A blockchain-based joint factoring data security protection method and system

Abstract

The embodiment of the application provides a kind of based on the joint factoring data security protection method and system of blockchain, belong to data transmission technical field.The method comprises: the initial factoring data is carried out key sentence identification and obtains target key sentence;Target key sentence is carried out sensitive information identification and obtains target sensitive information;According to initial factoring data and target sensitive information, data entropy analysis is carried out and obtains first encryption mode and second encryption mode;According to first encryption mode and second encryption mode, encryption is carried out and obtains target encryption result;The initial factoring data is carried out intention identification and obtains target intention, and according to target intention, target encryption result corresponding target permission is determined;Target encryption result and target permission are transmitted to relevant node using blockchain, and obtain the relevant permission corresponding to relevant node;According to target permission and relevant permission, relevant node is screened and target node is obtained, so that target object obtains target encryption result according to target node.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data transmission, in particular to a joint factoring data security protection method and system based on a blockchain. BACKGROUND

[0002] In today's digital era, the popularity of Internet electronic office and the rapid development of Internet finance make the demand for electronic informationization of factoring services more urgent for enterprises. Traditional joint factoring business mainly relies on offline operation mode, which requires frequent offline communication and audit between both parties in key links such as customer audit, credit limit approval and financing audit, in order to verify the authenticity and validity of the information and information provided by the customer at each stage.

[0003] However, this offline business processing method has many limitations and challenges. First of all, due to the lack of a unified electronic platform to manage the business data and information of both parties or multiple parties, it is difficult to ensure the consistency and accuracy of the data. Secondly, offline communication not only consumes a lot of human resources, but also increases the cost of communication and reduces the efficiency of business processing. In addition, this traditional operation mode also increases the probability of potential risks, such as information leakage, oversight, etc.

[0004] Therefore, in order to adapt to the development of the times and meet the needs of the market, it is urgent to develop an electronic informationization joint factoring business solution to improve the efficiency of business processing, reduce operating costs, and enhance the ability of risk management. SUMMARY

[0005] The main purpose of the embodiments of the present application is to provide a joint factoring data security protection method and system based on a blockchain, which aims to solve the problems of low efficiency and high risk in processing joint factoring business in related technologies.

[0006] In a first aspect, the embodiments of the present application provide a joint factoring data security protection method based on a blockchain, comprising:

[0007] Obtaining initial factoring data corresponding to a target construction enterprise, and performing key sentence recognition on the initial factoring data to obtain corresponding target key sentences;

[0008] Performing sensitive information recognition on the target key sentences to obtain target sensitive information corresponding to the target key sentences;

[0009] Performing data entropy analysis on the initial factoring data and the target sensitive information to obtain a first encryption method corresponding to the target sensitive information and a second encryption method corresponding to the initial factoring data;

[0010] encrypt the target sensitive information and the initial factoring data according to the first encryption mode and the second encryption mode to obtain a target encryption result;

[0011] perform intent recognition on the initial factoring data to obtain a target intent corresponding to the initial factoring data, and determine a target permission corresponding to the target encryption result according to the target intent;

[0012] transmit the target encryption result and the target permission to a related node by using a block chain, and obtain a related permission corresponding to the related node;

[0013] screen the related node according to the target permission and the related permission to obtain a target node, so that a target object obtains the target encryption result according to the target node.

[0014] In a second aspect, an embodiment of the present application provides a joint factoring data security protection system based on a block chain, comprising:

[0015] a data acquisition module configured to obtain initial factoring data corresponding to a target construction enterprise, and perform key sentence recognition on the initial factoring data to obtain a target key sentence corresponding thereto;

[0016] an information recognition module configured to perform sensitive information recognition on the target key sentence to obtain target sensitive information corresponding to the target key sentence;

[0017] a mode determination module configured to perform data entropy analysis on the initial factoring data and the target sensitive information to obtain a first encryption mode corresponding to the target sensitive information and a second encryption mode corresponding to the initial factoring data;

[0018] a data encryption module configured to encrypt the target sensitive information and the initial factoring data according to the first encryption mode and the second encryption mode to obtain a target encryption result;

[0019] an intent recognition module configured to perform intent recognition on the initial factoring data to obtain a target intent corresponding to the initial factoring data, and determine a target permission corresponding to the target encryption result according to the target intent;

[0020] a data transmission module configured to transmit the target encryption result and the target permission to a related node by using a block chain, and obtain a related permission corresponding to the related node;

[0021] a data screening module configured to screen the related node according to the target permission and the related permission to obtain a target node, so that a target object obtains the target encryption result according to the target node.

[0022] The embodiment of the present application provides a kind of based on the flow of joint factoring data security protection method and system of blockchain, which comprises: obtaining the initial factoring data corresponding to target construction enterprise, and the initial factoring data is carried out key sentence recognition and obtains the corresponding target key sentence, then by carrying out key sentence recognition to initial factoring data, the most important information can be extracted, reduce the processing of irrelevant data, reduce the risk of data leakage.To the target key sentence is carried out sensitive information identification and obtains the target sensitive information corresponding to target key sentence, carries out data entropy analysis according to initial factoring data and target sensitive information, obtains the first encryption mode corresponding to target sensitive information and the second encryption mode corresponding to initial factoring data, so as to select appropriate encryption mode according to data entropy analysis, sensitive information and initial factoring data are encrypted, further guarantee the confidentiality and integrity of data, so as to encrypt target sensitive information and initial factoring data according to the first encryption mode and the second encryption mode and obtain target encryption result, then the initial factoring data is carried out intention recognition and obtains the target intention corresponding to initial factoring data, and the target permission corresponding to target encryption result is determined according to target intention, so as to transmit encrypted data using blockchain technology, which can ensure the non-tamperability and transparency of data transmission, prevent data from being tampered with or stolen during transmission, and further verify the authority of the node when data is transmitted to the related node, to ensure that the receiver of data has legal access authority.To the target node is obtained according to target permission and related permission, so that target object obtains target encryption result, that is, target object obtains the corresponding target encryption result.To effectively reduce the risk of data leakage, improve the automation level of data processing, and further improve the efficiency of data transmission.The problem of low efficiency and high risk in the related art when processing joint factoring business is solved. BRIEF DESCRIPTION OF DRAWINGS

[0023] To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0024] Figure 1 A flowchart of a joint factoring data security protection method based on blockchain is provided for the embodiments of the present application.

[0025] Figure 2 A module structure diagram of a joint factoring data security protection system based on blockchain is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0026] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of the present application.

[0027] The flowchart shown in the drawings is only an example and does not necessarily include all the contents and operations / steps, nor does it necessarily be executed in the described order. For example, some operations / steps can be further decomposed, combined or partially merged, so that the actual execution order can be changed according to the actual situation.

