Router fault automatic repair method, system, device and medium

Abstract

The invention provides a router fault automatic repair method, system and device and a medium, and the scheme comprises the steps: responding to the occurrence of a fault, and obtaining log data corresponding to the current fault in real time; obtaining a problem classification result and a problem mark of the current fault by using a pre-trained fault classification model based on deep learning based on the obtained log data; based on the problem classification result and the problem mark, accessing a pre-constructed problem solving large model according to a preset public network service path to obtain a solution of the current fault; and executing the currently obtained solution to realize automatic repair of the router fault. According to the scheme, by designing the problem solving large model, the router can automatically repair most of self faults, and by periodically updating the problem solving large model, the robustness of the problem solving large model can be effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial routers, and in particular relates to a method, system, equipment and medium for automatically repairing router faults. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Industrial routers are generally used in very complex on-site environments. When network anomalies or product failures occur due to the industrial environment, there are high requirements for rapid resolution of the faults.

[0004] The inventors have found that existing solutions usually adopt manual on-site or remote operation, but this method, on the one hand, requires the operator to have high professional knowledge and experience accumulation, and on the other hand, the operator's schedule is difficult to meet the time limit requirements for fault resolution; secondly, although there are some automatic repair solutions in the existing solutions, these solutions usually automatically perform a restart operation after a fault occurs, and solve the fault problem by restarting. The range of problems that can be solved by this method is extremely narrow, and the robustness is poor. Other types of problems still need to be handled manually, and the processing efficiency is low. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a method, system, device and medium for automatic repair of router faults, so as to solve the problems that traditional solutions rely on manual processing, cannot meet the time limit requirements for fault resolution and have high requirements on the professional knowledge of operators, and the problems that the existing automated methods have a narrow range of problems to be solved and poor robustness.

[0006] According to a first aspect of an embodiment of the present invention, there is provided a method for automatically repairing a router fault, which is applied to a router and includes:

[0007] In response to the occurrence of a fault, the log data corresponding to the current fault is obtained in real time;

[0008] Based on the obtained log data, the pre-trained deep learning-based fault classification model is used to obtain the problem classification results and problem tags of the current fault;

[0009] Based on the problem classification results and problem tags, a pre-built problem solving big model is accessed according to a preset public network service path to obtain a solution to the current fault; wherein the problem solving big model uses a continuously updated database table, each record in the database table includes a problem category, a problem tag and a problem solution, and the problem solution is set using an executable file;

[0010] Execute the currently obtained solution to achieve automatic repair of router failures.

[0011] Furthermore, the router stores a large local problem solving model, wherein the stored large local problem solving model is updated from a public network service path based on a preset period.

[0012] Furthermore, when the router network is abnormal, a query for a solution to the fault problem is performed based on the local problem solving large model.

[0013] Furthermore, the automatic fault repair function is enabled by default in the router, and emergency contacts are automatically configured. When the fault cannot be solved or is not a fault of the router itself, an alarm is sent to the emergency contact via text message or AI intelligent voice.

[0014] Furthermore, the updating of the problem solving large model is specifically: based on the router failure problem descriptions and corresponding solutions periodically updated by the router manufacturer, they are periodically and automatically updated and synchronized to the database under the public network service path.

[0015] Furthermore, the judgment of the occurrence of the fault is specifically: real-time monitoring of the generated logs is performed, and when a new fault log appears, it is determined that a router fault occurs.

[0016] Furthermore, the fault classification includes router faults and non-router faults. The router faults include but are not limited to: LAN DHCP abnormality, default route loss, router process abnormality, router memory or CPU abnormality, and router default parameter or firewall parameter loss; the solution in the problem solving model is implemented in an executable patch manner.

[0017] According to a second aspect of an embodiment of the present invention, there is provided a system for automatically repairing a router fault, comprising:

[0018] A data acquisition unit, which is used to respond to the occurrence of a fault and obtain log data corresponding to the current fault in real time;

[0019] A fault classification unit, which is used to obtain a problem classification result and a problem tag of the current fault based on the obtained log data and using a pre-trained deep learning-based fault classification model;

[0020] A solution acquisition unit, which is used to access a pre-built problem-solving model based on the problem classification result and the problem tag according to a preset public network service path to obtain a solution to the current fault; wherein the problem-solving model adopts a continuously updated database table, each record in the database table includes a problem category, a problem tag and a problem solution, and the problem solution is set by an executable file;

[0021] The automatic repair unit is used to execute the currently obtained solution to realize automatic repair of router failure.

[0022] According to a third aspect of an embodiment of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored and running on the memory, wherein the processor implements the method for automatically repairing a router fault when executing the program.

[0023] According to a fourth aspect of an embodiment of the present invention, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for automatically repairing a router fault is implemented.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] (1) The present invention provides a method, system, device and medium for automatically repairing router faults. The scheme enables the router to automatically repair most of its own faults through a designed problem-solving big model, and can effectively improve the robustness of the problem-solving big model by periodically updating the problem-solving big model.

