Computer network fault detection method and system based on artificial intelligence technology

Abstract

The invention provides a computer network fault detection method and system based on an artificial intelligence technology, and the method comprises the steps: collecting the hardware self-inspection information and software self-inspection information of a computer, and the network data information of the computer, and recognizing the network abnormal information of the computer when a computer network fault occurs; identifying software and hardware exception information of the computer through a self-inspection analysis strategy, and identifying a network fault type of the computer and a network fault reason of the computer through an exception analysis network based on the network exception information and the software and hardware exception information; and based on the network fault type of the computer and the network fault reason of the computer, identifying a network fault detection result of the computer through a computer network fault identification strategy, and generating a network fault detection report corresponding to the network fault detection result. By adopting the scheme, the identification efficiency and the identification accuracy of the network fault detection result are improved.

Description

Technical Field

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

[0002] During computer network communication, signal interference, unstable network data, and busy network often occur, resulting in network communication failure, data loss, network disconnection and other network failures. In the stage of high-frequency use of network interaction, the above network failures will cause huge interference to users, affect the efficiency of computer network communication, and bring users a poor computer network communication experience. Therefore, computer network fault detection is one of the important ways to improve the computer network communication experience.

[0003] The traditional computer network fault detection method is to conduct comprehensive detection of computer network faults through a firewall combined with a network detection program. However, the above detection can only detect network data or abnormal intrusion situations, while there are fewer detections of network anomalies such as signal interference, abnormal network data transmission, and network faults caused by hardware anomalies, resulting in low accuracy in computer network fault detection. Summary of the invention

[0004] The main purpose of the present invention is to provide a computer network fault detection method and system based on artificial intelligence technology, aiming to solve the problem that the existing technology can only detect network data or abnormal intrusion situations, but has less detection of network faults caused by network anomalies such as signal interference and network data transmission anomalies, resulting in low accuracy of computer network fault detection.

[0005] To achieve the above object, the present invention provides a computer network fault detection method based on artificial intelligence technology, the method comprising: When a computer network fails, network data information of the computer, hardware self-check information of the computer, and software self-check information of the computer are collected, and network abnormal information of the computer is identified based on the network data information; Based on the hardware self-check information and the software self-check information, identifying the software and hardware abnormality information of the computer through a self-check analysis strategy, and based on the network abnormality information and the software and hardware abnormality information, identifying the network fault type of the computer and the cause of the network fault of the computer through an abnormal analysis network; Based on the network fault type of the computer and the network fault cause of the computer, a network fault detection result of the computer is identified through a computer network fault identification strategy, and a network fault detection report corresponding to the network fault detection result is generated.

[0006] Optionally, the identifying network abnormality information of the computer based on the network data information includes: Based on the network data information, network data distribution information of the computer is generated, and based on the network data distribution information, a network is extracted through distribution characteristics to extract network range characteristics of the computer and network data trend characteristics of the computer; Based on the network data range feature and the network data trend feature, the network is identified through abnormal feature, the abnormal network data range of the computer is identified, and the abnormal network data range of the computer is used as the network abnormality information of the computer.

[0007] Optionally, the identifying network abnormality information of the computer based on the network data information includes: Sending network inspection data packets to each transmission node of computer network transmission, and receiving node transmission results fed back by each transmission node; Based on the node transmission results fed back by each of the transmission nodes, abnormal transmission nodes among the transmission nodes are identified, and each of the abnormal transmission nodes is used as network abnormality information of the computer.

[0008] Optionally, the identifying software and hardware abnormality information of the computer through a self-check analysis strategy based on the hardware self-check information and the software self-check information includes: Based on the hardware self-check information, identifying sub-detection information of each hardware structure of the computer, and querying the hardware anomaly database for abnormal detection data in the sub-detection information of each hardware structure; Using all hardware structure anomaly detection data as hardware network anomaly information of the computer; Based on the software self-check information, identifying program detection log information of each software program of the computer, and identifying abnormal log content in each of the program detection log information; The content of each abnormal log is used as the software network abnormality information of the computer, and the hardware network abnormality information of the computer and the software network abnormality information of the computer are used as the software and hardware abnormality information of the computer.

[0009] Optionally, the identifying the type of network failure of the computer and the cause of the network failure of the computer by analyzing the network failure based on the network failure information and the software and hardware failure information includes: Filter target abnormal media information that affects network communication from the network abnormal information, and filter target software and hardware abnormal information that affects network communication from the software and hardware abnormal information; The target abnormal media information and the target software and hardware abnormal information are used through an abnormal analysis network to identify the network failure type and the cause of the network failure of the computer.

