Data security assessment management system based on artificial intelligence

Abstract

The invention relates to the technical field of data assessment management, and particularly discloses a data security assessment management system based on artificial intelligence, and the system comprises a data storage module which is used for storing all types of data sets in an enterprise and the past use records of all data sets; the sensitivity of different data sets is calculated by combining all types of data sets in an enterprise and the past use records of all the data sets, whether the data sets are core data or not can be accurately judged, and the core data sets are evaluated, graded and encrypted through the data evaluation module. Therefore, the accuracy and objectivity of the core data set evaluation and grading result are ensured, and the problems that the evaluation result of the core data set is not objective and accurate enough or has deviation due to personal prejudice of manual evaluation, and grading of the core data set has vulnerabilities are avoided. And therefore, the data in the core data group has a leakage risk.

Description

Technical Field

[0001] The present invention relates to the technical field of data evaluation management, and in particular to a data security evaluation management system based on artificial intelligence. Background Art

[0002] The data security management system is a comprehensive security system that aims to comprehensively and systematically protect and manage enterprise data by formulating and implementing a series of data security strategies, processes and technical means;

[0003] The data security management system is data-centric, ensuring the security, integrity and availability of enterprise data, preventing data leakage, tampering and loss, reducing data security risks, and improving the competitiveness and market position of enterprises. Among them, the most important enterprise data is core data, which represents the most important part of all data. Common data security management systems will encrypt core data to prevent unauthorized access and data leakage, thereby responding to increasingly severe data security challenges.

[0004] Common data security management systems encrypt core data to protect it, and the assessment of core data in enterprise data is usually performed manually. However, manual assessment may be subject to personal bias or lack of professional knowledge and skills required to fully understand data risks, resulting in the assessment results of core data being not objective and accurate or being biased, which leads to loopholes in the classification of core data groups and the risk of core data being leaked. Summary of the invention

[0005] The purpose of the present invention is to provide a data security assessment management system based on artificial intelligence to solve the following technical problems:

[0006] How to ensure the objectivity and accuracy of core data evaluation results.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A data security assessment management system based on artificial intelligence, the system comprising:

[0009] The data storage module is used to store all types of data groups within the enterprise and the past usage records of all data groups;

[0010] A data processing module, used to calculate and obtain the sensitivity of different data groups based on the data information in the data storage records;

[0011] The data analysis module is used to compare and analyze the sensitivity of different data groups with the preset sensitivity threshold, and determine whether different types of data groups belong to the core data group according to the analysis results;

[0012] A data evaluation module is used to evaluate and classify some data groups determined as core data groups in the data analysis module;

[0013] The data encryption module encrypts data groups of different levels according to the evaluation results of the data evaluation module.

[0014] Furthermore, the usage records stored in the data storage module include the access volume of different data groups, the allowed access IPs and the current encryption level.

[0015] Furthermore, the processing process of the data processing module includes:

[0016] By formula Calculate the sensitivity μ of the i-th data group i ;

[0017] Among them, i is a data group of any category, gr i is the storage amount of personal information data in the i-th data group, jy i is the storage volume of operating data in the i-th data group; zscq i is the storage amount of intellectual property data in the i-th data group; x1, x2 and x3 are the first weight coefficients, and θ is the error influence coefficient, which is set according to empirical fitting.

[0018] Furthermore, the analysis process of the data analysis module includes:

[0019] By taking the sensitivity μ of all data sets i Compare with the preset sensitivity threshold μ x ;

[0020] If all μ i All less than μ x , the system evaluates that the sensitivity of all data groups is small, and determines that the data group is a non-core data group;

[0021] If any μ i Greater than μ x The system evaluates that the sensitivity of the data group is high, determines that the data group is a core data group, and evaluates and grades it through the data evaluation module.

