Network traffic storage and updating method and system for virus firewall

By capturing and distributing network traffic in real-time in virus firewalls, and using deep learning models to identify abnormal traffic, dynamically generate firewall rules, the shortcomings of traditional firewalls in rule learning and threat response are solved, and detection efficiency and network security management are improved. efficiency.

CN118945181APending Publication Date: 2024-11-12JIANGSU FUTURE NETWORKS INNOVATION
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411184048.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Traditional virus firewalls have flaws in rule learning, threat detection and threat response, and cannot respond to cyber threats in a timely manner. Rule updates rely on manual labor, resulting in high security risks and management complexity.

Method used

By capturing network traffic in real time and storing it distributedly in the blockchain, using deep learning models to analyze traffic features and identify abnormal traffic, dynamically generate and adjust firewall rules, and deploying them in real time on virus firewalls.

Benefits of technology

It improves the detection efficiency and response speed of the virus firewall, reduces the false alarm rate and configuration difficulties, reduces manual intervention, and enhances the efficiency of network security management and system stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945181A_ABST
    Figure CN118945181A_ABST
Patent Text Reader

Abstract

The invention relates to a network traffic storage and updating method and system for a virus firewall, and the method comprises the steps: capturing network traffic in real time, storing the network traffic in a block chain in a distributed manner, and optimizing a storage space through incremental storage and archiving hierarchical storage; when the network traffic is stored, analyzing feature information of the network traffic through a deep learning model to identify abnormal traffic; and by analyzing the abnormal traffic, adjusting and generating a firewall rule, deploying in a virus firewall in real time. According to the invention, through the distributed block chain, the network traffic can be better stored and processed, and the traffic can be adjusted or adjusted according to actual needs. In addition, malicious data are identified through a deep learning model and a machine learning model, and once malicious attacks are analyzed, firewall rules can be automatically and quickly generated and updated; and the known and unknown network flow information is comprehensively processed and automatically adjusted to generate the security rule, so that the efficiency of security management personnel is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of network firewalls, and in particular to a network flow storage and updating method and system for virus firewalls. Background Art

[0002] With the rapid development of network technology, the role of network firewalls has become increasingly important, and the requirements for their security and intelligence have become increasingly higher. Traditional firewall rule formulation mostly relies on manual configuration based on the professional knowledge and experience of network administrators, but the complexity and flexibility of the network environment make it difficult for manually configured rules to cover all potential security threats, and it takes a lot of time to maintain the rules, which overwhelms network administrators.

[0003] At the same time, traditional network firewalls have major flaws in rule learning, threat detection, and threat response, which prevents network administrators from timely learning about the problems facing the firewall. First, virus firewalls can only determine whether traffic is virus traffic based on existing features, and can only perform passive defense, with no effective way to defend against unknown threats; second, firewalls have weak learning and updating capabilities, and when faced with new threats, they need to manually re-identify, formulate rules, and update them, which makes it impossible for firewalls to adapt to the rapidly evolving network threat environment; then, the rules in virus firewalls are stored and updated within a system, which makes it easy for people outside the network to attack the firewall through certain loopholes or channels to allow it to pass illegally obtained traffic, thereby creating a major network security risk. Summary of the invention

[0004] The object of the present invention is to provide a network traffic storage and updating method and system for a virus firewall, so as to solve the problem that the prior art has defects in rule learning, threat detection and threat response of the network firewall.

[0005] To achieve one of the above-mentioned purposes, an embodiment of the present invention provides a network traffic storage and update method for a virus firewall, the method comprising:

[0006] Capture network traffic in real time, store it in a distributed manner in the blockchain, and optimize storage space through incremental storage and archive tiered storage;

[0007] While storing the network traffic, analyzing feature information of the network traffic through a deep learning model to identify abnormal traffic;

[0008] By analyzing the abnormal traffic, adjusting and generating firewall rules, the rules are deployed in the virus firewall in real time.

[0009] As a further improvement of an embodiment of the present invention, the method further includes that the real-time capture of network traffic includes:

[0010] Use network monitoring tools to capture network traffic in real time, including all transmitted network packets and metadata;

[0011] Preprocess the captured network traffic, including removing noise data and redundant information;

[0012] Perform feature extraction on the preprocessed network traffic, including extracting the spatial and temporal features of the network traffic.

