Machine room computer fault detection system and method based on artificial intelligence

Abstract

The invention discloses a computer room computer fault detection system based on artificial intelligence, which comprises a real-time monitoring module, an anomaly detection module, a fault diagnosis module, a report module, a cloud server and a fault analysis computer, and is characterized in that the real-time monitoring module is client software and is installed in the computer; and the cloud server is used for carrying out background real-time monitoring on the computer, the cloud server is connected with the real-time monitoring module through the internet, and the cloud server is also connected with the fault analysis computer through the internet. The invention further discloses a using method of computer room computer fault detection based on artificial intelligence. By constructing the fault detection system, the fault of the computer can be checked and analyzed in an artificial intelligence mode and is not influenced by the fault, the computer blue screen reason can be analyzed even under the condition of the computer blue screen, the fault condition is visually fed back to the other computer, and the fault detection efficiency is improved. And the efficiency of maintenance personnel is greatly improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer fault detection, and in particular relates to a computer room computer fault detection system and method based on artificial intelligence. Background Art

[0002] When using computers in a computer room, due to the existence of usage time, the computers will have certain problems to a certain extent, which will lead to computer failures. The causes of computer failures are confusing and elusive, and because the components of the Windows operating system are relatively complex, once a computer fails, it is almost impossible for computer users to accurately find out the cause of the failure. Due to the large number of computers in the computer room, when a failure occurs, it is also necessary to rely more on manual experience or multiple experiments in the judgment process of the computer system failure. It takes a long time to determine the failure, and there is a lack of means to improve the efficiency of fault diagnosis. In this regard, we propose a computer room computer fault detection system and method based on artificial intelligence. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention provides a computer room computer fault detection system and method based on artificial intelligence to solve the above technical problems.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a computer room computer fault detection system based on artificial intelligence, the detection system comprising: a real-time monitoring module, an abnormality detection module, a fault diagnosis module, a reporting module, a cloud server and a fault analysis computer, the real-time monitoring module is client software installed in the computer, which is used to perform real-time background monitoring of the computer, the cloud server and the real-time monitoring module are connected to the Internet, and the cloud server is also connected to the fault analysis computer through a network.

[0005] Preferably, the detection system is hidden in the background system when the computer is working normally, and when the computer fails, the detection system automatically pops up the abnormal detection module to detect the abnormality.

[0006] Preferably, the real-time monitoring module can monitor and compare the values ​​of CPU, memory, hard disk and network bandwidth in real time, and pop up the abnormal detection module after reaching the threshold.

[0007] Preferably, the anomaly detection module identifies potential faults and attacks by analyzing the anomalies in log information and network traffic data, and loads the fault diagnosis module for fault diagnosis.

[0008] Preferably, the fault diagnosis module includes network diagnosis, program diagnosis, virus analysis and hardware diagnosis. The network diagnosis module performs diagnostic analysis on the network part, the program diagnosis performs diagnostic analysis on the system program, the virus analysis analyzes the viruses in the computer, and the hardware diagnosis is used to detect computer hardware failures. The fault diagnosis module performs fault detection by testing different hardware and software in the computer.

[0009] Preferably, the reporting module is connected to the cloud server through a network, the diagnosis structure is uploaded to the cloud server, and the analysis result is generated through the cloud server.

[0010] Prioritize, the cloud server can generate fault reports through data upload of the reporting module, and by feeding the data back to the fault analysis computer, the detected faults and abnormal conditions can be presented in a visual manner, which is convenient for administrators to view and analyze.

[0011] Preferably, the anomaly detection module performs predictive analysis by constructing a mathematical model and adopts logical analysis to perform screening.

[0012] Preferably, the detection system is located at the CPU end. After the computer is in a blue screen state, the detection system can also operate spontaneously to detect and analyze abnormal conditions in the computer and feed back the abnormal conditions to the fault analysis computer.

