A computer network data flow monitoring system and method
Through the design of the computer network data traffic monitoring system, including abnormal traffic analysis, network interface analysis and memory detection module, the problem of difficulty in monitoring and managing computer network data traffic in the existing technology is solved, and the network security and performance guarantees are achieved , ensuring timely response to potential threats.
Patent Information
- Application Number
- CN202111270297.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-10-29
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2041-10-29
AI Technical Summary
The existing technology is difficult to effectively monitor and manage computer network data traffic, resulting in network security and performance problems, especially in the face of a large number of users and potential security threats, which are difficult to detect and respond in a timely manner.
A computer network data traffic monitoring system was designed, including an abnormal traffic analysis module, a network interface analysis module, a memory detection module and a maintenance module. An abnormal data traffic was detected through a neural network model, a traffic alert library and an abnormal application list table were established, and maintenance was dispatched. Personnel carry out repairs to ensure network security.
Real-time monitoring and analysis of computer network data traffic is realized, abnormal data flow is discovered in a timely manner, user computer security is ensured, network performance and security is improved, and rapid response and handling of potential threats is ensured.
Smart Images

Figure CN113988183B_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of network data monitoring, and specifically relates to a computer network data flow monitoring system and method. Background Art
[0002] The rapid development of IP network technology has led to the emergence of a large number of emerging commercial applications and services. These emerging services and demands have prompted users to place higher demands on network bandwidth, performance, service quality, and security. Aggregation layer switches need to forward a large number of user messages, reasonably allocate bandwidth, and monitor network data flows, which is particularly critical. Through the classification and analysis of data traffic, the device status and user information can be effectively detected. Based on these statistical information, network management can use them to plan network and application resources to meet customer needs. At the same time, user status can be detected to obtain detailed information about the network and application resources used by customers; real-time identification and classification of data flows can be achieved; and DOS attacks, viruses, and network worms can be prevented. These data help to understand and feedback security incidents. Summary of the invention
[0003] The purpose of the present invention is to provide a computer network data flow monitoring system and method to monitor network data flow and maintain user computer network security.
[0004] The purpose of the present invention can be achieved through the following technical solutions:
[0005] A computer network data flow monitoring system, comprising an abnormal flow analysis module, a network interface analysis module, a memory detection module, a maintenance module and a server;
[0006] The network interface analysis module is used to analyze computer network interface data flow information, and the specific analysis method includes the following steps:
[0007] Step S21: a data flow detection unit is set at the computer network interface, the data flow detection unit is used to detect the data flow at the computer network interface when the user is not online, establish a coordinate system, input the obtained data flow at the computer network interface and the detection time into the coordinate system, and connect two adjacent points using a smooth curve;
[0008] Step S22: setting a data flow warning line, and inputting the data flow warning line into the coordinate system;
[0009] Step S23: when the data flow at the computer network interface in the coordinate system exceeds the data flow warning line, the exceeded data flow at the computer network interface is continuously marked in the coordinate system;
[0010] Step S24: establishing a flow alert database, storing the exceeded data flow at the computer network interface and the corresponding detection time in the flow alert database;
[0011] Step S25: Setting an exploration unit, the exploration unit is used to generate an exploration signal when the data flow at the computer network interface exceeds the data flow warning line, and track the exploration signal, and the exploration signal is transmitted along with the data flow at the network interface;
[0012] Step S26: obtaining the exploration signal path application, marking the exploration signal path application, and storing the marked application information in the corresponding position in the traffic alert library;
[0013] Step S27: Set up a capture unit, which is used to capture the data flow at the network interface that exceeds the data flow warning line when the data flow at the computer network interface exceeds the data flow warning line, analyze the captured data flow, and store the analysis results in the corresponding position in the flow warning library.