[0013] As a further improvement of an embodiment of the present invention, the method further includes that the distributed storage of the network traffic in the blockchain includes:

[0014] The structure of the blockchain adopts a consortium chain architecture, where multiple nodes jointly maintain the distributed storage of traffic data; the nodes include storage nodes and verification nodes;

[0015] The network traffic is divided into a plurality of traffic segments according to a preset size, and each traffic segment is stored as a traffic block; the traffic block includes a hash value and related metadata of the traffic segment;

[0016] The verification node uses a consensus algorithm to verify each traffic block, and adds the verified traffic blocks to different storage nodes of the local chain for storage.

[0017] As a further improvement of an embodiment of the present invention, the method further includes that optimizing storage space through incremental storage and archive tiered storage includes:

[0018] The real-time captured network traffic is compared with the stored historical network traffic using a difference calculation algorithm, and the difference traffic is extracted and stored as incremental data;

[0019] The network traffic stored in the blockchain is stored in different storage tiers based on data importance and access frequency;

[0020] And archive network traffic that has not been accessed within a preset time to cold storage devices.

[0021] As a further improvement of an embodiment of the present invention, the method further includes that the “analyzing characteristic information of the network traffic through a deep learning model to identify abnormal traffic” includes:

[0022] The deep learning model includes a convolutional neural network, a long short-term memory network and a deep fusion network;

[0023] The spatial features are analyzed by the convolutional neural network, and the temporal features are analyzed by the long short-term memory network. The outputs of the convolutional neural network and the long short-term memory network are used as inputs of the deep fusion network. By outputting the classification result of the network traffic, it is determined whether the network traffic is abnormal traffic.

[0024] As a further improvement of an embodiment of the present invention, the method further includes that the “adjusting and generating firewall rules by analyzing the abnormal traffic” includes:

[0025] Determining the attack mode of the abnormal traffic, and determining whether to store a firewall rule for intercepting the attack mode;

[0026] If yes, analyze the threat level of the abnormal traffic, and dynamically adjust the firewall rules based on the real-time traffic and historical interception data of the abnormal traffic;

[0027] If not, then the attack pattern of the abnormal traffic is matched with similar attack patterns in the attack patterns intercepted by the existing firewall rules to generate targeted firewall rules.

[0028] As a further improvement of an embodiment of the present invention, the method further includes: the "adjusting and generating firewall rules by analyzing the abnormal traffic" also includes:

[0029] Real-time detection of the current network environment, dynamic generation of firewall rules adapted to the current network environment through situational awareness technology, and prediction of possible attack types based on the firewall interception history and the current network environment situation, generating corresponding firewall rules in advance;

[0030] Whether there is a conflict between the newly generated rule and the existing rule is detected in real time; if there is, the conflict is resolved by adjusting or merging the newly generated rule.

[0031] To achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention provides a network traffic storage and update system for a virus firewall, including a traffic capture module, a traffic identification module and a rule update module.

[0032] The traffic capture module is used to capture network traffic in real time, store the network traffic in a distributed manner in the blockchain, and optimize storage space through incremental storage and archive layered storage;

[0033] The traffic identification module is used to analyze the characteristic information of the network traffic through a deep learning model while storing the network traffic and identifying abnormal traffic;

[0034] The rule updating module is used to generate and adjust firewall rules by analyzing the abnormal traffic, and deploy them in the virus firewall in real time.

[0035] In order to achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention also provides an electronic device, including a memory and a processor, characterized in that the memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the digital twin three-dimensional visual safety monitoring method based on Beidou as described above are implemented.

[0036] In order to achieve one of the above-mentioned purposes of the invention, an embodiment of the present invention also provides a storage medium, which stores a computer program, and is characterized in that when the computer program is executed by a processor, the steps in the Beidou-based digital twin three-dimensional visual safety monitoring method are implemented as described above.