[0028] It should be understood that the terms used in the present application description herein are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application description and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0029] The embodiments of the present application provide a joint factoring data security protection method and system based on a blockchain. The joint factoring data security protection method based on a blockchain can be applied to a terminal device, which can be an electronic device such as a tablet computer, a notebook computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0030] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

[0031] Please refer to Figure 1 , Figure 1 A flowchart of a joint factoring data security protection method based on a blockchain provided by the embodiments of the present application.

[0032] As shown in Figure 1 , the joint factoring data security protection method based on a blockchain includes steps S101 to S107.

[0033] Step S101, obtaining initial factoring data corresponding to a target construction enterprise, and performing key sentence recognition on the initial factoring data to obtain corresponding target key sentences.

[0034] Exemplarily, in the construction industry, factoring business is a comprehensive financial service that integrates financing, accounts receivable collection, management, and bad debt guarantee based on the transfer of receivables by the creditor. To better adapt to the diversified development of market economy, the business factoring mode is also increasingly diversified. In addition to the traditional positive and negative factoring mode, joint factoring mode is increasingly favored by construction enterprises, which has the advantages of providing large-scale capital financing, realizing the complementary advantages of assets and funds between different factoring companies, improving the credit system network while huddling together, realizing resource sharing, and broadening the financing channels of factoring companies.

[0035] Exemplarily, the initial factoring data required by the target construction enterprise when it needs to carry out commercial factoring is obtained, and the initial factoring data includes but is not limited to the unified social credit code, legal qualification, and credit report of the target construction enterprise, and other information related to the content evaluation of commercial factoring. The initial factoring data is the core basis of the commercial factoring business, and its integrity and accuracy directly affect the risk assessment and business decision of the factoring company. The initial factoring data is used to represent the enterprise data required by the factoring company for risk assessment of the target construction enterprise.

[0036] Exemplarily, the text in the initial factoring data is subjected to semantic analysis to ensure the accuracy and effectiveness of the sentences. For example, it is judged whether the sentence involves core business data (such as accounts receivable, contract terms, etc.), and then a weight is assigned to each filtered key sentence, which can be calculated according to the importance of the sentence (such as whether it involves amount, date, contract terms, etc.). Finally, the target key sentence with a higher weight is selected.

[0037] In some embodiments, the key sentence identification of the initial factoring data obtains the corresponding target key sentence, including: utilizing a word representation layer of a sentence classification model to perform word vector representation processing on the initial factoring data to obtain an initial word vector; utilizing a character level representation layer of the sentence classification model to perform character vector representation processing on the initial factoring data to obtain an initial character vector; utilizing a target convolution layer of the sentence classification model to perform aggregation processing on the initial word vector to obtain a target convolution result; utilizing a cross-channel fusion layer of the sentence classification model to perform high-level word-level feature extraction information fusion processing on the target convolution result to obtain an initial semantic feature; utilizing a multi-head attention layer of the sentence classification model to perform highlight feature screening on the initial semantic feature to obtain a target semantic feature; utilizing a gated fusion layer of the sentence classification model to perform fusion processing on the initial character vector and the target semantic feature to obtain a target fusion feature; utilizing a sentence classification layer of the sentence classification model to perform type classification on the target fusion feature to obtain a target sentence type corresponding to the initial factoring data; and according to the target sentence type, identifying the key sentence of the initial factoring data to obtain the target key sentence.

[0038] Exemplarily, the initial factoring data is subjected to word vector representation processing by using a word representation layer of a sentence classification model to obtain initial word vectors. The words in the initial factoring data are converted into vector representations of fixed dimensions by using a pre-trained word embedding model such as Word2Vec, GloVe or a pre-trained language model such as BERT.

[0039] Exemplarily, the initial factoring data is subjected to word vector representation processing by using a word representation layer of a sentence classification model to obtain initial word vectors. The words in the initial factoring data are converted into vector representations of fixed dimensions by using a pre-trained word embedding model such as Word2Vec, GloVe or a pre-trained language model such as BERT.

[0040] Exemplarily, the initial word vectors are subjected to aggregation processing by using a target convolution layer of the sentence classification model to obtain target convolution results. For example, a one-dimensional convolutional neural network (CNN) is used to slide on the sequence of word vectors to capture local features and generate higher-level feature representations.

[0041] Exemplarily, the target convolution results are subjected to fusion processing of high-level word-level features by using a cross-channel fusion layer of the sentence classification model to obtain initial semantic features. For example, semantic information is extracted from the convolution features by multiple ways such as max-pooling and average-pooling and then fused.

[0042] Exemplarily, the initial semantic features are subjected to highlight feature screening by using a multi-head attention layer of the sentence classification model to obtain target semantic features. Then, the attention mechanism is used to emphasize the feature parts that contribute more to the meaning of the sentence and suppress the unimportant parts.

[0043] Exemplarily, the initial word vectors and the target semantic features are subjected to fusion processing by using a gated fusion layer of the sentence classification model to obtain target fusion features. The weights of the word vectors and the semantic features are dynamically adjusted by the gating mechanism to realize effective feature fusion. Finally, the target fusion features are subjected to type classification by using a sentence classification layer to obtain the target sentence type corresponding to the initial factoring data. For example, the fusion features are mapped to the predefined sentence types by using a fully connected layer and a softmax activation function to obtain the corresponding target sentence type. The target sentence type is any one of the core sentence and the non-core sentence.

[0044] Exemplarily, the sentence whose target sentence type is the core sentence is determined as the target key sentence corresponding to the initial factoring data. Thus, the sentence belonging to the key sentence type is screened based on the classification result, and the target key sentence generally contains important information such as the amount, the date, the contract terms and the like.

[0045] In step S102, the target key sentence is subjected to sensitive information identification to obtain the target sensitive information corresponding to the target key sentence.

[0046] Exemplarily, the target key sentence is cleaned and standardized, for example, irrelevant characters such as punctuation marks, special symbols, etc. in the target key sentence are deleted, and the sentence is segmented into words or phrases, facilitating subsequent processing. Define the sensitive information categories that need to be identified, common sensitive information categories include but are not limited to name, phone number, address, ID number, bank account number, contract amount, date, etc. Then establish a rule library for each category, including related regular expressions or keyword lists. Thus, the sensitive information in the target key sentence is identified using rule matching technology and natural language processing technology, and the target sensitive information corresponding to the target key sentence is obtained.

[0047] In some embodiments, the sensitive information identification of the target key sentence obtains the target sensitive information corresponding to the target key sentence, comprising: performing named entity recognition on the target key sentence to obtain a first entity type corresponding to a target word in the target key sentence; determining a preset type and a preset word corresponding to the preset type, and replacing the target word in the target key sentence according to the preset type and the first entity type to obtain a target conversion sentence corresponding to the target key sentence; performing word frequency statistics on the target conversion sentence to obtain a word weight corresponding to the entity type in the target conversion sentence; determining a sensitive score corresponding to the target conversion sentence according to the word weight, and screening out a target sensitive sentence corresponding to the target key sentence according to the sensitive score; obtaining a second entity type corresponding to the target sensitive sentence from the first entity type, and determining the target sensitive information corresponding to the target sensitive sentence according to the second entity type.

