Information security intelligent management and control method and system based on big data

Abstract

The invention relates to the technical field of security management and control, in particular to an information security intelligent management and control method and system based on big data, and the method comprises the steps: distributing a key length for each piece of supervision information according to the security level of various pieces of supervision information; each kind of supervision information at each moment is used as a node, the prediction effectiveness of historical nodes on the supervision information of any node is used as the edge weight of a directed edge, pointing to the any node, of the historical nodes, a prediction relation graph is obtained, and the historical nodes are all nodes at multiple adjacent moments before the moment corresponding to the any node; calculating the leakage risk of each piece of supervision information at any moment; and giving an alarm when the leakage risk of any supervision information at any moment is greater than a risk threshold. According to the technical scheme, the risk of information leakage can be reduced.

Description

Technical Field

[0001] The present application relates to the field of security management and control technology, and in particular to an information security intelligent management and control method and system based on big data. Background Art

[0002] With the rapid development of computer technology, more and more information is transmitted through the Internet, and with it comes the issue of information security. How to supervise information security and take timely protective measures for information that is at risk of leakage is an issue that needs to be addressed urgently.

[0003] At present, a patent application document with publication number CN111784989A discloses an information security management system based on big data, which includes a data acquisition module, a big data analysis module, and a security prompt module; the big data acquisition module is used to collect status data of equipment in the computer room and environmental data of the computer room, and send the status data and environmental data to the big data analysis module; the big data analysis module is used to determine whether the value of the status data and / or environmental data is within a preset threshold range, and send the judgment result to the security prompt module; the security prompt module is used to receive the judgment result, and if the judgment result is that the value of the status data and / or environmental data is not within the preset threshold range, the security prompt module issues a security prompt to the computer room manager.

[0004] The above method realizes information security management in the data storage terminal by judging whether the equipment status data and environmental data in the computer room are within the preset threshold range. However, the above method ignores the risk of information leakage during information transmission outside the storage terminal and cannot monitor information security in real time, resulting in a greater risk of information leakage. Summary of the invention

[0005] In order to solve the technical problem of high risk of information leakage during information transmission, the present application provides an information security intelligent management and control method and system based on big data, which can reduce the risk of information leakage.

[0006] In the first aspect of the present application, a method for intelligent information security management and control based on big data is provided, and the management and control method includes: assigning a key length to each piece of regulatory information according to the security level of multiple regulatory information, wherein the regulatory information includes equipment operating parameters collected by sensors; taking each type of regulatory information at each moment as a node, and taking the predicted effectiveness of the historical node for the regulatory information of any node as the edge weight of the directed edge from the historical node to the arbitrary node, to obtain a prediction relationship graph, wherein the historical node is all nodes at multiple adjacent moments before the corresponding moment of any node; calculating the leakage risk of each piece of regulatory information at any moment, and the prediction validity of the historical node for the regulatory information of any node at each moment is obtained. Regulatory Information Risk of leakage for: ;in, For regulatory information The key length, is the maximum key length of all regulatory information, To predict the time in the relationship diagram Regulatory Information The number of in-degree edges of ; In-degree edge The starting key length, In-degree edge The edge rights, is the sum of the edge weights of all in-degree edges, where the in-degree edges point to the time in the prediction relationship graph. Regulatory Information Directed edge corresponding to the node; in response to the risk of leakage of any regulatory information at any time being greater than the risk threshold, an alarm is issued.

[0007] Firstly, a key length is assigned to each piece of regulatory information according to its security level. The higher the security level of the regulatory information, the larger the corresponding key length. In the process of information transmission, each piece of regulatory information at each moment is taken as a node. One moment contains multiple nodes. For any node, all nodes at multiple adjacent moments before the corresponding moment of the node are taken as historical nodes, and the predictive validity of the historical node on the regulatory information of the node is taken as the edge weight of the directed edge from the historical node to the node to obtain a prediction relationship graph. The prediction relationship graph can clearly and accurately reflect the prediction relationship of the regulatory information between each node. In the prediction relationship graph, the leakage risk of each piece of regulatory information at any moment is accurately quantified by combining the two aspects of information leakage caused by the cracking of its own key and the prediction of regulatory information caused by the leakage of regulatory information of historical nodes. In response to the leakage risk of any regulatory information at any moment being greater than the risk threshold, an alarm is issued to ensure the information security of various regulatory information.