[0014] Furthermore, the abnormal traffic analysis module is used to detect abnormal data traffic in a computer network, and the specific detection method includes the following steps:
[0015] Step S11: Obtain computer network abnormal data traffic case information from the Internet;
[0016] Step S12: Establish a neural network model, which includes an input layer, a processing layer and an output layer. The neuron nodes between adjacent layers are connected in one direction. The size of the computer network data flow, the network delay and the CPU utilization rate of the computer equipment are selected as the neural network input parameters. The output result of the output layer of the neural network model is the computer network abnormal data parameter;
[0017] Step S13: Entering the training and learning phase of the neural network, selecting c groups of known parameters of computer network data flow size, network delay and CPU utilization of computer equipment as input training samples, and enabling the neural network to establish the relationship between the computer network abnormal data parameters and the input parameters through training and learning;
[0018] Step S14: Entering the prediction and simulation result analysis phase of the neural network, selecting e groups of known computer network data flow sizes, network delays, CPU utilization rates of computer devices, and computer network abnormal data parameters as test samples and inputting them into the trained neural network model for verification, testing the feasibility and accuracy of the test neural network training and learning results, and simulating the training results. After the prediction results come out, the function is used to perform denormalization processing to obtain the required prediction results, and the output data is compared with the verification data to verify the training results of the neural network model;
[0019] Step S15: obtaining the current computer network data flow size, network delay and CPU utilization of the computer device, and inputting the current computer network data flow size, network delay and CPU utilization of the computer device into the neural network model to obtain computer network abnormal data parameters;
[0020] Step S16: When the obtained computer network abnormal data parameter is network abnormal data, an alarm signal is generated and sent to the server, and the server sends network abnormal data alarm information to the user.
[0021] Furthermore, the memory detection module is used to detect the usage status of the memory in the computer, and the specific detection method includes the following steps:
[0022] Step S31: Obtaining the usage status of the used memory in the computer;
[0023] Step S32: Acquire abnormal application information from the Internet, establish an abnormal application list table, and input the acquired abnormal application information into the abnormal application list table;
[0024] Step S33: Match the application occupying the computer memory with the abnormal application information in the abnormal application list. When the match is successful, mark the matched application in the computer and send the marked application alarm information to the customer.
[0025] Step S34: Establish an abnormal file quick access unit, which is used to set a quick access connection for the file of the marked application.
[0026] Furthermore, the maintenance module is used to dispatch maintenance personnel to perform maintenance when the computer has abnormal data flow problems and the user cannot solve the problem by himself. The specific method includes the following steps:
[0027] Step S41: The user sends a maintenance request through the maintenance module, and the user sending the maintenance request is marked as i, i=1, 2, ..., n, where n is a positive integer;
[0028] Step S42: obtaining personal information of the user who sent the maintenance request, obtaining the distance between the maintenance personnel and the user who sent the maintenance request, and marking the distance between the maintenance personnel and the user who sent the maintenance request as Pi;
[0029] Step S43: obtaining the working status of the maintenance personnel, which includes an idle state and a busy state, and marking the working status of the maintenance personnel as Li;
[0030] Step S44: Obtain the priority value Qi according to the formula Qi = λ * 10 * b1 * Li / (b2 * Pi + 1), where b1 and b2 are both proportionality coefficients, with the value range of 1 ≤ b1 ≤ 2, 0 < b2 ≤ 1, λ is a correction factor, with the value range of 0 < λ ≤ 1, and when the working state of the maintenance personnel is busy, b1 * Li = 0, and when the working state of the maintenance personnel is idle, b1 * Li = 1;
[0031] Step S45: Arrange the priority values Qi in descending order, and dispatch the maintenance personnel with the first - ranked priority value Qi for maintenance.