[0010] Optionally, the identifying the network fault detection result of the computer based on the network fault type of the computer and the network fault cause of the computer by using a computer network fault identification strategy includes: Based on the network fault type of the computer, querying the computer network fault database for each network fault information corresponding to the network fault type; Extracting a first network fault feature of the network fault cause and each second network fault feature corresponding to each network fault information, and respectively calculating a similarity between each second network fault feature and the first network fault feature; The network fault information corresponding to the second network fault feature with the maximum similarity is selected as the network fault detection result of the computer.

[0011] Optionally, the generating a network fault detection report corresponding to the network fault detection result includes: Acquire a network fault report template corresponding to the network fault type, and identify each template structure information of the network fault report template; Based on the target network fault characteristics of the network fault detection result and the template structure information of the network fault report template, identify the template structure information corresponding to the target network fault characteristics, and fill each target network fault characteristic into the template structure information to obtain the network fault detection report corresponding to the network fault detection result.

[0012] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer network fault detection system based on artificial intelligence technology, and the computer network fault detection system based on artificial intelligence technology includes: A collection module, used for collecting network data information of the computer, hardware self-check information of the computer, and software self-check information of the computer when a computer network fails, and identifying network abnormality information of the computer based on the network data information; an identification module, configured to identify the hardware and software abnormality information of the computer through a self-check analysis strategy based on the hardware self-check information and the software self-check information, and to identify the network fault type and the network fault cause of the computer through an abnormal analysis network based on the network abnormality information and the hardware and software abnormality information; A generation module is used to identify the network fault detection result of the computer based on the network fault type of the computer and the network fault cause of the computer through a computer network fault identification strategy, and generate a network fault detection report corresponding to the network fault detection result.

[0013] Optionally, the acquisition module is specifically used to: Based on the network data information, network data distribution information of the computer is generated, and based on the network data distribution information, a network is extracted through distribution characteristics to extract network range characteristics of the computer and network data trend characteristics of the computer; Based on the network data range feature and the network data trend feature, the network is identified through abnormal feature, the abnormal network data range of the computer is identified, and the abnormal network data range of the computer is used as the network abnormality information of the computer.

[0014] Optionally, the acquisition module is specifically used to: Sending network inspection data packets to each transmission node of computer network transmission, and receiving node transmission results fed back by each transmission node; Based on the node transmission results fed back by each of the transmission nodes, abnormal transmission nodes among the transmission nodes are identified, and each of the abnormal transmission nodes is used as network abnormality information of the computer.

[0015] Optionally, the identification module is specifically used to: Based on the hardware self-check information, identifying sub-detection information of each hardware structure of the computer, and querying the hardware anomaly database for abnormal detection data in the sub-detection information of each hardware structure; Using all hardware structure anomaly detection data as hardware network anomaly information of the computer; Based on the software self-check information, identifying program detection log information of each software program of the computer, and identifying abnormal log content in each of the program detection log information; The content of each abnormal log is used as the software network abnormality information of the computer, and the hardware network abnormality information of the computer and the software network abnormality information of the computer are used as the software and hardware abnormality information of the computer.

[0016] Optionally, the identification module is specifically used to: Filter target abnormal media information that affects network communication from the network abnormal information, and filter target software and hardware abnormal information that affects network communication from the software and hardware abnormal information; The target abnormal media information and the target software and hardware abnormal information are used through an abnormal analysis network to identify the network failure type and the cause of the network failure of the computer.

[0017] Optionally, the generating module is specifically used for: Based on the network fault type of the computer, querying the computer network fault database for each network fault information corresponding to the network fault type; Extracting a first network fault feature of the network fault cause and each second network fault feature corresponding to each network fault information, and respectively calculating a similarity between each second network fault feature and the first network fault feature; The network fault information corresponding to the second network fault feature with the maximum similarity is selected as the network fault detection result of the computer.

[0018] Optionally, the generating module is specifically used for: Acquire a network fault report template corresponding to the network fault type, and identify each template structure information of the network fault report template; Based on the target network fault characteristics of the network fault detection result and the template structure information of the network fault report template, identify the template structure information corresponding to the target network fault characteristics, and fill each target network fault characteristic into the template structure information to obtain the network fault detection report corresponding to the network fault detection result.

