Credit subject data security enhancement processing system and method

Abstract

The invention discloses a credit subject data security enhancement processing system and method, and the system comprises a service subsystem which is used for generating an account application request based on a first evaluation request when the first evaluation request of a credit subject is received, and transmitting the account application request to a credit investigation subsystem; the credit investigation subsystem is used for generating a credit shadow account based on the account application request and returning the credit shadow account to the service subsystem; the service subsystem is also used for generating a second credit evaluation request based on the credit shadow account and sending the second credit evaluation request to the service engine subsystem; and the service engine subsystem is used for acquiring credit investigation associated data corresponding to the credit subject from the credit investigation subsystem based on the second evaluation request, performing credit evaluation on the credit subject based on the credit investigation associated data, generating a credit evaluation result and returning the credit evaluation result to the service subsystem. According to the invention, data related to credit investigation can be analyzed and processed safely and accurately, so that enterprise credit assessment is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis and processing, and particularly to a system and method for enhancing the security of credit entity data processing. Background Art

[0002] In modern society, the importance of enterprise credit investigation is self-evident, and it has an important impact on aspects such as identifying and evaluating credit risks, investment decisions, and business cooperation. Therefore, securely and accurately processing data related to credit investigation is an effective way to ensure the accurate evaluation of enterprise credit investigation. However, the traditional method of processing data related to credit investigation is prone to data leakage risks, and its comprehensiveness and accuracy also need to be improved. Therefore, how to analyze and process data related to credit investigation safely and accurately to make enterprise credit evaluation more accurate is one of the technical problems that need to be solved currently. Summary of the Invention

[0003] The main object of the present invention is to provide a system and method for enhancing the security of credit entity data processing, aiming to solve the technical problem in the prior art of how to analyze and process data related to credit investigation safely and accurately to make enterprise credit evaluation more accurate.

[0004] To achieve the above object, the present invention provides a system for enhancing the security of credit entity data processing, which includes a business subsystem, a credit investigation subsystem, and a business engine subsystem;

[0005] The business subsystem is configured to generate an account application request based on the first evaluation request of the credit entity when receiving the first evaluation request of the credit entity, and send the account application request to the credit investigation subsystem;

[0006] The credit investigation subsystem is configured to generate a credit shadow account based on the account application request, and return the credit shadow account to the business subsystem;

[0007] The business subsystem is further configured to generate a second credit evaluation request based on the credit shadow account, and send the second credit evaluation request to the business engine subsystem;

[0008] The business engine subsystem is configured to obtain credit-related data corresponding to the credit entity from the credit investigation subsystem based on the second evaluation request, and perform a credit evaluation on the credit entity based on the credit-related data, and generate a credit evaluation result and return it to the business subsystem.

[0009] Preferably, the system for enhancing the security of credit entity data processing further includes a blockchain storage module;

[0010] The blockchain storage module is used to receive the credit investigation associated data uploaded by the business engine subsystem, and encrypt the credit investigation associated data based on a preset encryption algorithm to obtain encrypted credit investigation data for storage.

[0011] Preferably, the blockchain storage module includes:

[0012] A splitting unit, configured to split the credit investigation associated data to obtain a plurality of data block matrices, and perform the following steps for each of the data block matrices:

[0013] An encryption unit, configured to generate an encryption matrix corresponding to the data block matrix, and encrypt the data block matrix based on the encryption matrix by a preset encryption formula to obtain block-encrypted data, where the preset encryption formula is:

[0014] Sk = (Dk * Bk) * C / Ak;

[0015] where Sk represents the i-th block-encrypted data, Dk represents the k-th data block matrix, Bk represents the encryption matrix corresponding to the k-th data block matrix, Ck represents the data volume size corresponding to the k-th data block matrix, and A represents the data volume size corresponding to the credit investigation associated data;

[0016] A generating unit, configured to generate the encrypted credit investigation data for storage from each of the block-encrypted data after each of the data block matrices obtains the block-encrypted data.

[0017] Preferably, the credit subject data security enhancement processing system further includes a data analysis module;

[0018] The data analysis module is used for:

[0019] Performing feature extraction on the credit investigation associated data stored in the blockchain storage module based on a plurality of hidden layers in a preset network model to obtain credit feature values corresponding to each of the hidden layers, where the formula for feature extraction by the plurality of hidden layers is:

[0020] y(i) = h(ui * x + wi * y(i - 1) + bi);

[0021] where y(i) represents the credit feature value corresponding to the i-th hidden layer, h represents the activation function of the preset network model, ui represents the weight value between the input layer and the i-th hidden layer, x represents the credit investigation associated data, wi and bi respectively represent the weight value and bias value between the i-th hidden layer and the i - 1-th hidden layer, and y(i - 1) represents the credit feature value corresponding to the i - 1-th hidden layer;

[0022] Analyze the credit feature values corresponding to the last hidden layer based on the output layer in the preset network model, and generate an analysis result to update the credit assessment result.

[0023] Preferably, the credit investigation subsystem is further configured to obtain the credit subject account corresponding to the account application request, and form a corresponding relationship between the credit shadow account and the credit subject account;

[0024] The service engine subsystem is further configured to transmit the second assessment request to the credit investigation subsystem;

[0025] The credit investigation subsystem is further configured to obtain the credit shadow account corresponding to the second assessment request, and search for the account credit investigation data of the credit subject account corresponding to the credit shadow account in the credit investigation subsystem as the credit-related data corresponding to the credit subject.

