System and method for dynamically optimizing monitoring strategy of voice and video local area network

Abstract

The invention discloses a dynamic optimization system and method for a voice and video local area network monitoring strategy, relates to the technical field of local area network monitoring, and discloses a local area network communication marking module, a monitoring grade determining module, a monitoring strategy reserving module and a monitoring strategy optimization module. A local area network communication marking module, a monitoring grade determining module and a monitoring strategy reserving module are arranged, deep analysis can be carried out on corresponding voice and video terminals according to all established voice and video communication in the voice and video local area network, the local area network resource occupation condition faced by the established voice and video communication is comprehensively analyzed, and the voice and video communication efficiency is improved. A monitoring strategy optimization module is arranged, communication risks which will be encountered by a voice and video local area network in the actual communication process can be simulated by constructing audio and video simulation communication models of different communication risk types, simulated monitoring analysis is conducted on each monitoring strategy, and the communication risk can be optimized. And the monitoring condition of the monitoring strategy on various types of communication risks is analyzed.

Description

Technical Field

[0001] The present invention relates to the field of local area network monitoring technology, and more specifically, to a voice and video local area network monitoring strategy dynamic optimization system and method. Background Art

[0002] With the rapid development of information technology, voice and video LANs have been widely used in enterprises, education, medical and other fields. These LANs support real-time communication between multiple voice and video terminals, greatly improving work efficiency and communication effects. However, with the popularity and complexity of voice and video communications, LANs are facing increasing resource occupation and security risks.

[0003] Traditional LAN monitoring strategies often use static configurations, that is, monitoring the LAN according to preset rules and thresholds. However, this static strategy is difficult to adapt to the ever-changing communication environment and business needs. When the volume of voice and video communications increases or the communication mode changes, the static strategy may not be able to make timely adjustments, resulting in resource bottlenecks or security risks.

[0004] To meet this challenge, researchers have begun to explore methods to dynamically optimize monitoring strategies. These methods analyze the communication behavior, resource usage, and potential security risks of voice and video terminals, and dynamically adjust monitoring strategies to ensure efficient operation, security, and stability of the LAN.

[0005] However, existing dynamic optimization methods still have some shortcomings. For example, some methods only focus on resource usage and ignore the impact of communication risks on LAN security; other methods consider communication risks but lack the detailed classification of different risk types and the formulation of targeted monitoring strategies.

[0006] Therefore, there is an urgent need for a system and method that can comprehensively consider resource occupancy and communication risks and dynamically optimize monitoring strategies. Summary of the invention

[0007] In view of the deficiencies in the prior art, the present invention aims to provide a system and method for dynamically optimizing voice and video local area network monitoring strategies.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A dynamic optimization system for voice and video LAN monitoring strategies, including a LAN communication marking module, a monitoring level determination module, a monitoring strategy reservation module, and a monitoring strategy optimization module;

[0010] When voice and video communication is established in the voice and video LAN, the LAN communication marking module marks all voice and video terminals that establish voice and video communication as audio and video monitoring terminals, and obtains a preset value of the monitoring strategy;

[0011] The monitoring level determination module is used to determine the predetermined monitoring level of the voice and video local area network according to the predetermined value of the monitoring strategy;

[0012] The monitoring strategy presetting module marks all the pre-set monitoring strategies corresponding to the pre-set monitoring levels as preliminary monitoring strategies;

[0013] The monitoring strategy optimization module builds an audio-visual simulation communication model for each communication risk type based on the terminal behavior characteristics of each audio-visual monitoring terminal, obtains the monitoring satisfaction value of each preliminary monitoring strategy, marks the preliminary monitoring strategy with the largest monitoring satisfaction value as the determined monitoring strategy, uses the determined monitoring strategy to monitor the voice and video local area network, and stops monitoring when a voice and video disconnection is established in the voice and video local area network.

[0014] Furthermore, the method for obtaining the preset value of the monitoring strategy is as follows: obtain the audio and video communication behavior value of each audio and video monitoring terminal, match all audio and video monitoring terminals into an audio and video interaction group, obtain the audio and video interaction value of each audio and video interaction group, set the audio and video interaction threshold, and when the audio and video interaction value of the audio and video interaction group is greater than the audio and video interaction threshold, mark the audio and video interaction group as an occupied interaction group, sum the audio and video communication behavior values ​​of all audio and video monitoring terminals and take the average to obtain the communication behavior mean Ksdw, mark the total number of occupied interaction groups as Sau, and use the formula SKi=(Ksdw+v1)*(Sau+v2) to obtain the monitoring strategy preset value SKi.

