A network and data security analysis and supervision system based on artificial intelligence

Through the artificial intelligence-based network and data security analysis supervision system, the risk assessment and secondary analysis modules are used to evaluate the security risks and leakage risks of network equipment, and automatically handle it, solving the problem that network data protection is vulnerable to hackers in the existing technology and The issue of the spread of security risks has achieved accurate judgment and timely processing of security risks of network equipment to ensure the security of data and network.

CN118677707BActive Publication Date: 2024-11-08FUJIAN ZHONGXIN NET SAFETY INFORMATION TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411161702.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-11-08
Estimated Expiration
2044-08-23

AI Technical Summary

Technical Problem

Existing network data protection methods are prone to hackers to steal login information, leading to data security threats, and the security risks between networked devices are easily spread, leading to large-scale data leakage and network paralysis.

Method used

Design a network and data security analysis and supervision system based on artificial intelligence, and obtain and analyze the login information, storage information and access information of network equipment through parameter intelligence acquisition module, risk assessment module and secondary analysis module, and evaluate security risks and leakage. Risks and are automatically processed through processing modules, such as network disconnection, anti-virus and protection system updates.

Benefits of technology

It realizes accurate judgment and timely processing of network equipment security risks, prevents data leakage and network paralysis, and ensures data and network security.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118677707B_ABST
    Figure CN118677707B_ABST
Patent Text Reader

Abstract

The present invention discloses a network and data security analysis and supervision system based on artificial intelligence, which belongs to the field of network data security, including a parameter intelligent acquisition module, which acquires relevant parameter information generated by network equipment; a risk assessment module, which analyzes and judges according to the acquired relevant parameter information, and confirms whether the network equipment has security risks; a secondary analysis module, which further calculates and analyzes the network equipment with security risks, so as to judge whether the data has the risk of leakage; a processing module, which performs corresponding processing on the network equipment according to the results of the secondary analysis module analysis. The present invention can judge whether the network equipment has data security risks according to the login information and the storage information, and then further analyzes according to the secondary analysis module to judge whether the network equipment has the risk of data leakage, so that the security risks of the network equipment can be judged more accurately, thereby ensuring data security.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of network data security, and specifically relates to a network and data security analysis and supervision system based on artificial intelligence. Background Art

[0002] The existing method of protecting network data is to set a login password. When users access data, they can only access the data after entering the correct login password. Although this method can ensure data security to a certain extent, with the development of science and technology, by obtaining the user's login information, they can enter the corresponding network device to browse the data, which poses a threat to data security. In addition, since most networks are networked, when the data information of a network device encounters a security risk, the data information in other networked devices is also easily affected, which will not only cause large-scale data loss, but also cause multiple network devices to shut down, thereby affecting the normal operation of the network equipment.

[0003] The existing method of protecting network data is to set a login password. When users access data, they can only access the data after entering the correct login password. Although this method can ensure data security to a certain extent, with the development of science and technology, hackers can easily steal users' login information and hack into network devices to steal data. In addition, since most networks are connected, when the data information of a network device is hacked, the data information in other networked devices is also easily affected, which will not only cause large-scale data leakage, but also cause large-scale paralysis of network devices, thereby affecting the normal operation of network devices. Summary of the invention

[0004] The purpose of the present invention is to provide a network and data security analysis and supervision system based on artificial intelligence to solve the problems faced in the above-mentioned background technology.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A network and data security analysis and supervision system based on artificial intelligence, the system comprising:

[0007] A parameter intelligent acquisition module, which is used to acquire relevant parameter information generated by network devices;

[0008] A risk assessment module, which performs analysis and judgment based on the relevant parameter information obtained to confirm whether there are security risks in the network equipment; a secondary analysis module, which is used to perform further calculation and analysis on the network equipment with security risks, so as to analyze whether there is a risk of data leakage; a processing module, which is used to perform corresponding processing on the network equipment according to the results of the analysis by the secondary analysis module.

[0009] Furthermore, the relevant parameter information includes login information, storage information, data download flow information and access information.

[0010] Furthermore, the risk assessment module performs analysis and judgment in the following manner:

[0011] By formula Find the risk status value of network equipment ;

[0012] The risk profile value that will be obtained Pre-set risk thresholds in the system For comparison:

[0013] when When the network device is detected, it is considered that there is a security risk;

[0014] in, as well as is the system preset weight coefficient, is the login risk factor, is the equipment system risk factor.