[0037] Compared with the prior art, the network traffic storage and update method and system for virus firewall provided by the present invention can better store and process network traffic through distributed blockchain, and adjust or adjust traffic according to actual needs. At the same time, according to the traffic pattern of network traffic, network traffic data information is provided in a block manner, and the entire data management is provided in a blockchain manner, which reduces the false alarm rate and response time, and reduces the difficulty of virus firewall configuration. The traffic data is distributed in multiple blockchain nodes so that information can be synchronized and shared between network nodes. Any node needs to provide complete data, which ensures the security of the data. When a network anomaly occurs in one of the nodes, the data will not be tampered with due to network failure, which improves the data integrity and accuracy of the information. Data and information are not tampered with or lost, which will not affect the detection of network behavior or data protection, and improve the stability of the system. In addition, the present invention also identifies malicious data through deep learning and machine learning models. Once a malicious attack is analyzed, firewall rules will be automatically and quickly generated and updated; as well as data acquisition and data management technology, known and unknown network traffic information is comprehensively processed and automatically adjusted, reducing manual intervention, and generating security rules, which improves the efficiency of security management personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is an overall flow chart of the network traffic storage and updating method for virus firewall described in the present invention.

[0039] Figure 2 It is a schematic diagram of the architecture of the network traffic storage and update system for the virus firewall described in the present invention. DETAILED DESCRIPTION

[0040] The present invention will be described in detail below in conjunction with the specific embodiments shown in the accompanying drawings. However, these embodiments do not limit the present invention, and any structural, methodological, or functional changes made by a person skilled in the art based on these embodiments are all included in the protection scope of the present invention.

[0041] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0042] In the first embodiment of the present invention, the present invention provides a network traffic storage and updating method for a virus firewall, such as Figure 1 As shown, the method includes,

[0043] S1: Capture network traffic in real time, store the network traffic in a distributed manner in the blockchain, and optimize storage space through incremental storage and archive tiered storage;

[0044] S2: while storing the network traffic, analyzing feature information of the network traffic through a deep learning model to identify abnormal traffic;

[0045] S3: By analyzing the abnormal traffic, adjusting and generating firewall rules, the rules are deployed in the virus firewall in real time.

[0046] In a specific embodiment of the present invention, real-time capture of network traffic is specifically,

[0047] Use network monitoring tools to capture network traffic in real time, including all transmitted network packets and metadata;

[0048] Preprocess the captured network traffic, including removing noise data and redundant information;

[0049] Perform feature extraction on the preprocessed network traffic, including extracting the spatial and temporal features of the network traffic.

[0050] It should be noted that the present invention can improve the interpretability and efficiency of data through preprocessing, identify the characteristics of network traffic, provide data support for subsequent firewall rules, and can intercept virus networks more accurately and quickly, effectively ensure the normal operation of the network, and reduce the management complexity of the virus firewall.

[0051] In a specific embodiment of the present invention, the network traffic is distributed and stored in the blockchain, specifically,

[0052] The structure of the blockchain adopts a consortium chain architecture, where multiple nodes jointly maintain the distributed storage of traffic data; the nodes include storage nodes and verification nodes;

[0053] The network traffic is divided into a plurality of traffic segments according to a preset size, and each traffic segment is stored as a traffic block; the traffic block includes a hash value and related metadata of the traffic segment;

[0054] The verification node uses a consensus algorithm to verify each traffic block, and adds the verified traffic blocks to different storage nodes of the local chain for storage.

[0055] It should be noted that the distributed storage method has the characteristics of autonomous operation, high fault tolerance, and anti-interference. It can identify abnormal traffic better and faster, effectively improve the detection efficiency of the virus firewall, and reduce the probability of detection accidents.

[0056] In a specific embodiment of the present invention, the storage space is optimized by incremental storage and archive layered storage, specifically,

[0057] The real-time captured network traffic is compared with the stored historical network traffic using a difference calculation algorithm, and the difference traffic is extracted and stored as incremental data;

[0058] The network traffic stored in the blockchain is stored in different storage tiers based on data importance and access frequency;

[0059] And archive network traffic that has not been accessed within a preset time to cold storage devices.

[0060] It should be noted that by storing network traffic in layers, it is possible to avoid a large amount of unnecessary storage data occupying most of the space, saving the cost of hardware provision for virus firewall managers, avoiding a large amount of waste of resources, and increasing the update rate of the virus firewall.