[0026] Furthermore, to achieve the above object, the present invention further provides a method for enhancing the data security of a credit subject, which is applied to a system for enhancing the data security of a credit subject. The system for enhancing the data security of a credit subject includes a service subsystem, a credit investigation subsystem, and a service engine subsystem; the method for enhancing the data security of a credit subject includes:

[0027] When the service subsystem receives a first assessment request of a credit subject, generate an account application request based on the first assessment request, and send the account application request to the credit investigation subsystem;

[0028] When the credit investigation subsystem receives the account application request, generate a credit shadow account based on the account application request, and return the credit shadow account to the service subsystem;

[0029] When the service subsystem receives the credit shadow account, generate a second credit assessment request based on the credit shadow account, and send the second credit assessment request to the service engine subsystem;

[0030] When the service engine subsystem receives the second credit assessment request, obtain the credit-related data corresponding to the credit subject from the credit investigation subsystem based on the second assessment request, and perform a credit assessment on the credit subject based on the credit-related data to generate a credit assessment result and return it to the service subsystem.

[0031] Preferably, the system for enhancing the data security of a credit subject further includes a blockchain storage module;

[0032] After the step of performing a credit assessment on the credit subject based on the credit-related data to generate a credit assessment result and returning it to the service subsystem includes:

[0033] When the blockchain storage module receives the credit investigation associated data uploaded by the business engine subsystem, it encrypts the credit investigation associated data based on a preset encryption algorithm, and stores the encrypted credit investigation data obtained thereby.

[0034] Preferably, the step of encrypting the credit investigation associated data based on a preset encryption algorithm and storing the encrypted credit investigation data obtained thereby includes:

[0035] Performing data segmentation on the credit investigation associated data to obtain a plurality of data block matrices, and performing the following steps for each of the data block matrices:

[0036] Generating an encryption matrix corresponding to the data block matrix, and encrypting the data block matrix based on the encryption matrix by a preset encryption formula to obtain block encryption data, where the preset encryption formula is:

[0037] Sk = (Dk * Bk) * C / Ak;

[0038] where Sk represents the i-th block encryption data, Dk represents the k-th data block matrix, Bk represents the encryption matrix corresponding to the k-th data block matrix, Ck represents the data volume size corresponding to the k-th data block matrix, and A represents the data volume size corresponding to the credit investigation associated data;

[0039] After block encryption data is obtained for each of the data block matrices, generating the block encryption data into the encrypted credit investigation data for storage.

[0040] Preferably, the credit subject data security enhancement processing system further includes a data analysis module;

[0041] After the step of performing credit assessment on the credit subject based on the credit investigation associated data, generating a credit assessment result and returning it to the business subsystem, the following steps are included:

[0042] The data analysis module performs feature extraction on the credit investigation associated data stored on the blockchain storage module based on a plurality of hidden layers in a preset network model to obtain credit feature values corresponding to each of the hidden layers, where the formula for feature extraction by the plurality of hidden layers is:

[0043] y(i) = h(ui * x + wi * y(i - 1) + bi);

[0044] Among them, y(i) represents the credit investigation feature value corresponding to the i-th hidden layer, h represents the activation function of the preset network model, ui represents the weight value between the input layer and the i-th hidden layer, x represents the credit investigation associated data, wi and bi respectively represent the weight value and bias value between the i-th hidden layer and the (i - 1)-th hidden layer, and y(i - 1) represents the credit investigation feature value corresponding to the (i - 1)-th hidden layer;

[0045] Based on the analysis of the credit investigation feature value corresponding to the last hidden layer by the output layer in the preset network model, an analysis result is generated to update the credit assessment result.

[0046] Preferably, after the step of generating a credit shadow account based on the account application request, the following steps are included:

[0047] Obtain the credit subject account corresponding to the account application request, and form a corresponding relationship between the credit shadow account and the credit subject account;

[0048] The step of obtaining the credit investigation associated data corresponding to the credit subject from the credit investigation subsystem based on the second evaluation request includes:

[0049] Transmit the second evaluation request to the credit investigation subsystem,

[0050] When the credit investigation subsystem receives the second evaluation request, obtain the credit shadow account corresponding to the second evaluation request, and search for the account credit investigation data of the credit subject account corresponding to the credit shadow account in the credit investigation subsystem as the credit investigation associated data corresponding to the credit subject.

[0051] The present invention relates to a system and method for enhancing the security of credit entity data. The system includes a business subsystem, a credit investigation subsystem, and a business engine subsystem. When the business subsystem receives a first evaluation request from a credit entity, it generates an account application request based on the first evaluation request and sends the generated account application request to the credit investigation subsystem. The credit investigation subsystem generates a credit shadow account based on the account application request and returns it to the business subsystem. The business subsystem generates a second credit evaluation request based on the credit shadow account and sends it to the business engine subsystem. The business engine subsystem obtains the credit-related associated data corresponding to the credit entity from the credit investigation subsystem according to the second evaluation request, and conducts a credit evaluation on the credit entity based on the credit-related associated data, and generates a credit evaluation result and returns it to the business subsystem. In this way, by generating a credit shadow account, the direct association of data between the business subsystem and the business engine subsystem is cut off, and only the credit shadow account is disclosed to the business engine subsystem, reducing the risk of data leakage. At the same time, by storing various types of credit-related associated data related to the credit investigation of the credit entity in the credit investigation subsystem, the data used for credit evaluation of the credit entity is more comprehensive and accurate. It realizes the safe and accurate analysis and processing of data related to credit investigation, making the enterprise credit evaluation more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the modules of the first embodiment of the credit entity data security enhancement processing system of the present invention;

[0053] Figure 2 It is a schematic diagram of the modules of the second embodiment of the credit entity data security enhancement processing system of the present invention;

[0054] Figure 3 It is a schematic flowchart of the first embodiment of the credit entity data security enhancement processing method of the present invention;

[0055] Figure 4 It is a schematic flowchart of the third embodiment of the credit entity data security enhancement processing method of the present invention.