[0013] A method for using computer room computer fault detection based on artificial intelligence, the using steps comprising:

[0014] S1. The real-time monitoring system monitors the internal situation of the computer in real time;

[0015] S2. When an abnormal situation occurs, the abnormality detection module constructs an analytical mathematical model inside the computer to detect the abnormal situation;

[0016] S3, the fault diagnosis module roughly diagnoses the possible fault conditions;

[0017] S4. Generate a general report through the reporting module, upload it to the cloud server, and feed it back to the fault analysis computer so that people can observe and understand the fault situation intuitively;

[0018] S5. The technicians inspect and maintain the faulty parts.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] By constructing a fault detection system, the present application can check and analyze computer faults in an artificial intelligence manner and is not affected by the faults. Even in the case of a computer blue screen, the cause of the computer blue screen can be analyzed and the fault situation can be intuitively fed back to another computer, greatly improving the efficiency of maintenance personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a system framework diagram of the present invention;

[0022] Figure 2 2 is a diagram of the operation steps of the system of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The present invention provides a technical solution: a computer room computer fault detection system based on artificial intelligence, the detection system comprising: a real-time monitoring module, an abnormality detection module, a fault diagnosis module, a reporting module, a cloud server and a fault analysis computer, the real-time monitoring module is client software installed in the computer, and is used to perform background real-time monitoring of the computer, the cloud server and the real-time monitoring module are connected to the Internet, and the cloud server is also connected to the fault analysis computer through a network.

[0025] Furthermore, the detection system is hidden in the background system when the computer is working normally. When the computer fails, the detection system automatically pops up the abnormal detection module to detect the abnormality. The real-time monitoring module can monitor the values ​​of CPU, memory, hard disk and network bandwidth in real time, and compare them. When the threshold is reached, the abnormal detection module pops up.

[0026] Under normal circumstances, the values ​​of CPU, memory, hard disk and network bandwidth are within a certain range. After an abnormal situation occurs, the real-time monitoring module can promptly monitor the occurrence of the abnormal situation.

[0027] Furthermore, the anomaly detection module identifies potential faults and attacks by analyzing the anomalies in log information and network traffic data, and loads the fault diagnosis module for fault diagnosis.

[0028] Furthermore, the fault diagnosis module includes network diagnosis, program diagnosis, virus analysis and hardware diagnosis. The network diagnosis module performs diagnostic analysis on the network part, the program diagnosis performs diagnostic analysis on the system program, the virus analysis analyzes the viruses in the computer, and the hardware diagnosis is used to detect computer hardware failures. The fault diagnosis module performs fault detection by testing different hardware and software in the computer.

[0029] Network diagnosis refers to the process of diagnosing and evaluating the network system, aiming to identify the faults, potential problems and possible improvement points in the network system, so as to achieve efficient operation of the network and provide strong protection for the network security of the enterprise;

[0030] Network diagnosis is mainly used in the detection and diagnosis evaluation of network status. It can realize the diagnosis summary and real-time detection of network system architecture, equipment model, operating system, software operation, network security, network users, etc., so as to effectively and quickly locate the faults in the network system and quickly restore the normal operation of the network system.

[0031] Program diagnostic methods include:

[0032] Static analysis: without running the program, it can find potential problems in the program by analyzing the program's structure, data flow, control flow and other information;

[0033] Dynamic analysis method: by running the program, collect data during the program running, such as memory usage, CPU occupancy, etc., to find problems in the program;

[0034] Code review method: manually review the code to find errors, loopholes and bad designs in the program;

[0035] System testing method: Test the entire system to verify whether the system's functions and performance meet the requirements;

[0036] Integration testing method: Test the interfaces and integration between modules to find conflicts and errors between modules;

[0037] Furthermore, the reporting module is connected to the cloud server through a network, the diagnosis structure is uploaded to the cloud server, and the analysis result is generated through the cloud server.

[0038] Furthermore, the cloud server can generate fault reports by uploading data from the reporting module. By feeding the data back to the fault analysis computer, the detected faults and abnormal conditions can be presented in a visual manner, making it easier for administrators to view and analyze them.

[0039] Furthermore, the anomaly detection module constructs a mathematical model to perform predictive analysis and uses logical analysis to perform screening.

[0040] Logistic regression is a general classification algorithm for predicting binary problems. It is an extension of the linear regression model. It implements the classification task by mapping the output of linear regression through an activation function (usually a sigmoid function) and limiting the predicted value between 0 and 1.

[0041] The basic idea of ​​the logistic regression model is to estimate the optimal parameter value by maximizing the likelihood function and make the classification results of the sample data as accurate as possible. The model assumes that there is a constant linear relationship between the characteristics of the sample and the classification probability;

[0042] The training process of the logistic regression model usually uses the gradient descent algorithm to minimize the loss function using the cross entropy loss function. Once the training is completed, the logistic regression model can be used to classify and predict new samples;

[0043] It is very sensitive when z=0, and insensitive when z>>0 or z<<0, which helps to make intuitive classification judgments1;

[0044] The formula for logistic regression is: p = 1 / (1 + e^(-z)), where z = Tx + b, T is the weight matrix, x is the feature matrix, and b is the bias; when p is greater than a certain threshold, the sample is classified as a "positive class", otherwise it is classified as a "negative class"2;

[0045] It can perform well enough on unknown data sets. As for how to measure the quality of a binary classification model, we can use indicators such as classification error rate: Err=1N∑1[y*=y], or we can use accuracy, recall rate, AUC and other indicators to measure it. Through simulation analysis, we can deduce and analyze abnormal situations in the computer.