[0008] Preferably, allocating key lengths to respective regulatory information according to security levels of multiple types of regulatory information includes: setting a minimum key length, and taking the product of the security level of the regulatory information and the minimum key length as the key length of the regulatory information.

[0009] A key length is assigned to each piece of regulatory information according to its security level, and a larger key length is assigned to regulatory information with a higher security level, ensuring that regulatory information with a higher security level has a higher encryption complexity.

[0010] Preferably, the method for obtaining the prediction validity includes: inputting the supervision information of each historical node into a regression model, outputting the supervision prediction value of the arbitrary node, and taking the absolute value of the difference between the supervision prediction value and the supervision information of the arbitrary node as the initial error; after setting the supervision information of any historical node to 0, recalculating the absolute value of the difference between the supervision prediction value and the supervision information of the arbitrary node to obtain the reset error; the prediction validity of the historical node is positively correlated with the difference between the reset error and the initial error.

[0011] Accurately quantify the predictive effectiveness of each historical node in predicting the regulatory information of any node. The greater the predictive effectiveness, the more accurate the regulatory information of the node can be predicted based on the historical node.

[0012] Preferably, adjacent moments Regulatory Information Historical Nodes The predictive validity of for: , For historical nodes The reset error, is the initial error.

[0013] Preferably, the risk threshold is negatively correlated with the harmfulness of leakage of any regulatory information at any time.

[0014] For regulatory information whose leakage could be highly harmful, the risk threshold should be set at a smaller value so that alarms can be issued in a timely manner to ensure information security.

[0015] Preferably, the time Regulatory Information The danger of leakage for: ; To predict the time in the relationship diagram Regulatory Information The number of out-degree edges of ; Out-degree edge The security level of the termination point, Out-degree edge The edge weight of the out-degree edge is the starting point of the prediction relationship graph at time Regulatory Information Directed edges corresponding to nodes.

[0016] Out-degree edge The larger the edge weight, the more Regulatory Information Predict outgoing edges The greater the predictive validity of the end-point regulatory information, the greater the Regulatory Information The leakage will lead to out-of-degree edge The regulatory information of the termination point is accurately predicted, so the time Regulatory Information The greater the risk of leakage, the more harmful it is. Regulatory Information All out-degree edges can be accurately quantified at the time Regulatory Information The hazard of leakage.

[0017] Preferably, the time Regulatory Information Risk threshold for: , For the moment Regulatory Information The hazard of leakage, is the baseline threshold.

[0018] Preferably, after the alarm is issued, the management and control method also includes: in response to the leakage risk of any regulatory information at any time being greater than a risk threshold, the security level of the regulatory information and the leakage risk are added together and rounded up, and the product of the rounded-up result and the minimum key length is used as the key length of the regulatory information; otherwise, the key length of the regulatory information is kept unchanged.

[0019] After receiving the alarm information, for regulatory information with a leakage risk greater than the risk threshold, the key length of the regulatory information is increased, thereby increasing the encryption complexity of the regulatory information, reducing the leakage risk, and realizing intelligent management and control of information security.

[0020] In the second aspect of the present application, there is also provided an information security intelligent management and control system based on big data, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an information security intelligent management and control method based on big data as described in the first aspect of the present application is implemented.

[0021] The technical solution of this application has the following beneficial technical effects: Firstly, a key length is assigned to each piece of regulatory information according to its security level. The higher the security level of the regulatory information, the larger the corresponding key length. In the process of information transmission, each piece of regulatory information at each moment is taken as a node. One moment contains multiple nodes. For any node, all nodes at multiple adjacent moments before the corresponding moment of the node are taken as historical nodes, and the prediction validity of the historical node on the regulatory information of the node is taken as the edge weight of the directed edge from the historical node to the node to obtain a prediction relationship graph. The prediction relationship graph can clearly and accurately reflect the prediction relationship of the regulatory information between each node. In the prediction relationship graph, the leakage risk of each piece of regulatory information at any moment is accurately quantified by combining the two aspects of information leakage caused by the cracking of its own key and the prediction of regulatory information caused by the leakage of regulatory information of historical nodes. In response to the leakage risk of any regulatory information at any moment being greater than the risk threshold, an alarm is issued to monitor information security in real time to ensure the information security of various regulatory information. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easy to understand. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a flow chart of an information security intelligent management and control method based on big data according to an embodiment of the present application; Figure 2 is a schematic diagram of a prediction relationship diagram according to an embodiment of the present application; Figure 3 It is a structural block diagram of an information security intelligent management and control system based on big data according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0024] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0025] According to the first aspect of the present application, the present application provides an intelligent information security management and control method based on big data. Figure 1 1 is a flow chart of an information security intelligent management and control method based on big data according to an embodiment of the present application. Figure 1 As shown, the information security intelligent management and control method based on big data includes steps S101 to S104, which are described in detail below.