[0056] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] The present invention provides a system for enhancing the security of credit entity data. Please refer to Figure 1 , Figure 1This is a module diagram of the first embodiment of the credit subject data security enhancement processing system of the present invention. Specifically, the credit subject data security enhancement processing system in this embodiment includes at least a business subsystem 10, a credit investigation subsystem 20 and a business engine subsystem 30. Among them,

[0059] The business subsystem 10 is configured to generate an account application request based on the first evaluation request when receiving the first evaluation request of the credit subject, and send the account application request to the credit investigation subsystem 20;

[0060] In this embodiment, the credit subject can be a financial enterprise or other non-financial enterprise. The credit subject data security enhancement processing is to evaluate the credit risk of the credit subject by performing security enhancement processing on various types of data related to the credit subject and credit investigation. Specifically, when the credit subject has an evaluation demand, a first evaluation request is initiated to the business subsystem 10 of the credit subject data security enhancement processing system of this embodiment. After receiving the first evaluation request, the business subsystem 10 reads the corporate account carried therein, determines the specific enterprise that needs to be evaluated based on the corporate account, and uses the read corporate account as the credit subject account. Then, the credit subject account is added to the application request to generate an account application request, and the account application request is sent to the credit investigation subsystem 10.

[0061] The credit investigation subsystem 20 is used to generate a credit shadow account based on the account application request, and return the credit shadow account to the business subsystem 10;

[0062] Further, after receiving the account application request sent by the business subsystem 10, the credit investigation subsystem 20 generates a credit shadow account corresponding to the credit subject account according to the preset account generation rules. Among them, the credit shadow account is an account used for the business engine subsystem. The credit investigation subsystem 20 returns the generated credit shadow account to the business subsystem 10. At the same time, in order to reflect the corresponding relationship between the credit shadow account and the credit subject, the credit investigation subsystem 20 also obtains the credit subject account carried in the account application request, and forms a corresponding relationship between the credit subject account and the credit shadow account for storage.

[0063] The business subsystem 10 is further configured to generate a second credit evaluation request based on the credit shadow account number, and send the second credit evaluation request to the business engine subsystem 30 .

[0064] Furthermore, the business subsystem 10 receives the credit shadow account number returned by the credit investigation subsystem 20 , and adds the credit shadow account number to the evaluation request to generate a second credit evaluation request, and then sends the second credit evaluation request to the business engine subsystem 30 .

[0065] The business engine subsystem 30 is configured to obtain credit-related data corresponding to the credit subject from the credit investigation subsystem 20 based on the second evaluation request, and perform a credit assessment on the credit subject based on the credit-related data, and generate a credit assessment result and return it to the business subsystem 10.

[0066] Furthermore, the business engine subsystem 30 receives the second credit assessment request sent by the business subsystem 10, and obtains the credit management data corresponding to the credit subject from the credit investigation subsystem 20 according to the second credit assessment request. Specifically, the business engine subsystem 30 transmits the second credit assessment request to the credit investigation subsystem 20, and the credit investigation subsystem 20 receives the second credit assessment request and obtains the credit shadow account number carried by it. Then, according to the corresponding relationship between each credit subject account number and each credit shadow account number stored in it, the credit subject account number corresponding to the credit shadow account number is found.

[0067] At the same time, a large amount of credit subjects and their respective corresponding credit investigation sub-data are stored in the credit investigation subsystem, and the storage method can be in the form of a data group. That is, one credit subject corresponds to one data group, and the data group contains various data related to the credit investigation of the credit subject. For example, data related to the credit investigation of the credit subject collected from various data channels such as official websites, news websites, social platforms, and government affairs platforms through technologies such as API calls and web crawlers. Such data related to credit investigation at least includes the credit subject's borrowing data, news media data, tax data, invoice data, financial statements, and transaction data, etc. Form such data into a data group, and use the credit subject as the keyword of the data group. For the credit subject account number corresponding to the found credit shadow account number, find the target data group corresponding to the credit subject account number in each data group. The data contained in the target data group is the account credit investigation data of the credit subject account number corresponding to the credit shadow account number in the credit investigation subsystem 20. Return the account credit investigation data as the credit-related data corresponding to the credit subject to the business engine subsystem 30. The business engine subsystem 30 receives the credit-related data and analyzes it, and performs a credit assessment on the credit subject through the analysis, generates a credit assessment result and returns it to the business subsystem 10, and the business subsystem 10 returns it to the credit subject to complete the credit risk assessment of the credit subject.

