Operation and maintenance method and device and access controller

Abstract

The invention provides an operation and maintenance method, an operation and maintenance device and an access controller. The method is applied to an access controller and comprises the steps of obtaining local operation and maintenance data, inputting the local operation and maintenance data into an AI model to obtain an operation and maintenance decision result, and finally executing operation and maintenance operation according to the operation and maintenance decision result, and in the operation and maintenance stage, the access controller performs updating according to the historical operation and maintenance data. According to the method, the AI model is built in the access controller, intelligent operation and maintenance of the access controller are realized by using the AI technology, timely response to network problems is realized, user data leakage is avoided, and network stability is ensured.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to an operation and maintenance method, device and access controller. Background Art

[0002] The access controller (AC) is the core of the wireless network, responsible for managing access points (APs) and forwarding wireless traffic. If the access controller is busy or has unknown problems, the user's network will be stuck or even unable to access the Internet. With the development of AI (Artificial Intelligence), intelligent network operation and maintenance is the general trend to ensure 24-hour stable operation of the network.

[0003] At present, intelligent operation and maintenance is generally implemented based on cloud platforms. The main body of intelligent operation and maintenance based on cloud platforms is divided into two parts: one is the access controller or access point, and the other is the online cloud server. In actual applications, the devices in the network regularly report data to the cloud platform, and the cloud server or operation and maintenance personnel conduct statistical analysis and operation and maintenance decisions on the data, and then send subsequent operation and maintenance operations to the devices to avoid or solve problems.

[0004] However, for public clouds, some users are worried that their network data will be exposed and do not want to connect to the public cloud, so the intelligent operation and maintenance function cannot be used. Moreover, intelligent operation and maintenance makes operation and maintenance decisions based on reported data, and most problems still rely on manual data analysis and judgment by operation and maintenance personnel. In addition, due to the need to relieve wireless network pressure, the granularity of the reported data of each device is generally large, resulting in the inability to respond in time even if a problem occurs. Summary of the invention

[0005] In order to overcome the problems existing in the related art, the present application provides an operation and maintenance method, device and access controller.

[0006] According to a first aspect of an embodiment of the present application, an operation and maintenance method is provided, the method being applied to an access controller, the method comprising:

[0007] Obtain local operation and maintenance data;

[0008] Inputting the local operation and maintenance data into the AI ​​model to obtain an operation and maintenance decision result, wherein the input data of the AI ​​model in the initialization phase is standard operation and maintenance data, and the access controller is updated according to historical operation and maintenance data in the operation and maintenance phase;

[0009] Execute operation and maintenance operations according to the operation and maintenance decision result.

[0010] According to a second aspect of an embodiment of the present application, an operation and maintenance device is provided, the device being applied to an access controller, the device comprising:

[0011] Data acquisition module, used to obtain local operation and maintenance data;

[0012] A decision module, used to input the local operation and maintenance data into the AI ​​model to obtain an operation and maintenance decision result, wherein the input data of the AI ​​model in the initialization phase is standard operation and maintenance data, and the access controller is updated according to historical operation and maintenance data in the operation and maintenance phase;

[0013] The operation and maintenance module is used to perform operation and maintenance operations according to the operation and maintenance decision results.

[0014] According to a third aspect of an embodiment of the present application, there is provided an access controller, including: an operating system module, a product driver module and an AI module;

[0015] The product driving module is used to obtain local operation and maintenance data from the operating system module, and send the local operation and maintenance data to the AI ​​module, the AI ​​module uses the AI ​​model to analyze the local operation and maintenance data and outputs an operation and maintenance decision result, and the product driving module calls the operating system module to perform an operation and maintenance operation according to the operation and maintenance decision result;

[0016] Among them, the input data of the AI ​​model in the initialization stage is standard operation and maintenance data, and in the operation and maintenance stage, the access controller is updated according to historical operation and maintenance data.

[0017] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0018] In an embodiment of the present application, the AI ​​model is initialized in advance according to standard operation and maintenance data, and the AI ​​model is deployed to the access controller, and the access controller subsequently iterates and updates the AI ​​model based on historical operation and maintenance data. The present application implements an operation and maintenance method based on an access controller integrated with an AI model, which can obtain local operation and maintenance data, input the local operation and maintenance data into the AI ​​model, obtain an operation and maintenance decision result, and then perform an operation and maintenance operation according to the operation and maintenance decision result.

[0019] The present application integrates an AI model in an access controller and uses the AI ​​model to implement intelligent operation and maintenance of the access controller. Compared with the intelligent operation and maintenance solution based on the cloud platform, on the one hand, the AI ​​model set locally in the access controller of the present application can obtain richer operation and maintenance data with smaller data granularity, thereby enabling further expansion and improvement of the intelligent operation and maintenance function based on the cloud platform and improving the timeliness of operation and maintenance; on the other hand, the present application does not need to upload the data of the access controller to the public cloud, thereby ensuring the privacy of user data; on the third hand, based on the autonomous learning ability of the AI ​​model, the present application uses the historical operation and maintenance data of the access controller in the actual application scenario to continuously adjust and optimize the AI ​​model, thereby ensuring that the operation and maintenance solution decided based on the AI ​​model is more in line with the actual application scenario requirements and improving the reliability of the overall operation and maintenance solution.

[0020] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in the specification and constitute a part of this application, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application.

[0022] Figure 1 A flowchart of the operation and maintenance method provided in the embodiment of the present application;

[0023] Figure 2 The AI ​​model update process in a stand-alone environment provided in the embodiment of the present application;

[0024] Figure 3 A schematic diagram of the overall structure of the access controller provided in the embodiment of the present application;

[0025] Figure 4 A data flow diagram of an access controller provided in an embodiment of the present application;

[0026] Figure 5 A schematic diagram of the AI ​​model update process in a multi-machine environment provided in an embodiment of the present application;

[0027] Figure 6 A schematic diagram of an operation and maintenance device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0029] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0030] It should be understood that, although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" or "if" as used herein may be interpreted as "at the time of" or "when...".