[0026] S101, allocating a key length to each piece of supervision information according to the security level of the multiple pieces of supervision information.

[0027] In one embodiment, a large amount of supervision information will be generated at every moment in a smart park or a production enterprise. This supervision information will be transmitted between multiple communication terminals. The supervision information includes equipment operating parameters collected by sensors. The equipment operating parameters can be voltage values ​​collected by voltage sensors, current values ​​collected by current sensors, or concentration values ​​collected by gas sensors. And the security levels of different supervision information are different. The higher the security level, the greater the impact caused by the leakage of the corresponding supervision information. In order to ensure the information security of supervision information with different security levels, it is necessary to assign key lengths to each supervision information according to the security levels of various supervision information; the larger the key length, the higher the security of the corresponding supervision information.

[0028] Specifically, allocating a key length to each piece of regulatory information according to the security level of the multiple pieces of regulatory information includes: setting a minimum key length, and taking the product of the security level of the regulatory information and the minimum key length as the key length of the regulatory information, wherein the security level is a positive integer.

[0029] Among them, the key length is an integer multiple of the minimum key length. The value of the minimum key length is related to the encryption algorithm adopted. The encryption algorithm includes the RSA algorithm, the ECC algorithm and the ElGamal algorithm. For example, when the encryption algorithm adopts the RSA algorithm, the value of the minimum key length is 8, that is, in the RSA algorithm, the key length is an integer multiple of 8.

[0030] In this way, a key length is allocated to each piece of regulatory information according to its security level, and a larger key length is allocated to regulatory information with a higher security level.

[0031] S102, taking each piece of supervision information at each moment as a node, taking the predictive effectiveness of the historical node on the supervision information of any node as the edge weight of the directed edge from the historical node to the any node, and obtaining a prediction relationship graph, where the historical node is all the nodes at multiple adjacent moments before the corresponding moment of any node.

[0032] In one embodiment, the prediction relationship graph includes nodes and directed edges.

[0033] Take each supervision information at any time as a node, for example, The supervision information 1 is recorded as node , the moment The supervision information 2 is recorded as node If the types of regulatory information are shared Kind, then time Total nodes.

[0034] In the prediction relationship diagram, a node corresponds to a time and a value of supervision information; the historical nodes of a node are all nodes at multiple adjacent times before the corresponding time of the node, and the number of adjacent times is recorded as , then a node has There are directed edges between a node and each historical node. The starting point of the directed edge is the historical node, the end point is the node, and the edge weight of the directed edge is the predictive validity of the historical node on the supervisory information of the node; in other words, the edge weight of the directed edge is the predictive validity of the supervisory information at the starting point to the end point.

[0035] See also Figure 2 , is a schematic diagram of a prediction relationship diagram according to an embodiment of the present application. For the convenience of drawing, The value of is set to 2, which reduces the number of regulatory information types. The value of is set to 2, that is, one moment contains 2 nodes, and one node corresponds to 4 historical nodes; for the moment Regulatory Information Corresponding nodes , which has 4 in-degree edges and 4 out-degree edges, and the in-degree edges point to nodes The directed edge of For easy understanding, the node The in-degree edges of nodes are represented by dashed lines. The out-degree edges of the nodes are represented by solid lines; the directed edge graphs of other nodes are not shown. It can be understood that the other nodes also include 4 in-degree edges and 4 out-degree edges.

[0036] Among them, the prediction validity is obtained according to the regression model, and the method for obtaining the prediction validity includes: inputting the supervision information of each historical node into the regression model, outputting the supervision prediction value of the arbitrary node, and taking the absolute value of the difference between the supervision prediction value and the supervision information of the arbitrary node as the initial error; setting the supervision information of any historical node to 0, and recalculating the absolute value of the difference between the supervision prediction value and the supervision information of the arbitrary node to obtain the reset error, and the prediction validity of the historical node is positively correlated with the difference between the reset error and the initial error.

[0037] The regression model may be a polynomial model or a recurrent neural network, which is not limited here. For example, when the regression model is a recurrent neural network, its input is the time before any node corresponds to The time series composed of supervision information of adjacent moments is output as the supervision prediction value of any node; the recurrent neural network can adopt the network structure of LSTM or GRU.