[0068] The credit subject data security enhancement processing system of this embodiment includes a business subsystem, a credit investigation subsystem, and a business engine subsystem. Among them, when the business subsystem receives a first evaluation request of a credit subject, it generates an account application request based on the first evaluation request and sends the generated account application request to the credit investigation subsystem. The credit investigation subsystem generates a credit shadow account based on the account application request and returns it to the business subsystem. The business subsystem generates a second credit evaluation request based on the credit shadow account and sends it to the business engine subsystem. The business engine subsystem obtains the credit investigation associated data corresponding to the credit subject from the credit investigation subsystem according to the second evaluation request, and conducts a credit evaluation on the credit subject based on the credit investigation associated data, and generates a credit evaluation result and returns it to the business subsystem. In this way, by generating a credit shadow account, the direct association of data between the business subsystem and the business engine subsystem is cut off, and only the credit shadow account is disclosed to the business engine subsystem, reducing the risk of data leakage. At the same time, by storing various credit investigation associated data related to the credit investigation of the credit subject in the credit investigation subsystem, the data used for credit evaluation of the credit subject is more comprehensive and accurate. It realizes the safe and accurate analysis and processing of data related to credit investigation, making the enterprise credit evaluation more accurate.

[0069] Further, please refer to Figure 2 , based on the first embodiment of the credit subject data security enhancement processing system of the present invention, the second embodiment of the credit subject data security enhancement processing system of the present invention is proposed.

[0070] The difference between the second embodiment of the credit subject data security enhancement processing system and the first embodiment of the credit subject data security enhancement processing system is that the credit subject data security enhancement processing system further includes a blockchain storage module 40;

[0071] The blockchain storage module 40 is used to receive the credit investigation associated data uploaded by the business engine subsystem, and encrypt the credit investigation associated data based on a preset encryption algorithm to obtain encrypted credit investigation data for storage.

[0072] In order to further ensure the security of the credit investigation associated data, the credit subject data security enhancement processing system of this embodiment is also provided with a blockchain storage module 40. After the business engine subsystem 30 obtains the credit investigation associated data from the credit investigation subsystem 20 and conducts a credit evaluation on the credit subject based on the credit investigation associated data to generate a credit evaluation result, it uploads the obtained credit investigation management data to the blockchain storage module. The blockchain storage module receives the uploaded credit investigation associated data, and encrypts the credit investigation associated data according to a preset encryption algorithm to obtain encrypted credit investigation data for storage. Specifically, the blockchain storage module 40 includes:

[0073] The segmentation unit 41 is used to segment the credit-related data to obtain a plurality of data block matrices, and perform the following steps for each of the data block matrices:

[0074] An encryption unit 42 is used to generate an encryption matrix corresponding to the data block matrix, and encrypt the data block matrix based on the encryption matrix using a preset encryption formula to obtain block encrypted data;

[0075] The generating unit 43 is used to generate each block of encrypted data into the encrypted credit data storage after each of the data block matrices obtains the block encrypted data.

[0076] Furthermore, the segmentation unit 41 in the blockchain storage module 40 performs data segmentation on the credit management data, and obtains multiple data blocks through segmentation. The amount of data contained in each data block may be the same or different, and it is preferably explained here with different amounts of data. Each data block is formed into a data block matrix according to the number of matrix rows and matrix columns corresponding to the size of each data amount, and the encryption unit 42 performs encryption operations on each data block matrix. Specifically, an encryption matrix corresponding to the data block matrix is ​​generated, and the generation method can be to operate each element in the data block matrix in a preset operation method to obtain new elements to form an encryption matrix. In addition, the encryption matrix and the data block matrix can have the same number of matrix rows and matrix columns to make encryption safer, or they can have different numbers of matrix rows and matrix columns to reduce the data operation dimension.

[0077] Furthermore, a preset encryption formula is pre-set, and the data block matrix is ​​encrypted by the preset encryption formula to obtain block encrypted data. After each data block is encrypted by the preset encryption formula and the corresponding block encrypted data is obtained, the generation unit 43 combines the block encrypted data to generate encrypted credit data. The combination method can be to arrange the encrypted data blocks in the order of segmentation of the credit-related data, or to add and calculate the encrypted data blocks to obtain the encrypted credit data to be stored by the blockchain storage module 40. The preset encryption formula can be specifically referred to as the following formula (1).

[0078] Sk= (Dk*Bk) *C / Ak (1);

[0079] Among them, Sk represents the encrypted data of the i-th block, Dk represents the k-th data block matrix, Bk represents the encryption matrix corresponding to the k-th data block matrix, Ck represents the data volume corresponding to the k-th data block matrix, and A represents the data volume corresponding to the credit-related data.

[0080] In this embodiment, by setting up a blockchain storage module to encrypt and store credit investigation associated data, the security and immutability of the credit investigation associated data are ensured. Even if the credit investigation associated data is transmitted to other modules or systems, the authenticity of the credit investigation associated data in other modules or systems can be verified through the credit investigation associated data stored in the blockchain storage module.

[0081] Furthermore, based on the first or second embodiment of the credit subject data security enhancement processing system of the present invention, a third embodiment of the credit subject data security enhancement processing system of the present invention is proposed.