[0046] Furthermore, the detection system is located at the CPU end. After the computer is in a blue screen state, the detection system can also operate spontaneously to detect and analyze abnormal conditions in the computer and feed back the abnormal conditions to the fault analysis computer.

[0047] A method for using computer room computer fault detection based on artificial intelligence, the using steps comprising:

[0048] S1. The real-time monitoring system monitors the internal situation of the computer in real time;

[0049] S2. When an abnormal situation occurs, the abnormality detection module constructs an analytical mathematical model inside the computer to detect the abnormal situation;

[0050] S3, the fault diagnosis module roughly diagnoses the possible fault conditions;

[0051] S4. Generate a general report through the reporting module, upload it to the cloud server, and feed it back to the fault analysis computer so that people can observe and understand the fault situation intuitively;

[0052] S5. The technicians inspect and maintain the faulty parts.

[0053] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0054] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A computer room computer fault detection system based on artificial intelligence, characterized in that: The detection system includes: a real-time monitoring module, an anomaly detection module, a fault diagnosis module, a reporting module, a cloud server and a fault analysis computer. The real-time monitoring module is client software installed in the computer to perform real-time background monitoring of the computer. The cloud server and the real-time monitoring module are connected to the Internet, and the cloud server is also connected to the fault analysis computer through the Internet.

2. The computer room computer fault detection system based on artificial intelligence according to claim 1 is characterized in that: The detection system is hidden in the background system when the computer is working normally. When the computer fails, the detection system will automatically pop up the abnormal detection module to detect the abnormality.

3. The computer room computer fault detection system based on artificial intelligence according to claim 1 is characterized in that: The real-time monitoring module can monitor and compare the values ​​of CPU, memory, hard disk and network bandwidth in real time, and pop up the anomaly detection module when the threshold is reached.

4. The computer room computer fault detection system based on artificial intelligence according to claim 1 is characterized in that: The anomaly detection module identifies potential faults and attacks by analyzing the anomalies in log information and network traffic data, and loads the fault diagnosis module for fault diagnosis.

5. The computer room computer fault detection system based on artificial intelligence according to claim 1 is characterized in that: The fault diagnosis module includes network diagnosis, program diagnosis, virus analysis and hardware diagnosis. The network diagnosis module performs diagnostic analysis on the network part, the program diagnosis performs diagnostic analysis on the system program, the virus analysis analyzes the viruses in the computer, and the hardware diagnosis is used to detect computer hardware failures. The fault diagnosis module performs fault detection by testing different hardware and software in the computer.

6. The computer room computer fault detection system based on artificial intelligence according to claim 1 is characterized in that: The reporting module is connected to the cloud server through a network, the diagnosis structure is uploaded to the cloud server, and the analysis result is generated through the cloud server.

7. The computer room computer fault detection system based on artificial intelligence according to claim 1 is characterized in that: The cloud server can generate fault reports by uploading data from the reporting module. By feeding the data back to the fault analysis computer, the detected faults and abnormal conditions can be presented in a visual manner, making it easier for administrators to view and analyze them.

8. The computer room computer fault detection system based on artificial intelligence according to claim 1 is characterized in that: The anomaly detection module constructs a mathematical model to perform predictive analysis and uses logical analysis to perform screening.

9. The computer room computer fault detection system based on artificial intelligence according to claim 1 is characterized in that: The detection system is located at the CPU end. After the computer is in a blue screen state, the detection system can also operate spontaneously to detect and analyze abnormal conditions in the computer and feed back the abnormal conditions to the fault analysis computer.

10. A method for using computer room computer fault detection based on artificial intelligence, characterized in that: The steps for use include: S1. The real-time monitoring system monitors the internal situation of the computer in real time; S2. When an abnormal situation occurs, the abnormality detection module constructs an analytical mathematical model inside the computer to detect the abnormal situation; S3, the fault diagnosis module roughly diagnoses the possible fault conditions; S4. Generate a general report through the reporting module, upload it to the cloud server, and feed it back to the fault analysis computer so that people can observe and understand the fault situation intuitively; S5. The technicians inspect and maintain the faulty parts.

Images