[0038] It should be noted that in order to enable the regression model to accurately obtain the regulatory prediction value of any node, before obtaining the prediction validity of each historical node, it is necessary to train the regression model using the gradient descent method based on the regulatory information of the historical time period; The time series composed of the supervision information of adjacent moments is input into the trained regression model, which can accurately output the supervision prediction value of any node; the specific training process is a well-known technology for those skilled in the art and will not be repeated here.

[0039] Understandably, the adjacent moments The historical node corresponding to the regulatory information 2 For example, the initial error is the prediction effect of the supervision information of all historical nodes on the supervision information of any node; the reset error is the prediction effect of the supervision information of all historical nodes without considering the historical nodes. After that, the prediction effect of the supervision information in any node is calculated; if the reset error is greater than the initial error (that is, the difference between the reset error and the initial error is greater than 0), it means that the historical node is not considered The later prediction error becomes larger, and the historical nodes The more effective the prediction of regulatory information in any node, the more historical nodes On the contrary, if the reset error is not greater than the initial error (that is, the difference between the reset error and the initial error is less than or equal to 0), it means that the historical nodes are not considered. The prediction error becomes smaller and the historical nodes It cannot provide effective information for predicting the regulatory information in any node and is noise. Therefore, the historical node The predictive validity is 0.

[0040] Specifically, adjacent moments Regulatory Information Historical Nodes The predictive validity of for: , For historical nodes The reset error, is the initial error.

[0041] Thus, a node corresponds to Historical nodes are used to determine the predictive effectiveness of each historical node in predicting the regulatory information of the node. The greater the predictive effectiveness, the more accurate the regulatory information of the node can be predicted based on the historical node. The predictive effectiveness of the historical node is further used as the edge weight to complete the construction of the prediction relationship graph. The prediction relationship graph can clearly and accurately reflect the predictive relationship between the regulatory information of each node.

[0042] S103, calculating the leakage risk of each regulatory information at any time.

[0043] In one embodiment, each type of regulatory information is encrypted and transmitted according to its own key length, and a prediction relationship graph is constructed during the transmission process, and then the leakage risk of regulatory information at any time is monitored based on the prediction relationship graph. Regulatory information The risk of leakage comes from two aspects. First, Regulatory information The information leakage caused by the cracking of its own key, secondly, at all times Regulatory Information The corresponding regulatory information of the historical node is leaked, resulting in Regulatory information Therefore, when calculating the risk of regulatory information leakage at any time, the above two aspects need to be considered.

[0044] Specifically, the time Regulatory Information Risk of leakage for: ;in, For regulatory information The key length, is the maximum key length of all regulatory information, To predict the time in the relationship diagram Regulatory Information The number of in-degree edges of ; In-degree edge The starting key length, In-degree edge The edge rights, is the sum of the edge weights of all in-degree edges, where the in-degree edges point to the time in the prediction relationship graph. Regulatory Information Directed edges corresponding to nodes.

[0045] Among them, regulatory information The longer the key length, The larger the value, the more regulatory information The more difficult it is to crack your own key, the more Regulatory information The smaller the risk of information leakage due to the cracking of the key, It can accurately quantify the risk of information leakage caused by cracking of its own keys.

[0046] time Regulatory Information The in-degree edge of the prediction relationship graph points to the time Regulatory Information Directed edges corresponding to nodes; In-degree edge The edge rights, Used to reflect the in-degree edge Starting point to time Regulatory Information The normalized predictive validity of Used to quantify the in-degree edges The starting point is that the key is cracked, resulting in the in-degree edge The risk of starting point information leakage is weighted according to the normalized prediction effectiveness for the risk of starting point information leakage of all in-degree edges to obtain the leakage risk: In This part can accurately quantify the time caused by the leakage of regulatory information at historical nodes. Regulatory information Predicted risks.

[0047] In summary, the information leakage caused by the cracking of the key itself and the leakage of regulatory information at historical nodes caused the moment Regulatory information Two aspects are predicted to quantify the leakage risk of each type of regulatory information at any time.

[0048] S104, in response to the risk of leakage of any regulatory information at any time being greater than a risk threshold, an alarm is issued.

