A network security situation awareness platform based on traffic monitoring

Through the network security situation awareness platform based on traffic monitoring, the problem of difficulty in accurately capturing and monitoring network traffic in network security perception is solved, and more efficient security risk identification and early warning is achieved, and analysis accuracy is improved.

CN118764323BActive Publication Date: 2024-11-05JIANGSU WANGQING SECURITY TECHNOLOGY CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411245584.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-11-05
Estimated Expiration
2044-09-06

AI Technical Summary

Technical Problem

Existing network security perception technologies are difficult to accurately capture and monitor network traffic in real time, resulting in limitations in abnormal identification and insufficient warning timeliness and accuracy of potential security risks.

Method used

Provide a network security situation awareness platform based on traffic monitoring, including traffic monitoring port acquisition module, traffic monitoring data set generation module, multi-port traffic data extraction module, traffic abnormality probability indicator generation module, traffic uniform distribution identification module and network security reminder The information generation module obtains and analyzes network traffic data through a traffic mirror, identifies abnormal patterns and generates network security reminder information.

Benefits of technology

It enhances the timeliness and accuracy of security warnings, improves the accuracy of user behavior analysis, and can promptly detect and warn of potential security risks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118764323B_ABST
    Figure CN118764323B_ABST
Patent Text Reader

Abstract

The present invention discloses a network security situation awareness platform based on flow monitoring, which relates to the technical field related to electric communication. The platform includes: obtaining multiple flow monitoring ports in a preset network area; generating multiple flow monitoring data sets; extracting multi-port flow data of the first user in the preset network area, generating a multi-port user flow monitoring data set; identifying flow distribution anomalies, generating flow anomaly probability indicators; identifying uniform flow distribution of the first user, generating multi-port flow anomaly indicators; generating network security reminder information with network security risk indicators. The platform solves the technical problems that the existing network security perception is difficult to accurately capture and monitor network flow in an all-round way in real time, which leads to limitations in anomaly identification, insufficient timeliness and accuracy of early warning of potential security risks, and achieves the technical effect of enhancing the timeliness and accuracy of security early warnings and improving the accuracy of user behavior analysis.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field related to electrical communications, and in particular to a network security situation awareness platform based on traffic monitoring. Background Art

[0002] Network security has become an important cornerstone for ensuring social security, stability and development in today's digital era. With the popularization and complexity of network applications, security risks in cyberspace have become increasingly prominent. Frequent incidents such as data leakage, network attacks, and malware propagation have caused huge losses to individuals and enterprises. How to achieve real-time monitoring and risk warning of network traffic has become a key issue that needs to be urgently solved in the field of network security. Traditional network security protection methods mostly rely on single-point defense measures such as firewalls and intrusion detection systems. There are many monitoring blind spots and limited coverage. It is difficult to fully and dynamically grasp the overall security situation of the network. It can often only defend against known threats, but it is powerless for new and complex attack methods. It is impossible to deeply analyze and intelligently identify network traffic, so as to timely discover and warn of potential security risks, and the analysis of abnormal user behavior is insufficient, which affects network security.

[0003] Therefore, in the current network security perception-related technologies, there are technical problems such as difficulty in accurately capturing and monitoring network traffic in a comprehensive manner in real time, which leads to limitations in anomaly identification and insufficient timeliness and accuracy in warnings of potential security risks. Summary of the invention

[0004] This application provides a network security situation awareness platform based on traffic monitoring to solve the technical problems existing in existing network security perception, such as the difficulty in accurately capturing and monitoring network traffic in a comprehensive manner, which in turn leads to limitations in anomaly identification and insufficient timeliness and accuracy in warnings of potential security risks. This application achieves the technical effect of enhancing the timeliness and accuracy of security warnings and improving the accuracy of user behavior analysis.

[0005] The present application provides a network security situation awareness platform based on traffic monitoring, the platform comprising: a traffic monitoring port acquisition module, the traffic monitoring port acquisition module is used to acquire multiple traffic monitoring ports in a preset network area and deploy a traffic mirror; a traffic monitoring data set generation module, the traffic monitoring data set generation module is used to connect to the traffic mirror, perform traffic monitoring on the multiple traffic monitoring ports, and generate multiple traffic monitoring data sets, wherein any traffic monitoring data set includes the access traffic of multiple users corresponding to any traffic monitoring port; a multi-port traffic data extraction module, the multi-port traffic data extraction module is used to perform multi-port traffic data extraction on a first user in the preset network area based on the multiple traffic monitoring data sets, and generate a multi-port user traffic monitoring data set. A measurement data set, wherein the first user is any user who initiates a network request in the preset network area; a traffic anomaly probability indicator generation module, the traffic anomaly probability indicator generation module is used to identify the traffic distribution anomaly of the multiple traffic monitoring ports based on the multiple traffic monitoring data sets, and generate a traffic anomaly probability indicator; a traffic distribution uniformity identification module, the traffic distribution uniformity identification module is used to identify the traffic distribution uniformity of the first user based on the multi-port user traffic monitoring data set, and generate a multi-port traffic anomaly indicator; a network security reminder information generation module, the network security reminder information generation module is used to identify network security risks according to the traffic anomaly probability indicator and the multi-port traffic anomaly indicator, and generate network security reminder information with the network security risk indicator.