[0015] Furthermore, the audio and video communication behavior value of the audio and video monitoring terminal is obtained as follows: all terminal behavior data of the audio and video monitoring terminal before the current time of the system are collected, all terminal behavior data are preprocessed and feature extracted to obtain terminal behavior features, and an audio and video communication behavior model is obtained, and the terminal behavior features are used as input data of the audio and video communication behavior model. The audio and video communication behavior value of the audio and video monitoring terminal is obtained by the output of the audio and video communication behavior model.

[0016] Furthermore, the audio-visual interaction value of the audio-visual interaction group is obtained as follows: the audio-visual communication behavior values ​​of the two audio-visual monitoring terminals in the audio-visual interaction group are summed to obtain the audio-visual interaction value of the audio-visual interaction group.

[0017] Furthermore, the predetermined monitoring level of the voice and video LAN is determined according to the predetermined monitoring strategy value, and the specific steps are as follows: a total of i predetermined monitoring levels are set, namely predetermined monitoring level 1, predetermined monitoring level 2, ..., predetermined monitoring level i-1, and predetermined monitoring level i, and the predetermined monitoring strategy value within each range corresponds to a predetermined monitoring level. The range of the predetermined monitoring strategy value includes (0, SK1], (SK1, SK2], ..., (SKi-1, SKi], the LAN resource occupancy of the predetermined monitoring level 1 is greater than the LAN resource occupancy of the predetermined monitoring level 2, the LAN resource occupancy of the predetermined monitoring level i-1, and the LAN resource occupancy of the predetermined monitoring level i, and each predetermined monitoring level corresponds to multiple predetermined monitoring strategies.

[0018] Furthermore, a communication risk type audio and video simulation communication model is constructed as follows: select simulation software such as OPNET and NS2, create a local area network model in the simulation software, the local area network model includes various audio and video monitoring terminals, and set the communication relationship between various audio and video monitoring terminals according to the network topology. Set corresponding communication parameters based on the terminal behavior characteristics of the audio and video monitoring terminals, including network delay, packet loss rate, data packet size, and sending frequency, add corresponding risk parameters involved in a communication risk type, and then construct an audio and video simulation communication model of the communication risk type.

[0019] Furthermore, the monitoring satisfaction value of the preliminary monitoring strategy is obtained as follows: input a preliminary monitoring strategy into the audio-visual simulation communication model of each communication risk type, obtain the monitoring feedback value of the audio-visual simulation communication model of each communication risk type, compare all the monitoring feedback values ​​in pairs, calculate the difference of the compared monitoring feedback values ​​and take the absolute value to obtain the monitoring feedback gap value, sum up all the monitoring feedback gap values ​​and take the average to obtain the monitoring feedback mean distance value Fzg, sum up all the monitoring feedback values ​​and take the average to obtain the monitoring feedback average value Pkg, and use the formula The monitoring satisfaction value Xkr of the primary monitoring strategy is obtained, where wa is the monitoring feedback mean coefficient and wb is the monitoring feedback average coefficient.

[0020] Furthermore, the monitoring feedback value of an audio-visual simulation communication model of a communication risk type is obtained as follows: an audio-visual simulation communication model of a communication risk type performs simulated communication, and uses a preliminary monitoring strategy to monitor the audio-visual simulation communication model for T time. After the monitoring is completed, monitoring data is generated, and the monitoring data is preprocessed and features are advanced to obtain monitoring features, and a monitoring feedback model corresponding to the communication risk type is obtained, and the monitoring features are used as input data of the monitoring feedback model. The monitoring feedback model outputs the monitoring feedback value.