[0082] The difference between the third embodiment of the credit subject data security enhancement processing system and the first and second embodiments of the credit subject data security enhancement processing system is that the credit subject data security enhancement processing system further includes a data analysis module 50;

[0083] The data analysis module 50 is used for:

[0084] extracting features from the credit investigation associated data stored on the blockchain storage module based on multiple hidden layers in a preset network model to obtain credit feature values corresponding to each hidden layer;

[0085] analyzing the credit feature values corresponding to the last hidden layer based on the output layer in the preset network model, generating an analysis result to update the credit assessment result.

[0086] Furthermore, in order to make the credit assessment of the credit subject more accurate, this embodiment also sets up a data analysis module 50 to conduct in-depth mining and analysis of the credit investigation associated data. Specifically, a preset network model is pre-trained in the data analysis module 50 with a large number of credit-related data samples. The preset network model includes an input layer, multiple hidden layers, and an output layer. The credit investigation associated data stored on the blockchain storage module 40 is input into the data analysis model through the input layer of the preset network model. The input layer processes it to obtain an output result as the input data for the multiple hidden layers. The multiple hidden layers extract features from this input data one by one according to the arrangement order of each input layer, and obtain credit feature values corresponding to each hidden layer one by one. Among them, the credit feature values obtained by the previous hidden layer are used as the input data for the next hidden layer, and so on in a cycle until the credit feature values obtained by the last hidden layer are used as the input data for the output layer. The output layer conducts analysis and processing to obtain the final analysis result. The credit assessment result generated by the business engine subsystem 30 is updated through this analysis result, making the credit assessment result more accurate. Among them, the feature extraction by each hidden layer can be carried out according to the following formula (2).

[0087] y(i) =h(ui*x+wi*y(i-1) +bi) (2);

[0088] Among them, y(i) represents the credit feature value corresponding to the i-th hidden layer, h represents the activation function of the preset network model, ui represents the weight value between the input layer and the i-th hidden layer, x represents the credit-related data, wi and bi represent the weight value and bias value between the i-th hidden layer and the i-1-th hidden layer respectively, and y(i-1) represents the credit feature value corresponding to the i-1-th hidden layer.

[0089] This embodiment sets up a data analysis module, and sets up a preset network model formed by training a large number of credit-related data samples in the data analysis module, conducts in-depth mining and analysis on credit-related data, updates credit assessment results, and improves the accuracy of credit assessment of credit subjects.

[0090] In addition, the present invention provides a credit subject data security enhancement processing method, please refer to Figure 3 , Figure 3 This is a flowchart of the first embodiment of the credit subject data security enhancement processing method of the present invention. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be performed in a different order than here. Specifically, the credit subject data security enhancement processing method in this embodiment is applied to the credit subject data security enhancement processing system, which includes a business subsystem, a credit investigation subsystem and a business engine subsystem; the method includes:

[0091] Step S10, when the business subsystem receives the first evaluation request of the credit subject, it generates an account application request based on the first evaluation request, and sends the account application request to the credit investigation subsystem;

[0092] In this embodiment, the credit subject can be a financial enterprise or other non-financial enterprise. The credit subject data security enhancement processing is to evaluate the credit risk of the credit subject by performing security enhancement processing on various types of data related to the credit subject and credit investigation. Specifically, when the credit subject has an evaluation demand, a first evaluation request is initiated to the business subsystem of the credit subject data security enhancement processing system of this embodiment. After receiving the first evaluation request, the business subsystem reads the enterprise account carried therein, determines the specific enterprise that needs to be evaluated based on the enterprise account, and uses the read enterprise account as the credit subject account. Then, the credit subject account is added to the application request to generate an account application request, and the account application request is sent to the credit investigation subsystem.

[0093] Step S20, when the credit investigation subsystem receives the account application request, it generates a credit shadow account based on the account application request, and returns the credit shadow account to the business subsystem;

[0094] Furthermore, after receiving the account application request sent by the business subsystem, the credit investigation subsystem generates a credit shadow account corresponding to the credit subject account according to the preset account generation rule. The credit shadow account is an account used for the business engine subsystem. The credit investigation subsystem returns the generated credit shadow account to the business subsystem. At the same time, in order to reflect the corresponding relationship between the credit shadow account and the credit subject, the credit investigation subsystem also obtains the credit subject account carried in the account application request and stores the corresponding relationship formed between the credit subject account and the credit shadow account.

[0095] Step S30: When the business subsystem receives the credit shadow account, it generates a second credit assessment request based on the credit shadow account and sends the second credit assessment request to the business engine subsystem.

[0096] Furthermore, the business subsystem receives the credit shadow account returned by the credit investigation subsystem, adds the credit shadow account to the assessment request to generate a second credit assessment request, and then sends the second credit assessment request to the business engine subsystem.

[0097] Step S40: When the business engine subsystem receives the second credit assessment request, it obtains the credit investigation associated data corresponding to the credit subject from the credit investigation subsystem based on the second assessment request, and conducts a credit assessment on the credit subject based on the credit investigation associated data, and returns the credit assessment result to the business subsystem.

[0098] Furthermore, the business engine subsystem receives the second credit assessment request sent by the business subsystem, and obtains the credit investigation management data corresponding to the credit subject from the credit investigation subsystem according to the second credit assessment request. Specifically, the business engine subsystem transmits the second credit assessment request to the credit investigation subsystem, the credit investigation subsystem receives the second credit assessment request, and obtains the credit shadow account carried in it. Then, according to the corresponding relationship stored between each credit subject account and each credit shadow account, it finds out the credit subject account corresponding to the credit shadow account.