[0048] Exemplarily, the target key sentence is subjected to named entity recognition to obtain a first entity type corresponding to a target word. A pre-trained named entity recognition model is used to identify entities in the target key sentence and label their types (such as person name, place name, date, amount, etc.), and the identified entities are labeled as the first entity type.

[0049] Exemplarily, the preset type and the preset word corresponding thereto are determined, and the target word in the target key sentence is replaced according to the preset type and the first entity type to obtain a target conversion sentence. For example, define the entity type that needs to be replaced, and establish a corresponding preset word for the preset type, such as replacing the preset type with a unified fixed identifier, so that the target word in the target key sentence is replaced with the preset word according to the first entity type. For example, replace the name "Zhang San" with MN, and replace the time "October 1, 2023" with MN.

[0050] Exemplarily, word frequency statistics are performed on the target conversion sentence to obtain the word weight corresponding to the entity type in the target conversion sentence. For example, the frequency of occurrence of each preset word in the target conversion sentence is counted, and the weight of the word under each preset type is calculated according to the word frequency.

[0051] Exemplarily, the sensitive score corresponding to the target conversion sentence is determined according to the word weight, and the target sensitive sentence corresponding to the target key sentence is screened according to the sensitive score. For example, the sensitive score of the target conversion sentence is calculated according to the word weight. For example, the sensitive score can be weighted sum based on the weight of the entity type, so as to set a threshold value of the sensitive score, and screen the sentence with a sensitive score higher than the threshold value as the target sensitive sentence.

[0052] Exemplarily, the second entity type corresponding to the target sensitive sentence is obtained from the first entity type, and the target sensitive information corresponding to the target sensitive sentence is determined according to the second entity type. For example, the second entity type (such as "person name", "date", etc.) is extracted from the target sensitive sentence, and then the target sensitive information corresponding to the target sensitive sentence is determined according to the second entity type. For example, if the second entity type is "person name", the target sensitive information is a specific person name (such as "Zhang San").

[0053] In some embodiments, the sensitive score corresponding to the target conversion sentence is determined according to the word weight, including: obtaining the entity position distribution corresponding to the entity type, and determining the position weight corresponding to the entity type according to the entity position distribution; determining the entity sensitive level corresponding to the entity type according to a preset rule, and determining the type sensitive weight corresponding to the entity type according to the entity sensitive level; fusing the word weight, the position weight and the type sensitive weight to determine the entity sensitive weight corresponding to the entity type; fusing the entity sensitive weight to determine the sensitive score corresponding to the target conversion sentence; wherein the sensitive score is obtained according to the following formula:

[0054]

[0055] wherein, represents the sensitive score corresponding to the i-th target conversion sentence, represents the number corresponding to the entity type corresponding to the i-th target conversion sentence, represents the word weight corresponding to the j-th entity type, represents the word frequency information corresponding to the j-th entity type, represents the position weight corresponding to the j-th entity type, represents the type sensitive weight corresponding to the j-th entity type, , and These represent the adjustment parameters corresponding to the word weight, the position weight, and the type sensitivity weight, respectively.

[0056] For example, the entity position distribution for each entity type is obtained, and the position weight corresponding to each entity type is determined based on the entity position distribution. For instance, the position information of each entity type in the target transformation statement is statistically analyzed, such as whether the entity appears at the beginning, middle, or end of the sentence, and different weights are assigned according to the importance of the position. Generally, entities at the beginning and end of the sentence may be more important and can be assigned higher weights. For example, the position weight at the beginning of the sentence is 1.2, in the middle is 1.0, and at the end is 1.1, thereby calculating the average position weight of each entity type in all target transformation statements, which is used as the position weight of that entity type.

[0057] For example, the entity sensitivity level corresponding to the entity type is determined according to preset rules, and the type sensitivity weight corresponding to the entity type is determined according to the entity sensitivity level. For example, sensitivity levels for different entity types are defined, such as "high", "medium", and "low". For example, the sensitivity level is high when the entity type is a monetary amount, medium when the entity type is a date, and low when the entity type is a location. The sensitivity level is then mapped to a specific weight, such as 1.5 for "high", 1.0 for "medium", and 0.5 for "low". Thus, the type sensitivity weight of the entity type is determined according to the weight corresponding to the sensitivity level.

[0058] For example, the entity sensitivity weight corresponding to the entity type is determined by fusing word weight, position weight, and type sensitivity weight according to the following formula, and the sensitivity score corresponding to the target transformation statement is determined based on the entity sensitivity weight:

[0059]

[0060] in, This represents the sensitivity score corresponding to the i-th target transformation statement. This indicates the number of entity types corresponding to the i-th target transformation statement. This represents the word weight corresponding to the j-th entity type. This represents the word frequency information corresponding to the j-th entity type. This represents the position weight corresponding to the j-th entity type. This represents the type sensitivity weight corresponding to the j-th entity type. , and These represent the adjustment parameters corresponding to word weight, position weight, and type sensitivity weight, respectively.

[0061] Exemplarily, by fusing the word weight, position weight and type-sensitive weight, the word frequency, position distribution and sensitive level of the entity in the sentence are comprehensively considered, so that the calculation of the sensitive score is more comprehensive and accurate. Compared with single-dimensional (such as word frequency) analysis, comprehensive multi-dimensional information can more accurately reflect the contribution of the entity to the overall sensitivity of the sentence.

[0062] Exemplarily, the above formula introduces adjustment parameters 、 and , which can flexibly adjust the importance of the word weight, position weight and type-sensitive weight according to actual needs. The use of adjustment parameters enables flexible weight allocation in different scenarios to adapt to different business needs. For example, in some scenarios, more attention can be paid to word frequency by adjusting , and in other scenarios, more attention can be paid to position or sensitive level by adjusting and .

[0063] Exemplarily, by using the weighted sum formula, the sensitive weight of each entity type can be accurately calculated, and then the sensitive score of the target conversion sentence can be accurately calculated. The accuracy of the sensitive score helps to more accurately filter out high-sensitivity sentences, avoid misjudgment or omission, and makes the calculation of the sensitive score more scientific and efficient, and provides strong support for subsequent sensitive information screening and management.

[0064] Step S103, according to the initial factoring data and the target sensitive information, data entropy analysis is performed to obtain a first encryption mode corresponding to the target sensitive information and a second encryption mode corresponding to the initial factoring data.

[0065] Exemplarily, existing public data is obtained, and data entropy analysis is performed on the initial factoring data and the target sensitive information under the existing public data, so as to obtain the randomness corresponding to the initial factoring data and the target sensitive information respectively.