[0022] Furthermore, the evaluation and grading process of the data evaluation module includes:

[0023] First, all the data groups that are judged to be core data groups are listed;

[0024] And through the formula Calculate the core index δ of the i-th data group i ;

[0025] Among them, a is any day in the past period of time, b is the total number of days in the past period of time, fw ai is the total number of visits to the i-th data group on the a-th day in the past period of time, fw a0 is the number of invalid accesses of the i-th data group on the a-th day in the past period of time, fw 0i The preset number of visits for the i-th data group, yx i is the number of IP addresses allowed to access the i-th data group, yx t yx i The standard value, f c It is the adjustment coefficient comparison table function. According to the empirical data (β i The influence of the value range of β on the important index is obtained based on the test data. i is the current encryption level of the i-th data group, y1 and y2 are the second weight coefficients.

[0026] Furthermore, the evaluation and grading process of the data evaluation module also includes:

[0027] By taking all the core indexes δ of all data sets i Compare with the preset core index threshold interval [δ1, δ2] respectively;

[0028] If δ i <δ1, the system determines that the core index of the data group is low and marks it as a first-level core data group;

[0029] If δ i ∈[δ1,δ2], the system determines that the core index of the data group is medium and marks it as a secondary core data group;

[0030] If δ i >δ2, the system determines that the core index of the data group is high and marks it as a third-level core data group.

[0031] Furthermore, the encryption process of the data encryption module includes:

[0032] When a data group is judged to be a first-level core data group, AI will encrypt it with a fixed 6-digit password and facial recognition;

[0033] When a data group is judged to be a secondary core data group, AI will encrypt it with a fixed 6-digit password, facial recognition, and IP restrictions;

[0034] When a data group is judged to be a third-level core data group, artificial intelligence will perform a 6-digit dynamic password, facial recognition, IP restriction, and identity authentication encryption.

[0035] Furthermore, the management process of the data security assessment management system includes:

[0036] S1: Store all types of data groups within the enterprise and the past usage records of all data groups through the data storage module;

[0037] S2: Calculate the sensitivity of different data groups according to the data information in the data storage record through the data processing module;

[0038] S3: Compare and analyze the sensitivity of different data groups with the preset sensitivity threshold through the data analysis module, and determine whether the data groups of different categories belong to the core data group according to the analysis results;

[0039] S4: evaluating and grading some of the data groups determined as core data groups in the data analysis module through the data evaluation module;

[0040] S5: The data encryption module encrypts data groups of different levels according to the evaluation results of the data evaluation module.

[0041] Beneficial effects of the present invention:

[0042] (1) The present invention calculates the sensitivity of different data groups by combining all categories of data groups in the enterprise and the past usage records of all data groups, so as to make an accurate judgment on whether a data group is core data, and evaluates, grades and encrypts the core data group through the data evaluation module, thereby ensuring the accuracy and objectivity of the evaluation and grading results of the core data group, thereby avoiding the situation where the evaluation results of the core data group are not objective, accurate or biased due to personal bias in human evaluation, which in turn leads to loopholes in the grading of the core data group, resulting in the risk of data in the core data group being leaked.

[0043] (2) The present invention calculates the sensitivity μ of all data sets by i Compare with the preset sensitivity threshold μ x According to the comparison results, the system can accurately judge the sensitivity of all data groups, and based on the judgment results, further judge which data groups among all data groups belong to the core data groups. Through such settings, different data groups can be accurately divided, thereby avoiding the situation where human evaluation is subject to personal bias and leads to deviations in the evaluation results of the core data group, thereby improving the accuracy of the core data group evaluation and grading, and ensuring the objectivity and accuracy of the core data evaluation results.

[0044] (3) The present invention calculates the core index δ of all data sets by i They are compared with the preset core index threshold interval [δ1, δ2] respectively. Through this comparison method, the core index δ of all data groups can bei The data assessment module evaluates and grades different core data groups based on accurate data, which can avoid the situation where the evaluation results of core data are not objective, accurate or biased due to personal bias in human evaluation or lack of professional knowledge and skills required to fully understand data risks, thus leading to loopholes in the classification of core data groups.