[0021] Furthermore, the method for dynamically optimizing the voice and video LAN monitoring strategy includes the following steps:

[0022] Step 1: When voice and video communication is established in the voice and video LAN, all voice and video terminals that establish voice and video communication are marked as audio and video monitoring terminals, and a monitoring strategy preset value is obtained;

[0023] Step 2: Determine the predetermined monitoring level of the voice and video local area network according to the predetermined value of the monitoring strategy;

[0024] Step 3: Mark all the predetermined monitoring strategies corresponding to the predetermined monitoring levels as preliminary monitoring strategies;

[0025] Step 4: construct an audio-visual simulation communication model for each communication risk type based on the terminal behavior characteristics of each audio-visual monitoring terminal, obtain the monitoring satisfaction value of each preliminary monitoring strategy, and mark the preliminary monitoring strategy with the largest monitoring satisfaction value as the decision monitoring strategy;

[0026] Step 5: Use the determined monitoring strategy to monitor the voice and video LAN. When the voice and video are disconnected in the voice and video LAN, stop monitoring.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The method of the present invention dynamically selects a monitoring strategy with higher monitoring effectiveness and pertinence for actual monitoring, and comprehensively ensures that the selection of the monitoring strategy meets resource and security requirements;

[0029] 2. Set up a LAN communication marking module, a monitoring level determination module, and a monitoring strategy reservation module. According to all the established voice and video communications in the voice and video LAN, the corresponding voice and video terminals can be deeply analyzed, and the LAN resource occupancy faced by the established voice and video communications can be comprehensively analyzed. Through the monitoring level classification system, different monitoring strategies are divided into detailed categories according to the differences in LAN resource occupancy, and multiple monitoring strategies with reasonable LAN resource occupancy are dynamically selected to ensure that the monitoring strategy will not have the risk of resource bottlenecks in the voice and video LAN, and ensure that the system can cope with voice and video communication scenarios of different scales and complexities. Set up a monitoring strategy optimization module, and by constructing audio and video simulation communication models of different communication risk types, it can simulate the communication risks that the voice and video LAN will encounter in the actual communication process, and conduct simulated monitoring analysis on each monitoring strategy to analyze the monitoring situation of the monitoring strategy for various types of communication risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 System module diagram for dynamic optimization system of voice and video LAN monitoring strategy;

[0031] Figure 2 A method flow chart of a method for dynamically optimizing a voice and video LAN monitoring strategy;

[0032] Figure 3 The present invention is a flow chart for obtaining monitoring feedback values ​​of an audio-visual simulation communication model of a communication risk type. DETAILED DESCRIPTION

[0033] Example 1: Reference Figure 1 , the method for dynamic optimization of voice and video LAN monitoring strategy includes the following steps:

[0034] Step 1: When voice and video communication is established in the voice and video local area network, all voice and video terminals that establish voice and video communication are marked as audio and video monitoring terminals, and a monitoring strategy preset value is obtained.

[0035] Step 2: Determine the predetermined monitoring level of the voice and video LAN according to the predetermined value of the monitoring strategy.

[0036] Step 3: Mark all the predetermined monitoring strategies corresponding to the predetermined monitoring levels as preliminary monitoring strategies.

[0037] Step 4: Build an audio-visual simulation communication model for each communication risk type based on the terminal behavior characteristics of each audio-visual monitoring terminal, obtain the monitoring satisfaction value of each preliminary monitoring strategy, and mark the preliminary monitoring strategy with the largest monitoring satisfaction value as the decision monitoring strategy.

[0038] Step 5: Use the determined monitoring strategy to monitor the voice and video LAN. When the voice and video are disconnected in the voice and video LAN, stop monitoring.

[0039] The above method dynamically selects a monitoring strategy with higher monitoring effectiveness and pertinence for actual monitoring, and comprehensively ensures that the selection of the monitoring strategy meets resource and security requirements.

[0040] Example 2: Reference Figure 2-Figure 3 The voice and video LAN monitoring strategy dynamic optimization system includes a LAN communication marking module, a monitoring level determination module, a monitoring strategy reservation module, and a monitoring strategy optimization module.

[0041] LAN communication marking module: When voice and video communication is established in the voice and video LAN (the voice and video LAN contains multiple voice and video terminals, and voice and video communication means that two or more voice and video terminals appear in the voice and video LAN to generate a voice and video connection. Once the voice and video communication is established, it needs to be monitored), all voice and video terminals that establish voice and video communication will be marked as audio and video monitoring terminals, and the preset value of the monitoring strategy will be obtained.