[0019] The present invention provides a computer network fault detection method and system based on artificial intelligence technology. The method comprises: when a computer network fault occurs, collecting network data information of the computer, hardware self-check information of the computer, and software self-check information of the computer, and identifying network abnormality information of the computer based on the network data information; identifying software and hardware abnormality information of the computer through a self-check analysis strategy based on the hardware self-check information and the software self-check information, and identifying the network fault type of the computer and the cause of the network fault of the computer through an abnormal analysis network based on the network abnormality information and the software and hardware abnormality information; identifying the network fault detection result of the computer based on the network fault type of the computer and the cause of the network fault of the computer through a computer network fault identification strategy, and generating a network fault detection report corresponding to the network fault detection result. This solution conducts a comprehensive detection of computer network failures from three angles: computer network data, hardware self-test information, and software self-test information, thereby avoiding the problem of detection limitations and one-sidedness, which affects the detection accuracy. Then, this solution conducts a comprehensive analysis of the three angles through an abnormal analysis network, thereby avoiding the error rate problem of manual analysis. Moreover, after analyzing the network failure type and the cause of the network failure, this solution comprehensively analyzes the network failure detection result, thereby improving the analysis efficiency and analysis accuracy of the computer network failure detection result. Moreover, after multi-angle failure analysis, the network failure detection result is identified from the perspective of the network failure type and the cause of the network failure, thereby improving the recognition efficiency and recognition accuracy of the network failure detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 is a flow chart of a computer network fault detection method based on artificial intelligence technology provided by an embodiment of the present invention; Figure 2 It is a structural diagram of a computer network fault detection system based on artificial intelligence technology provided by an embodiment of the present invention; Figure 3 An internal structure diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The computer network fault detection method based on artificial intelligence technology provided by the embodiment of the present invention is applied to the computer network fault detection system based on artificial intelligence technology. Unless otherwise defined, all technical and scientific terms used in this article have the same meaning as those generally understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned drawings and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0023] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0025] The computer network fault detection method based on artificial intelligence technology provided in the embodiment of the present application can be applied to the computer network fault detection application environment based on artificial intelligence technology. Among them, the method can be applied to the terminal, can also be applied to the server, can also be applied to the system including the terminal and the server, and is realized through the interaction between the terminal and the server. Among them, the terminal can be, but not limited to, various personal computers, laptops, etc. Among them, the terminal performs a full range of detection of computer network faults from three angles: the network data of the computer, the hardware self-check information, and the software self-check information, thereby avoiding the detection limitations and the one-sidedness of the detection, thereby affecting the problem of detection accuracy. Then, this scheme analyzes the three angles comprehensively through the abnormal analysis network, thereby avoiding the error rate problem of manual analysis. Moreover, after analyzing the network fault type and the network fault cause, this scheme comprehensively analyzes the network fault detection result, thereby improving the analysis efficiency and analysis accuracy of the network fault detection result of the computer, and after the multi-angle fault analysis, the network fault detection result is identified from the perspective of the network fault type and the network fault cause, thereby improving the recognition efficiency and recognition accuracy of the network fault detection result.

[0026] In one embodiment, Figure 1As shown, a computer network fault detection method based on artificial intelligence technology is provided, which is described by taking the method applied to a terminal as an example, and includes the following steps: Step S101, when a computer network failure occurs, collect computer network data information, computer hardware self-check information, and computer software self-check information, and identify computer network abnormality information based on the network data information.

[0027] In this embodiment, when the terminal detects a computer network failure, it collects the computer's network data information from the computer's network receiving port, and starts the computer's hardware self-test program and software self-test program to obtain the computer's hardware self-test information and the computer's software self-test information. Then, the terminal identifies the computer's network abnormality information based on the network data information. The specific identification process will be described in detail later. Among them, the network data information includes wireless network data, optical fiber network data, and twisted pair network data. Among them, the network data is not only used to characterize the data transmission process in the computer network transmission process, but also includes the network transmission medium feedback information in the network transmission process. Among them, network abnormality information is abnormal fluctuation information in network data information, which includes: weak signal, which is manifested as unstable wireless network connection, slow speed, or even frequent disconnection. The reasons are too far away from the wireless router, obstacles, wireless signal interference, etc.; wrong password, which is manifested as the inability to connect to the wireless network. The reason is that the entered wireless network password is wrong; wireless network card driver problem, which is manifested as the inability to search for the wireless network, or the inability to use it normally after connection. The reason is that the wireless network card driver is damaged, the version is incompatible, etc.; wireless router setting problem, which is manifested as the wireless network cannot work normally, or some devices cannot connect. The reason is hidden SSID, improper channel setting, wrong encryption method, etc.

[0028] Step S102, based on the hardware self-check information and the software self-check information, the computer's software and hardware abnormality information is identified through a self-check analysis strategy, and based on the network abnormality information and the software and hardware abnormality information, the computer's network failure type and the computer's network failure cause are identified through an abnormal analysis network.