[0032] A computer network data traffic monitoring method, and the specific method includes the following steps:
[0033] Step 1: Detect abnormal data traffic in the computer network; obtain computer network abnormal data traffic case information from the Internet, establish a neural network model, select the computer network data flow size, network delay, and CPU utilization rate of the computer device as the input parameters of the neural network. The output result of the output layer of the neural network model is the computer network abnormal data parameter. After the neural network model is established, obtain the current computer network data flow size, network delay, and CPU utilization rate of the computer device, and input the current computer network data flow size, network delay, and CPU utilization rate of the computer device into the neural network model to obtain the computer network abnormal data parameter;
[0034] Step 2: Analyze the data flow information of the computer network interface;
[0035] Step A11: Detect the data flow of the computer network interface, establish a coordinate system, input the obtained data flow at the computer network interface and the detection time into the coordinate system, and connect the adjacent two points with a smooth curve;
[0036] Step A12: Set a data flow warning line and input the data flow warning line into the coordinate system. When the data flow at the computer network interface in the coordinate system exceeds the data flow warning line, continuously mark the exceeded data flow at the computer network interface in the coordinate system;
[0037] Step A13: Establish a traffic warning library, and store the exceeded data flow at the computer network interface and the corresponding detection time in the traffic warning library;
[0038] Step A14: When the data flow at the computer network interface exceeds the data flow warning line, track and mark the data flow at the computer network interface;
[0039] Step A15: When the data flow at the computer network interface exceeds the data flow warning line, the data flow at the network interface exceeding the data flow warning line is captured, the captured data flow is analyzed, and the analysis result is stored in a corresponding position in the flow warning library;
[0040] Step 3: Detect the usage of the computer's memory, identify abnormal application information, obtain the usage of the computer's used memory, establish an abnormal application list, match the application occupying the computer's memory with the abnormal application information in the abnormal application list, and when the match is successful, mark the matched application in the computer, send the marked application alarm information to the customer, and set a quick access connection for the marked application file;
[0041] Step 4: When the computer has abnormal data flow problems and the user cannot solve it by himself, dispatch maintenance personnel for repair.
[0042] Beneficial effects of the present invention: by setting up the abnormal traffic analysis module, abnormal data in the computer network can be discovered to ensure the safety of the user's computer; by setting up the network interface analysis module, it is possible to analyze whether an abnormal data flow occurs; by establishing a coordinate system, the data flow and detection time at the computer network interface obtained are input into the coordinate system, and a data flow warning line is set, so that abnormal data can be intuitively discovered; a flow warning library is established, and the data flow at the computer network interface that exceeds the limit and the corresponding detection time are stored in the flow warning library for summary storage, which is convenient for viewing and extraction; an exploration unit is set to track the exploration signal and obtain the exploration signal path Path applications, and mark the exploration signal path applications, find out the abnormal applications, store the marked application information in the corresponding position in the traffic warning library for easy viewing, set up a capture unit, capture the data flow at the network interface that exceeds the data flow warning line, analyze the captured data flow, and store the analysis results in the corresponding position in the traffic warning library for summary storage, which is convenient for viewing and retrieval; through the setting of the memory detection module, the usage status of the computer's memory can be detected and abnormal application information can be identified; through the setting of the maintenance module, when the computer has abnormal data flow problems and the user cannot solve them by himself, maintenance personnel can be dispatched for maintenance. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0044] Figure 1This is a principle block diagram of the present invention. DETAILED DESCRIPTION
[0045] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0046] like Figure 1 As shown, a computer network data flow monitoring system includes an abnormal flow analysis module, a network interface analysis module, a memory detection module, a maintenance module and a server;
[0047] The abnormal traffic analysis module is used to detect abnormal data traffic in a computer network. The specific detection method includes the following steps:
[0048] Step S11: Obtain computer network abnormal data flow case information from the Internet; the abnormal data flow case information includes several groups of parameters, each group of parameters includes computer network data flow size, network delay, CPU utilization of computer equipment and computer network abnormal data parameters;