[0006] In a possible implementation, the multi-port traffic data extraction module also performs the following processing: extracting IP addresses based on the data packet header information of the multiple traffic monitoring data sets, and identifying multiple user sets corresponding to the multiple traffic monitoring data sets according to the IP addresses; performing same user extraction on the multiple user sets to obtain the first user; extracting corresponding traffic data from the multiple traffic monitoring data sets according to the IP address of the first user to generate the multi-port user traffic monitoring data set; wherein the multi-port user traffic monitoring data set includes the traffic data corresponding to the first user at the multiple traffic monitoring ports respectively.

[0007] In a possible implementation, the traffic anomaly probability index generation module also performs the following processing: identifying port traffic distribution characteristics based on the multiple traffic monitoring data sets, and establishing multiple real-time port traffic distribution characteristics; wherein any real-time port traffic distribution characteristics include upstream traffic characteristics, downstream traffic characteristics, and data packet characteristics; inputting the multiple real-time port traffic distribution characteristics into a first traffic analysis model for anomaly analysis, and generating the traffic anomaly probability index, wherein the first traffic analysis model is connected to a traffic portrait library, and the traffic portrait library includes multiple baseline traffic feature portrait sets corresponding to the multiple traffic monitoring ports.

[0008] In a possible implementation, the traffic anomaly probability indicator generation module also performs the following processing: collecting multiple historical traffic monitoring data sets of the multiple traffic monitoring ports in normal traffic mode, wherein the multiple historical traffic monitoring data sets have time period identifiers; extracting the first historical traffic monitoring data set of the first traffic monitoring port among the multiple historical traffic monitoring data sets, and identifying the uplink traffic characteristics, downlink traffic characteristics and data packet characteristics of multiple time periods according to the time period identifier to generate multiple historical traffic distribution characteristics; performing deviation comparison on the multiple historical traffic distribution characteristics, merging the historical traffic distribution characteristics whose deviation values ​​are less than the preset deviation, and updating the corresponding time period identifier at the same time; establishing a mapping relationship between the merged traffic distribution characteristics and the updated time period identifier to form a first baseline traffic feature portrait set of the first traffic monitoring port; and associating the first baseline traffic feature portrait set with the first traffic monitoring port and adding it to the traffic portrait library.

[0009] In a possible implementation, the traffic anomaly probability index generation module also performs the following processing: inputting the multiple real-time port traffic distribution characteristics into the first traffic analysis model, calling the traffic portrait library through the first traffic analysis model, and performing a similarity comparison between the multiple real-time port traffic distribution characteristics and the traffic characteristics in the corresponding benchmark traffic feature portrait set according to the port correspondence, and outputting multiple maximum similarity indicators; performing anomaly probability calculations based on the multiple maximum similarity indicators respectively to generate the traffic anomaly probability index, wherein the anomaly probability is inversely proportional to the maximum similarity index.

[0010] In a possible implementation, the traffic distribution uniformity identification module also performs the following processing: collecting multi-port traffic mutation characteristics of the same user under abnormal traffic mode; identifying multi-port traffic mutation characteristics of the multi-port user traffic monitoring data set to generate real-time multi-port mutation characteristics; comparing the real-time multi-port mutation characteristics with the multi-port traffic mutation characteristics to generate the multi-port traffic anomaly indicator.

[0011] In a possible implementation, the network security alert information generation module also performs the following processing: when any one of the traffic anomaly probability index and the multi-port traffic anomaly index is greater than or equal to a preset threshold, the corresponding index is used as the network security risk index; and the network security alert information is generated using the network security risk index.

[0012] In a possible implementation, the traffic monitoring port acquisition module also performs the following processing: obtaining multiple network nodes in a preset network area; performing network security attack simulation on the multiple network nodes, performing abnormal traffic correlation analysis based on the simulation results, and generating multiple abnormal correlation node combinations; randomly extracting a node from each of the multiple abnormal correlation node combinations to generate the multiple traffic monitoring ports.

[0013] It is intended to obtain multiple traffic monitoring ports in a preset network area and deploy a traffic mirror through a network security situation awareness platform based on traffic monitoring proposed in this application; connect the traffic mirror, perform traffic monitoring on the multiple traffic monitoring ports, and generate multiple traffic monitoring data sets, wherein any traffic monitoring data set includes the access traffic of multiple users corresponding to any traffic monitoring port; based on the multiple traffic monitoring data sets, extract multi-port traffic data for a first user in the preset network area, and generate a multi-port user traffic monitoring data set, wherein the first user is any user who initiates a network request in the preset network area; based on the multiple traffic monitoring data sets, identify traffic distribution anomalies for the multiple traffic monitoring ports, and generate a traffic anomaly probability index; based on the multi-port user traffic monitoring data set, identify the uniform traffic distribution of the first user, and generate a multi-port traffic anomaly index; identify network security risks based on the traffic anomaly probability index and the multi-port traffic anomaly index, and generate network security reminder information with the network security risk index. It solves the technical problems of existing network security perception, such as difficulty in accurately capturing and monitoring network traffic in a comprehensive manner, which in turn leads to limitations in anomaly identification and insufficient timeliness and accuracy in warnings of potential security risks. It achieves the technical effect of enhancing the timeliness and accuracy of security warnings and improving the accuracy of user behavior analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure are briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the platform according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of the structure of a network security situation awareness platform based on traffic monitoring provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of the execution flow of a multi-port traffic data extraction module in a network security situation awareness platform based on traffic monitoring provided in an embodiment of the present application.