[0029] In this embodiment, the terminal identifies the computer's software and hardware anomaly information through a self-check analysis strategy based on hardware self-check information and software self-check information, and identifies the computer's network failure type and the computer's network failure cause through anomaly analysis network based on network anomaly information and software and hardware anomaly information. The software and hardware anomaly information includes software network anomaly information and hardware network anomaly information, wherein the software network anomaly information includes the anomaly log information of each software program, and the hardware network anomaly information includes the anomaly detection information of each hardware structure. Among them, hardware network abnormal information includes: network card failure, which is manifested as the computer cannot connect to the network, and the network connection icon displays abnormally, such as a red cross or a yellow exclamation mark. The reasons may be damage to the network card driver, damage to the network card hardware, conflict between the network card and other devices, etc.; network cable failure, which is manifested as network connection interruption or extremely slow speed. The reasons include damage to the network cable, poor contact of the crystal head, and the network cable being squeezed or pulled, resulting in internal line breakage, etc.; router failure, which is manifested as the inability of devices in the entire LAN to access the Internet, or some devices cannot access the Internet. The reasons may be router overheating, configuration errors, hardware damage, software failure, etc.; switch failure, which is manifested as the inability of devices connected to the switch to communicate, network interruption or congestion, and the reasons include switch hardware failure, power supply problems, port damage, etc.; server failure, which is manifested as the inability to use network services that rely on the server, such as inaccessible websites and inability to send and receive emails. The reasons may be server hardware failure, operating system crash, software service shutdown, etc. Software network abnormal information includes: IP address conflict, which is manifested as a problem with the network connection, prompting an IP address conflict, because multiple devices are assigned the same IP address; Network configuration error, which is manifested as an inability to connect to the network or an unstable network connection, due to errors in the subnet mask, gateway, and DNS server settings; Virus and malware infection, which is manifested as slow network speed, frequent disconnection, and system abnormalities, because the computer is infected by viruses, Trojans, and malware, which damage network settings or occupy network resources; Firewall problems, which are manifested as some applications cannot connect to the network or cannot access specific websites, because the firewall settings are too strict and prevent legitimate network connections; Software conflicts, which are manifested as unstable network connections and some network functions cannot be used normally, because conflicts occur between different network software, affecting the normal operation of the network. The specific identification process will be described in detail later. The abnormal analysis network is an artificial neural network based on reinforcement learning. Among them, the network data includes the data fluctuation process in the network data transmitted during the transmission process when the signal is transmitted through optical fiber or twisted pair. The fluctuation process is the network fluctuation caused by the attenuation of the transmission signal of the optical fiber or twisted pair.

[0030] Step S103, based on the network fault type of the computer and the network fault cause of the computer, the network fault detection result of the computer is identified through the computer network fault identification strategy, and a network fault detection report corresponding to the network fault detection result is generated.

[0031] In this embodiment, the terminal identifies the network fault detection result of the computer based on the network fault type of the computer and the network fault cause of the computer through the computer network fault identification strategy, and generates a network fault detection report corresponding to the network fault detection result. Among them, the network fault detection result is a comprehensive detection result corresponding to each network detection angle of the computer, and the detection result is used to characterize the abnormal detection information related to the network fault at each angle corresponding to the network fault of the computer network.

[0032] Based on the above scheme, the computer network fault is comprehensively detected from three angles: computer network data, hardware self-test information, and software self-test information, avoiding the detection limitations and one-sidedness, which affect the detection accuracy. Then, this scheme analyzes the three angles comprehensively through the abnormal analysis network, avoiding the error rate problem of manual analysis. Moreover, after analyzing the network fault type and the network fault cause, this scheme comprehensively analyzes the network fault detection result, thereby improving the analysis efficiency and analysis accuracy of the computer network fault detection result. Moreover, after multi-angle fault analysis, the network fault detection result is identified from the perspective of the network fault type and the network fault cause, thereby improving the recognition efficiency and recognition accuracy of the network fault detection result.

[0033] Optionally, based on the network data information, identifying the network anomaly information of the computer, including: generating the network data distribution information of the computer based on the network data information, and extracting the network through distribution characteristics based on the network data distribution information, extracting the network data range characteristics of the computer, and the network data trend characteristics of the computer; based on the network data range characteristics and the network data trend characteristics, identifying the network through anomaly characteristics, identifying the abnormal network data range of the computer, and using the abnormal network data range of the computer as the network anomaly information of the computer.

[0034] In this embodiment, the terminal generates network data distribution information of the computer based on the network data information, and extracts the network data range characteristics of the computer and the network data trend characteristics of the computer through the distribution feature extraction network based on the network data distribution information. The distribution feature extraction network is a convolutional neural network based on deep learning.