[0066] Exemplarily, if the data entropy of the target sensitive information is high, it means that the target sensitive information is more random, and a symmetric encryption algorithm (such as AES) can be considered to be used because the symmetric encryption algorithm is efficient and suitable for processing data with high randomness. If the data entropy is low, it means that the data has a certain regularity, and a more secure encryption algorithm can be considered to be used, such as asymmetric encryption (such as RSA), or a hybrid encryption mode combining symmetric and asymmetric encryption. Similarly, for high-entropy initial factoring data, a high-efficiency symmetric encryption algorithm is selected, and for low-entropy data, a higher encryption means may be needed to protect the security of the data, such as using a longer key or multiple encryption technology.

[0067] In some embodiments, the data entropy analysis based on the initial factoring data and the target sensitive information obtains a first encryption mode corresponding to the target sensitive information and a second encryption mode corresponding to the initial factoring data, including: removing the target sensitive information from the initial factoring data to obtain target factoring data; performing information entropy calculation on the target sensitive information to obtain a first entropy value corresponding to the target sensitive information; performing information entropy calculation on the target factoring data to obtain a second entropy value corresponding to the target factoring data; determining a first preset entropy value corresponding to the target sensitive information and a second preset entropy value corresponding to the target factoring data; determining a first information frequency level corresponding to the target sensitive information according to the first entropy value and the first preset entropy value; determining the first encryption mode corresponding to the target sensitive information according to the first information frequency level; determining a second information frequency level corresponding to the target factoring data according to the second entropy value and the second preset entropy value; and determining the second encryption mode corresponding to the target factoring data according to the second information frequency level.

[0068] For example, the target sensitive information is identified and located by keyword matching, regular expression or other methods, so that the identified target sensitive information is removed from the initial factoring data to obtain the target factoring data.

[0069] For example, the target sensitive information and the target factoring data are subjected to information entropy calculation to obtain a first entropy value and a second entropy value, respectively, and then the threshold value of the entropy value is set according to historical data or industry standards to determine the first preset entropy value of the target sensitive information and the second preset entropy value of the target factoring data.

[0070] For example, the first information frequency level of the target sensitive information is determined by comparing the first entropy value with the first preset entropy value, and the second information frequency level of the target factoring data is determined by comparing the second entropy value with the second preset entropy value. For example, if the first entropy value is higher than the first preset entropy value, the first information frequency level is low; otherwise, it is high.

[0071] For example, the first encryption mode corresponding to the target sensitive information is determined according to the first information frequency level, and the first encryption mode can be any one of dynamic encryption or static encryption. At the same time, the second encryption mode corresponding to the target factoring data is determined according to the second information frequency level, and the second encryption mode can also be any one of dynamic encryption or static encryption. Static encryption means using a fixed encryption password to encrypt data, while dynamic encryption means using different encryption passwords to encrypt data to enhance security. In this way, the most suitable encryption method can be selected according to the sensitivity and frequency level of the data to ensure the security of the information and the efficiency of the system.

[0072] Step S104, encrypting the target sensitive information and the initial factoring data according to the first encryption mode and the second encryption mode to obtain a target encryption result.

[0073] For example, the target sensitive information is encrypted by the first encryption mode to obtain a first encryption result, and the initial factoring data is encrypted by the second encryption mode to obtain a second encryption result, so as to merge the first encryption result and the second encryption result to obtain the target encryption result.

[0074] In some embodiments, the encrypting the target sensitive information and the initial factoring data according to the first encryption mode and the second encryption mode to obtain a target encryption result comprises: when the first encryption mode is dynamic encryption, determining a first classification attribute of the target sensitive information in a first encryption key, and determining a first encoding corresponding to the target sensitive information according to the first classification attribute; determining first key information corresponding to the target sensitive information in the first encryption key according to the first encoding and the first entropy value; when the first encryption mode is static encryption, obtaining the first key information corresponding to the target sensitive information from a database; encrypting the target sensitive information according to the first key information to obtain a first encryption result; when the second encryption mode is the dynamic encryption, determining a second classification attribute of the target factoring data in a second encryption key, and determining a second encoding corresponding to the target factoring data according to the second classification attribute; determining second key information corresponding to the target factoring data in the second encryption key according to the second encoding and the second entropy value; when the second encryption mode is the static encryption, obtaining the second key information corresponding to the target factoring data from the database; encrypting the target factoring data according to the second key information to obtain a second encryption result; and merging the first encryption result and the second encryption result to obtain the target encryption result.

[0075] For example, it is determined whether the first encryption mode is dynamic encryption or static encryption, and when the first encryption mode is dynamic encryption, a classification attribute of the target sensitive information in a first encryption key is determined. For example, when the target sensitive information is a number, the first classification attribute is a number type, and when the target sensitive information is a character, the first classification attribute is a character type, so that a first encoding corresponding to the target sensitive information is obtained according to a corresponding encoding type according to different first classification attributes, and then first key information corresponding to the target sensitive information in the first encryption key is determined in combination with the first encoding and the first entropy value, so that the target sensitive information is encrypted according to the first key information to obtain a first encryption result.

[0076] Exemplarily, when the first encryption mode is static encryption, the first key information corresponding to the target sensitive information is directly obtained from the database, and then the target sensitive information is encrypted by using the determined first key information to obtain the first encryption result.

[0077] Exemplarily, it is judged whether the second encryption mode is dynamic encryption or static encryption. When the second encryption mode is dynamic encryption, the classification attribute of the target factoring information in the second encryption key is determined. For example, when the target factoring information is a number, the second classification attribute is a number type, and when the target factoring information is a character, the second classification attribute is a character type. Then, the second code corresponding to the target factoring information is obtained by using the corresponding coding type according to the different second classification attributes, and then the second key information corresponding to the target sensitive information in the second encryption key is determined by combining the second code and the second entropy value, so that the target sensitive information is encrypted according to the second key information to obtain the second encryption result.

[0078] Exemplarily, when the second encryption mode is static encryption, the second key information corresponding to the target factoring information is directly obtained from the database, and then the target factoring information is encrypted by using the determined second key information to obtain the second encryption result.

[0079] Exemplarily, the first encryption result and the second encryption result are fused by using a splicing algorithm to generate the final target encryption result.

[0080] In some embodiments, determining the first key information corresponding to the target sensitive information in the first encryption key according to the first code and the first entropy value comprises: determining a first maximum entropy value corresponding to the target sensitive information from the first entropy value; determining a first key distribution parameter corresponding to the target sensitive information according to the first entropy value and the first maximum entropy value; determining a first frequency corresponding to the target sensitive information, and adjusting the first code according to the first frequency and the first key distribution parameter to obtain a first target code; and classifying the first target code by using a first classification model to obtain the first key information corresponding to the target sensitive information in the first encryption key.