[0042] The method for obtaining the preset value of the monitoring strategy is as follows: obtain the audio-visual communication behavior value of each audio-visual monitoring terminal, match all audio-visual monitoring terminals into an audio-visual interaction group, obtain the audio-visual interaction value of each audio-visual interaction group, set the audio-visual interaction threshold (the audio-visual interaction threshold is a preset threshold), when the audio-visual interaction value of the audio-visual interaction group is greater than the audio-visual interaction threshold, mark the audio-visual interaction group as an occupied interaction group, when the audio-visual interaction value of the audio-visual interaction group is less than or equal to the audio-visual interaction threshold, no processing is performed, the audio-visual communication behavior values ​​of all audio-visual monitoring terminals are summed and averaged to obtain the communication behavior mean Ksdw, mark the total number of occupied interaction groups as Sau, and use the formula SKi = (Ksdw + v1) * (Sau + v2) to obtain the monitoring strategy preset value SKi, v1 is the communication behavior mean coefficient, v2 is the occupied interaction number coefficient, the value of v1 is 0.84, and the value of v2 is 0.97.

[0043] The audio-visual interaction value of the audio-visual interaction group is obtained as follows: the audio-visual communication behavior values ​​of the two audio-visual monitoring terminals in the audio-visual interaction group are summed to obtain the audio-visual interaction value of the audio-visual interaction group.

[0044] The method for obtaining the audio and video communication behavior value of the audio and video monitoring terminal is as follows: collect all terminal behavior data of the audio and video monitoring terminal before the current time of the system (the terminal behavior data will be generated after the voice and video communication is established, including the voice and video communication duration, voice and video communication frequency, audio quality, video resolution and other data of the audio and video monitoring terminal), preprocess and extract features of all terminal behavior data (preprocessing includes data cleaning, denoising, normalization and other steps, feature extraction includes statistical feature extraction, frequency domain feature extraction and other steps), obtain terminal behavior features, obtain the audio and video communication behavior model, use the terminal behavior features as the input data of the audio and video communication behavior model, and output the audio and video communication behavior value of the audio and video monitoring terminal.

[0045] The audio-visual communication behavior model is constructed as follows: collect multiple terminal behavior data, the terminal behavior data can be the real characteristics of the audio-visual monitoring terminal, or it can be a virtually set feature for building the audio-visual communication behavior model, build a deep learning model, use the terminal behavior data as the training data of the deep learning model, assign an audio-visual communication behavior value to each training data, the audio-visual communication behavior value range is (1.0~6.0), the larger the audio-visual communication behavior value, the more LAN resources the audio-visual monitoring terminal occupies, the smaller the audio-visual communication behavior value, the fewer LAN resources the audio-visual monitoring terminal occupies, and divide the training data into a training set and a validation set according to a set ratio of 4:1, train the training set and the validation set, and after the training is completed, the audio-visual communication behavior model is constructed.

[0046] Monitoring level determination module: determines the predetermined monitoring level of the voice and video LAN according to the predetermined value of the monitoring strategy.

[0047] Monitoring strategy reservation module: all the scheduled monitoring strategies corresponding to the scheduled monitoring levels are marked as preliminary monitoring strategies.

[0048] The predetermined monitoring level of the voice and video local area network is determined according to the predetermined value of the monitoring strategy. The specific steps are as follows: a total of i predetermined monitoring levels are set, namely predetermined monitoring level 1, predetermined monitoring level 2, ..., predetermined monitoring level i-1, and predetermined monitoring level i. The predetermined monitoring value of the monitoring strategy in each range corresponds to a predetermined monitoring level. The range of the predetermined monitoring value of the monitoring strategy includes (0, SK1], (SK1, SK2], ..., (SKi-1, SKi]. When the predetermined monitoring value SKi∈(SK1, SK2], the predetermined monitoring level of the voice and video local area network is determined to be predetermined monitoring level 2. The LAN resource occupancy of the predetermined monitoring level 1 is greater than the LAN resource occupancy of the predetermined monitoring level 2, the LAN resource occupancy of the predetermined monitoring level i-1 is greater than the LAN resource occupancy of the predetermined monitoring level i. Each predetermined monitoring level corresponds to multiple predetermined monitoring strategies, and the multiple predetermined monitoring strategies all meet the LAN resource occupancy of the predetermined monitoring level.