[0017] Explanation of the reference numerals: traffic monitoring port acquisition module 10, traffic monitoring data set generation module 20, multi-port traffic data extraction module 30, traffic anomaly probability index generation module 40, traffic distribution uniformity identification module 50, network security reminder information generation module 60. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or components that are not clearly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The present application embodiment provides a network security situation awareness platform based on traffic monitoring, such as Figure 1 As shown, the platform includes:

[0022] The traffic monitoring port acquisition module 10 is used to acquire multiple traffic monitoring ports in a preset network area and deploy a traffic mirror. Acquiring multiple traffic monitoring ports in a preset network area means clarifying the network range that needs to be monitored, identifying key traffic nodes in the preset network area, which are usually the intersection points of network traffic, such as ports on switches, routers, firewalls and other network devices, and using key traffic nodes as traffic monitoring ports. These ports should be able to cover the main traffic paths in the network to ensure the comprehensiveness and accuracy of monitoring, and then deploying traffic mirrorers. Specifically, a traffic mirrorer (also known as a port mirrorer) is a network device that can copy (mirror) network traffic of one or more ports to another port or device for subsequent analysis and monitoring, without affecting the original network traffic, ensuring the normal operation of the network. The traffic mirrorer is deployed in the network and configured accordingly, including specifying the source port (i.e., the acquired traffic monitoring port) and the target port (i.e., the port or device that receives the mirrored traffic). After the configuration is completed, the traffic mirrorer will start to capture and copy the network traffic of the specified port to the target port, which can achieve comprehensive, real-time and in-depth monitoring of network traffic, thereby timely discovering and warning of potential security risks and improving the overall protection level of network security.

[0023] A traffic monitoring data set generation module 20 is used to connect to the traffic mirror, perform traffic monitoring on the multiple traffic monitoring ports, and generate multiple traffic monitoring data sets, wherein any traffic monitoring data set includes the access traffic of multiple users corresponding to any traffic monitoring port. The traffic mirror is connected to the switch or router in the network through a physical link (such as a network cable, optical fiber, etc.), and is configured on the switch or router. The designated traffic monitoring port is set as the mirror source port, and the receiving port of the traffic mirror is set as the mirror target port. The traffic on the source port will be copied to the target port, that is, the receiving port of the traffic mirror. The traffic mirror begins to receive traffic data from the mirror source port, including all network data packets passing through these ports, covering the access traffic of multiple users. The traffic mirror processes the received data packets, including parsing, filtering, statistics, etc. During the processing, key information such as source IP address, destination IP address, port number, protocol type, data packet size, timestamp, etc. is extracted as needed. Based on the processed data packet information, the traffic mirror or the data analysis system connected to it constructs multiple traffic monitoring data sets. Each data set corresponds to a traffic monitoring port and contains the access traffic information of all users on the port. That is, any traffic monitoring data set records the access traffic of each user on the corresponding port in detail. This includes but is not limited to the user's IP address, access time, access service type (such as HTTP, FTP, SMTP, etc.), amount of data transmitted, and possible abnormal behavior identification.

[0024] A multi-port traffic data extraction module 30 is used to extract multi-port traffic data for a first user in the preset network area based on the multiple traffic monitoring data sets, and generate a multi-port user traffic monitoring data set, wherein the first user is any user who initiates a network request in the preset network area. Extracting multi-port traffic data for a first user in the preset network area refers to analyzing the traffic of the first user on multiple ports. Specifically, the traffic data related to the first user is located from multiple traffic monitoring data sets, and the traffic data belonging to the first user from different ports is associated by analyzing the source IP address, destination IP address, port number and other information of the data packet, and the traffic data belonging to the first user from different ports is extracted. The traffic data on all relevant ports of the first user may include the request initiated by the user, the response received, the amount of data transmitted, the communication time, etc., and then the extracted multi-port traffic data is integrated into a data set, namely, a multi-port user traffic monitoring data set, which contains the complete traffic information of the first user on all relevant ports. Through the multi-port user traffic monitoring data set, the network behavior of the first user can be deeply analyzed, which is helpful to identify the user's normal behavior pattern, abnormal behavior and potential security risks.