[0035] Then, based on the network data range characteristics and network data trend characteristics, the terminal identifies the abnormal network data range of the computer through the abnormal feature recognition network, and uses the abnormal network data range of the computer as the network abnormality information of the computer. Among them, the abnormal feature recognition network is a convolutional neural network based on the self-attention mechanism.

[0036] Based on the above scheme, each network data range feature and network data trend feature are identified respectively through feature extraction, so as to identify the computer's network anomaly information, thereby improving the comprehensiveness and accuracy of the identification of network anomaly information.

[0037] Optionally, based on network data information, identifying network anomaly information of the computer, including: sending a network inspection data packet to each transmission node of the computer network transmission, and receiving node transmission results fed back by each transmission node; based on the node transmission results fed back by each transmission node, identifying abnormal transmission nodes among each transmission node, and using each abnormal transmission node as the network anomaly information of the computer.

[0038] In this embodiment, the terminal presets a network inspection data packet, which is used to check the operating status of each transmission node of the computer during the network data transmission process. Then, after traversing all transmission nodes through the network inspection data packet, the terminal receives the network inspection results fed back by each transmission node. Then, the terminal identifies the node operating status corresponding to each node transmission result for the node transmission result of each transmission node. Finally, the terminal regards the transmission node with abnormal node operating status as an abnormal transmission node. Among them, the abnormal node operating status includes, but is not limited to, abnormal states such as no node feedback, abnormal node feedback, and abnormal node transmission medium.

[0039] Based on the above scheme, by performing node self-inspection on each transmission node of computer network transmission, abnormal transmission media in each transmission medium can be identified, thereby improving the comprehensiveness and accuracy of identifying transmission medium anomalies and transmission node anomalies.

[0040] Optionally, based on the hardware self-check information and the software self-check information, the computer's hardware and software anomaly information is identified through a self-check analysis strategy, including: based on the hardware self-check information, identifying the sub-detection information of each hardware structure of the computer, and querying the hardware anomaly database for the anomaly detection data in the sub-detection information of each hardware structure; using the anomaly detection data of all hardware structures as the computer's hardware network anomaly information; based on the software self-check information, identifying the program detection log information of each software program of the computer, and identifying the anomaly log content in each program detection log information; using the content of each anomaly log as the computer's software network anomaly information, and using the computer's hardware network anomaly information and the computer's software network anomaly information as the computer's hardware and software anomaly information.

[0041] In this embodiment, the terminal identifies the sub-detection information of each hardware structure of the computer based on the hardware self-check information, and queries the hardware anomaly database for abnormal detection data in the sub-detection information of each hardware structure. The hardware anomaly database includes an abnormal detection data identification strategy for each sub-detection information, and then the terminal identifies each abnormal detection data in the sub-detection information of each hardware structure through the abnormal detection data identification strategy for each sub-detection information.

[0042] Then, the terminal takes all the abnormal detection data of the hardware structure as the hardware network abnormality information of the computer.

[0043] Then, the terminal identifies the program detection log information of each software program of the computer based on the software self-check information, and identifies the abnormal log content in each program detection log information. Among them, the abnormal log content is the non-conventional operation log information in the operation log information of each software program. The terminal presets the regular operation log range of each software program, and then the terminal regards the operation log information that does not belong to the regular operation log range as non-conventional operation log information.

[0044] Finally, the terminal uses the content of each abnormal log as the software network abnormality information of the computer, and uses the hardware network abnormality information of the computer and the software network abnormality information of the computer as the software and hardware abnormality information of the computer.

[0045] Based on the above scheme, by classifying and identifying the sub-detection information of each hardware structure and the program detection log information of each software program, the computer's software and hardware abnormal information is analyzed, thereby improving the comprehensiveness and accuracy of the identification of software and hardware information.

[0046] Optionally, based on the network anomaly information and the software and hardware anomaly information, the type of network failure of the computer and the cause of the network failure of the computer are identified through an anomaly analysis network, including: in the network anomaly information, screening target abnormal media information that affects network communication, and in the software and hardware anomaly information, screening target software and hardware anomaly information that affects network communication; using the target abnormal media information and the target software and hardware anomaly information through an anomaly analysis network to identify the type of network failure of the computer and the cause of the network failure of the computer.

[0047] In this embodiment, the terminal screens the target abnormal media information that affects the network communication in the network abnormal information, and screens the target software and hardware abnormal information that affects the network communication in the software and hardware abnormal information. Each network abnormal information includes a network abnormal information identifier, and each network abnormal information identifier corresponds to an abnormal type. Then, the terminal screens the network abnormal information whose abnormal type is the network communication abnormal type as the target abnormal media information (i.e., the target abnormal media information and the target software and hardware abnormal information).