[0061] In a specific embodiment of the present invention, the characteristic information of the network traffic is analyzed by a deep learning model to identify abnormal traffic, specifically,

[0062] The deep learning model includes a convolutional neural network, a long short-term memory network and a deep fusion network;

[0063] The spatial features are analyzed by the convolutional neural network, and the temporal features are analyzed by the long short-term memory network. The outputs of the convolutional neural network and the long short-term memory network are used as inputs of the deep fusion network. By outputting the classification result of the network traffic, it is determined whether the network traffic is abnormal traffic.

[0064] It should be noted that the present invention combines convolutional neural networks and long short-term memory networks to jointly analyze network traffic, which greatly improves the recognition accuracy and recognition rate of abnormal traffic, and realizes intelligent judgment of whether network traffic is abnormal, thereby effectively deploying virus firewall rules and improving the update efficiency of virus firewall.

[0065] Furthermore, the spatial features of network traffic, such as network packet size, source IP address, destination IP address, packet interval, etc., are input into the convolutional network for feature learning through the convolutional neural network. By identifying and judging these spatial features, abnormal traffic can be effectively identified. The temporal features of network traffic, such as the timing relationship and frequency of data packets, are input into the long short-term memory unit through the long short-term memory network, and combined with the deep understanding of the neural network on the data flow, abnormal traffic can be accurately identified.

[0066] Furthermore, the convolutional network structure adopts a hierarchical convolutional network structure with five layers, including an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer. An n*9 data structure is input as a training set, and the output is an abnormal and normal classification result. The input of the long short-term memory network comes from the above abnormal traffic recognition result, and after passing through multiple long short-term memory units and pooling layers, the abnormal pattern and attack category are identified, and the abnormal value is updated.

[0067] Furthermore, a fusion layer is connected after the original convolutional neural network and long short-term memory network to connect the outputs of the two models into a high-dimensional feature vector, which is further processed through several layers of fully connected layers (or other suitable architectures) and finally outputs the final classification result.

[0068] In a specific embodiment of the present invention, the abnormal traffic is analyzed and adjusted and firewall rules are generated, specifically,

[0069] Determining the attack mode of the abnormal traffic, and determining whether to store a firewall rule for intercepting the attack mode;

[0070] If yes, analyze the threat level of the abnormal traffic, and dynamically adjust the firewall rules based on the real-time traffic and historical interception data of the abnormal traffic;

[0071] If not, then the attack pattern of the abnormal traffic is matched with similar attack patterns in the attack patterns intercepted by the existing firewall rules to generate targeted firewall rules.

[0072] Real-time detection of the current network environment, dynamic generation of firewall rules adapted to the current network environment through situational awareness technology, and prediction of possible attack types based on the firewall interception history and the current network environment situation, generating corresponding firewall rules in advance;

[0073] Whether there is a conflict between the newly generated rule and the existing rule is detected in real time; if there is, the conflict is resolved by adjusting or merging the newly generated rule.

[0074] Furthermore, the firewall rules include adding the attack pattern to the firewall rule set so that the firewall has the ability to intercept the attack pattern; setting the priority of the firewall rules to quickly detect and handle these attacks, and adding the IP address to the "blocked address / port" list in the firewall rules.

[0075] Furthermore, the firewall rules also include analyzing the characteristics of abnormal traffic data and matching known attack models. If the match is successful, a special firewall rule is generated.

[0076] Furthermore, when the firewall rules are generated or adjusted, they are updated to the current defense rule library in a timely manner. In addition, the defense rule library also includes the effectiveness conditions of the firewall rules, such as time and location, to limit the effectiveness of certain rules at specific times or specific IP addresses; the time period of the firewall rules.

[0077] Preferably, the firewall rules are adjusted dynamically, accurately and timely in combination with the current network environment, historical data and system predictions; for more aggressive rules, such as dynamically adjusting IP restriction information, a short-term effective strategy is adopted.

[0078] Furthermore, in some implementations of the present invention, the conflict between the newly generated rule and the existing rule includes the matching degree between the firewall rule and the existing rule, the source IP of different data, and the IP addresses of different databases.