[0025] The flow anomaly probability index generation module 40 is used to identify the flow distribution anomaly of the multiple flow monitoring ports based on the multiple flow monitoring data sets, and generate the flow anomaly probability index. The multiple flow monitoring data sets are preprocessed, including data cleaning (removing noise data, duplicate data, etc.), data format unification (ensuring that data from different sources have the same format and unit) and data standardization (converting data into a comparable numerical range), extracting key features for flow anomaly identification from the preprocessed data, which may include flow size, flow pattern, flow behavior, flow source and destination, etc., applying anomaly detection algorithms to analyze flow data to identify abnormal patterns in flow distribution, such as statistical methods (such as threshold detection, cluster analysis, etc.) or deep learning methods (such as neural networks, convolutional neural networks, etc.), and identifying abnormal points or abnormal areas in flow distribution according to the analysis results of the algorithm. These anomalies may indicate potential network attacks (such as DDoS attacks, port scanning, etc.), network failures (such as link congestion, equipment failure, etc.) or abnormal network behaviors (such as illegal access, malware propagation, etc.); an anomaly score is assigned to each identified anomaly point or abnormal area, reflecting the severity and credibility of the anomaly. Based on the anomaly score and the overall distribution of traffic data, a traffic anomaly probability index is generated. The higher the index, the greater the risk of abnormal behavior in the network. It is used to quantify the possibility and risk level of abnormal activities in network traffic. The traffic anomaly probability index can help network administrators quickly understand the security status of network traffic, assess potential risks, and take corresponding countermeasures. For example, when the traffic anomaly probability index exceeds the preset threshold, an alarm mechanism can be triggered.

[0026] The flow distribution uniformity identification module 50 is used to identify the uniform flow distribution of the first user based on the multi-port user flow monitoring data set, and generate a multi-port flow anomaly index. The multi-port user flow monitoring data set is deeply analyzed to understand the flow distribution of the first user on different ports, including statistics of indicators such as the flow size, flow proportion, and flow peak of each port. According to the statistical results, whether the flow distribution of the first user is uniform is evaluated. If the flow of a certain port is significantly different from that of other ports (such as abnormally high or abnormally low), it may indicate that the flow distribution of the port is uneven. Further analyze the ports with uneven flow distribution to identify whether there are abnormal network behavior patterns, such as continuous high-flow attacks, abnormal data transmission patterns, etc., and assign an abnormal score to the identified abnormal flow, which reflects the severity and credibility of the anomaly. Based on the anomaly score and the overall distribution of the flow data, a multi-port flow anomaly index is generated. This index should be able to comprehensively reflect the abnormal flow conditions of the first user on different ports.

[0027] The network security reminder information generation module 60 is used to identify network security risks according to the traffic anomaly probability index and the multi-port traffic anomaly index, and generate network security reminder information according to the network security risk index. Comprehensively evaluate the traffic anomaly probability index and the multi-port traffic anomaly index to fully understand the security risks in the network, including weighted summation, cluster analysis, etc., to identify potential security threats. According to the evaluation results, classify network security risks, which may include classification according to attack type (such as DDoS attack, intrusion behavior, malicious code propagation, etc.), impact scope (such as local risk, global risk) or severity (such as low risk, medium risk, high risk), etc., sort the identified security risks, and give priority to those with high threat level and large impact scope, which helps to reasonably allocate resources and energy to ensure network security, and then obtain a comprehensive network security risk score, namely, network security risk index, which is used to quantify the current network security risk level. Finally, generate network security reminder information based on the network security risk index. The network security reminder information should include clear risk warnings, possible impact scope, recommended countermeasures, etc. When generating multiple network security reminder information, they should be prioritized according to the severity and urgency of the risks, and high-risk and urgent reminder information should be given priority to ensure that network security is protected in a timely and effective manner.

[0028] A network security situation awareness platform based on traffic monitoring according to an embodiment of the present invention is used to solve the technical problems that the existing network security perception is difficult to accurately capture and monitor network traffic in real time, which leads to limitations in abnormal identification and insufficient timeliness and accuracy of early warning of potential security risks, thereby achieving the technical effect of enhancing the timeliness and accuracy of security early warning and improving the accuracy of user behavior analysis. A network security situation awareness platform based on traffic monitoring includes: a traffic monitoring port acquisition module 10, a traffic monitoring data set generation module 20, a multi-port traffic data extraction module 30, a traffic anomaly probability indicator generation module 40, a traffic distribution uniformity identification module 50, and a network security reminder information generation module 60.

[0029] The specific configuration of the multi-port flow data extraction module 30 will be described in detail below. Figure 2As shown, the multi-port traffic data extraction module 30 may further include: extracting IP addresses based on the data packet header information of the multiple traffic monitoring data sets, and identifying multiple user sets corresponding to the multiple traffic monitoring data sets according to the IP addresses. The traffic monitoring data set usually contains a large number of data packets transmitted through the network, each data packet has a header information, and in the data packet header information, there are two key IP address fields, the source IP address and the destination IP address. The source IP address identifies the IP address of the device that sends the data packet, and the destination IP address identifies the IP address of the device to which the data packet should be sent. Each data packet in the multiple traffic monitoring data sets is traversed, and the source IP address and the destination IP address are extracted from the data packet header, and then these addresses are used to identify different network users or devices. In most cases, each user or device will have one or more fixed IP addresses in the network. The data packets with the same IP address are classified into the same user set, and finally multiple user sets corresponding to the multiple traffic monitoring data sets are identified, and each user set contains all traffic data related to a specific user or device. It also includes performing the same user extraction on the multiple user sets to obtain the first user. Users with specific conditions (such as specific IP addresses, MAC addresses, user names, etc.) are further randomly screened out from the multiple user sets and designated as first users.