[0015] Furthermore, the method for obtaining the login risk coefficient and the device system risk coefficient is:

[0016] According to the login information in the network device, get the time difference between the current login time and the last login time of the id , the distance difference between the IP address of this login and the IP address of the last login , the duration of this login and the number of login attempts during this time ;

[0017] Through the following formula Determine the login risk factor , is the average time difference between each login interval;

[0018] Based on the information stored in the network device, obtain the number of virus attacks on the system of the network device in the period before the current login. , the number of error messages in the system log of the network device , warning message times , the number of new service items in the network device service process list that do not belong to the normal operation scope of the device q;

[0019] Through the following formula Derive the risk factor of the equipment system .

[0020] Furthermore, the method for the secondary analysis module to perform calculation analysis is:

[0021] When there is a security risk in the network equipment, According to the data download flow information and access information, a curve of the data download flow of the data stored in the network device over time is drawn up. ;

[0022] Then obtain the leakage anomaly value of the network device , , and will leak outliers The system preset abnormal threshold Make a comparison;

[0023] when When the data is detected, it is judged that there is a risk of data leakage;

[0024] in, The number of clicks in which the ID in the access information attempts to access data beyond its own access permissions. The time-varying curve of the standard data download flow set for the system. For preset cycle within Maximum value, For preset cycle within Minimum value, It is the preset reference value.

[0025] Furthermore, the method in which the processing module performs corresponding processing on the network device according to the analysis result is:

[0026] when When the network device is disconnected from other network devices, the access ID is forced to pop up;

[0027] when At this time, the network device is disinfected and the processing module determines whether the protection system of the network device needs to be updated according to the risk status value.

[0028] Furthermore, the method by which the processing module determines whether it is necessary to update the protection system of the network device according to the risk status value is:

[0029] Get multiple risk status values ​​obtained in the preset update within the preset update cycle ;

[0030] By formula Get the updated judgment value ;

[0031] when When the protection system is updated;

[0032] in, is the number of risk status values ​​obtained within the preset update cycle, and , is the risk status value currently obtained within the preset period, is the judgment function, when hour, ,when hour, , The update judgment threshold preset by the system.

[0033] Beneficial effects of the present invention:

[0034] The present invention can determine whether there are data security risks in the network device based on the login information and storage information of the network device, and then perform further analysis and calculation based on the secondary analysis module to determine whether the network device with security risks has the risk of data leakage. In this way, the security risks of the network device can be judged more accurately to ensure data security; when the network device has a leakage risk or a security risk, the processing module can automatically perform corresponding network disconnection, virus disinfection, update and other processing on the network device according to the analysis results, so as to ensure the security of the network and data in time.

[0035] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0037] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0038] 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.

[0039] In one embodiment, an artificial intelligence-based network and data security analysis and supervision system is disclosed, such as Figure 1As shown, the regulatory system includes:

[0040] A parameter intelligent acquisition module is used to acquire relevant parameter information generated by network devices, and the relevant parameter information includes login information, storage information, data download flow information and access information;

[0041] The risk assessment module analyzes and determines whether there are security risks in the network equipment based on the acquired relevant parameter information;

[0042] Secondary analysis module: The secondary analysis module is used to further calculate and analyze network devices with potential security risks, so as to determine whether there is a risk of data leakage;

[0043] The processing module is used to perform corresponding processing on the network device according to the analysis result of the secondary analysis module.

[0044] Through the above technical scheme, the present application can determine whether the network device has a security risk of intrusion based on the login information and storage information of the network device, and then perform further analysis and calculation based on the secondary analysis module to determine whether the network device with security risks has a risk of data leakage. In this way, the security risks of the network device can be judged more accurately, thereby ensuring the data security in the network device; when it is found that there is a risk of data leakage or a security risk, the processing module can automatically perform corresponding network disconnection, antivirus, update and other processing on the network device according to the analysis results, so as to ensure the security of the network and data in time.

[0045] As an implementation of the present invention, the method for the risk assessment module to perform analysis and judgment is:

[0046] According to the login information in the network device, get the time difference between the current login time and the last login time of the id , the distance difference between the IP address of this login and the IP address of the last login , the duration of this login and the number of login attempts during this time ;

[0047] Through the following formula Determine the login risk factor , is the average time difference between each login interval;

[0048] Based on the information stored in the network device, obtain the number of virus attacks on the system of the network device in the period before the current login. , the number of error messages in the system log of the network device , warning message times , the number of new service items in the network device service process list that do not belong to the normal operation scope of the device q;

[0049] Through the following formula Derive the risk factor of the equipment system ;

[0050] Then through the formula Find the risk status value of network equipment ;

[0051] The risk profile value that will be obtained Pre-set risk thresholds in the system For comparison:

[0052] when When the network device is detected, it is considered that there is a security risk;

[0053] in, as well as is the system preset weight coefficient, is the login risk factor, is the equipment system risk factor.

