragraph, within the paragraph comparison block centered around the C-th paragraph, most are ordinary paragraphs. Therefore, the difference in the within-paragraph sentence pattern mixing mark significance matrices between the two is relatively large, that is, the difference between ‖G m ‖ F and ‖G C ‖ F is relatively large. In addition, the distance weight is restricted by ln(ε + |m - C|). When the m-th paragraph within the paragraph comparison block is farther from the C-th paragraph, the weight is smaller, and the closer the distance, the greater the weight. Eventually, the paragraph mark comparison credibility index q C has a larger value. On the contrary, if the C-th paragraph is an ordinary paragraph, most of the paragraphs within its paragraph comparison block are normal paragraphs. Therefore, the difference in the within-paragraph sentence pattern mixing mark significance matrices between the two is relatively small, and eventually the value of q C decreases.

[0065] Obtain the paragraph mark comparison credibility index of each paragraph in the electronic contract document data, which reflects the influence degree of the current paragraph content on the electronic contract. Sort the paragraph mark comparison credibility indices of each paragraph in the order of their appearance in the electronic contract document data to form the paragraph mark comparison credibility sequence Q of the electronic contract document data. Combine with the user identity identification sequence U, and form the mark index private key generation sequence S by combining the paragraph mark comparison credibility sequence Q and the user identity identification sequence U. There are information such as Chinese characters, numbers, and special characters in the mark index private key generation sequence. Process the mark index private key generation sequence S using UTF-8 encoding to obtain the binary encoding sequence S' of the electronic contract document data and the user information digital signature. Since UTF-8 encoding is a well-known technology in the field of character encoding, it will not be elaborated in this embodiment.

[0066] Take the binary-encoded sequence S′ as the input of the hash function, and the output is the hash value, denoted as D. The hash value combines the contract information and user information, and the hash function is a well-known technology to those skilled in the art, so it will not be elaborated here. Use the hash value D as the digital signature security factor of the electronic document user data. Combine the electronic contract document data and the user identity flag information to generate the digital signature security factor, and use it as the private key generation parameter of the ECDSA signature algorithm, and finally generate the private key and public key of the digital signature.

[0067] Step S003, according to the obtained digital signature security factor, use the ECDSA digital signature algorithm to generate the key and digital signature, and verify the digital signature.

[0068] According to step S002, combine the electronic contract document data and the user identity flag information to generate a highly reliable marker index private key generation sequence, and obtain the digital signature security factor D in the private key generation parameter.

[0069] Take the electronic contract document data and the digital signature security factor D as the input of the ECDSA digital signature algorithm. The output of the ECDSA digital signature algorithm is the private key X, public key Y and digital signature Z corresponding to the user. The private key X is the private data of the user and cannot be transmitted over the network. The public key Y and the digital signature can be transmitted arbitrarily over the network.

[0070] Signature verification: When the receiving party receives the electronic contract and the digital signature, signature verification is required, that is, verify the digital signature by combining the public key of the signing user of the sender, and the integrity of the document and the identity information of the signing user of the sender can be determined according to the verification result, thereby preventing the electronic contract document data from being tampered with and the user's signature from being denied.

[0071] It should be noted that: the above sequence of the embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. And the above describes specific embodiments of this specification. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0072] Each embodiment in this specification is described in a progressive manner. The same or similar parts between each embodiment can be referred to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