[0026] (2) The solution of the present invention deploys the problem-solving big model in a public network server, so that both the router and the router manufacturer can communicate with the public network server. Based on the fault problems and solutions continuously obtained by the technical support personnel of the router manufacturer, the problem-solving big model can be quickly updated periodically. At the same time, by querying the fault problem solution in the problem-solving big model in the public network server when there is no network abnormality, it can effectively ensure that the router can obtain the problem solution in the latest and most complete problem-solving big model. And by storing the local problem-solving big model in the router and updating it periodically, it can guarantee to a certain extent that the router can query the fault problem solution when the network is abnormal.

[0027] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0029] Figure 1 The present invention is a flowchart of a method for automatically repairing a router fault according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0031] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0032] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0033] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0034] In order to solve the problems existing in the prior art, such as Figure 1 As shown, this embodiment provides a method for automatically repairing a router fault, which is applied to a router and includes:

[0035] Step 1: In response to the occurrence of a fault, the log data corresponding to the current fault is obtained in real time;

[0036] The judgment of the occurrence of the fault is specifically: real-time monitoring of the generated logs is performed, and when a new fault log appears, it is determined that a router fault occurs.

[0037] Specifically, a fault log analysis program is built into the router, and the newly generated router log is analyzed in real time by the fault log analysis program. When the newly generated log is identified as a fault log, it is determined that the router has a fault, and subsequent processing steps are executed.

[0038] It can be understood that the specific code implementation of the above-mentioned fault log analysis program is not the focus of the solution described in this embodiment, and it is not difficult for the technical personnel in this field to implement the above-mentioned functions, so it will not be repeated here.

[0039] In one or more embodiments, the fault log can be identified by using a pre-trained deep learning-based fault log identification model; it can also be identified by identifying relevant identifiers in the log, for example: adding relevant identifiers to different categories of logs in the log settings, and different categories of log settings have different identifiers. Therefore, it can be determined whether it is a fault log by identifying the log identifier at a specific location in the log.

[0040] Step 2: Based on the obtained log data, use the pre-trained deep learning-based fault classification model to obtain the problem classification result and problem tag of the current fault;

[0041] In one or more embodiments, two deep learning-based fault classification models are provided (including model one and model two), model one is used to determine whether the current fault is a fault of the router itself; model two is used to determine the specific problem (i.e., problem tag) corresponding to the router fault.

[0042] In a specific implementation, the fault classification model needs to be pre-trained based on a pre-constructed training set, wherein the samples in the training set of model one include log data and whether it is a fault of the router itself. Model one is essentially a binary classifier; the samples in the training set of model two include log data and specific problems corresponding to the current fault. Model two is essentially a multi-classifier.

[0043] Step 3: Based on the problem classification result and the problem tag, access the pre-built problem solving big model according to the preset public network service path to obtain a solution to the current fault; wherein the problem solving big model adopts a continuously updated database table, each record in the database table includes a problem category, a problem tag and a problem solution, and the problem solution is set by an executable file;

[0044] In a specific implementation, the updating of the problem solving big model is specifically: based on the router failure problem descriptions and corresponding solutions periodically updated by the router manufacturer, they are periodically and automatically updated and synchronized to the database under the public network service path.

[0045] Specifically, the technical support personnel of the router manufacturer need to provide technical support to all router users. The router manufacturer can obtain a large amount of user feedback data. By analyzing and processing these feedback data, it can obtain different router failure problems in real time and provide solutions to different failure problems. Based on this, the solution described in this embodiment periodically updates the problem-solving big model stored in the local computer and public network service path of the router manufacturer's technical support personnel to achieve continuous and rapid updating of the problem-solving big model.

[0046] For example, when a router manufacturer's technical support staff updates a local database table on their local computer, the problem-solving model is automatically updated and uploaded to the public network service path, thereby achieving continuous updating of the problem-solving model.

[0047] In real time, the router can interact with the public network server to obtain the public network service path, which is the access path of the problem-solving model (i.e., a database table of a problem and its solution stored in the database), through which the database table can be queried and read.

[0048] In one or more real-time modes, in order to address the problem that the router cannot communicate with the public network server, the solution described in this embodiment stores a local problem-solving big model in the router, wherein the stored local problem-solving big model is updated from the public network service path based on a preset period.

[0049] For example, the problem solving model under the public network service path is updated to the router every 5 minutes.

[0050] In a specific implementation, when the router network is abnormal, a query for a fault problem solution is performed based on a local problem solving large model.

[0051] In a specific implementation, the fault classification includes router faults and non-router faults. The router faults include but are not limited to: LAN DHCP abnormality, default route loss, router process abnormality, router memory or CPU abnormality, and router default parameter or firewall parameter loss; the solution in the problem solving model is implemented in an executable patch manner, wherein:

[0052] For LAN DHCP abnormality, use the following solutions:

[0053] The LAN port phy chip parameters are rewritten from the backup area and the phy restart operation is performed, and the LAN port is tested to see if it can normally assign an IP to the device;

[0054] If the default route is lost and the Internet cannot be accessed, the following solutions are used:

[0055] Check the route and add it again;

[0056] For router process abnormality, use the following solutions:

[0057] Close abnormal processes;

[0058] For router memory or CPU abnormalities, use the following solutions:

[0059] Release some garbage cache;

[0060] The following solutions are used to solve the problem of router default parameters or firewall parameters being lost:

[0061] Restore parameters through the backup area.