[0054] Through the above technical solution, this embodiment provides a specific method for the risk assessment module to determine whether there is a security risk in the network device. First, the login risk coefficient of the network device is obtained. According to the login information in the network device, the time difference between the current login time and the last login time of the id is obtained. , the distance difference between the IP address of this login and the IP address of the last login , the duration of this login and the number of login attempts during this time , and then by the formula Determine the login risk factor , is the average time difference between each login. Generally speaking, when the time difference between the current login time and the last login time of the same ID is closer to the average time difference between the ID's historical logins, the higher the security of this login. The smaller the value of is, the lower the security of this login is. The larger the value, the shorter the login time and the number of login attempts, the greater the possibility that the login is for the user himself. The smaller the value, the safer the login is, and the lower the security risk of the network device is. Then, the risk factor of the device system is obtained, and the number of virus attacks on the network device in the period before the current login is obtained based on the stored information in the network device. , the time range can be manually determined, the number of error messages in the system log of the network device , warning message times , the number of new service items in the network device service process list that do not belong to the normal operation scope of the device q, and then through the following formula Derive the risk factor of the equipment system Generally speaking, when a device is frequently attacked by viruses, it means that the network device is more likely to leak data. Similarly, if the number of error messages and warning messages in the system log is significantly higher than normal, it means that the risk value is greater. When the network device is running normally, its service and process list generally only shows service activities in the commonly used operation scope. When new service items that do not belong to the normal operation scope of the device appear in the service process list, there may be security risks. The more new service items there are, the greater the data security risk. Therefore, through the formula Derive the risk factor of the equipment system , the larger the value, the lower the security of the network device. Finally, through the formula Find the risk status value of network equipment , the equipment system risk coefficient obtained above And the login risk factor Comprehensive analysis can more accurately determine whether there are any abnormalities in the security risks of network devices, so the risk status value obtained can be Pre-set risk thresholds in the system For comparison: When the network device is detected, it is considered that there is a security risk. At this time, the network device needs to be further analyzed and processed to ensure the security of network data. Through this technical solution, a comprehensive analysis can be performed based on the login risk factor when logging on the network device and the device system risk factor of the network device to determine whether the network device has a security risk, thereby reducing the occurrence of data leakage.

[0055] In the above technical solution, the average time difference between each login interval is The system preset weight coefficient can be obtained based on historical data as well as , risk status thresholds pre-set in the system All of these can be determined based on empirical data and will not be described in detail here.

[0056] As an embodiment of the present invention, the method for the secondary analysis module to perform calculation analysis is:

[0057] When there is a security risk in the network equipment, According to the data download flow information and access information, a curve of the data download flow of the data stored in the network device over time is drawn up. ;

[0058] Then obtain the leakage anomaly value of the network device , , and will leak outliers The system preset abnormal threshold Make a comparison;

[0059] when When the data is detected, it is judged that there is a risk of data leakage;

[0060] in, The number of clicks in which the ID in the access information attempts to access data beyond its own access permissions. The time-varying curve of the standard data download flow set for the system. For preset cycle within Maximum value, For preset cycle within Minimum value, It is the preset reference value.

[0061] Through the above technical solution, this embodiment provides a specific method for the secondary analysis module to determine whether there is a data leakage risk in the network device with potential security risks. Generally speaking, after the user accesses the data, there will be a normal data download flow. When the download flow in a certain period of time is compared with the baseline of the normal download flow, there may be data leakage. Therefore, this embodiment will detect the network device in a preset period of time when there is a security risk. The preset period can be considered to be certain, and according to the data download flow information and access information, a curve of the data download flow of the data stored in the network device over time is drawn up. , through the formula Obtaining leakage anomalies of network devices , from the formula It can be seen that the greater the difference between the current data download flow accumulation and the preset standard data download flow accumulation, the greater the possibility of abnormality. From the formula It can be seen that the greater the difference between the maximum slope change and the minimum slope change of the download traffic within the preset time period, the greater the possibility of a surge, which means the greater the possibility of abnormality. In addition, if the number of clicks by the user ID trying to access modules beyond its own access rights after entering the database is higher, the greater the possibility of abnormality. Therefore, through the formula Conduct a comprehensive analysis to determine whether there is a risk of data leakage in network devices. Greater than the system preset abnormal threshold In this way, network devices with potential security risks can be further analyzed to determine whether they have data leakage risks, which can reduce misjudgments and make the judgment results more accurate, thereby effectively ensuring data security.

[0062] In the above technical solution, the curve of the standard data download flow rate set by the system over time Can be formulated based on historical data and preset reference values , System preset abnormal threshold It can be formulated based on empirical data, which will not be described in detail here.