[0049] Step S12: Establish a neural network model, which includes an input layer, a processing layer and an output layer. The neuron nodes between adjacent layers are connected in one direction. The size of the computer network data flow, the network delay and the CPU utilization rate of the computer equipment are selected as the neural network input parameters. The output result of the output layer of the neural network model is the computer network abnormal data parameter;
[0050] Step S13: Entering the training and learning phase of the neural network, selecting c groups of known parameters of computer network data flow size, network delay and CPU utilization of computer equipment as input training samples, c is a ratio coefficient and is a positive integer greater than 500, and the neural network is enabled to establish the relationship between the computer network abnormal data parameters and the input parameters through training and learning;
[0051] Step S14: Enter the prediction and simulation result analysis stage of the neural network, select e groups of known computer network data flow size, network delay, CPU utilization of computer equipment and computer network abnormal data parameters as test samples and input them into the trained neural network model for verification, e is the ratio coefficient and is a positive integer greater than 100, check the feasibility and accuracy of the test neural network training and learning results, and simulate the training results. After the prediction results come out, use the function to perform denormalization processing to obtain the required prediction results, compare the output data with the verification data, and verify the training results of the neural network model;
[0052] Step S15: obtaining the current computer network data flow size, network delay and CPU utilization of the computer device, and inputting the current computer network data flow size, network delay and CPU utilization of the computer device into the neural network model, obtaining computer network abnormal data parameters, and obtaining whether the computer network abnormal data parameters are computer network abnormal data;
[0053] Step S16: when the obtained computer network abnormal data parameter is network abnormal data, an alarm signal is generated, and the alarm signal is sent to the server, and the server sends network abnormal data alarm information to the user;
[0054] The network interface analysis module is used to analyze the computer network interface data flow information. The specific analysis method includes the following steps:
[0055] Step S21: a data flow detection unit is set at the computer network interface, the data flow detection unit is used to detect the data flow at the computer network interface when the user is not online, establish a coordinate system, input the obtained data flow at the computer network interface and the detection time into the coordinate system, and connect two adjacent points using a smooth curve;
[0056] Step S22: setting a data flow warning line. The data flow warning line is a warning line summarized by experts based on a large amount of Internet data. That is, when a user is not online, a large amount of data flows in and out of the computer network interface. The data flow warning line value does not change with time, and the data flow warning line is input into the coordinate system;
[0057] Step S23: when the data flow at the computer network interface in the coordinate system exceeds the data flow warning line, the exceeded data flow at the computer network interface is continuously marked in the coordinate system;
[0058] Step S24: establishing a flow alert database, storing the exceeded data flow at the computer network interface and the corresponding detection time in the flow alert database;
[0059] Step S25: Setting an exploration unit, the exploration unit is used to generate an exploration signal when the data flow at the computer network interface exceeds the data flow warning line, and to track the exploration signal. The exploration signal is a traceable data signal that can be transmitted along with the data stream, and the exploration signal is transmitted along with the data stream at the network interface;
[0060] Step S26: Acquire the exploration signal path application, mark the exploration signal path application, and store the marked application information in the corresponding position in the traffic alert library. The corresponding position is stored together with the corresponding exceeded data flow at the computer network interface in the traffic alert library for easy viewing;
[0061] Step S27: Setting a capture unit, the capture unit is used to capture the data flow at the network interface that exceeds the data flow warning line when the data flow at the computer network interface exceeds the data flow warning line, which can be a copy, analyze the captured data flow, and store the analysis result in a corresponding position in the flow warning library;
[0062] The memory detection module is used to detect the usage status of the memory in the computer. The specific detection method includes the following steps:
[0063] Step S31: Obtaining the usage status of the used memory in the computer, where the usage status refers to which applications and programs occupy the memory;
[0064] Step S32: Acquire abnormal application information from the Internet. The abnormal application information refers to software and applications that may generate abnormal data traffic, including software names and memory usage, such as virus software. Establish an abnormal application list table and input the acquired abnormal application information into the abnormal application list table.
[0065] Step S33: Match the application occupying the computer memory with the abnormal application information in the abnormal application list. When the match is successful, mark the matched application in the computer and send the marked application alarm information to the customer.