[0030] It also includes extracting the corresponding traffic data from the multiple traffic monitoring data sets according to the IP address of the first user to generate the multi-port user traffic monitoring data set; wherein the multi-port user traffic monitoring data set includes the traffic data corresponding to the first user at the multiple traffic monitoring ports. Using the IP address of the first user as a screening condition, all traffic data related to the first user are extracted from the multiple traffic monitoring data sets. These traffic data may be scattered on multiple different monitoring ports, so the extraction process needs to ensure that all relevant ports can be covered, thereby generating a multi-port user traffic monitoring data set. The multi-port user traffic monitoring data set includes the traffic data corresponding to the first user at the multiple traffic monitoring ports. The data of each port records the traffic activity of the first user on the port in detail, including key information such as traffic size, timestamp, and protocol type.

[0031] The specific configuration of the traffic anomaly probability index generating module 40 will be described in detail below. The traffic anomaly probability index generating module 40 may further include: identifying port traffic distribution characteristics based on the multiple traffic monitoring data sets, and establishing multiple real-time port traffic distribution characteristics; wherein any real-time port traffic distribution characteristics include uplink traffic characteristics, downlink traffic characteristics, and data packet characteristics. Extract and identify the traffic distribution characteristics of each port from multiple traffic monitoring data sets. The traffic monitoring data set contains information about all data packets transmitted in the network. These data packets communicate through different ports. Port traffic distribution characteristics refer to the statistical and distribution characteristics of traffic on a specific port, including but not limited to the size, rate, time distribution, etc. of the traffic. After identifying the traffic distribution characteristics of each port, these characteristics are collected and updated in real time to establish multiple real-time port traffic distribution characteristics, which means that the system can continuously monitor network traffic and capture its dynamic changes. Each real-time port traffic distribution characteristic contains information in multiple dimensions, the most important of which are uplink traffic characteristics, downlink traffic characteristics and data packet characteristics. Uplink traffic characteristics refer to the characteristics of data traffic sent from the port, such as the sending rate, the number of data packets sent, etc.; downlink traffic characteristics refer to the characteristics of data traffic arriving at the port, such as the receiving rate, the number of data packets received, etc.; data packet characteristics refer to the characteristics of the data packet itself, such as data packet size, frequency, timestamp, etc.

[0032] It also includes inputting the multiple real-time port traffic distribution characteristics into a first traffic analysis model for anomaly analysis to generate the traffic anomaly probability index, wherein the first traffic analysis model is connected to a traffic portrait library, and the traffic portrait library includes multiple baseline traffic feature portrait sets corresponding to the multiple traffic monitoring ports. When multiple real-time port traffic distribution features are input into the first traffic analysis model, the model will compare these features with the benchmark traffic feature portrait set in the traffic portrait library. By comparison, the model can identify which features deviate from the normal range, thereby determining whether the current traffic is abnormal. Based on this comparison and analysis, the model will generate a traffic anomaly probability indicator to indicate the possibility of abnormal behavior in the current network traffic. Generally, the higher the value, the greater the possibility of abnormal behavior in the traffic. The traffic portrait library is a database that stores benchmark traffic feature portrait sets corresponding to multiple traffic monitoring ports. Each benchmark traffic feature portrait set is generated based on the historical traffic data of the port and represents the traffic characteristics of the port under normal conditions. These portrait sets provide a comparison benchmark for the first traffic analysis model, enabling the model to identify the deviation between the current traffic and normal conditions. The first traffic analysis model needs to maintain a connection with the traffic portrait library so that the model can access and query the benchmark traffic feature portrait set in the portrait library in real time, ensuring that the model can perform anomaly analysis based on the latest benchmark data, thereby improving the accuracy and timeliness of the analysis. The construction of the first traffic analysis model specifically includes collecting historical data of network traffic from multiple traffic monitoring data sources (such as network monitoring equipment, sensors, etc.), preprocessing the data, and then analyzing and extracting normal traffic characteristics. According to the analysis results, a baseline traffic feature portrait set is generated for each port, and an analysis model is constructed based on the ARIMA model of time series analysis, a convolutional neural network or a multivariate linear model of regression analysis, etc. The model is trained using the preprocessed data and the baseline traffic feature portrait set. During the training process, the recognition accuracy and generalization ability of the model are improved by adjusting model parameters, optimizing algorithms, and other methods, and finally the first traffic analysis model is obtained.