[0063] As an implementation mode of the present invention, the method in which the processing module performs corresponding processing on the network device according to the analysis result is:

[0064] when When the network device is disconnected from other network devices, the access ID is forced to pop up;

[0065] when At this time, the network device is disinfected, and the processing module determines whether the protection system of the network device needs to be updated according to the risk status value;

[0066] The updating method is: within the preset update cycle, obtain multiple risk status values ​​obtained in the preset update ;

[0067] By formula Get the updated judgment value ;

[0068] when When the protection system is updated;

[0069] in, is the number of risk status values ​​obtained within the preset update cycle, and , is the risk status value currently obtained within the preset update cycle, is the judgment function, when hour, ,when hour, , The update judgment threshold preset by the system.

[0070] Through the above technical solution, this embodiment provides a specific method for the processing module to perform corresponding processing on the network device according to the analysis result. When the data is leaked, it is judged that there is a risk of data leakage. In order to ensure data security and reduce data leakage in a timely manner, the network connecting the network device to other network devices is cut off, and the access ID is forced to pop up. This can prevent the access user from continuing to obtain data and make the network device independent of other network devices to avoid affecting other devices. , it means that there are potential safety hazards in the device, but there is no risk of leakage. In this case, the network device should be disinfected in time. It is also determined whether the protection system of the network device needs to be updated. The method for determining whether to update is as follows: within the preset update cycle, obtain multiple risk status values ​​obtained in the preset update. , through the formula Get the updated judgment value ,when When , the protection system is updated; from the formula It can be obtained that the risk status value fluctuates within the preset update cycle. The smaller the fluctuation value, the more stable the protection function of the protection system. It indicates the difference between the risk status value obtained this time and the risk status value obtained last time. When When the difference is large, it means that the system protection function is weaker, and when the evaluation value is updated Exceeding the preset update judgment threshold When the protection system is updated, the data security of network devices can be guaranteed in time.

[0071] In the above technical solution, the preset update cycle time can be determined manually based on historical data, and the system preset update judgment threshold It is determined based on empirical data and will not be described in detail here.

[0072] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A network and data security analysis and supervision system based on artificial intelligence, It is characterized in that The system comprises: A parameter intelligent acquisition module, which is used to acquire relevant parameter information generated by network devices, wherein the relevant parameter information includes login information, storage information, data download flow information, and access information; A risk assessment module, which analyzes and determines whether there are security risks in the network equipment based on the acquired relevant parameter information; A secondary analysis module, which is used to perform further calculation and analysis on network devices with potential security risks, so as to determine whether there is a risk of data leakage; A processing module, the processing module is used to perform corresponding processing on the network device according to the analysis result of the secondary analysis module; The method for the secondary analysis module to perform calculation and analysis is: when there is a potential safety hazard in the network equipment, According to the data download flow information and access information, a curve of the data download flow of the data stored in the network device over time is drawn up. ; Then obtain the leakage anomaly value of the network device , , and will leak outliers The system preset abnormal threshold Make a comparison; when When the data is detected, it is judged that there is a risk of data leakage; in, The number of clicks in which the ID in the access information attempts to access data beyond its own access permissions. The time-varying curve of the standard data download flow set for the system. is the slope value of the download flow, For preset cycle within Maximum value, For preset cycle within Minimum value, is the preset reference value; The method for analyzing and judging the risk assessment module is: Find the risk status value of network equipment ; The risk profile value that will be obtained Pre-set risk thresholds in the system For comparison: when When the network device is detected, it is considered that there is a security risk; in, as well as is the system preset weight coefficient, is the login risk factor, is the equipment system risk factor; The method for obtaining the login risk coefficient and the device system risk coefficient is: according to the login information in the network device, obtain the time difference between the current login time and the last login time of the id , the distance difference between the IP address of this login and the IP address of the last login , the duration of this login and the number of login attempts during this time ; Through the following formula Determine the login risk factor , is the average time difference between each login interval; Based on the information stored in the network device, obtain the number of virus attacks on the system of the network device in the period before the current login. , the number of error messages in the system log of the network device , warning message times , the number of new service items in the network device service process list that do not belong to the normal operation scope of the device q; Through the following formula Derive the risk factor of the equipment system ; The method in which the processing module performs corresponding processing on the network device according to the analysis result is: When the network device is disconnected from other network devices, the access ID is forced to pop up; when At this time, the network device is disinfected and the processing module determines whether the protection system of the network device needs to be updated according to the risk status value.

2. According to claim 1, a network and data security analysis and supervision system based on artificial intelligence, It is characterized in that The method by which the processing module determines whether it is necessary to update the protection system of the network device according to the risk status value is: Get multiple risk status values ​​obtained in the preset update within the preset update cycle ; By formula Get the updated judgment value ; when When the protection system is updated; in, is the number of risk status values ​​obtained within the preset update cycle, and , is the risk status value currently obtained within the preset period, is the judgment function, when hour, ,when hour, , The update judgment threshold preset by the system.