[0073] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; modifying the technical solutions recorded in the foregoing embodiments, or equivalently replacing some of the technical features, does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of each embodiment of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for generating a trusted hybrid tag index based on digital signature, characterized in that: The method comprises the following steps: Collect electronic contract document data and user identity sequence; For each Chinese character in each sentence in the electronic contract document data, calculate the probability that each Chinese character and its previous adjacent Chinese character appear in the electronic contract document data at the same time as a first probability, calculate the probability that each Chinese character and its subsequent adjacent Chinese character appear in the electronic contract document data at the same time as a second probability, and calculate the sum of the first probability and the second probability; Calculate the probability of each Chinese character appearing in the electronic contract document as a third probability, calculate the calculation result of an exponential function with the number 10 as the base and the third probability as the exponent, and use the ratio of the negative value of the calculation result to the sum value as the word perception frequency sensitivity coefficient of each Chinese character in the electronic contract document data; if each Chinese character belongs to a preset contract sensitive numeral set, use the first preset numeral adjustment factor as the numeral verification coefficient of each Chinese character; otherwise, use the second preset numeral adjustment factor as the numeral verification coefficient of each Chinese character, wherein the first preset numeral adjustment factor is greater than the second preset numeral adjustment factor; obtain the Chinese character frequency sequence of each sentence according to the frequency of each Chinese character; calculate the calculation result of a logarithmic function with a natural constant as the base and the numeral verification coefficient of each Chinese character as a true number, and calculate the ratio of the calculation result to the numeral verification coefficient of each Chinese character. The product of the word perception frequency sensitivity coefficients, the product of the mean of the product in each sentence and the information entropy of the Chinese character frequency sequence of each sentence is used as the sentence numeral check sensitivity coefficient of each sentence; for each paragraph in the electronic contract document data, the DTW distance between the i-th sentence and the j-th sentence in the paragraph is calculated, and the calculation result of an exponential function with a natural constant as the base and the sum of the sentence numeral check sensitivity coefficients of the i-th sentence and the j-th sentence as the exponent is calculated, and the product of the DTW distance and the calculation result is used as the mixed mark significance coefficient between the i-th sentence and the j-th sentence; the mixed mark significance coefficient between the i-th and the j-th sentences in each paragraph is used as the element of the i-th row and j-th column in the intra-paragraph sentence mixed mark significance matrix of the paragraph, to form the intra-paragraph sentence mixed mark significance matrix of each paragraph; Selecting a paragraph comparison block of each paragraph in the electronic contract document data, for the electronic contract document data, calculating the absolute value of the difference between the paragraph sequence of each paragraph in the paragraph comparison block of the Cth paragraph in the electronic contract document and the paragraph sequence of the Cth paragraph in the electronic contract document, calculating the sum of the preset parameter adjustment factor and the absolute value of the difference, and calculating the calculation result of a logarithmic function with a natural constant as the base and the sum as a true number; Calculating the absolute value of the difference between the F norm of the intra-paragraph sentence mixed mark saliency matrix of the C-th paragraph and each paragraph in the paragraph comparison block of the C-th paragraph as the first absolute value of the difference, calculating the ratio of the first absolute value of the difference to the calculation result, and taking the sum of the ratios of the C-th paragraph and all paragraphs in the paragraph comparison block of the C-th paragraph as the paragraph mark comparison credibility index of each paragraph in the electronic contract document data; The paragraph mark comparison trust index of each paragraph is used to form a paragraph mark comparison trust sequence of the electronic contract document data in the order in which the corresponding paragraphs appear in the electronic contract document data, the paragraph mark comparison trust sequence and the user identity sequence are used to form a mark index private key generation sequence, and the mark index private key generation sequence is processed using UTF-8 encoding to obtain a binary encoding sequence; The binary code sequence is used as the input of the hash function, the output of the hash function is the hash value, the hash value is used as the digital signature security factor of the electronic document user data, the electronic contract document data and the digital signature security factor are used as the input of the ECDSA digital signature algorithm, and the output of the ECDSA digital signature algorithm is the private key, public key and digital signature of the electronic document user data.

2. The method for generating a trusted hybrid tag index based on digital signature according to claim 1, characterized in that: The step of obtaining the frequency sequence of Chinese characters in each sentence includes: For each sentence in the electronic contract document, the frequency of each Chinese character in the sentence in the electronic contract document data is calculated, and the frequency of each Chinese character is arranged according to the order of the Chinese characters in the sentence to construct a Chinese character frequency sequence for each sentence.

3. The method for generating a trusted hybrid tag index based on digital signature according to claim 1, characterized in that: The selecting of paragraph comparison blocks of each paragraph in the electronic contract document data includes: Centered on each paragraph in the electronic contract document data, select paragraphs as the paragraph comparison block of the current paragraph, where The preset number of paragraphs.

Images