[0081] Exemplarily, by analyzing the first entropy value, the maximum value is found, and then the maximum value is determined as the first maximum entropy value for subsequent calculation. Then, according to the first entropy value and the first maximum entropy value, the first key distribution parameter corresponding to the target sensitive information is determined. For example, the ratio of the first entropy value to the first maximum entropy value is calculated to reflect the distribution characteristics of the data, and then the first key distribution parameter is determined based on the calculated ratio. These parameters will be used to describe the distribution characteristics of the key.

[0082] The frequencies of the elements in the target sensitive information are counted and determined, and the frequencies are used for subsequent encoding adjustment, so that the first encoding is adjusted according to the first frequency and the first key distribution parameter to obtain the first target encoding, for example, the structure and content of the first encoding are adjusted according to the first frequency and the first key distribution parameter, so as to generate the adjusted first target encoding to adapt to the subsequent key classification.

[0083] The first target encoding is classified by using the first classification model to obtain the first key information corresponding to the target sensitive information in the first encryption key.

[0084] The key distribution parameter and the encoding adjustment are accurately determined by analyzing the entropy value and the frequency, the accuracy of the key classification is improved, the encoding is adjusted according to different data characteristics, the flexibility and adaptability are enhanced, and then the first classification model is used for key classification, and the efficiency of obtaining the key information is improved.

[0085] In some embodiments, the second key information corresponding to the target factoring data in the second encryption key is determined according to the second encoding and the second entropy value, comprising: determining the second maximum entropy value corresponding to the target factoring data from the second entropy value; determining the second key distribution parameter corresponding to the target factoring data according to the second entropy value and the second maximum entropy value; determining the second frequency corresponding to the target factoring data, and adjusting the second encoding according to the second frequency and the second key distribution parameter to obtain the second target encoding; and classifying the second target encoding by using a second classification model to obtain the second key information corresponding to the target factoring data in the second encryption key.

[0086] The maximum value in the second entropy value is found out, and the maximum value is determined as the second maximum entropy value for subsequent calculation, and then the second key distribution parameter corresponding to the target factoring information is determined according to the second entropy value and the second maximum entropy value, for example, the ratio of the second entropy value to the second maximum entropy value is calculated to reflect the distribution characteristics of the data, and then the second key distribution parameter is determined based on the calculated ratio, which will be used to describe the distribution characteristics of the key.

[0087] The frequencies of the elements in the target factoring information are counted and determined, and the frequencies are used for subsequent encoding adjustment, so that the second encoding is adjusted according to the second frequency and the second key distribution parameter to obtain the second target encoding, for example, the structure and content of the second encoding are adjusted according to the second frequency and the second key distribution parameter, so as to generate the adjusted second target encoding to adapt to the subsequent key classification.

[0088] Exemplarily, the second target code is classified by using the second classification model, and first key information corresponding to the target sensitive information in the second encryption key is obtained.

[0089] Exemplarily, by analyzing the entropy value and the frequency, the key distribution parameter and the code adjustment are accurately determined, the accuracy of the key classification is improved, the code is adjusted according to different data characteristics, the flexibility and adaptability are enhanced, and then the second classification model is used for key classification, and the acquisition efficiency of the key information is improved.

[0090] In step S105, the initial factoring data is subjected to intention recognition to obtain a target intention corresponding to the initial factoring data, and a target permission corresponding to the target encryption result is determined according to the target intention.

[0091] Exemplarily, an intention recognition model (such as a natural language processing model or a machine learning model) is applied to the initial factoring data for intention recognition to determine the target intention of the initial factoring data, and the target intention is used to determine the receiving object corresponding to the initial factoring data.

[0092] Exemplarily, a mapping relationship between the target intention and the permission is established, and the permission level corresponding to different intentions is determined, so that the target permission of the target encryption result is determined according to the identified target intention and the corresponding permission level.

[0093] In some embodiments, the intention recognition of the initial factoring data to obtain the target intention corresponding to the initial factoring data comprises: performing key target recognition on the initial factoring data by using a target recognition layer of a target intention model to obtain target key information corresponding to the initial factoring data; performing data representation on the target key information by using a text representation layer of the target intention model to obtain an initial representation vector; performing relationship recognition on the target key information according to the initial factoring data by using a relationship recognition layer of the target intention model to obtain target relationship information; performing feature fusion on the initial representation vector according to the target relationship information by using a feature fusion layer of the target intention model to obtain a target representation vector; and performing intention recognition on the target representation vector by using an intention classification layer of the target intention model to obtain the target intention corresponding to the initial factoring data.

[0094] Exemplarily, the target recognition layer of the target intent model is applied to extract the target key information in the initial factoring data. The target recognition layer usually uses deep learning techniques (such as convolutional neural networks or recurrent neural networks) to extract important entities and keywords in the text, and then uses the text representation layer of the target intent model to data represent the target key information to obtain an initial representation vector. Features are extracted from the target key information, which can be word embeddings (such as Word2Vec, GloVe) or sentence embeddings (such as BERT), and then the extracted features are converted into vector form to generate the initial representation vector. This step usually uses word embedding techniques and context encoders (such as Transformer).

[0095] Exemplarily, the relationship recognition layer is applied to analyze the relationship between the target key information. The relationship recognition layer usually uses graph neural networks (GNN) or attention mechanisms (Attention Mechanism) to identify the relationship between entities to obtain target relationship information, so as to represent the identified target relationship information as structured data such as graph structure or relationship matrix.

[0096] Exemplarily, the feature fusion layer of the target intent model is used to fuse the initial representation vector according to the target relationship information through splicing, weighted averaging or self-attention mechanism (Self-Attention) and the like to obtain a target representation vector. Then, the intent classification layer such as logistic regression, support vector machine or deep neural network is used to classify the target representation vector, and then according to the classification result, the target intent corresponding to the initial factoring data is determined.

[0097] Step S106, the target encryption result and the target permission are transmitted to the related node by using the blockchain, and the related permission corresponding to the related node is obtained.

[0098] Exemplarily, the target encryption result and the corresponding target permission are packaged into a data unit to ensure the integrity of the data, and then the packaged data is encoded, usually in JSON or Protobuf format, to facilitate storage and transmission on the blockchain. Thus, the target encryption result and the target permission are transmitted to the related node by using the blockchain technology.

[0099] For example, a suitable blockchain network (such as Ethereum, Hyperledger Fabric, etc.) is selected to ensure the security and reliability of the network. A transaction containing the target encryption result and the target permission is created on the blockchain. The transaction should also include the information of the sender and the receiver, as well as the signature of the transaction (using the private key of the sender). The created transaction is broadcast to all nodes in the blockchain network for verification and recording.

[0100] Illustratively, the related nodes query the recorded transactions through the blockchain network, and extract the related permissions corresponding to the related nodes.

[0101] In step S107, the target nodes are obtained by screening the related nodes according to the target permission and the related permission, so that the target object obtains the target encryption result according to the target nodes.