[0049] By setting up a LAN communication marking module, a monitoring level determination module and a monitoring strategy reservation module, it is possible to conduct in-depth analysis of the corresponding voice and video terminals based on all established voice and video communications in the voice and video LAN, comprehensively analyze the LAN resource occupancy faced by the established voice and video communications, and use a monitoring level classification system to make detailed divisions of different monitoring strategies based on the differences in LAN resource occupancy, and dynamically select multiple monitoring strategies with reasonable LAN resource occupancy to ensure that the monitoring strategy will not present the risk of resource bottlenecks in the voice and video LAN, and ensure that the system can cope with voice and video communication scenarios of different scales and complexities.

[0050] Monitoring strategy optimization module: Build an audio-visual simulation communication model for each communication risk type based on the terminal behavior characteristics of each audio-visual monitoring terminal (communication risk types include voice and video leakage risk, terminal failure risk, etc.), obtain the monitoring satisfaction value of each preliminary monitoring strategy, mark the preliminary monitoring strategy with the largest monitoring satisfaction value as the decision monitoring strategy, use the decision monitoring strategy to monitor the voice and video LAN, and stop monitoring when the voice and video disconnection is established in the voice and video LAN.

[0051] The method of constructing an audio and video simulation communication model of a communication risk type is as follows: select simulation software such as OPNET and NS2, and create a local area network model in the simulation software. The local area network model includes various audio and video monitoring terminals. According to the topology of the network, the communication relationship between each audio and video monitoring terminal is set, and the corresponding communication parameters are set based on the terminal behavior characteristics of the audio and video monitoring terminal, including network delay, packet loss rate, data packet size, sending frequency, etc., and a corresponding risk parameter involved in a communication risk type is added to construct an audio and video simulation communication model of the communication risk type.

[0052] The monitoring satisfaction value of the preliminary monitoring strategy is obtained as follows: input a preliminary monitoring strategy into the audio-visual simulation communication model of each communication risk type (the preliminary monitoring strategy can be converted into a format or script that can be recognized by the audio-visual simulation communication model for input), obtain the monitoring feedback value of the audio-visual simulation communication model of each communication risk type, compare all monitoring feedback values ​​in pairs, calculate the difference between the compared monitoring feedback values ​​and take the absolute value to obtain the monitoring feedback gap value, sum up all monitoring feedback gap values ​​and take the average to obtain the monitoring feedback mean distance value Fzg, sum up all monitoring feedback values ​​and take the average to obtain the monitoring feedback average value Pkg, and use the formula The monitoring satisfaction value Xkr of the primary monitoring strategy is obtained, where wa is the monitoring feedback mean coefficient, wb is the monitoring feedback average coefficient, the value of wa is 3.12, and the value of wb is 1.35.

[0053] A method for obtaining the monitoring feedback value of an audio-visual simulation communication model of a communication risk type is as follows: an audio-visual simulation communication model of a communication risk type performs simulated communication, and uses a preliminary monitoring strategy to monitor the audio-visual simulation communication model for T time. After the monitoring is completed, monitoring data is generated, and the monitoring data is preprocessed and features are advanced to obtain monitoring features, and a monitoring feedback model corresponding to the communication risk type is obtained, and the monitoring features are used as input data of the monitoring feedback model. The monitoring feedback model outputs the monitoring feedback value.

[0054] Each communication risk type corresponds to a monitoring feedback model, and each monitoring feedback model is constructed based on deep learning. In this embodiment, the monitoring feedback models of two communication risk types are disclosed as examples. First, the construction process of the monitoring feedback model of voice and video leakage risk is disclosed in detail, and then the construction process of the monitoring feedback model of terminal failure risk is briefly disclosed.

[0055] The process of constructing the monitoring feedback model of voice and video leakage risk is as follows: collect multiple monitoring features, build a deep school model, use the monitoring features as training data for the deep school model, assign a monitoring feedback value to each training data, and the monitoring feedback value range is (1.0~3.0). The larger the monitoring feedback value, the more comprehensive the voice and video leakage risk detected by the preliminary monitoring strategy; the smaller the monitoring feedback value, the less comprehensive the voice and video leakage risk detected by the preliminary monitoring strategy. The training data is divided into training set, verification set and validation set according to the set ratio of 5:1:1, and the training set, verification set and validation set are trained. After the training is completed, the construction of the monitoring feedback model of voice and video leakage risk is completed.