[0049] In one embodiment, if the time Regulatory Information The leakage risk is greater than the risk threshold, indicating that the moment Regulatory information The risk of leakage is high, and an early warning is issued to remind staff to strengthen supervision of information Security protection to avoid monitoring information during transmission The risk threshold is 0.7.

[0050] It should be noted that, since the key length of each regulatory information at different times is the same, combined with the calculation formula of leakage risk, it can be seen that the difference in leakage risk of the same regulatory information at different times is caused by the prediction validity (i.e., the edge weight of the directed edge). Regulatory information In terms of time, Regulatory information can be accurately predicted, The larger the time Regulatory Information The greater the risk of leakage.

[0051] In another embodiment, the harm caused by the leakage of any supervisory information at any time is different. Regulatory Information The leakage will cause the moment If the supervision information of the adjacent moments can be accurately predicted, it means that the moment Regulatory Information The leakage of information at other times will increase the risk of leakage of regulatory information at other times. Regulatory Information For regulatory information with a high risk of leakage, the risk threshold should be set at a lower value so that an alarm can be issued in time to ensure information security.

[0052] Specifically, the risk threshold is negatively correlated with the harmfulness of leakage of any regulatory information at any time. Regulatory Information The danger of leakage for: ; To predict the time in the relationship diagram Regulatory Information The number of out-degree edges of ; Out-degree edge The security level of the termination point, Out-degree edge The edge weight of the out-degree edge is the starting point of the prediction relationship graph at time Regulatory Information Directed edges corresponding to nodes.

[0053] Among them, the time Regulatory Information The out-degree edge is the starting point in the prediction relationship graph, and the time Regulatory Information Directed edge of The larger the edge weight, the more Regulatory Information Predict outgoing edges The greater the predictive validity of the regulatory information at the end point, the greater the Regulatory Information The leakage will lead to out-of-degree edge The regulatory information of the termination point is accurately predicted, so the moment Regulatory Information The greater the danger of leakage.

[0054] Specifically, the time Regulatory Information Risk threshold for: , For the moment Regulatory Information The hazard of leakage, is the benchmark threshold, where the value of the benchmark threshold is 0.6.

[0055] In this way, the leakage risk of any regulatory information at any time is monitored in real time, and when the leakage risk of any regulatory information at any time is greater than the risk threshold, an alarm is issued in time.

[0056] In one embodiment, after an alarm is issued, the management and control method also includes: in response to the risk of leakage of any regulatory information at any time being greater than a risk threshold, the security level of the regulatory information and the leakage risk are added together and rounded up, and the product of the rounded-up result and the minimum key length is used as the key length of the regulatory information; otherwise, the key length of the regulatory information is kept unchanged.

[0057] It is understandable that the greater the security level of the regulatory information, the longer the key length needs to be, and the greater the risk of leakage of the regulatory information, the longer the key length needs to be, so as to increase the encryption complexity of the regulatory information. When the risk of leakage of any regulatory information at any time is greater than the risk threshold, it means that the encryption complexity of the regulatory information needs to be increased. Since the value range of the leakage risk is 0-2, the security level of the regulatory information and the leakage risk are added and rounded up. The result of rounding up is a positive integer increased by 1 or 2. The product of the positive integer and the minimum key length is used as the key length of the regulatory information, thereby increasing the key length of the regulatory information. Conversely, when the risk of leakage of any regulatory information at any time is not greater than the risk threshold, it means that the encryption complexity of the regulatory information can ensure information security, and there is no need to adjust the key length of the regulatory information.

[0058] In this way, after receiving the alarm information, for the regulatory information whose leakage risk is greater than the risk threshold, the key length of the regulatory information is increased, thereby increasing the encryption complexity of the regulatory information, reducing the leakage risk, and realizing intelligent management and control of information security.

[0059] The above introduces the technical principles and implementation details of an information security intelligent management and control method based on big data of the present application through specific embodiments. First, a key length is assigned to each piece of regulatory information according to the security level of multiple regulatory information. The higher the security level of the regulatory information, the larger the corresponding key length; in the process of information transmission, each type of regulatory information at each moment is taken as a node, and a moment contains multiple nodes. For any node, all nodes at multiple adjacent moments before the corresponding moment of the node are taken as historical nodes, and the predicted validity of the historical node for the regulatory information of the node is taken as the edge weight of the directed edge from the historical node to the node, and a prediction relationship graph is obtained. The prediction relationship graph can clearly and accurately reflect the prediction relationship of the regulatory information between each node; in the prediction relationship graph, the two aspects of information leakage caused by the cracking of its own key and the prediction of regulatory information caused by the leakage of regulatory information of the historical node are comprehensively considered to accurately quantify the leakage risk of each type of regulatory information at any moment, and in response to the leakage risk of any regulatory information at any moment being greater than the risk threshold, an alarm is issued to ensure the information security of various regulatory information.