[0062] It is understandable that the above solution can be implemented using a .patch patch file. When the above fault occurs in the router, the fault can be automatically repaired by executing the corresponding .patch patch file.

[0063] Step 4: Execute the currently obtained solution to automatically repair the router fault.

[0064] In one or more embodiments, the automatic fault repair function is enabled by default in the router, and emergency contacts are automatically configured. When the fault cannot be resolved or is not a fault of the router itself, an alarm is sent to the emergency contact via text message or AI intelligent voice.

[0065] In one or more embodiments, corresponding to the above method, this embodiment provides a router fault automatic repair system, including:

[0066] A data acquisition unit, which is used to respond to the occurrence of a fault and obtain log data corresponding to the current fault in real time;

[0067] A fault classification unit, which is used to obtain a problem classification result and a problem tag of the current fault based on the obtained log data and using a pre-trained deep learning-based fault classification model;

[0068] A solution acquisition unit, which is used to access a pre-built problem-solving model based on the problem classification result and the problem tag according to a preset public network service path to obtain a solution to the current fault; wherein the problem-solving model adopts a continuously updated database table, each record in the database table includes a problem category, a problem tag and a problem solution, and the problem solution is set by an executable file;

[0069] The automatic repair unit is used to execute the currently obtained solution to realize automatic repair of router failure.

[0070] It can be understood that the system described in this embodiment corresponds one-to-one to the above-mentioned method embodiment, and its technical details have been described in detail in the method embodiment, so they will not be repeated here.

[0071] In further embodiments, there is also provided:

[0072] An electronic device includes a memory and a processor and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the method described in the above embodiment. For the sake of brevity, no further description is given here.

[0073] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0074] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0075] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method described in the above embodiment is completed.

[0076] The method in the above embodiment can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0077] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in the present embodiment can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0078] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for automatically repairing router faults, which is applied to routers, characterized in that: include: In response to the occurrence of a fault, the log data corresponding to the current fault is obtained in real time; Based on the obtained log data, the pre-trained deep learning-based fault classification model is used to obtain the problem classification results and problem tags of the current fault; Based on the problem classification results and problem tags, a pre-built problem solving big model is accessed according to a preset public network service path to obtain a solution to the current fault; wherein the problem solving big model uses a continuously updated database table, each record in the database table includes a problem category, a problem tag and a problem solution, and the problem solution is set using an executable file; Execute the currently obtained solution to achieve automatic repair of router failures.

2. A method for automatically repairing a router fault as claimed in claim 1, characterized in that: The router stores a large local problem solving model, wherein the stored large local problem solving model is updated from a public network service path based on a preset period.

3. A method for automatically repairing a router fault as claimed in claim 2, characterized in that: When the router network is abnormal, a query for a solution to the fault problem is performed based on a local problem solving model.

4. A method for automatically repairing a router fault as claimed in claim 1, characterized in that: The automatic fault repair function is enabled by default in the router, and emergency contacts are automatically configured. When the fault cannot be solved or is not a fault of the router itself, an alarm is sent to the emergency contact via SMS or AI intelligent voice.

5. A method for automatically repairing a router fault as claimed in claim 1, characterized in that: The updating of the problem solving model is specifically as follows: based on the description of the router failure problem and its corresponding solution periodically updated by the router manufacturer, the description is automatically updated and synchronized to the database under the public network service path periodically.

6. A method for automatically repairing a router fault as claimed in claim 1, characterized in that: The judgment of the occurrence of the fault is specifically: real-time monitoring of the generated logs is performed, and when a new fault log appears, it is determined that a router fault occurs.

7. A method for automatically repairing a router fault as claimed in claim 1, characterized in that: The fault classification includes router faults and non-router faults. The router faults include but are not limited to: LAN DHCP abnormality, default route loss, router process abnormality, router memory or CPU abnormality, and router default parameter or firewall parameter loss. The solution in the problem solving model is implemented in an executable patch manner.

8. A router fault automatic repair system, characterized in that: include: A data acquisition unit, which is used to respond to the occurrence of a fault and obtain log data corresponding to the current fault in real time; A fault classification unit, which is used to obtain a problem classification result and a problem tag of the current fault based on the obtained log data and using a pre-trained deep learning-based fault classification model; A solution acquisition unit, which is used to access a pre-built problem-solving model based on the problem classification result and the problem tag according to a preset public network service path to obtain a solution to the current fault; wherein the problem-solving model adopts a continuously updated database table, each record in the database table includes a problem category, a problem tag and a problem solution, and the problem solution is set by an executable file; The automatic repair unit is used to execute the currently obtained solution to realize automatic repair of router failure.

9. An electronic device comprising a memory, a processor and a computer program stored and running on the memory, characterized in that: When the processor executes the program, the method for automatically repairing a router fault as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a method for automatically repairing a router fault as described in any one of claims 1 to 7 is implemented.

Images