[0056] The process of constructing the monitoring feedback model for terminal failure risk is as follows: the larger the monitoring feedback value, the more comprehensive the terminal failure risk detected by the preliminary monitoring strategy; the smaller the monitoring feedback value, the less comprehensive the terminal failure risk detected by the preliminary monitoring strategy. The rest is consistent with the construction process of the monitoring feedback model for voice and video leakage risk.

[0057] A monitoring strategy optimization module is set up. By constructing audio and video simulation communication models of different communication risk types, the communication risks that the voice and video LAN will encounter in the actual communication process can be simulated, and each monitoring strategy can be simulated for monitoring analysis to analyze the monitoring situation of the monitoring strategy for various types of communication risks, and dynamically select monitoring strategies with higher monitoring effectiveness and pertinence for actual monitoring, to comprehensively ensure that the selection of monitoring strategies meets resource and security requirements.

[0058] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0059] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0060] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0061] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0062] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0063] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0064] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0065] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Voice and video LAN monitoring strategy dynamic optimization system, characterized by: It includes a LAN communication marking module, a monitoring level determination module, a monitoring strategy reservation module, and a monitoring strategy optimization module; When voice and video communication is established in the voice and video LAN, the LAN communication marking module marks all voice and video terminals that establish voice and video communication as audio and video monitoring terminals, and obtains a preset value of the monitoring strategy; The monitoring level determination module is used to determine the predetermined monitoring level of the voice and video local area network according to the predetermined value of the monitoring strategy; The monitoring strategy presetting module marks all the pre-set monitoring strategies corresponding to the pre-set monitoring levels as preliminary monitoring strategies; The monitoring strategy optimization module builds an audio-visual simulation communication model for each communication risk type based on the terminal behavior characteristics of each audio-visual monitoring terminal, obtains the monitoring satisfaction value of each preliminary monitoring strategy, marks the preliminary monitoring strategy with the largest monitoring satisfaction value as the determined monitoring strategy, uses the determined monitoring strategy to monitor the voice and video local area network, and stops monitoring when a voice and video disconnection is established in the voice and video local area network.

2. The voice and video LAN monitoring strategy dynamic optimization system according to claim 1 is characterized in that: The method for obtaining the preset value of the monitoring strategy is as follows: obtain the audio and video communication behavior value of each audio and video monitoring terminal, match all audio and video monitoring terminals into an audio and video interaction group, obtain the audio and video interaction value of each audio and video interaction group, set the audio and video interaction threshold, and when the audio and video interaction value of the audio and video interaction group is greater than the audio and video interaction threshold, mark the audio and video interaction group as an occupied interaction group, sum the audio and video communication behavior values ​​of all audio and video monitoring terminals and take the average to obtain the communication behavior mean Ksdw, mark the total number of occupied interaction groups as Sau, and use the formula SKi=(Ksdw+v1)*(Sau+v2) to obtain the preset value SKi of the monitoring strategy.

3. The voice and video LAN monitoring strategy dynamic optimization system according to claim 2 is characterized in that: The method for obtaining the audio and video communication behavior value of the audio and video monitoring terminal is as follows: collect all terminal behavior data of the audio and video monitoring terminal before the current time of the system, preprocess and extract features of all terminal behavior data to obtain terminal behavior features, obtain the audio and video communication behavior model, and use the terminal behavior features as the input data of the audio and video communication behavior model. The audio and video communication behavior value of the audio and video monitoring terminal is obtained by the output of the audio and video communication behavior model.

4. The voice and video LAN monitoring strategy dynamic optimization system according to claim 2 is characterized in that: The audio-visual interaction value of the audio-visual interaction group is obtained as follows: the audio-visual communication behavior values ​​of the two audio-visual monitoring terminals in the audio-visual interaction group are summed to obtain the audio-visual interaction value of the audio-visual interaction group.