[0102] Illustratively, the target permission and the related permission are compared, and the target nodes are screened from the related nodes according to the comparison result, so that the target object obtains the target encryption result according to the target nodes.

[0103] For example, the specific content of the target permission and the related permission is analyzed to understand the permission range and level, so as to determine whether the related permission of the related node meets the requirements of the target permission. This can be based on the inclusion relationship, priority, etc. of the permission, and then the screening condition is determined, for example, the related permission must completely contain the target permission, or the level of the related permission is higher than or equal to the target permission, so that the nodes meeting the condition are screened from the related nodes as the target nodes according to the screening condition. Thus, it is ensured that the target object can only obtain the target encryption result from the target nodes, and its access complies with the permission management regulations.

[0104] Please refer to Figure 2 , Figure 2A blockchain-based joint factoring data security protection system 200 is provided for an embodiment of the present application. The blockchain-based joint factoring data security protection system 200 comprises a data acquisition module 201, an information identification module 202, a mode determination module 203, a data encryption module 204, an intent identification module 205, a data transmission module 206, and a data screening module 207. The data acquisition module 201 is configured to obtain initial factoring data corresponding to a target construction enterprise, and perform key sentence identification on the initial factoring data to obtain corresponding target key sentences. The information identification module 202 is configured to perform sensitive information identification on the target key sentences to obtain target sensitive information corresponding to the target key sentences. The mode determination module 203 is configured to perform data entropy analysis on the initial factoring data and the target sensitive information to obtain a first encryption mode corresponding to the target sensitive information and a second encryption mode corresponding to the initial factoring data. The data encryption module 204 is configured to encrypt the target sensitive information and the initial factoring data according to the first encryption mode and the second encryption mode to obtain a target encryption result. The intent identification module 205 is configured to perform intent identification on the initial factoring data to obtain a target intent corresponding to the initial factoring data, and determine a target permission corresponding to the target encryption result according to the target intent. The data transmission module 206 is configured to transmit the target encryption result and the target permission to a related node using a blockchain, and obtain a related permission corresponding to the related node. The data screening module 207 is configured to screen the related node according to the target permission and the related permission to obtain a target node, so that a target object obtains the target encryption result according to the target node.

[0105] In some embodiments, the data acquisition module 201 performs the following in the process of identifying the key sentences in the initial factoring data to obtain the corresponding target key sentences:

[0106] performing word vector representation processing on the initial factoring data using a word representation layer of a sentence classification model to obtain an initial word vector;

[0107] performing word vector representation processing on the initial factoring data using a word-level representation layer of the sentence classification model to obtain an initial word vector;

[0108] performing aggregation processing on the initial word vector using a target convolution layer of the sentence classification model to obtain a target convolution result;

[0109] performing high-level word-level feature extraction information fusion processing on the target convolution result using a cross-channel fusion layer of the sentence classification model to obtain an initial semantic feature;

[0110] highlighting feature screening on the initial semantic features by using a multi-head attention layer of the sentence classification model to obtain target semantic features;

[0111] fusion processing on the initial word vector and the target semantic features by using a gated fusion layer of the sentence classification model to obtain target fusion features;

[0112] type classification on the target fusion features by using a sentence classification layer of the sentence classification model to obtain a target sentence type corresponding to the initial factoring data;

[0113] key sentence identification on the initial factoring data according to the target sentence type to obtain the target key sentence.

[0114] In some embodiments, the information identification module 202, in the process of sensitive information identification on the target key sentence to obtain target sensitive information corresponding to the target key sentence, performs:

[0115] named entity recognition on the target key sentence to obtain a first entity type corresponding to a target word in the target key sentence;

[0116] determining a preset type and a preset word corresponding to the preset type, and replacing the target word in the target key sentence according to the preset word according to the preset type and the first entity type to obtain a target conversion sentence corresponding to the target key sentence;

[0117] word frequency statistics on the target conversion sentence to obtain a word weight corresponding to the entity type in the target conversion sentence;

[0118] determining a sensitive score corresponding to the target conversion sentence according to the word weight, and screening a target sensitive sentence corresponding to the target key sentence according to the sensitive score;

[0119] obtaining a second entity type corresponding to the target sensitive sentence from the first entity type, and determining the target sensitive information corresponding to the target sensitive sentence according to the second entity type.

[0120] In some embodiments, the information identification module 202, in the process of determining a sensitive score corresponding to the target conversion sentence according to the word weight, performs:

[0121] obtaining an entity position distribution corresponding to the entity type, and determining a position weight corresponding to the entity type according to the entity position distribution;

[0122] determining an entity sensitive level corresponding to the entity type according to a preset rule, and determining a type sensitive weight corresponding to the entity type according to the entity sensitive level;

[0123] fusing the term weight, the position weight and the type sensitive weight to determine an entity sensitive weight corresponding to the entity type;

[0124] fusing the entity sensitive weight to determine the sensitive score corresponding to the target conversion sentence;

[0125] wherein the sensitive score is obtained according to the following formula:

[0126]

[0127] wherein, denotes the sensitive score corresponding to the i-th target conversion sentence, denotes the number of the entity types corresponding to the i-th target conversion sentence, denotes the term weight corresponding to the j-th entity type, denotes the term frequency information corresponding to the j-th entity type, denotes the position weight corresponding to the j-th entity type, denotes the type sensitive weight corresponding to the j-th entity type, , and denote the adjustment parameters corresponding to the term weight, the position weight and the type sensitive weight respectively.

[0128] In some embodiments, the mode determining module 203 performs the following in the process of determining the first encryption mode corresponding to the target sensitive information and the second encryption mode corresponding to the initial factoring data according to the initial factoring data and the target sensitive information:

[0129] obtaining target factoring data by excluding the target sensitive information from the initial factoring data;

[0130] performing information entropy calculation on the target sensitive information to obtain a first entropy value corresponding to the target sensitive information;

[0131] performing information entropy calculation on the target factoring data to obtain a second entropy value corresponding to the target factoring data;

[0132] determining a first preset entropy value corresponding to the target sensitive information and a second preset entropy value corresponding to the target factoring data;

[0133] determining a first information frequency level corresponding to the target sensitive information according to the first entropy value and the first preset entropy value;

[0134] determining a first encryption mode corresponding to the target sensitive information according to the first information frequency level;

[0135] determining a second information frequency level corresponding to the target factoring data according to the second entropy value and the second preset entropy value;

[0136] determining a second encryption mode corresponding to the target factoring data according to the second information frequency level.