[0066] Step S34: establishing an abnormal file quick access unit, which is used to set a quick access connection for the file of the marking application. The user can use the abnormal file quick access unit to directly find the file location of the marking software;
[0067] The maintenance module is used to dispatch maintenance personnel to perform maintenance when the computer has abnormal data flow problems and the user cannot solve them by himself. The specific method includes the following steps:
[0068] Step S41: The user sends a maintenance request through the maintenance module, and the user sending the maintenance request is marked as i, i=1, 2, ..., n, where n is a positive integer;
[0069] Step S42: Obtain personal information of the user who sent the maintenance request, including the maintenance address, contact information, and name, obtain the distance between the maintenance personnel and the user who sent the maintenance request, and mark the distance between the maintenance personnel and the user who sent the maintenance request as Pi;
[0070] Step S43: obtaining the working status of the maintenance personnel, which includes an idle state and a busy state, and marking the working status of the maintenance personnel as Li;
[0071] Step S44: Obtain the priority value Qi according to the formula Qi = λ * 10 * b1 * Li / (b2 * Pi + 1), where b1 and b2 are both proportionality coefficients, with the value range of 1 ≤ b1 ≤ 2, 0 < b2 ≤ 1, λ is a correction factor, with the value range of 0 < λ ≤ 1, and when the working state of the maintenance personnel is busy, b1 * Li = 0, and when the working state of the maintenance personnel is idle, b1 * Li = 1;
[0072] Step S45: Arrange the priority values Qi in descending order, and dispatch the maintenance personnel with the first-ranked priority value Qi for maintenance.
[0073] A method for monitoring computer network data traffic, the specific method includes the following steps:
[0074] Step 1: Detect abnormal data traffic in the computer network; obtain computer network abnormal data traffic case information from the Internet, establish a neural network model, select the computer network data flow size, network delay, and CPU utilization rate of the computer device as the input parameters of the neural network, and the output result of the output layer of the neural network model is the computer network abnormal data parameter. After the neural network model is established, obtain the current computer network data flow size, network delay, and CPU utilization rate of the computer device, and input the current computer network data flow size, network delay, and CPU utilization rate of the computer device into the neural network model to obtain the computer network abnormal data parameter;
[0075] Step 2: Analyze the data flow information of the computer network interface;
[0076] Step A11: Detect the data flow of the computer network interface, establish a coordinate system, input the obtained data flow at the computer network interface and the detection time into the coordinate system, and connect the adjacent two points with a smooth curve;
[0077] Step A12: Set a data flow warning line and input the data flow warning line into the coordinate system. When the data flow at the computer network interface in the coordinate system exceeds the data flow warning line, continuously mark the exceeded data flow at the computer network interface in the coordinate system;
[0078] Step A13: Establish a traffic warning library, and store the exceeded data flow at the computer network interface and the corresponding detection time in the traffic warning library;
[0079] Step A14: When the data flow at the computer network interface exceeds the data flow warning line, track and mark the data flow at the computer network interface;
[0080] Step A15: When the data flow at the computer network interface exceeds the data flow warning line, the data flow at the network interface exceeding the data flow warning line is captured, the captured data flow is analyzed, and the analysis result is stored in a corresponding position in the flow warning library;
[0081] Step 3: Detect the usage of the computer's memory, identify abnormal application information, obtain the usage of the computer's used memory, establish an abnormal application list, match the application occupying the computer's memory with the abnormal application information in the abnormal application list, and when the match is successful, mark the matched application in the computer, send the marked application alarm information to the customer, and set a quick access connection for the marked application file;
[0082] Step 4: When the computer has abnormal data flow problems and the user cannot solve it by himself, dispatch maintenance personnel for repair.
[0083] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual 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.