[0060] According to the second aspect of the present application, the present application also provides an information security intelligent management and control system based on big data. Figure 3 1 is a block diagram of an information security intelligent management and control system based on big data according to an embodiment of the present application. Figure 3 As shown, the system 50 includes a processor and a memory, and the memory stores computer program instructions. When the computer program instructions are executed by the processor, a method for intelligent information security management and control based on big data according to the first aspect of the present application is implemented. The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, whose settings and functions are known in the art, so they are not described here.

[0061] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in this application may be implemented by computer-readable / executable instructions stored or otherwise maintained by such a computer-readable medium.

[0062] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0063] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. An intelligent information security management and control method based on big data, characterized in that: The control method includes: assigning a key length to each piece of regulatory information according to a security level of multiple pieces of regulatory information, the regulatory information including equipment operating parameters collected by sensors; Each type of supervision information at each moment is taken as a node, and the prediction validity of the historical node on the supervision information of any node is taken as the edge weight of the directed edge from the historical node to the arbitrary node, so as to obtain a prediction relationship graph, where the historical node is all the nodes at multiple adjacent moments before the corresponding moment of any node; Calculate the leakage risk of each regulatory information at any time. Regulatory Information Risk of leakage for: ; For regulatory information The key length, is the maximum key length of all regulatory information, To predict the time in the relationship diagram Regulatory Information The number of in-degree edges of ; In-degree edge The starting key length, In-degree edge The edge rights, is the sum of the edge weights of all in-degree edges, where the in-degree edges point to the time in the prediction relationship graph. Regulatory Information Directed edges corresponding to nodes; In response to the risk of leakage of any regulatory information at any time being greater than the risk threshold, an alarm is issued.

2. According to the big data-based information security intelligent management and control method of claim 1, it is characterized in that: The allocating key lengths to each piece of regulatory information according to the security levels of the multiple pieces of regulatory information includes: setting a minimum key length, and taking the product of the security level of the regulatory information and the minimum key length as the key length of the regulatory information.

3. According to the big data-based information security intelligent management and control method of claim 1, it is characterized in that: Methods for obtaining predictive validity include: Inputting the supervision information of each historical node into the regression model, outputting the supervision prediction value of the arbitrary node, and taking the absolute value of the difference between the supervision prediction value of the arbitrary node and the supervision information as the initial error; After setting the supervision information of any historical node to 0, the absolute value of the difference between the supervision prediction value and the supervision information of the arbitrary node is calculated again to obtain the reset error; The prediction validity of the historical node is positively correlated with the difference between the reset error and the initial error.

4. According to the big data-based information security intelligent management and control method of claim 3, it is characterized in that: Adjacent moments Regulatory Information Historical Nodes The predictive validity of for: , For historical nodes The reset error, is the initial error.

5. According to the big data-based information security intelligent management and control method of claim 1, it is characterized in that: The risk threshold is negatively correlated with the harmfulness of the leakage of any regulatory information at any time.

6. The method for intelligent information security management and control based on big data according to claim 5 is characterized in that: time Regulatory Information The danger of leakage for: ; To predict the time in the relationship diagram Regulatory Information The number of out-degree edges of ; Out-degree edge The security level of the termination point, Out-degree edge The edge weight of the out-degree edge is the starting point of the prediction relationship graph at time Regulatory Information Directed edges corresponding to nodes.

7. The method for intelligent information security management and control based on big data according to claim 5 is characterized in that: time Regulatory Information Risk threshold for: , For the moment Regulatory Information The hazard of leakage, is the baseline threshold.

8. The method for intelligent information security management and control based on big data according to claim 1 is characterized in that: After the alarm is issued, the control method further includes: In response to the leakage risk of any regulatory information being greater than a risk threshold at any time, the security level of the regulatory information and the leakage risk are added and then rounded up, and the product of the rounded-up result and the minimum key length is used as the key length of the regulatory information; On the contrary, the key length of the supervision information remains unchanged.

9. An information security intelligent management and control system based on big data, characterized in that: It includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an information security intelligent management and control method based on big data is implemented according to any one of claims 1 to 8.

Images