[0033] The specific configuration of the traffic anomaly probability index generation module 40 will be described in detail below. The traffic anomaly probability index generation module 40 may further include: collecting multiple historical traffic monitoring data sets of the multiple traffic monitoring ports in normal traffic mode, wherein the multiple historical traffic monitoring data sets have time period identifiers. Use network monitoring equipment, sensors, etc. to collect historical traffic monitoring data sets of multiple traffic monitoring ports in normal traffic mode. These data sets have time period identifiers and generally include traffic data of different time periods (such as hours, days, weeks, etc.). It also includes extracting the first historical traffic monitoring data set of the first traffic monitoring port from the multiple historical traffic monitoring data sets, identifying the uplink traffic characteristics, downlink traffic characteristics, and data packet characteristics of multiple time periods according to the time period identifier, and generating multiple historical traffic distribution characteristics. All historical traffic data related to the first traffic monitoring port are screened out from the entire historical traffic monitoring data set, namely, the first historical traffic monitoring data set. This data set contains all traffic records of the port within a period of time. The first traffic monitoring port refers to any one of the multiple traffic monitoring ports. According to the time period identifier (such as hour, day, week, etc.), the first historical traffic monitoring data set is divided into data subsets of multiple time periods. Each subset represents the traffic data within a specific time period. For the data subset of each time period, detailed traffic feature identification is performed, including uplink traffic feature identification, downlink traffic feature identification and data packet feature identification, and then corresponding historical traffic distribution features are generated for the data subset of each time period. These features are a quantitative description of the traffic behavior within the time period, reflecting the basic characteristics and changing trends of the traffic.

[0034] It also includes, performing deviation comparison on the multiple historical traffic distribution features, merging the historical traffic distribution features with deviation values ​​less than the preset deviation, and updating the corresponding time period identifier. Performing deviation comparison on the multiple historical traffic distribution features identified, calculating the deviation values ​​between them, merging the historical traffic distribution features with deviation values ​​less than the preset deviation, so as to reduce data redundancy and improve analysis efficiency, and updating the time period identifier corresponding to the merged features to reflect the time period represented by these features. It also includes, establishing a mapping relationship between the merged traffic distribution features and the updated time period identifier to form the first benchmark traffic feature portrait set of the first traffic monitoring port. Establishing a mapping relationship between the merged traffic distribution features and the updated time period identifier, combining the traffic distribution features in the mapping relationship and the corresponding time period identifier to form the first benchmark traffic feature portrait set of the first traffic monitoring port, including a collection of multiple benchmark traffic features and their corresponding time period identifiers, which jointly describe the traffic behavior of the first traffic monitoring port in a specific time period. It also includes, associating the first benchmark traffic feature portrait set with the first traffic monitoring port and adding it to the traffic portrait library. Add all merged traffic distribution features and their corresponding time period identifiers to the traffic portrait library, upload the portrait set data to the database, and update the database records to reflect this change. During the adding process, it is necessary to ensure that the data structure of the traffic portrait library can efficiently store and retrieve the portrait set data. The traffic portrait library can be used for real-time network traffic monitoring. By comparing the differences between real-time traffic data and the benchmark portrait set, abnormal situations in the network can be discovered in time and corresponding measures can be taken.

[0035] The specific configuration of the traffic anomaly probability index generation module 40 will be described in detail below. The traffic anomaly probability index generation module 40 may further include: inputting the multiple real-time port traffic distribution features into the first traffic analysis model, calling the traffic portrait library through the first traffic analysis model, and performing similarity comparison between the multiple real-time port traffic distribution features and the traffic features in the corresponding benchmark traffic feature portrait set according to the port correspondence, and outputting multiple maximum similarity indicators. The traffic distribution features of multiple real-time ports are input into the first traffic analysis model, and then the first traffic analysis model will call a traffic portrait library. The model will perform similarity comparison between the real-time port traffic distribution features and the traffic features in the corresponding benchmark traffic feature portrait set according to the port correspondence, that is, by calculating the similarity between the two. The higher the similarity, the closer the real-time traffic is to the normal state; the lower the similarity, the more abnormal the situation may be. For each real-time port traffic distribution feature, the model will output a maximum similarity indicator, which indicates the similarity between the real-time traffic and the most similar portrait among all the benchmark traffic feature portraits.

[0036] It also includes, based on the multiple maximum similarity indicators, performing abnormal probability calculations respectively to generate the traffic abnormal probability indicator, wherein the abnormal probability is inversely proportional to the maximum similarity indicator. The abnormal probability is calculated based on multiple maximum similarity indicators, and the abnormal probability is inversely proportional to the maximum similarity indicator, that is, if the maximum similarity indicator of a port is very low (that is, the similarity between the real-time traffic and the benchmark profile is very low), then the abnormal probability of the traffic of the port will be very high; conversely, if the maximum similarity indicator is very high, then the abnormal probability will be very low. Finally, according to the abnormal probability of each port, a traffic abnormal probability indicator is generated to evaluate the abnormal degree of the entire network traffic.