[0048] Finally, the terminal uses the target abnormal medium information and target software and hardware abnormal information to identify the computer network failure type and the computer network failure cause through the abnormal analysis network. The abnormal analysis network is a classifier network based on artificial neural network.

[0049] Based on the above solution, after filtering the network anomaly information that affects network communication, the network fault type and the cause of the network fault are identified, thereby improving the accuracy and efficiency of network fault anomaly identification.

[0050] Optionally, based on the network fault type of the computer and the network fault cause of the computer, a network fault detection result of the computer is identified through a computer network fault identification strategy, including: based on the network fault type of the computer, querying each network fault information corresponding to the network fault type in a computer network fault database; extracting a first network fault feature of the network fault cause and each second network fault feature corresponding to each network fault information, and respectively calculating the similarity between each second network fault feature and the first network fault feature; and selecting the network fault information corresponding to the second network fault feature with the maximum similarity as the network fault detection result of the computer.

[0051] In this embodiment, the terminal queries each network fault information corresponding to the network fault type in the computer network fault database based on the network fault type of the computer. Then, the terminal extracts the first network fault feature of the network fault cause and each second network fault feature corresponding to each network fault information, and respectively calculates the similarity between each second network fault feature and the first network fault feature. Among them, the method of extracting the network fault feature is to extract the semantic features of the text information corresponding to the network fault cause and the text information corresponding to the network fault information through a large language model, and then obtain the first network fault feature of the network fault cause and each second network fault feature corresponding to each network fault information. Then, the terminal calculates the similarity between each second network fault feature and the first network fault feature through the cosine similarity recognition algorithm.

[0052] Finally, the terminal selects the network fault information corresponding to the second network fault feature with the maximum similarity as the network fault detection result of the computer.

[0053] Based on the above scheme, after feature extraction, the network fault detection results are identified by similarity recognition, which improves the recognition accuracy and efficiency of network fault detection.

[0054] Optionally, a network fault detection report corresponding to the network fault detection result is generated, including: obtaining a network fault report template corresponding to the network fault type, and identifying each template structure information of the network fault report template; based on each target network fault feature of the network fault detection result, and each template structure information of the network fault report template, identifying each template structure information corresponding to each target network fault feature, and filling each target network fault feature into each template structure information to obtain a network fault detection report corresponding to the network fault detection result.

[0055] In this embodiment, the terminal obtains the network fault report template corresponding to the network fault type, and identifies each template structure information of the network fault report template. Each template structure information is a template filling structure in the network fault report template, and all template filling structures are combined to obtain the network fault report template.

[0056] Then, the terminal identifies each template structure information corresponding to each target network fault feature based on each target network fault feature of the network fault detection result and each template structure information of the network fault report template. Each template filling structure is used to fill in network fault features of different fault angles. The fault angle includes but is not limited to the hardware angle, the software angle, and the network angle. Each template structure information includes a fault angle identifier. The terminal identifies each template structure information corresponding to each target network fault feature based on the corresponding relationship between each fault angle identifier and the fault angle corresponding to each network fault feature.

[0057] Finally, the terminal fills each target network fault feature into each template structure information to obtain a network fault detection report corresponding to the network fault detection result.

[0058] Based on the above scheme, after analyzing the template structure, the correspondence between the network fault characteristics and the template structure information is identified, so as to fill in the template. This not only improves the efficiency of intelligent template filling, but also effectively improves the visualization display effect of fault information, thereby comprehensively improving the visualization recognition efficiency of network fault detection information.

[0059] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0060] Based on the same inventive concept, the embodiment of the present application also provides a computer network fault detection system based on artificial intelligence technology for implementing the computer network fault detection method based on artificial intelligence technology involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the computer network fault detection system based on artificial intelligence technology provided below can refer to the limitations of the computer network fault detection method based on artificial intelligence technology above, and will not be repeated here.

[0061] Further references Figure 2 , as a response to the above Figure 1 In order to realize the method shown in the figure, the present application provides an embodiment of a computer network fault detection system 200 based on artificial intelligence technology. The computer network fault detection system based on artificial intelligence technology includes a collection module 210, an identification module 220, and a generation module 230, wherein: The collection module 210 is used to collect the network data information of the computer, the hardware self-check information of the computer, and the software self-check information of the computer when the computer network fails, and identify the network abnormality information of the computer based on the network data information; The identification module 220 is used to identify the hardware and software abnormality information of the computer through a self-check analysis strategy based on the hardware self-check information and the software self-check information, and to identify the network fault type of the computer and the cause of the network fault of the computer through an abnormal analysis network based on the network abnormality information and the hardware and software abnormality information; The generating module 230 is used to identify the network fault detection result of the computer based on the network fault type of the computer and the network fault cause of the computer through the computer network fault identification strategy, and generate a network fault detection report corresponding to the network fault detection result.