[0137] In some embodiments, the data encryption module 204, in the process of encrypting the target sensitive information and the initial factoring data according to the first encryption mode and the second encryption mode to obtain a target encryption result, performs:

[0138] when the first encryption mode is dynamic encryption, determining a first classification attribute of the target sensitive information in a first encryption key, and determining a first code corresponding to the target sensitive information according to the first classification attribute;

[0139] determining first key information corresponding to the target sensitive information in the first encryption key according to the first code and the first entropy value;

[0140] when the first encryption mode is static encryption, obtaining the first key information corresponding to the target sensitive information from a database;

[0141] encrypting the target sensitive information according to the first key information to obtain a first encryption result;

[0142] when the second encryption mode is the dynamic encryption, determining a second classification attribute of the target factoring data in a second encryption key, and determining a second code corresponding to the target factoring data according to the second classification attribute;

[0143] determining second key information corresponding to the target factoring data in the second encryption key according to the second code and the second entropy value;

[0144] when the second encryption mode is the static encryption, obtaining the second key information corresponding to the target factoring data from the database;

[0145] encrypting the target factoring data according to the second key information to obtain a second encryption result;

[0146] fusing the first encryption result and the second encryption result to obtain the target encryption result.

[0147] In some embodiments, the data encryption module 204, in the process of determining the first key information corresponding to the target sensitive information in the first encryption key according to the first encoding and the first entropy value, performs:

[0148] determining a first maximum entropy value corresponding to the target sensitive information from the first entropy value;

[0149] determining a first key distribution parameter corresponding to the target sensitive information according to the first entropy value and the first maximum entropy value;

[0150] determining a first frequency corresponding to the target sensitive information, and adjusting the first encoding according to the first frequency and the first key distribution parameter to obtain a first target encoding;

[0151] performing key classification on the first target encoding by using a first classification model to obtain the first key information corresponding to the target sensitive information in the first encryption key.

[0152] In some embodiments, the data encryption module 204, in the process of determining the second key information corresponding to the target factoring data in the second encryption key according to the second encoding and the second entropy value, performs:

[0153] determining a second maximum entropy value corresponding to the target factoring data from the second entropy value;

[0154] determining a second key distribution parameter corresponding to the target factoring data according to the second entropy value and the second maximum entropy value;

[0155] determining a second frequency corresponding to the target factoring data, and adjusting the second encoding according to the second frequency and the second key distribution parameter to obtain a second target encoding;

[0156] performing key classification on the second target encoding by using a second classification model to obtain the second key information corresponding to the target factoring data in the second encryption key.

[0157] In some embodiments, the intent recognition module 205, in the process of performing intent recognition on the initial factoring data to obtain target intent corresponding to the initial factoring data, performs:

[0158] performing key target recognition on the initial factoring data by using a target recognition layer of a target intent model to obtain target key information corresponding to the initial factoring data;

[0159] performing data representation on the target key information by using a text representation layer of the target intent model to obtain an initial representation vector;

[0160] The relationship identification layer of the target intention model performs relationship identification on the target key information according to the initial factoring data to obtain target relationship information;

[0161] The feature fusion layer of the target intention model performs feature fusion on the initial representation vector according to the target relationship information to obtain a target representation vector;

[0162] The intention classification layer of the target intention model performs intention recognition on the target representation vector to obtain the target intention corresponding to the initial factoring data.

[0163] In some embodiments, the blockchain-based joint factoring data security protection system 200 can be applied to a terminal device.

[0164] It should be noted that, for the convenience and brevity of description, the specific working process of the blockchain-based joint factoring data security protection system 200 described above can refer to the corresponding process in the foregoing embodiment of the blockchain-based joint factoring data security protection method, which will not be described here.

[0165] The embodiment of the application further provides a storage medium for computer readable storage, the storage medium storing one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of the blockchain-based joint factoring data security protection methods provided in the specification of the embodiment of the application.

[0166] The storage medium can be an internal storage unit of the terminal device, such as a hard disk or a memory of the terminal device. The storage medium can also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0167] Those skilled in the art can understand that all or some of the steps in the methods disclosed above, the functional modules / units in the systems and devices can be implemented by software, firmware, hardware, or a combination thereof. In hardware embodiments, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component can have multiple functions, or one function or step can be performed by several physical components in cooperation. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on computer-readable media, which can include computer storage media (or non-transitory media) and communication media (or transitory media). As is well known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and can include any information delivery media.

[0168] It should be understood that the term "and / or" as used herein refers to any combination of associated listed items, and all possible combinations, and includes these combinations. It should be noted that the terms "comprising", "including", or any other variant thereof, are intended to cover non-exclusive inclusion, so that processes, methods, articles, or systems including a series of elements not only include those elements, but also include other elements not explicitly listed, or other elements inherent to such processes, methods, articles, or systems. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or system including the element.

[0169] The above-mentioned serial numbers of the embodiments of the application are only for description, and do not represent the advantages and disadvantages of the embodiments. The above is only a specific embodiment of the application, but the protection scope of the application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the application, and these modifications or replacements should be covered in the protection scope of the application. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A blockchain-based joint factoring data security protection method, characterized in that, The method comprises: obtaining initial factoring data corresponding to a target construction enterprise, and performing key sentence recognition on the initial factoring data to obtain target key sentences corresponding to the initial factoring data; performing sensitive information recognition on the target key sentences to obtain target sensitive information corresponding to the target key sentences; performing data entropy analysis on the initial factoring data and the target sensitive information to obtain a first encryption mode corresponding to the target sensitive information and a second encryption mode corresponding to the initial factoring data; encrypting the target sensitive information and the initial factoring data according to the first encryption mode and the second encryption mode to obtain a target encryption result; performing intent recognition on the initial factoring data to obtain a target intent corresponding to the initial factoring data, and determining a target permission corresponding to the target encryption result according to the target intent; transmitting the target encryption result and the target permission to a related node using a blockchain, and obtaining a related permission corresponding to the related node; screening the related node according to the target permission and the related permission to obtain a target node, so that a target object obtains the target encryption result according to the target node.

2. The method of claim 1, wherein, The key sentence recognition on the initial factoring data to obtain the target key sentences comprises: performing word vector representation processing on the initial factoring data using a word representation layer of a sentence classification model to obtain an initial word vector; performing character vector representation processing on the initial factoring data using a character level representation layer of the sentence classification model to obtain an initial character vector; performing aggregation processing on the initial word vector using a target convolution layer of the sentence classification model to obtain a target convolution result; performing high-level word-level feature extraction information fusion processing on the target convolution result using a cross-channel fusion layer of the sentence classification model to obtain an initial semantic feature; performing prominent feature screening on the initial semantic feature using a multi-head attention layer of the sentence classification model to obtain a target semantic feature; performing fusion processing on the initial character vector and the target semantic feature using a gating fusion layer of the sentence classification model to obtain a target fusion feature; performing type classification on the target fusion feature using a sentence classification layer of the sentence classification model to obtain a target sentence type corresponding to the initial factoring data; performing key sentence recognition on the initial factoring data according to the target sentence type to obtain the target key sentences.