[0099] Meanwhile, a large amount of credit subjects and their respective corresponding credit sub-data are stored in the credit reporting subsystem, and the storage method can be in the form of data groups. That is, one credit subject corresponds to one data group, and this data group contains various types of data related to the credit reporting of the credit subject. For example, data related to the credit reporting of the credit subject collected from various data channels such as official websites, news websites, social platforms, and government affairs platforms through technologies such as API calls and web crawlers. This type of data related to credit reporting at least includes the credit subject's lending data, news media data, tax data, invoice data, financial statements, and transaction data, etc. Form this type of data into a data group, and use the credit subject as the keyword of the data group. For the credit subject account corresponding to the searched credit shadow account, search for the target data group corresponding to the credit subject account in each data group. The data contained in this target data group is the account credit reporting data of the credit subject account corresponding to the credit shadow account in the credit reporting subsystem. Use this account credit reporting data as the credit-related data associated with the credit subject and return it to the business engine subsystem. The business engine subsystem receives this credit-related data and analyzes it, conducts a credit assessment on the credit subject through the analysis, generates a credit assessment result and returns it to the business subsystem, and the business subsystem returns it to the credit subject to complete the credit risk assessment of the credit subject.

[0100] In the method for enhancing the security of credit subject data in this implementation, once the business subsystem receives the first assessment request of the credit subject, it generates an account application request based on the first assessment request and sends the generated account application request to the credit reporting subsystem; the credit reporting subsystem generates a credit shadow account based on the account application request and returns it to the business subsystem; the business subsystem generates a second credit assessment request based on this credit shadow account and sends it to the business engine subsystem; the business engine subsystem obtains the credit-related data corresponding to the credit subject from the credit reporting subsystem according to the second assessment request, and conducts a credit assessment on the credit subject based on the credit-related data, generates a credit assessment result and returns it to the business subsystem. In this way, by generating a credit shadow account, the direct association of data between the business subsystem and the business engine subsystem is cut off, and only the credit shadow account is disclosed to the business engine subsystem, reducing the risk of data leakage. At the same time, by storing various types of credit-related data related to the credit reporting of the credit subject in the credit reporting subsystem, the data used for credit assessment of the credit subject is more comprehensive and accurate. It realizes the safe and accurate analysis and processing of data related to credit reporting, making the enterprise credit assessment more accurate.

[0101] Furthermore, based on the first embodiment of the method for enhancing the security of credit subject data of the present invention, a second embodiment of the method for enhancing the security of credit subject data of the present invention is proposed.

[0102] The second embodiment of the method for enhancing the security of credit subject data is different from the first embodiment of the method for enhancing the security of credit subject data in that the credit subject data security enhancement processing system further includes a blockchain storage module; after the step of performing credit assessment on the credit subject based on the credit investigation associated data and generating a credit assessment result and returning it to the business subsystem, the following steps are included:

[0103] Step S50, when the blockchain storage module receives the credit investigation associated data uploaded by the business engine subsystem, encrypt the credit investigation associated data based on a preset encryption algorithm to obtain encrypted credit investigation data for storage.

[0104] To further ensure the security of the credit investigation associated data, the credit subject data security enhancement processing system is further provided with a blockchain storage module. After the business engine subsystem obtains the credit investigation associated data from the credit investigation subsystem and performs credit assessment on the credit subject based on the credit investigation associated data to generate a credit assessment result, the obtained credit investigation management data is uploaded to the blockchain storage module. The blockchain storage module receives the uploaded credit investigation associated data and performs encryption processing on the credit investigation associated data based on a preset encryption algorithm to obtain encrypted credit investigation data for storage. Specifically, the step of encrypting the credit investigation associated data based on a preset encryption algorithm to obtain encrypted credit investigation data for storage includes:

[0105] Step S51, perform data segmentation on the credit investigation associated data to obtain a plurality of data block matrices, and perform the following steps for each of the data block matrices:

[0106] Step S52, generate an encryption matrix corresponding to the data block matrix, and encrypt the data block matrix based on the encryption matrix by a preset encryption formula to obtain block encryption data;

[0107] Step S53, after each of the data block matrices obtains the block encryption data, generate the block encryption data into the encrypted credit investigation data for storage.

[0108] Further, the credit investigation management data is segmented to obtain multiple data blocks. The amount of data contained in each data block can be the same or different. Here, it is preferably described with different amounts of data. Each data block is formed into a data block matrix according to the number of matrix rows and matrix columns corresponding to its own data volume, and an encryption operation is performed on each data block matrix. Specifically, an encryption matrix corresponding to the data block matrix is generated. The generation method can be to perform an operation on each element in the data block matrix in a preset operation mode to obtain new elements to form the encryption matrix. Moreover, the encryption matrix and the data block matrix can have the same number of matrix rows and matrix columns to make the encryption more secure, or can have different numbers of matrix rows and matrix columns to reduce the data operation dimension.

[0109] Furthermore, a preset encryption formula is pre-set, and the data block matrix is encrypted through the preset encryption formula to obtain block-encrypted data. After each data block is encrypted through the preset encryption formula to obtain its corresponding block-encrypted data, the respective block-encrypted data are combined, that is, encrypted credit investigation data is generated. The combination method can be to arrange the block-encrypted data in the order of credit investigation association data segmentation, or perform an addition operation on the block-encrypted data to obtain the encrypted credit investigation data, which is stored by the blockchain storage module 40. Among them, the specific preset encryption formula can refer to the above formula (1), which will not be elaborated here.