[0079] Furthermore, rule adjustments include: if the conflict mainly involves rule priority, the system can automatically adjust the priority of new and existing rules to ensure that the firewall applies the rules in the expected order; if the new and existing rules conflict in terms of conditions, the system may adjust the conditions of the new rule so that it does not conflict with the existing rules. For example, the conditions of the new rule are limited to a range that does not overlap with the existing rules.

[0080] Furthermore, rule merging includes merging the conditions of multiple rules into one rule, such as merging restrictions on multiple IP addresses into one rule; merging the actions of multiple rules (such as blocking, allowing), for example, if multiple rules block similar traffic, these rules may be merged into a more general blocking rule.

[0081] It should be noted that the present invention can generate more quickly and effectively by classifying viruses in network information, and by analyzing the threat level of network traffic, it can better deploy virus firewalls, greatly improve the anti-virus capabilities of virus firewalls, and ensure network security.

[0082] It should be noted that the present invention combines the deployment of firewall rules with the network environment, can dynamically adjust the firewall rules according to changes in the network environment, improves the security prevention capabilities of the virus firewall, and effectively reduces the occurrence of erroneous rule updates due to complex situations.

[0083] It should be noted that the present invention processes network traffic at multiple levels and finally feeds it back to the virus firewall, forming a closed-loop control. Each network traffic is detected and identified at each stage, which greatly improves the security and accuracy of the virus firewall.

[0084] In the second embodiment of the present invention, the present invention provides a network traffic storage and update system for a virus firewall, including a traffic capture module, a traffic identification module and a rule update module, such as Figure 2 shown.

[0085] The traffic capture module is used to capture network traffic in real time, store the network traffic in a distributed manner in the blockchain, and optimize storage space through incremental storage and archive layered storage;

[0086] The traffic identification module is used to analyze the characteristic information of the network traffic through a deep learning model while storing the network traffic and identifying abnormal traffic;

[0087] The rule updating module is used to generate and adjust firewall rules by analyzing the abnormal traffic, and deploy them in the virus firewall in real time.

[0088] In a third embodiment of the present invention, the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the distributed training scheduling method based on SDN networking as described above are implemented.

[0089] In a fourth embodiment of the present invention, the present invention provides a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps in the distributed training scheduling method based on SDN networking as described above.

[0090] In summary, the network traffic storage and update method and system for virus firewall provided by the present invention can better store and process network traffic through distributed blockchain, and adjust or adjust traffic according to actual needs. At the same time, according to the traffic pattern of network traffic, network traffic data information is provided in a block manner, and the entire data management is provided in a blockchain manner, which reduces the false alarm rate and response time, and reduces the difficulty of virus firewall configuration. The traffic data is distributed in multiple blockchain nodes so that information can be synchronized and shared between network nodes. Any node needs to provide complete data, which ensures the security of the data. When a network anomaly occurs in one of the nodes, the data will not be tampered with due to network failure, which improves the data integrity and accuracy of the information. Data and information are not tampered with or lost, which will not affect the detection or data protection of network behavior, and improve the stability of the system. In addition, the present invention also identifies malicious data through deep learning and machine learning models. Once a malicious attack is analyzed, firewall rules will be automatically and quickly generated and updated; as well as data acquisition and data management technology, known and unknown network traffic information is comprehensively processed and automatically adjusted, reducing manual intervention, and generating security rules, which improves the efficiency of security management personnel.

[0091] It should be understood that although this specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each implementation mode may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

[0092] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the modules described above can refer to the corresponding process in the aforementioned method implementation, and will not be repeated here.

[0093] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present implementation scheme.

[0094] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0095] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for a computer system (which can be a personal computer, a server, or a network system, etc.) or a processor to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0096] Finally, it should be noted that the above implementation modes are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned implementation modes, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned implementation modes, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various implementation modes of the present application.

Claims

1. A network traffic storage and update method for a virus firewall, characterized in that: include, Capture network traffic in real time, store it in a distributed manner in the blockchain, and optimize storage space through incremental storage and archive tiered storage; While storing the network traffic, analyzing feature information of the network traffic through a deep learning model to identify abnormal traffic; By analyzing the abnormal traffic, adjusting and generating firewall rules, the rules are deployed in the virus firewall in real time.