[0084] When the present invention is used, it detects abnormal data flow in a computer network; obtains computer network abnormal data flow case information from the Internet, establishes a neural network model, selects computer network data flow size, network delay and CPU utilization of computer equipment as neural network input parameters, and the output result of the output layer of the neural network model is the computer network abnormal data parameter. After the neural network model is established, the current computer network data flow size, network delay and CPU utilization of computer equipment are obtained, and the current computer network data flow size, network delay and CPU utilization of computer equipment are input into the neural network model to obtain the computer network abnormal data parameter; analyzes computer network interface data flow information, detects the computer network interface data flow, establishes a coordinate system, and compares the obtained data flow at the computer network interface with the detection time. Input into the coordinate system, and connect two adjacent points with a smooth curve, set a data flow warning line, and input the data flow warning line into the coordinate system, when the data flow at the computer network interface in the coordinate system exceeds the data flow warning line, continuously mark the exceeded data flow at the computer network interface in the coordinate system, establish a flow warning library, store the exceeded data flow at the computer network interface and the corresponding detection time in the flow warning library, when the data flow at the computer network interface exceeds the data flow warning line, track and mark the data flow at the computer network interface, when the data flow at the computer network interface exceeds the data flow warning line, capture the data flow at the network interface that exceeds the data flow warning line, analyze the captured data flow, and store the analysis result in the corresponding position in the flow warning library;
[0085] Detect the memory usage in the computer, identify abnormal application information, obtain the usage of the used memory in the computer, establish an abnormal application list, match the applications occupying the computer memory with the abnormal application information in the abnormal application list, and when the match is successful, mark the matched application in the computer, send the marked application alarm information to the customer, set up a quick access connection for the marked application's files, and dispatch maintenance personnel for repair when the computer has abnormal data flow problems and the user cannot solve them by himself.
[0086] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0087] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0088] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.
Claims
1. A computer network data flow monitoring system, characterized in that: It includes abnormal traffic analysis module, network interface analysis module, memory detection module, maintenance module and server; The network interface analysis module is used to analyze computer network interface data flow information, and the specific analysis method includes the following steps: Step S21: a data flow detection unit is set at the computer network interface, the data flow detection unit is used to detect the data flow at the computer network interface when the user is not online, establish a coordinate system, input the obtained data flow at the computer network interface and the detection time into the coordinate system, and connect two adjacent points using a smooth curve; Step S22: setting a data flow warning line, and inputting the data flow warning line into the coordinate system; Step S23: when the data flow at the computer network interface in the coordinate system exceeds the data flow warning line, the exceeded data flow at the computer network interface is continuously marked in the coordinate system; Step S24: establishing a flow alert database, storing the exceeded data flow at the computer network interface and the corresponding detection time in the flow alert database; Step S25: Setting an exploration unit, the exploration unit is used to generate an exploration signal when the data flow at the computer network interface exceeds the data flow warning line, and track the exploration signal, and the exploration signal is transmitted along with the data flow at the network interface; Step S26: obtaining the exploration signal path application, marking the exploration signal path application, and storing the marked application information in the corresponding position in the traffic alert library; Step S27: Setting a capture unit, the capture unit is used to capture the data flow at the network interface that exceeds the data flow warning line when the data flow at the computer network interface exceeds the data flow warning line, analyze the captured data flow, and store the analysis result in a corresponding position in the flow warning library; The abnormal traffic analysis module is used to detect abnormal data traffic in a computer network. The specific detection method includes the following steps: Step S11: Obtain computer network abnormal data traffic case information from the Internet; Step S12: Establish a neural network model, which includes an input layer, a processing layer and an output layer. The neuron nodes between adjacent layers are connected in one direction. The size of the computer network data flow, the network delay and the CPU utilization rate of the computer equipment are selected as the neural network input parameters. The output result of the output layer of the neural network model is the computer network abnormal data parameter; Step S13: Entering the training and learning phase of the neural network, selecting c groups of known parameters of computer network data flow size, network delay and CPU utilization of computer equipment as input training samples, and enabling the neural network to establish the relationship between the computer network abnormal data parameters and the input parameters through training and learning; Step S14: Enter the prediction and simulation result analysis stage of the neural network. Select e groups of known computer network data flow sizes, network delays, CPU utilization rates of computer devices, and computer