[0110] In this embodiment, by setting the blockchain storage module to encrypt and store the credit investigation association data, the security and immutability of the credit investigation association data are ensured. Even if the credit investigation association data is transmitted to other modules or systems, the authenticity of the credit investigation association data in other modules or systems can be verified through the credit investigation association data stored in the blockchain storage module.

[0111] Further, please refer to Figure 4 Based on the first and second embodiments of the method for enhancing the security of credit subject data of the present invention, a third embodiment of the method for enhancing the security of credit subject data of the present invention is proposed.

[0112] The difference between the third embodiment of the method for enhancing the security of credit subject data and the first and second embodiments of the method for enhancing the security of credit subject data is that the system for enhancing the security of credit subject data further includes a data analysis module; after the step of performing a credit assessment on the credit subject based on the credit investigation association data and generating a credit assessment result and returning it to the business subsystem, the following steps are included:

[0113] Step S60, based on multiple hidden layers in the preset network model, feature extraction is performed on the credit investigation association data stored on the blockchain storage module to obtain credit feature values corresponding to each hidden layer;

[0114] Step S70: Analyze the credit feature values corresponding to the last hidden layer based on the output layer in the preset network model, and generate an analysis result to update the credit assessment result.

[0115] Furthermore, in order to make the credit assessment of the credit subject more accurate, the credit subject data security enhancement processing system is also provided with a data analysis module for in-depth mining and analysis of credit-related data. Specifically, a preset network model is pre-trained in the data analysis module with a large number of credit-related data samples. The preset network model includes an input layer, multiple hidden layers, and an output layer. The credit-related data stored on the blockchain storage module is input into the data analysis model through the input layer of the preset network model. The input layer processes it to obtain an output result as the input data for the multiple hidden layers. The multiple hidden layers sequentially extract features from this input data according to the arrangement order of each input layer, and obtain the credit feature values corresponding to each hidden layer one by one. Among them, the credit feature value obtained by the previous hidden layer is used as the input data for the next hidden layer. This cycle continues until the last hidden layer obtains the credit feature value as the input data for the output layer. The output layer performs analysis and processing to obtain the final analysis result. The credit assessment result generated by the business engine subsystem 30 is updated through this analysis result, making the credit assessment result more accurate. Among them, the feature extraction of each hidden layer can be carried out according to the above formula (2), which will not be elaborated here.

[0116] In this embodiment, by setting up a data analysis module and a preset network model trained with a large number of credit-related data samples in the data analysis module, in-depth mining and analysis of credit-related data are carried out to update the credit assessment result, improving the accuracy of the credit assessment of the credit subject.

[0117] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose and scope protected by the claims of the present invention. Any equivalent structural or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied to other related technical fields, all fall within the protection scope of the present invention.

Claims

1. A credit subject data security enhancement processing system, characterized in that: The credit subject data security enhancement processing system includes a business subsystem, a credit investigation subsystem and a business engine subsystem; The business subsystem is configured to generate an account application request based on the first evaluation request when receiving the first evaluation request from the credit subject, and send the account application request to the credit investigation subsystem; The credit investigation subsystem is used to generate a credit shadow account number based on the account application request, and return the credit shadow account number to the business subsystem; The business subsystem is further configured to generate a second credit evaluation request based on the credit shadow account number, and send the second credit evaluation request to the business engine subsystem; The business engine subsystem is used to obtain the credit-related data corresponding to the credit subject from the credit investigation subsystem based on the second evaluation request, and to perform a credit evaluation on the credit subject based on the credit investigation related data, and to generate a credit evaluation result and return it to the business subsystem.

2. The credit subject data security enhancement processing system according to claim 1, characterized in that: The credit subject data security enhancement processing system also includes a blockchain storage module; The blockchain storage module is used to receive the credit-related data uploaded by the business engine subsystem, and encrypt the credit-related data based on a preset encryption algorithm to obtain encrypted credit data storage.

3. The credit subject data security enhancement processing system according to claim 2, characterized in that: The blockchain storage module includes: The segmentation unit is used to segment the credit-related data to obtain a plurality of data block matrices, and perform the following steps for each of the data block matrices: The encryption unit is used to generate an encryption matrix corresponding to the data block matrix, and encrypt the data block matrix based on the encryption matrix by a preset encryption formula to obtain block encrypted data, wherein the preset encryption formula is: Sk=(Dk*Bk)*C / Ak; Among them, Sk represents the encrypted data of the i-th block, Dk represents the k-th data block matrix, Bk represents the encryption matrix corresponding to the k-th data block matrix, Ck represents the data size corresponding to the k-th data block matrix, and A represents the data size corresponding to the credit-related data; A generating unit is used to generate each block of encrypted data into the encrypted credit data storage after each of the data block matrices obtains the block encrypted data.