[0037] The specific configuration of the traffic distribution uniformity identification module 50 will be described in detail below. The traffic distribution uniformity identification module 50 may further include: collecting multi-port traffic mutation characteristics of the same user in abnormal traffic patterns. Abnormal traffic may manifest as a sudden increase or decrease in traffic, an abnormal traffic distribution pattern, or a traffic pattern that does not conform to normal network behavior. The traffic of the same user on all its active ports is continuously monitored, including collecting key information such as traffic size, rate, timestamp, protocol type, etc., and extracting features related to traffic mutations from the monitoring data, i.e., multi-port traffic mutation features, such as traffic peaks, valleys, the time when mutations occur, and the traffic change rate before and after mutations.

[0038] It also includes identifying the multi-port traffic mutation characteristics of the multi-port user traffic monitoring data set to generate real-time multi-port mutation characteristics. The collected multi-port user traffic monitoring data set is cleaned and preprocessed, and the change trend and abnormal pattern of each port traffic are identified based on statistical analysis, and the characteristics that can characterize the multi-port traffic mutation are extracted from the analyzed data. The network traffic of multi-port users is continuously monitored using real-time monitoring technology, and then the characteristics of the real-time monitored data are calculated, including calculating the traffic change rate, fluctuation range, abnormal points and other key indicators of each port, and finally generating real-time multi-port mutation characteristics.

[0039] The method further includes comparing the real-time multi-port mutation feature with the multi-port traffic mutation feature to generate the multi-port traffic anomaly index. The multi-port mutation feature generated in real time is compared with the multi-port traffic mutation feature collected previously, such as calculating the similarity, and judging whether the current traffic is abnormal based on the comparison result. If the real-time mutation feature is highly similar to the known abnormal feature, it may indicate that the current traffic is abnormal. Based on the result of the abnormal judgment, a multi-port traffic anomaly index is generated to quantify the degree of abnormality of the current traffic.

[0040] The specific configuration of the network security reminder information generation module 60 will be described in detail below. The network security reminder information generation module 60 may further include: when any of the traffic anomaly probability index and the multi-port traffic anomaly index is greater than or equal to a preset threshold, the corresponding index is used as the network security risk index. In the network monitoring system, a threshold is pre-set to determine whether different network indicators are in an abnormal state, and the real-time calculated traffic anomaly probability index and the multi-port traffic anomaly index are compared with the preset threshold. If the value of any indicator is greater than or equal to the threshold, it is considered that there is a network security risk. After the risk is found, the indicator that reaches or exceeds the threshold is determined as a network security risk indicator. Generate the network security reminder information with the network security risk indicator. Based on the determined network security risk indicator, the network security reminder information should be constructed to clearly indicate the risk type (such as traffic anomaly), the port or user involved, the risk level (which can be divided according to the size of the indicator value) and the possible consequences or impacts.

[0041] The specific configuration of the traffic monitoring port acquisition module 10 will be described in detail below. The traffic monitoring port acquisition module 10 may further include: acquiring multiple network nodes in a preset network area. Acquire multiple network nodes in a preset network area, such as servers, routers, switches, personal computers, IoT devices, etc., and collect relevant information of each network node, including IP address, MAC address, device type, operating system, running services, etc.

[0042] It also includes: performing network security attack simulation on the multiple network nodes, performing abnormal traffic correlation analysis based on the simulation results, and generating multiple abnormal correlation node combinations. Performing network security attack simulation on multiple network nodes means simulating the network attack behavior in the real world as much as possible to verify the security and response capabilities of the network nodes. During the attack simulation, key information such as network traffic, system logs, and security events are monitored in real time, and the impact and results of the attack are recorded. The collected traffic data, system logs, and security events are analyzed in depth to identify abnormal traffic patterns, which may be related to network security attacks. Using network correlation analysis technology, the abnormal traffic characteristics of different nodes and different time points are correlated and analyzed to find the causal relationship and common characteristics between abnormal behaviors to reveal potential network attack paths and purposes. Based on the results of the correlation analysis, multiple abnormal correlation node combinations are generated. These combinations represent sets of nodes that may be affected by the same or related network attacks. It also includes randomly extracting a node from each of the multiple abnormal correlation node combinations to generate the multiple traffic monitoring ports. Randomly extract a node from each abnormal correlation node combination, and configure multiple traffic monitoring ports for these selected nodes to capture and analyze network traffic data flowing through the nodes in real time.