network anomaly data parameters as test samples and input them into the trained neural network model for verification. Examine the feasibility and accuracy of the training and learning results of the test neural network, and simulate the training results. After the prediction results come out, perform inverse normalization processing using a function to obtain the required prediction results. Compare the output data with the verification data to verify the training results of the neural network model; Step S15: Obtain the current computer network data flow size, network delay, and CPU utilization rate of the computer device, and input the current computer network data flow size, network delay, and CPU utilization rate of the computer device into the neural network model to obtain computer network anomaly data parameters; Step S16: When the obtained computer network anomaly data parameters are network anomaly data, generate an alarm signal and send the alarm signal to the server, and the server sends network anomaly data alarm information to the user; The memory detection module is used to detect the usage status of the memory in the computer. The specific detection method includes the following steps: Step S31: Obtain the usage status of the used memory in the computer; Step S32: Obtain abnormal application information from the Internet, establish an abnormal application list table, and input the obtained abnormal application information into the abnormal application list table; Step S33: Match the applications occupying the computer memory with the abnormal application information in the abnormal application list table. When the match is successful, mark the applications in the computer that are matched, and send a marked application alarm message to the customer; Step S34: Establish a fast access unit for abnormal files. The fast access unit for abnormal files is used to set up a fast access connection for the files of the marked applications; The maintenance module is used to dispatch maintenance personnel for maintenance when the computer has abnormal data traffic problems and the user cannot solve them by themselves. The specific method includes the following steps: Step S41: The user sends a maintenance request through the maintenance module, and mark the user who sends the maintenance request as i, where i = 1, 2,..., n, and n is a positive integer; Step S42: Obtain the personal information of the user who sends the maintenance request, obtain the distance between the maintenance personnel and the user who sends the maintenance request, and mark the distance between the maintenance personnel and the user who sends the maintenance request as Pi; Step S43: Obtain the working status of the maintenance personnel. The working status includes an idle status and a busy status, and mark the working status of the maintenance personnel as Li; Step S44: Obtain the priority value Qi according to the formula Qi = λ * 10 * b1 * Li / (b2 * Pi + 1), where b1 and b2 are both proportionality coefficients, and the value range is 1 ≤ b1 ≤ 2, 0 < b2 ≤ 1, λ is a correction factor, and the value range is 0 < λ ≤ 1. When the working status of the maintenance personnel is the busy status, b1 * Li = 0, and when the working status of the maintenance personnel is the idle status, b1 * Li = 1; Step S45: Arrange the priority values Qi in descending order, and dispatch the maintenance personnel with the first priority value Qi to perform maintenance.
2. A monitoring method of a computer network data flow monitoring system as claimed in claim 1, characterized in that: The specific method includes the following steps: Step 1: Detect abnormal data traffic in a computer network; obtain case information of abnormal data traffic in a computer network from the Internet, establish a neural network model, select the size of a computer network data flow, network delay, and CPU utilization of a computer device as neural network input parameters, and the output result of the output layer of the neural network model is the abnormal data parameter of the computer network. After the establishment of the neural network model, obtain the current size of a computer network data flow, network delay, and CPU utilization of a computer device, and input the current size of a computer network data flow, network delay, and CPU utilization of a computer device into the neural network model to obtain the abnormal data parameter of the computer network; Step 2: Analyze computer network interface data flow information; Step A11: Detect the data flow of the computer network interface, establish a coordinate system, input the obtained data flow and detection time at the computer network interface into the coordinate system, and connect two adjacent points using a smooth curve; Step A12: setting a data flow warning line, and inputting the data flow warning line into the coordinate system, when the data flow at the computer network interface in the coordinate system exceeds the data flow warning line, continuously marking the exceeded data flow at the computer network interface in the coordinate system; Step A13: establishing a flow alert database, storing the exceeded data flow at the computer network interface and the corresponding detection time in the flow alert database; Step A14: When the data flow at the computer network interface exceeds the data flow warning line, the data flow at the computer network interface is tracked and marked; Step A15: When the data flow at the computer network interface exceeds the data flow warning line, the data flow at the network interface exceeding the data flow warning line is captured, the captured data flow is analyzed, and the analysis result is stored in a corresponding position in the flow warning library; Step 3: Detect the usage of the computer's memory, identify abnormal application information, obtain the usage of the computer's used memory, establish an abnormal application list, match the application occupying the computer's memory with the abnormal application information in the abnormal application list, and when the match is successful, mark the matched application in the computer, send the marked application alarm information to the customer, and set a quick access connection for the marked application file; Step 4: When the computer has abnormal data flow problems and the user cannot solve it by himself, dispatch maintenance personnel for repair.