5. The voice and video LAN monitoring strategy dynamic optimization system according to claim 1 is characterized in that: The predetermined monitoring level of the voice and video local area network is determined according to the predetermined value of the monitoring strategy. The specific steps are as follows: a total of i predetermined monitoring levels are set, namely predetermined monitoring level 1, predetermined monitoring level 2, ..., predetermined monitoring level i-1, and predetermined monitoring level i. The predetermined monitoring strategy value in each range corresponds to a predetermined monitoring level. The range of the predetermined monitoring strategy value includes (0, SK1], (SK1, SK2], ..., (SKi-1, SKi], the LAN resource occupancy of the predetermined monitoring level 1 is greater than the LAN resource occupancy of the predetermined monitoring level 2, the LAN resource occupancy of the predetermined monitoring level i-1, and the LAN resource occupancy of the predetermined monitoring level i. Each predetermined monitoring level corresponds to multiple predetermined monitoring strategies.

6. The voice and video LAN monitoring strategy dynamic optimization system according to claim 1 is characterized in that: The method of constructing an audio and video simulation communication model of a communication risk type is as follows: select simulation software such as OPNET and NS2, and create a local area network model in the simulation software. The local area network model includes various audio and video monitoring terminals. According to the network topology, the communication relationship between each audio and video monitoring terminal is set, and the corresponding communication parameters are set based on the terminal behavior characteristics of the audio and video monitoring terminal, including network delay, packet loss rate, data packet size, and sending frequency. Add the corresponding risk parameters involved in a communication risk type, and then construct an audio and video simulation communication model of the communication risk type.

7. The voice and video LAN monitoring strategy dynamic optimization system according to claim 1 is characterized in that: The monitoring satisfaction value of the preliminary monitoring strategy is obtained as follows: input a preliminary monitoring strategy into the audio-visual simulation communication model of each communication risk type, obtain the monitoring feedback value of the audio-visual simulation communication model of each communication risk type, compare all the monitoring feedback values ​​in pairs, calculate the difference between the compared monitoring feedback values ​​and take the absolute value to obtain the monitoring feedback gap value, sum up all the monitoring feedback gap values ​​and take the average to obtain the monitoring feedback mean distance value Fzg, sum up all the monitoring feedback values ​​and take the average to obtain the monitoring feedback average value Pkg, and use the formula The monitoring satisfaction value Xkr of the primary monitoring strategy is obtained, where wa is the monitoring feedback mean distance coefficient and wb is the monitoring feedback average coefficient.

8. The voice and video LAN monitoring strategy dynamic optimization system according to claim 7 is characterized in that: A method for obtaining the monitoring feedback value of an audio-visual simulation communication model of a communication risk type is as follows: an audio-visual simulation communication model of a communication risk type performs simulated communication, and uses a preliminary monitoring strategy to monitor the audio-visual simulation communication model for T time. After the monitoring is completed, monitoring data is generated, and the monitoring data is preprocessed and features are advanced to obtain monitoring features, and a monitoring feedback model corresponding to the communication risk type is obtained, and the monitoring features are used as input data of the monitoring feedback model. The monitoring feedback model outputs the monitoring feedback value.

9. A method for dynamically optimizing a voice and video local area network monitoring strategy, applied to a system for dynamically optimizing a voice and video local area network monitoring strategy as claimed in any one of claims 1 to 8, characterized in that: The steps include: Step 1: When voice and video communication is established in the voice and video local area network, all voice and video terminals that establish voice and video communication are marked as audio and video monitoring terminals, and a monitoring strategy preset value is obtained; Step 2: Determine the predetermined monitoring level of the voice and video local area network according to the predetermined value of the monitoring strategy; Step 3: Mark all the predetermined monitoring strategies corresponding to the predetermined monitoring levels as preliminary monitoring strategies; Step 4: construct an audio-visual simulation communication model for each communication risk type based on the terminal behavior characteristics of each audio-visual monitoring terminal, obtain the monitoring satisfaction value of each preliminary monitoring strategy, and mark the preliminary monitoring strategy with the largest monitoring satisfaction value as the decision monitoring strategy; Step 5: Use the determined monitoring strategy to monitor the voice and video LAN. When the voice and video are disconnected in the voice and video LAN, stop monitoring.

Images