[0045] (4) The present invention can improve data security and privacy by formulating different levels of encryption methods for core data groups of different levels. In addition, since the classification of core data groups is performed by a data evaluation module based on accurate data information, it can avoid the situation where human evaluation may be subject to personal bias or lack of professional knowledge and skills required to fully understand data risks, which may lead to loopholes in the classification of core data groups. This ensures the security of encrypted core data and ensures the security, integrity and availability of enterprise data through comprehensive data protection measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The present invention will be further described below in conjunction with the accompanying drawings.

[0047] Figure 1 It is a schematic block diagram of a data security assessment management system based on artificial intelligence in the present invention;

[0048] Figure 2 It is a flow chart of the management process of the data security assessment management system in the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] See also Figure 1 As shown, in one embodiment, the present application provides a data security assessment management system based on artificial intelligence, the system comprising:

[0051] The data storage module is used to store all types of data groups within the enterprise and the past usage records of all data groups;

[0052] A data processing module, used to calculate and obtain the sensitivity of different data groups based on the data information in the data storage records;

[0053] The data analysis module is used to compare and analyze the sensitivity of different data groups with the preset sensitivity threshold, and determine whether different types of data groups belong to the core data group according to the analysis results;

[0054] A data evaluation module is used to evaluate and classify some data groups determined as core data groups in the data analysis module;

[0055] The data encryption module encrypts data groups of different levels according to the evaluation results of the data evaluation module;

[0056] Through the above technical solution, this embodiment provides a data storage module to store all categories of data groups in the enterprise and the past usage records of all data groups, and the data processing module calculates the sensitivity of different data groups according to the data information in the data storage records, and then compares and analyzes the sensitivity of different data groups with the preset sensitivity threshold through the data analysis module, and judges whether the data groups of different categories belong to the core data group according to the analysis results, and then evaluates and grades the data groups judged as the core data group through the data evaluation module, and finally encrypts the data groups of different levels according to the evaluation results of the data evaluation module through the data encryption module;

[0057] With such a setting, by combining all categories of data groups within the enterprise and all data groups' past usage records to calculate the sensitivity of different data groups, it is possible to make an accurate judgment on whether the data group is core data, and evaluate, grade and encrypt the core data groups through the data evaluation module, thereby ensuring the accuracy and objectivity of the core data group evaluation and grading results, thereby avoiding the possibility that human evaluation is subject to personal bias, resulting in objective, inaccurate or biased evaluation results for the core data groups, which in turn leads to loopholes in the grading of the core data groups, making the data in the core data groups at risk of being leaked.

[0058] The usage records stored in the data storage module include the number of visits to different data groups, the allowed access IPs, and the current encryption level;

[0059] Through the above technical solution, this embodiment provides a usage record of data groups, including the number of visits to different data groups, the allowed access IP addresses, and the current encryption level. Through this data, a preliminary judgment can be made on the access rights and encryption level of the current data group, and when the subsequent core data groups are graded in combination with this data, the accuracy of the grading results can be improved, thereby ensuring the objectivity and accuracy of the evaluation results of the core data.

[0060] The processing process of the data processing module includes:

[0061] By formula Calculate the sensitivity μ of the i-th data group i ;

[0062] Among them, i is a data group of any category, gr i is the storage amount of personal information data in the i-th data group, jy i is the storage volume of operating data in the i-th data group; zscq i is the storage amount of intellectual property data in the i-th data group; x1, x2 and x3 are first weight coefficients, which can be set according to empirical fitting; θ is the error influence coefficient, which is set according to empirical fitting;