4. The credit subject data security enhancement processing system according to any one of claims 1 to 3, characterized in that: The credit subject data security enhancement processing system also includes a data analysis module; The data analysis module is used for: Based on the multiple hidden layers in the preset network model, the credit-related data stored in the blockchain storage module is feature extracted to obtain the credit feature value corresponding to each hidden layer, wherein the formula for feature extraction of the multiple hidden layers is: y(i)=h(ui*x+wi*y(i-1)+bi); Wherein, y(i) represents the credit feature value corresponding to the i-th hidden layer, h represents the activation function of the preset network model, ui represents the weight value between the input layer and the i-th hidden layer, x represents the credit-related data, wi and bi represent the weight value and bias value between the i-th hidden layer and the i-1-th hidden layer, and y(i-1) represents the credit feature value corresponding to the i-1-th hidden layer; The credit feature value corresponding to the last hidden layer is analyzed based on the output layer in the preset network model, and an analysis result is generated to update the credit assessment result.

5. The credit subject data security enhancement processing system according to any one of claims 1 to 3, characterized in that: The credit investigation subsystem is further used to obtain the credit subject account number corresponding to the account application request, and form a corresponding relationship between the credit shadow account number and the credit subject account number; The business engine subsystem is also used to transmit the second evaluation request to the credit investigation subsystem; The credit investigation subsystem is further used to obtain the credit shadow account corresponding to the second assessment request, and to search for the account credit investigation data of the credit subject account corresponding to the credit shadow account in the credit investigation subsystem as the credit investigation associated data corresponding to the credit subject.

6. A credit subject data security enhancement processing method, applied to a credit subject data security enhancement processing system, characterized in that: The credit subject data security enhancement processing system includes a business subsystem, a credit investigation subsystem and a business engine subsystem; The credit subject data security enhancement processing method includes: When the business subsystem receives the first evaluation request of the credit subject, it generates an account application request based on the first evaluation request, and sends the account application request to the credit investigation subsystem; When the credit investigation subsystem receives the account application request, it generates a credit shadow account based on the account application request and returns the credit shadow account to the business subsystem; When the business subsystem receives the credit shadow account, it generates a second credit evaluation request based on the credit shadow account, and sends the second credit evaluation request to the business engine subsystem; When the business engine subsystem receives the second credit assessment request, it obtains the credit-related data corresponding to the credit subject from the credit investigation subsystem based on the second assessment request, performs a credit assessment on the credit subject based on the credit investigation related data, and generates a credit assessment result and returns it to the business subsystem.

7. The credit subject data security enhancement processing method according to claim 6, characterized in that: The credit subject data security enhancement processing system also includes a blockchain storage module; After the step of performing credit assessment on the credit subject based on the credit investigation related data and generating a credit assessment result and returning it to the business subsystem, the following steps are included: When the blockchain storage module receives the credit-related data uploaded by the business engine subsystem, it encrypts the credit-related data based on a preset encryption algorithm and obtains the encrypted credit data for storage.

8. The credit subject data security enhancement processing method according to claim 6, characterized in that: The step of encrypting the credit-related data based on a preset encryption algorithm to obtain the encrypted credit data for storage comprises: The credit-related data is segmented to obtain a plurality of data block matrices, and the following steps are performed for each of the data block matrices: Generate an encryption matrix corresponding to the data block matrix, and encrypt the data block matrix based on the encryption matrix using a preset encryption formula to obtain block encrypted data, wherein the preset encryption formula is: Sk=(Dk*Bk)*C / Ak; Among them, Sk represents the encrypted data of the i-th block, Dk represents the k-th data block matrix, Bk represents the encryption matrix corresponding to the k-th data block matrix, Ck represents the data size corresponding to the k-th data block matrix, and A represents the data size corresponding to the credit-related data; After each of the data block matrices obtains the block encrypted data, each of the block encrypted data is generated as the encrypted credit information data storage.

9. The method for enhancing the security of credit subject data according to any one of claims 6 to 8, characterized in that: The credit subject data security enhancement processing system also includes a data analysis module; After the step of performing credit assessment on the credit subject based on the credit investigation related data and generating a credit assessment result and returning it to the business subsystem, the following steps are included: The data analysis module performs feature extraction on the credit-related data stored in the blockchain storage module based on multiple hidden layers in the preset network model to obtain the credit feature value corresponding to each hidden layer, wherein the formula for feature extraction of multiple hidden layers is: y(i)=h(ui*x+wi*y(i-1)+bi); Wherein, y(i) represents the credit feature value corresponding to the i-th hidden layer, h represents the activation function of the preset network model, ui represents the weight value between the input layer and the i-th hidden layer, x represents the credit-related data, wi and bi represent the weight value and bias value between the i-th hidden layer and the i-1-th hidden layer, and y(i-1) represents the credit feature value corresponding to the i-1-th hidden layer; The credit feature value corresponding to the last hidden layer is analyzed based on the output layer in the preset network model, and an analysis result is generated to update the credit assessment result.

10. The method for enhancing the security of credit subject data according to any one of claims 6 to 8, characterized in that: The step of generating a credit shadow account based on the account application request includes: Obtaining the credit subject account number corresponding to the account application request, and forming a corresponding relationship between the credit shadow account number and the credit subject account number; The step of acquiring the credit investigation related data corresponding to the credit subject from the credit investigation subsystem based on the second evaluation request comprises: transmitting the second evaluation request to the credit investigation subsystem, When the credit investigation subsystem receives the second evaluation request, it obtains the credit shadow account corresponding to the second evaluation request, and searches for the account credit data of the credit subject account corresponding to the credit shadow account in the credit investigation subsystem as the credit association data corresponding to the credit subject.

Images