3. The method of claim 1, wherein, The sensitive information recognition on the target key sentences to obtain the target sensitive information corresponding to the target key sentences comprises: performing named entity recognition on the target key sentences to obtain a first entity type corresponding to a target word in the target key sentences; determining a preset type and a preset word corresponding to the preset type, and replacing the target word in the target key sentences with the preset word according to the preset type and the first entity type to obtain a target converted sentence corresponding to the target key sentences; performing word frequency statistics on the target converted sentence to obtain a word weight corresponding to the entity type in the target converted sentence; According to the word weight, a sensitive score corresponding to the target conversion sentence is determined, and a target sensitive sentence corresponding to the target key sentence is screened according to the sensitive score; A second entity type corresponding to the target sensitive sentence is obtained from the first entity type, and the target sensitive information corresponding to the target sensitive sentence is determined according to the second entity type.

4. The method of claim 3, wherein, The sensitive score corresponding to the target conversion sentence is determined according to the word weight, comprising: An entity position distribution corresponding to the entity type is obtained, and a position weight corresponding to the entity type is determined according to the entity position distribution; According to a preset rule, an entity sensitive level corresponding to the entity type is determined, and a type sensitive weight corresponding to the entity type is determined according to the entity sensitive level; The entity sensitive weight corresponding to the entity type is determined by fusing the word weight, the position weight and the type sensitive weight; The sensitive score corresponding to the target conversion sentence is determined by fusing the entity sensitive weight; The sensitive score is obtained according to the following formula: wherein, denotes the sensitive score corresponding to the i-th target conversion statement, denotes the number of entity types corresponding to the i-th target conversion statement, denotes the word weight corresponding to the j-th entity type, denotes the word frequency information corresponding to the j-th entity type, denotes the position weight corresponding to the j-th entity type, denotes the type sensitive weight corresponding to the j-th entity type, and denote the adjustment parameters corresponding to the word weight, the position weight and the type sensitive weight, respectively.​ 5. The method of claim 1, wherein, The data entropy analysis is performed according to the initial financing data and the target sensitive information, to obtain a first encryption mode corresponding to the target sensitive information and a second encryption mode corresponding to the initial financing data, comprising: The target sensitive information is removed from the initial financing data to obtain target financing data; An information entropy calculation is performed on the target sensitive information to obtain a first entropy value corresponding to the target sensitive information; An information entropy calculation is performed on the target financing data to obtain a second entropy value corresponding to the target financing data; A first preset entropy value corresponding to the target sensitive information and a second preset entropy value corresponding to the target financing data are determined; A first information frequency level corresponding to the target sensitive information is determined according to the first entropy value and the first preset entropy value; A first encryption mode corresponding to the target sensitive information is determined according to the first information frequency level; A second information frequency level corresponding to the target financing data is determined according to the second entropy value and the second preset entropy value; A second encryption mode corresponding to the target financing data is determined according to the second information frequency level.

6. The method of claim 5, wherein, The target sensitive information and the initial financing data are encrypted according to the first encryption mode and the second encryption mode to obtain a target encryption result, comprising: When the first encryption mode is dynamic encryption, a first classification attribute of the target sensitive information in a first encryption key is determined, and a first code corresponding to the target sensitive information is determined according to the first classification attribute; The first key information corresponding to the target sensitive information in the first encryption key is determined according to the first code and the first entropy value; When the first encryption mode is static encryption, the first key information corresponding to the target sensitive information is obtained from the database; The target sensitive information is encrypted according to the first key information to obtain a first encryption result; When the second encryption mode is the dynamic encryption, a second classification attribute of the target factoring data in a second encryption key is determined, and a second encoding corresponding to the target factoring data is determined according to the second classification attribute; Second key information corresponding to the target factoring data in the second encryption key is determined according to the second encoding and the second entropy value; When the second encryption mode is the static encryption, the second key information corresponding to the target factoring data is obtained from the database; The target factoring data is encrypted according to the second key information to obtain a second encryption result; The first encryption result and the second encryption result are fused to obtain the target encryption result.

7. The method of claim 6, wherein, The first key information corresponding to the target sensitive information in the first encryption key is determined according to the first encoding and the first entropy value, including: A first maximum entropy value corresponding to the target sensitive information is determined from the first entropy value; A first key distribution parameter corresponding to the target sensitive information is determined according to the first entropy value and the first maximum entropy value; A first frequency corresponding to the target sensitive information is determined, and a first target encoding is obtained by adjusting the first encoding according to the first frequency and the first key distribution parameter; The first target encoding is classified by a first classification model to obtain the first key information corresponding to the target sensitive information in the first encryption key.

8. The method of claim 6, wherein, The second key information corresponding to the target factoring data in the second encryption key is determined according to the second encoding and the second entropy value, including: A second maximum entropy value corresponding to the target factoring data is determined from the second entropy value; A second key distribution parameter corresponding to the target factoring data is determined according to the second entropy value and the second maximum entropy value; A second frequency corresponding to the target factoring data is determined, and a second target encoding is obtained by adjusting the second encoding according to the second frequency and the second key distribution parameter; The second target encoding is classified by a second classification model to obtain the second key information corresponding to the target factoring data in the second encryption key.

9. The method of claim 1, wherein, The target intent corresponding to the initial factoring data is obtained by performing intent recognition on the initial factoring data, including: Target key information corresponding to the initial factoring data is obtained by performing key target recognition on the initial factoring data by a target recognition layer of a target intent model; An initial representation vector is obtained by performing data representation on the target key information by a text representation layer of the target intent model; Target relationship information is obtained by performing relationship recognition on the target key information according to the initial factoring data by a relationship recognition layer of the target intent model; A target representation vector is obtained by performing feature fusion on the initial representation vector according to the target relationship information by a feature fusion layer of the target intent model; The target intent corresponding to the initial factoring data is obtained by performing intent recognition on the target representation vector by an intent classification layer of the target intent model. 10.A blockchain-based joint factoring data security protection system, characterized in that, including: The data acquisition module is configured to obtain initial factoring data corresponding to the target construction enterprise, and perform key sentence recognition on the initial factoring data to obtain target key sentences corresponding to the target construction enterprise. The information identification module is configured to perform sensitive information identification on the target key sentences to obtain target sensitive information corresponding to the target key sentences. The mode determination module is configured to perform data entropy analysis on the initial factoring data and the target sensitive information to obtain a first encryption mode corresponding to the target sensitive information and a second encryption mode corresponding to the initial factoring data. The data encryption module is configured to encrypt the target sensitive information and the initial factoring data according to the first encryption mode and the second encryption mode to obtain a target encryption result. The intent identification module is configured to perform intent identification on the initial factoring data to obtain a target intent corresponding to the initial factoring data, and determine a target permission corresponding to the target encryption result according to the target intent. The data transmission module is configured to transmit the target encryption result and the target permission to a related node by using a block chain, and obtain a related permission corresponding to the related node. The data screening module is configured to screen the related node according to the target permission and the related permission to obtain a target node, so that a target object obtains the target encryption result according to the target node.

Images