2. The network traffic storage and updating method for virus firewall according to claim 1 is characterized in that: The real-time capture of network traffic includes: Use network monitoring tools to capture network traffic in real time, including all transmitted network packets and metadata; Preprocess the captured network traffic, including removing noise data and redundant information; Perform feature extraction on the preprocessed network traffic, including extracting the spatial and temporal features of the network traffic.

3. The network traffic storage and updating method for virus firewall according to claim 2 is characterized in that: The distributed storage of the network traffic in the blockchain includes: The structure of the blockchain adopts a consortium chain architecture, where multiple nodes jointly maintain the distributed storage of traffic data; the nodes include storage nodes and verification nodes; The network traffic is divided into a plurality of traffic segments according to a preset size, and each traffic segment is stored as a traffic block; the traffic block includes a hash value and related metadata of the traffic segment; The verification node uses a consensus algorithm to verify each traffic block, and adds the verified traffic blocks to different storage nodes of the local chain for storage.

4. The network traffic storage and updating method for virus firewall according to claim 3 is characterized in that: The optimization of storage space by incremental storage and archive tiered storage includes: The real-time captured network traffic is compared with the stored historical network traffic using a difference calculation algorithm, and the difference traffic is extracted and stored as incremental data; The network traffic stored in the blockchain is stored in different storage tiers based on data importance and access frequency; And archive network traffic that has not been accessed within a preset time to cold storage devices.

5. The network traffic storage and updating method for virus firewall according to claim 2 is characterized in that: The “identifying abnormal traffic by analyzing the characteristic information of the network traffic through a deep learning model” includes: The deep learning model includes a convolutional neural network, a long short-term memory network and a deep fusion network; The spatial features are analyzed by the convolutional neural network, and the temporal features are analyzed by the long short-term memory network. The outputs of the convolutional neural network and the long short-term memory network are used as inputs of the deep fusion network. By outputting the classification result of the network traffic, it is determined whether the network traffic is abnormal traffic.

6. The network traffic storage and updating method for virus firewall according to claim 5 is characterized in that: The "adjusting and generating firewall rules by analyzing the abnormal traffic" includes: Determining the attack mode of the abnormal traffic, and determining whether to store a firewall rule for intercepting the attack mode; If yes, analyze the threat level of the abnormal traffic, and dynamically adjust the firewall rules based on the real-time traffic and historical interception data of the abnormal traffic; If not, then the attack pattern of the abnormal traffic is matched with similar attack patterns in the attack patterns intercepted by the existing firewall rules to generate targeted firewall rules.

7. The network traffic storage and updating method for virus firewall according to claim 6 is characterized in that: The "adjusting and generating firewall rules by analyzing the abnormal traffic" also includes: Real-time detection of the current network environment, dynamic generation of firewall rules adapted to the current network environment through situational awareness technology, and prediction of possible attack types based on the firewall interception history and the current network environment situation, generating corresponding firewall rules in advance; Real-time detection of conflicts between newly generated rules and existing rules; If there is, the conflict is resolved by adjusting or merging the newly generated rules.

8. A network traffic storage and update system for a virus firewall, comprising a traffic capture module, a traffic identification module and a rule update module, characterized in that: The traffic capture module is used to capture network traffic in real time, store the network traffic in a distributed manner in the blockchain, and optimize storage space through incremental storage and archive layered storage; The traffic identification module is used to analyze the characteristic information of the network traffic through a deep learning model while storing the network traffic and identifying abnormal traffic; The rule updating module is used to generate and adjust firewall rules by analyzing the abnormal traffic, and deploy them in the virus firewall in real time.

9. An electronic device, comprising a memory and a processor, characterized in that: The memory stores a computer program that can be run on the processor, and when the program is executed on the processor, the steps in the network traffic storage and update method for a virus firewall as described in any one of claims 1-7 are implemented.

10. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the network traffic storage and updating method for a virus firewall as described in any one of claims 1 to 7 are implemented.