[0062] Optionally, the acquisition module 210 is specifically used for: Based on the network data information, network data distribution information of the computer is generated, and based on the network data distribution information, a network is extracted through distribution characteristics to extract network range characteristics of the computer and network data trend characteristics of the computer; Based on the network data range feature and the network data trend feature, the network is identified through abnormal feature, the abnormal network data range of the computer is identified, and the abnormal network data range of the computer is used as the network abnormality information of the computer.

[0063] Optionally, the identification module 220 is specifically configured to: Based on the hardware self-check information, identifying sub-detection information of each hardware structure of the computer, and querying the hardware anomaly database for abnormal detection data in the sub-detection information of each hardware structure; Using all hardware structure anomaly detection data as hardware network anomaly information of the computer; Based on the software self-check information, identifying program detection log information of each software program of the computer, and identifying abnormal log content in each of the program detection log information; The content of each abnormal log is used as the software network abnormality information of the computer, and the hardware network abnormality information of the computer and the software network abnormality information of the computer are used as the software and hardware abnormality information of the computer.

[0064] Optionally, the identification module 220 is specifically configured to: Filter target abnormal media information that affects network communication from the network abnormal information, and filter target software and hardware abnormal information that affects network communication from the software and hardware abnormal information; The target abnormal media information and the target software and hardware abnormal information are used through an abnormal analysis network to identify the network failure type and the cause of the network failure of the computer.

[0065] Optionally, the generating module 230 is specifically configured to: Based on the network fault type of the computer, querying the computer network fault database for each network fault information corresponding to the network fault type; Extracting a first network fault feature of the network fault cause and each second network fault feature corresponding to each network fault information, and respectively calculating a similarity between each second network fault feature and the first network fault feature; The network fault information corresponding to the second network fault feature with the maximum similarity is selected as the network fault detection result of the computer.

[0066] Optionally, the generating module 230 is specifically configured to: Acquire a network fault report template corresponding to the network fault type, and identify each template structure information of the network fault report template; Based on the target network fault characteristics of the network fault detection result and the template structure information of the network fault report template, identify the template structure information corresponding to the target network fault characteristics, and fill each target network fault characteristic into the template structure information to obtain the network fault detection report corresponding to the network fault detection result.

[0067] Each module in the above-mentioned computer network fault detection system based on artificial intelligence technology can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0068] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input system connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a computer network fault detection method based on artificial intelligence technology is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input system of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0069] The target hardware can be a repeater, hub, modem, bridge, switch, router, etc. The target software can be session layer software, presentation layer software, web server, mail server, DNS server, etc.

[0070] Computer networks are divided into seven layers according to the OSI (Open Systems Interconnection) model. Each layer has its own specific functions and corresponding network devices. The following are the devices corresponding to each layer: 1. Physical Layer Equipment: Repeater, Hub, Modem.

[0071] 2. Data Link Layer Equipment: Bridge, Switch.

[0072] 3. Network Layer Function: Responsible for selecting the best path between the source and the destination to implement the routing and forwarding of data packets.

[0073] Equipment: Router, Layer 3 Switch.

[0074] 4. Transport Layer Function: Responsible for providing end-to-end data transmission services and ensuring data integrity and reliability.

[0075] Devices: There are usually no dedicated transport layer devices, but some advanced switches and routers can provide transport layer functions.

[0076] 5. Session Layer Function: Responsible for establishing, managing and terminating sessions.

[0077] Device: Usually implemented by software, without dedicated hardware devices.

[0078] 6. Presentation Layer Function: Responsible for data representation, encoding, and conversion, ensuring that the information sent by the application layer of one system can be read by the application layer of another system.

[0079] Device: Usually implemented by software, without dedicated hardware devices.

[0080] 7. Application Layer Equipment: There is no dedicated hardware equipment, but it includes various network services and applications, such as Web servers, mail servers, DNS servers, etc.

[0081] In the actual TCP / IP model, the functions of the session layer, presentation layer, and application layer are usually merged into the application layer. In actual network devices, the functions of many devices span multiple layers. For example, some advanced routers and switches can handle problems at multiple layers.

[0082] In addition: Computer network failures mostly occur in the medium, such as twisted pair cables and optical fibers being broken, pulled hard, or bent during the laying process, or the tightness of network connectors, which result in signal attenuation and packet loss.

[0083] When conducting detection, packets with special information are often sent manually.