[0063] Through the above technical solution, this embodiment provides the sensitivity μ of the i-th data group i , can be obtained by formula Calculated, once personal identity information is leaked, it may be used for identity theft, fraud or other illegal activities, and intellectual property data is the key data for enterprises to maintain their competitive advantage. Once leaked, it may cause enterprises to lose their market advantage. The leakage of business data may cause significant damage to the commercial interests of enterprises. Therefore, the more the storage of personal information data, business data and intellectual property data in the i-th data group, the higher the sensitivity μ of the i-th data group. i On the contrary, when the storage amount of human information data, business data and intellectual property data in the i-th data group is less, the sensitivity μ of the i-th data group is i the lower;

[0064] By calculating the sensitivity of the ith data group, a preliminary judgment can be made on the importance and degree of importance of the ith data group based on the sensitivity data, thereby making a preliminary assessment of whether the data group is a core data group, thereby improving the accuracy of subsequent grading assessments of core data groups and avoiding loopholes in the grading of core data groups, which may lead to the risk of data leakage in the core data groups.

[0065] The analysis process of the data analysis module includes:

[0066] By taking the sensitivity μ of all data sets i Compare with the preset sensitivity threshold μ x ;

[0067] If all μ i All less than μ x , the system evaluates that the sensitivity of all data groups is small, and determines that the data group is a non-core data group;

[0068] If any μ i Greater than μ x, the system evaluates that the sensitivity of the data group is high, determines that the data group is a core data group, and evaluates and grades it through the data evaluation module;

[0069] Through the above technical solution, this embodiment sets the sensitivity μ of all data groups i Compare with the preset sensitivity threshold μ x According to the comparison results, the system can accurately judge the sensitivity of all data groups, and based on the judgment results, further judge which data groups among all data groups belong to the core data groups. Through such settings, different data groups can be accurately divided, thereby avoiding the situation where human evaluation is subject to personal bias and leads to deviations in the evaluation results of the core data group, thereby improving the accuracy of the core data group evaluation and grading, and ensuring the objectivity and accuracy of the core data group evaluation results.

[0070] The evaluation and grading process of the data evaluation module includes:

[0071] First, all the data groups that are judged to be core data groups are listed;

[0072] And through the formula Calculate the core index δ of the i-th data group i ;

[0073] Among them, a is any day in the past period of time, b is the total number of days in the past period of time, fw ai is the total number of visits to the i-th data group on the a-th day in the past period of time, fw a0 is the number of invalid accesses of the i-th data group on the a-th day in the past period of time, fw 0i The preset number of visits for the i-th data group, yx i is the number of IP addresses allowed to access the i-th data group, yx t yx i The standard value of f can be selected and set according to the allowable error in empirical data. c It is the adjustment coefficient comparison table function. According to the empirical data (β i The influence of the value range of β on the important index is obtained based on the test data. i is the current encryption level of the i-th data group, y1 and y2 are second weight coefficients, and the second weight coefficients can be set according to empirical fitting;

[0074] Through the above technical solution, this embodiment provides the core index δ of the i-th data group: i First, all the data groups that are judged as core data groups are listed, and then the formula It is calculated that, obviously, when the number of valid visits and the number of allowed accessible IPs on the a-th day in the past period of time for the i-th data group is smaller, and the current encryption level is higher, it means that the privacy and security of the data group are higher, which further shows that the core index of the data group is higher; conversely, when the number of valid visits and the number of allowed accessible IPs on the a-th day in the past period of time for the i-th data group is larger, and the current encryption level is lower, it means that the privacy and security of the data group are lower, which further shows that the core index of the data group is lower.