[0043] Although the present application makes various references to certain components in the platform according to the embodiments of the present application, any number of different components may be used and run on the user terminal and / or server, and the various units and components included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0044] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A network security situation awareness platform based on traffic monitoring, characterized in that: include: A traffic monitoring port acquisition module, which is used to acquire multiple traffic monitoring ports in a preset network area and deploy a traffic mirror; A flow monitoring data set generation module, the flow monitoring data set generation module is used to connect to the flow mirror, perform flow monitoring on the multiple flow monitoring ports, and generate multiple flow monitoring data sets, wherein any flow monitoring data set includes access flows of multiple users corresponding to any flow monitoring port; A multi-port traffic data extraction module, the multi-port traffic data extraction module is used to extract multi-port traffic data for a first user in the preset network area based on the multiple traffic monitoring data sets to generate a multi-port user traffic monitoring data set, wherein the first user is any user who initiates a network request in the preset network area; A flow anomaly probability index generation module, the flow anomaly probability index generation module is used to identify flow distribution anomalies of the multiple flow monitoring ports based on the multiple flow monitoring data sets and generate a flow anomaly probability index; A flow distribution uniformity identification module, the flow distribution uniformity identification module is used to identify the flow distribution uniformity of the first user based on the multi-port user flow monitoring data set, and generate a multi-port flow anomaly indicator; A network security reminder information generation module, the network security reminder information generation module is used to identify network security risks according to the traffic anomaly probability index and the multi-port traffic anomaly index, and generate network security reminder information according to the network security risk index; Based on the multiple traffic monitoring data sets, traffic distribution anomalies are identified for the multiple traffic monitoring ports to generate traffic anomaly probability indicators, including: Identify port traffic distribution features based on the multiple traffic monitoring data sets, and establish multiple real-time port traffic distribution features; Among them, any real-time port traffic distribution characteristics include uplink traffic characteristics, downlink traffic characteristics and data packet characteristics; Inputting the plurality of real-time port traffic distribution features into a first traffic analysis model for anomaly analysis to generate the traffic anomaly probability index, wherein the first traffic analysis model is connected to a traffic portrait library, and the traffic portrait library includes a plurality of reference traffic feature portrait sets corresponding to the plurality of traffic monitoring ports; The method of uniformly identifying the traffic distribution of the first user based on the multi-port user traffic monitoring data set and generating a multi-port traffic anomaly indicator includes: Collect multi-port traffic mutation characteristics of the same user under abnormal traffic patterns; Performing multi-port traffic mutation feature recognition on the multi-port user traffic monitoring data set to generate real-time multi-port mutation features; Comparing the real-time multi-port mutation feature with the multi-port traffic mutation feature to generate the multi-port traffic anomaly indicator; Get multiple traffic monitoring ports within a preset network area, including: Obtain multiple network nodes in a preset network area; Performing network security attack simulation on the multiple network nodes, performing abnormal traffic correlation analysis based on the simulation results, and generating multiple abnormal correlation node combinations; A node is randomly extracted from each of the plurality of abnormal associated node combinations to generate the plurality of traffic monitoring ports.

2. A network security situation awareness platform based on traffic monitoring as claimed in claim 1, characterized in that: Based on the multiple traffic monitoring data sets, extracting multi-port traffic data of a first user in the preset network area to generate a multi-port user traffic monitoring data set includes: Extracting IP addresses based on data packet header information of the plurality of traffic monitoring data sets, and identifying a plurality of user sets corresponding to the plurality of traffic monitoring data sets according to the IP addresses; Extracting the same user from the multiple user sets to obtain the first user; Extracting corresponding traffic data from the multiple traffic monitoring data sets according to the IP address of the first user to generate the multi-port user traffic monitoring data set; The multi-port user traffic monitoring data set includes traffic data corresponding to the first user at the multiple traffic monitoring ports respectively.

3. A network security situation awareness platform based on traffic monitoring as claimed in claim 1, characterized in that: Also includes: Collecting a plurality of historical flow monitoring data sets of the plurality of flow monitoring ports in a normal flow mode, wherein the plurality of historical flow monitoring data sets have time period identifiers; Extracting a first historical traffic monitoring data set of a first traffic monitoring port from the multiple historical traffic monitoring data sets, identifying uplink traffic characteristics, downlink traffic characteristics, and data packet characteristics of multiple time periods according to the time period identifier, and generating multiple historical traffic distribution characteristics; Performing deviation comparison on the multiple historical traffic distribution features, merging the historical traffic distribution features whose deviation values ​​are less than a preset deviation, and updating the corresponding time period identifiers at the same time; Establishing a mapping relationship between the merged traffic distribution characteristics and the update time period identifier to form a first reference traffic characteristic portrait set of the first traffic monitoring port; The first reference traffic feature portrait set is associated with the first traffic monitoring port and then added to the traffic portrait library.

4. A network security situation awareness platform based on traffic monitoring as claimed in claim 3, characterized in that: Inputting the plurality of real-time port traffic distribution features into the first traffic analysis model for anomaly analysis to generate the traffic anomaly probability index comprises: Input the multiple real-time port traffic distribution features into a first traffic analysis model, call the traffic portrait library through the first traffic analysis model, perform similarity comparison between the multiple real-time port traffic distribution features and the traffic features in the corresponding benchmark traffic feature portrait set according to the port correspondence, and output multiple maximum similarity indicators; The abnormal probability is calculated based on the multiple maximum similarity indicators respectively to generate the traffic abnormality probability indicator, wherein the abnormal probability is inversely proportional to the maximum similarity indicator.

5. A network security situation awareness platform based on traffic monitoring as claimed in claim 1, characterized in that: The network security risk is identified according to the traffic anomaly probability index and the multi-port traffic anomaly index, and network security reminder information is generated according to the network security risk index, including: When any one of the traffic anomaly probability index and the multi-port traffic anomaly index is greater than or equal to a preset threshold, the corresponding index is used as the network security risk index; The network security warning information is generated based on the network security risk indicator.