[0084] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0086] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A computer network fault detection method based on artificial intelligence technology, characterized in that: The method comprises: When a computer network fails, network data information of the computer, hardware self-check information of the computer, and software self-check information of the computer are collected, and network abnormal information of the computer is identified based on the network data information; Based on the hardware self-check information and the software self-check information, identifying the software and hardware abnormality information of the computer through a self-check analysis strategy, and based on the network abnormality information and the software and hardware abnormality information, identifying the network fault type of the computer and the cause of the network fault of the computer through an abnormal analysis network; Based on the network fault type of the computer and the network fault cause of the computer, a network fault detection result of the computer is identified through a computer network fault identification strategy, and a network fault detection report corresponding to the network fault detection result is generated.

2. The computer network fault detection method based on artificial intelligence technology according to claim 1 is characterized in that: The identifying network abnormality information of the computer based on the network data information includes: Based on the network data information, network data distribution information of the computer is generated, and based on the network data distribution information, a network is extracted through distribution characteristics to extract network range characteristics of the computer and network data trend characteristics of the computer; Based on the network data range feature and the network data trend feature, the network is identified through abnormal feature, the abnormal network data range of the computer is identified, and the abnormal network data range of the computer is used as the network abnormality information of the computer.

3. The computer network fault detection method based on artificial intelligence technology according to claim 1 is characterized in that: The identifying network abnormality information of the computer based on the network data information includes: Sending network inspection data packets to each transmission node of computer network transmission, and receiving node transmission results fed back by each transmission node; Based on the node transmission results fed back by each of the transmission nodes, abnormal transmission nodes among the transmission nodes are identified, and each of the abnormal transmission nodes is used as network abnormality information of the computer.

4. The computer network fault detection method based on artificial intelligence technology according to claim 1 is characterized in that: The identifying the abnormal software and hardware information of the computer through a self-check analysis strategy based on the hardware self-check information and the software self-check information includes: Based on the hardware self-check information, identifying sub-detection information of each hardware structure of the computer, and querying the hardware anomaly database for abnormal detection data in the sub-detection information of each hardware structure; Using all hardware structure anomaly detection data as hardware network anomaly information of the computer; Based on the software self-check information, identifying program detection log information of each software program of the computer, and identifying abnormal log content in each of the program detection log information; The content of each abnormal log is used as the software network abnormality information of the computer, and the hardware network abnormality information of the computer and the software network abnormality information of the computer are used as the software and hardware abnormality information of the computer.

5. The computer network fault detection method based on artificial intelligence technology according to claim 1 is characterized in that: The identifying the type of network failure of the computer and the cause of the network failure of the computer by analyzing the network failure based on the network failure information and the software and hardware failure information includes: In the network abnormality information, target abnormal media information that affects network communication is screened, and in the software and hardware abnormality information, target software and hardware abnormality information that affects network communication is screened; The target abnormal media information and the target software and hardware abnormal information are used through an abnormal analysis network to identify the network failure type and the cause of the network failure of the computer.

6. The computer network fault detection method based on artificial intelligence technology according to claim 1 is characterized in that: The method of identifying the network fault detection result of the computer based on the network fault type of the computer and the network fault cause of the computer by using a computer network fault identification strategy includes: Based on the network fault type of the computer, querying the computer network fault database for each network fault information corresponding to the network fault type; Extracting a first network fault feature of the network fault cause and each second network fault feature corresponding to each network fault information, and respectively calculating a similarity between each second network fault feature and the first network fault feature; The network fault information corresponding to the second network fault feature with the maximum similarity is selected as the network fault detection result of the computer.

7. The computer network fault detection method based on artificial intelligence technology according to claim 6 is characterized in that: The generating a network fault detection report corresponding to the network fault detection result includes: Acquire a network fault report template corresponding to the network fault type, and identify each template structure information of the network fault report template; Based on the target network fault characteristics of the network fault detection result and the template structure information of the network fault report template, identify the template structure information corresponding to the target network fault characteristics, and fill each target network fault characteristic into the template structure information to obtain the network fault detection report corresponding to the network fault detection result.

8. A computer network fault detection system based on artificial intelligence technology, characterized in that: The system comprises: A collection module, used for collecting network data information of the computer, hardware self-check information of the computer, and software self-check information of the computer when a computer network fails, and identifying network abnormality information of the computer based on the network data information; an identification module, configured to identify the hardware and software abnormality information of the computer through a self-check analysis strategy based on the hardware self-check information and the software self-check information, and to identify the network fault type and the network fault cause of the computer through an abnormal analysis network based on the network abnormality information and the hardware and software abnormality information; A generation module is used to identify the network fault detection result of the computer based on the network fault type of the computer and the network fault cause of the computer through a computer network fault identification strategy, and generate a network fault detection report corresponding to the network fault detection result.

Images