[0075] The evaluation and grading process of the data evaluation module also includes:

[0076] By taking all the core indexes δ of all data sets i Compare with the preset core index threshold interval [δ1, δ2] respectively;

[0077] If δ i <δ1, the system determines that the core index of the data group is low and marks it as a first-level core data group;

[0078] If δ i ∈[δ1,δ2], the system determines that the core index of the data group is medium and marks it as a secondary core data group;

[0079] If δ i >δ2, the system determines that the core index of the data group is high and marks it as a third-level core data group;

[0080] Through the above technical solution, this implementation calculates the core index δ of all data sets i They are compared with the preset core index threshold interval [δ1, δ2] respectively. Through this comparison method, the core index δ of all data groups can be i The data assessment module evaluates and grades different core data groups based on accurate data, which can avoid the situation where the evaluation results of core data are not objective, accurate or biased due to personal bias in human evaluation or lack of professional knowledge and skills required to fully understand data risks, thus leading to loopholes in the classification of core data groups.

[0081] The encryption process of the data encryption module includes:

[0082] When a data group is judged to be a first-level core data group, AI will encrypt it with a fixed 6-digit password and facial recognition;

[0083] When a data group is judged to be a secondary core data group, AI will encrypt it with a fixed 6-digit password, facial recognition, and IP restrictions;

[0084] When a data group is judged to be a third-level core data group, AI will encrypt it with a 6-digit dynamic password, facial recognition, IP restrictions, and identity verification;

[0085] Through the above technical solution, this example can improve data security and privacy by formulating different levels of encryption methods for core data groups of different levels. Moreover, since the classification of core data groups is classified according to accurate data information through the data evaluation module, it can avoid the situation where there are loopholes in the classification of core data groups due to personal bias or lack of professional knowledge and skills required to fully understand data risks in human evaluation, thereby ensuring the security of core data after encryption, and ensuring the security, integrity and availability of enterprise data through comprehensive data protection measures.

[0086] See also Figure 2 As shown, the management process of the data security assessment management system includes:

[0087] S1: Store all types of data groups within the enterprise and the past usage records of all data groups through the data storage module;

[0088] S2: Calculate the sensitivity of different data groups according to the data information in the data storage record through the data processing module;

[0089] S3: Compare and analyze the sensitivity of different data groups with the preset sensitivity threshold through the data analysis module, and determine whether the data groups of different categories belong to the core data group according to the analysis results;

[0090] S4: evaluating and grading some of the data groups determined as core data groups in the data analysis module through the data evaluation module;

[0091] S5: Encrypting data groups of different levels according to the evaluation results of the data evaluation module through the data encryption module;

[0092] Through the above technical solution, this embodiment provides a management process of a data security assessment management system. First, the data storage module is used to store all types of data groups in the enterprise and the past use records of all data groups. Then, the data processing module is used to calculate the sensitivity of different data groups according to the data information in the data storage records. Then, the data analysis module is used to compare and analyze the sensitivity of different data groups with the preset sensitivity threshold, and according to the analysis results, it is determined whether the data groups of different categories belong to the core data group, and the data evaluation module is used to evaluate and grade some data groups determined as core data groups in the data analysis module. Finally, the data encryption module is used to encrypt the data groups of different levels according to the evaluation results of the data evaluation module.

[0093] Through such a setting, after multi-layer processing of different data groups, not only can an accurate judgment be made on whether the data group is core data, but the core data can also be accurately evaluated and graded through the data evaluation module. After the evaluation and grading, different levels of encryption methods can be formulated for core data groups of different levels to improve data security and privacy, thereby avoiding personal bias in human evaluation, resulting in objective, inaccurate or biased evaluation results for core data groups, which in turn leads to loopholes in the grading of core data groups, making the data in the core data groups at risk of being leaked.

[0094] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A data security assessment management system based on artificial intelligence, It is characterized in that The system comprises: The data storage module is used to store all types of data groups within the enterprise and the past usage records of all data groups; A data processing module, used to calculate and obtain the sensitivity of different data groups based on the data information in the data storage records; The data analysis module is used to compare and analyze the sensitivity of different data groups with the preset sensitivity threshold, and determine whether different types of data groups belong to the core data group according to the analysis results; A data evaluation module is used to evaluate and classify some data groups that are determined as core data groups in the data analysis module; The data encryption module encrypts data groups of different levels according to the evaluation results of the data evaluation module.

2. According to claim 1, a data security assessment management system based on artificial intelligence, It is characterized in that The usage records stored in the data storage module include the access volume of different data groups, the allowed access IP and the current encryption level.

3. According to claim 1, a data security assessment management system based on artificial intelligence, It is characterized in that The processing process of the data processing module includes: By formula Calculate the sensitivity μ of the i-th data group i ; Among them, i is a data group of any category, gr i is the storage amount of personal information data in the i-th data group, jy i is the storage volume of operating data in the i-th data group; zscq i is the storage amount of intellectual property data in the i-th data group; x1, x2 and x3 are the first weight coefficients, and θ is the error influence coefficient, which is set according to empirical fitting.

4. According to claim 3, a data security assessment management system based on artificial intelligence, It is characterized in that The analysis process of the data analysis module includes: By taking the sensitivity μ of all data sets i Compare with the preset sensitivity threshold μ x ; If all μ i All less than μ x , the system evaluates that the sensitivity of all data groups is small, and determines that the data group is a non-core data group; If any μ i Greater than μ x The system evaluates that the sensitivity of the data group is high, determines that the data group is a core data group, and evaluates and grades it through the data evaluation module.

5. According to claim 4, a data security assessment management system based on artificial intelligence, It is characterized in that The evaluation and grading process of the data evaluation module includes: First, all the data groups that are judged to be core data groups are listed; And through the formula Calculate the core index δ of the i-th data group i ; Among them, a is any day in the past period of time, b is the total number of days in the past period of time, fw ai is the total number of visits to the i-th data group on the a-th day in the past period of time, fw a0 is the number of invalid accesses of the i-th data group on the a-th day in the past period of time, fw 0i The preset number of visits for the i-th data group, yx i is the number of IP addresses allowed to access the i-th data group, yx t yx i The standard value of f c It is the adjustment coefficient comparison table function. According to the empirical data (β i The influence of the value range of β on the important index is obtained based on the test data. i is the current encryption level of the i-th data group, y1 and y2 are the second weight coefficients.

6. According to claim 5, a data security assessment management system based on artificial intelligence, It is characterized in that The evaluation and grading process of the data evaluation module also includes: By taking all the core indexes δ of all data sets i Respectively with the preset core index threshold interval [δ 1 , δ 2 ] for comparison; If δ i <δ 1 , the system determines that the core index of this data group is low and marks it as a first-level core data group; If δ i ∈[δ 1 , δ 2 ], the system determines that the core index of the data group is medium and marks it as a secondary core data group; If δ i >δ 2 , the system determines that the core index of this data group is high and marks it as a third-level core data group.

7. According to claim 6, a data security assessment management system based on artificial intelligence, It is characterized in that The encryption process of the data encryption module includes: When a data group is judged to be a first-level core data group, AI will encrypt it with a fixed 6-digit password and facial recognition; When a data group is judged to be a secondary core data group, AI will encrypt it with a fixed 6-digit password, facial recognition, and IP restrictions; When a data group is judged to be a third-level core data group, artificial intelligence will perform a 6-digit dynamic password, facial recognition, IP restriction, and identity authentication encryption.

8. According to claim 1, a data security assessment management system based on artificial intelligence, It is characterized in that The management process of the data security assessment management system includes: S1: Store all types of data groups within the enterprise and the past usage records of all data groups through the data storage module; S2: Calculate the sensitivity of different data groups according to the data information in the data storage record through the data processing module; S3: Compare and analyze the sensitivity of different data groups with the preset sensitivity threshold through the data analysis module, and determine whether the data groups of different categories belong to the core data group according to the analysis results; S4: evaluating and grading some of the data groups determined as core data groups in the data analysis module through the data evaluation module; S5: The data encryption module encrypts data groups of different levels according to the evaluation results of the data evaluation module.

Images