[0031] Next, the embodiments of the present application are described in detail.

[0032] The present application embodiment provides an operation and maintenance method, which is applied to an access controller, such as Figure 1 As shown, the method comprises the following steps:

[0033] Step 110: Obtain local operation and maintenance data;

[0034] Step 120: Input the local operation and maintenance data into the AI ​​model to obtain an operation and maintenance decision result, wherein the input data of the AI ​​model in the initialization phase is standard operation and maintenance data, and the access controller is updated according to historical operation and maintenance data in the operation and maintenance phase;

[0035] Step 130: Perform operation and maintenance operations according to the operation and maintenance decision result.

[0036] This embodiment integrates the AI ​​computing and analysis function into the access controller, and builds an AI model into the access controller to realize intelligent operation and maintenance of the access controller. Therefore, the access controller no longer needs to upload its own operation and maintenance data to the cloud platform, thereby avoiding user data leakage. In addition, the access controller inputs local operation and maintenance data into the AI ​​model to realize operation and maintenance decisions. Compared with the operation and maintenance solution based on the cloud platform, the access controller can input richer, more specific, and more timely operation and maintenance data into the AI ​​model. Therefore, the operation and maintenance solution based on the AI ​​model of this embodiment can supplement the operation and maintenance function of the cloud platform-based operation and maintenance solution. Moreover, since the AI ​​model runs locally on the access controller, the access controller has greater flexibility in the time of collecting operation and maintenance data. Therefore, the access controller can obtain operation and maintenance data with a smaller time granularity and input it into the AI ​​model for operation and maintenance decisions, thereby improving the timeliness of operation and maintenance response.

[0037] Specifically, an AI model is created in advance. In the initialization phase, the AI ​​model is initialized using standard operation and maintenance data, and then the initialized AI model is deployed to the access controller in the actual user network. In the subsequent operation and maintenance phase, the access controller iteratively updates and optimizes the AI ​​model based on historical operation and maintenance data, so that the AI ​​model can output operation and maintenance decision results that are more in line with the actual user network needs, ensuring the reliability of the overall operation and maintenance solution.

[0038] That is to say, in view of the fact that the commonly used network environments at different sites are very different, this embodiment first initializes the AI ​​model using standard operation and maintenance data, and then the access controller uses a linear regression algorithm to continuously adjust and optimize the AI ​​model through historical operation and maintenance data, so that the operation and maintenance decision-making capabilities of the AI ​​model can better adapt to the site environment.

[0039] The operation and maintenance method of this embodiment can be used to solve various types of problems, including but not limited to uneven network traffic distribution, abnormal terminal traffic, and irreversible equipment failure. The operation and maintenance process of each type of problem is described below.

[0040] In actual networks, the network traffic on site is not always evenly distributed, and the utilization rate of a CPU forwarding core is often too high, causing some users to freeze. In order to fully utilize the CPU performance of the device, this application uses a traffic diversion algorithm to perform hash calculations on the network traffic based on the MAC, IP address, and port number of the message to evenly distribute the network traffic to each CPU of the access controller, thereby giving full play to the forwarding performance of the access controller.

[0041] Specifically, in this application, the access controller uses an AI model to predict the changing trend of network traffic on the access controller, and determines the target diversion algorithm or target diversion algorithm parameters with the best diversion effect based on the traffic trend. After that, the access controller changes the diversion algorithm or modifies the diversion algorithm parameters in advance according to the target diversion algorithm or target diversion algorithm parameters output by the AI ​​model, so as to distribute the traffic as evenly as possible to each CPU to maximize the forwarding performance.

[0042] In summary, this embodiment provides the following two solutions to the problem of uneven network traffic distribution:

[0043] Solution 1: Pre-set multiple diversion algorithms on the access controller. When it is detected that the effect of the current diversion algorithm is not ideal, such as when the CPU utilization reaches a threshold, the access controller uses the AI ​​model to predict the target diversion algorithm with the best diversion effect. The access controller then performs corresponding operation and maintenance operations to switch the current diversion algorithm to the target diversion algorithm.

[0044] Specifically, the access controller inputs the local network traffic data into the AI ​​model to perform a first traffic diversion operation and obtain a target traffic diversion algorithm identifier, wherein the first traffic diversion operation includes predicting a traffic trend based on the local network traffic data and determining a target traffic diversion algorithm identifier based on the traffic trend. Afterwards, the access controller performs a traffic diversion algorithm switching operation based on the target traffic diversion algorithm identifier output by the AI ​​model, and switches the current traffic diversion algorithm to the target traffic diversion algorithm.

[0045] Solution 2: When the effect of the current diversion algorithm is not ideal, for example, when the CPU utilization reaches a threshold, the access controller uses the AI ​​model to predict the target diversion algorithm parameters with the best diversion effect. The access controller then performs corresponding operation and maintenance operations, that is, updates the algorithm parameters of the current diversion algorithm to the target diversion algorithm parameters.

[0046] Specifically, the access controller inputs the local network traffic data into the AI ​​model to perform the second traffic diversion operation and obtain the target traffic diversion algorithm parameters, wherein the second traffic diversion operation includes predicting the traffic trend according to the local network traffic data and determining the target traffic diversion algorithm parameters according to the traffic trend. Afterwards, the access controller updates the parameters of the current traffic diversion algorithm to the target traffic diversion algorithm parameters according to the target traffic diversion algorithm parameters output by the AI ​​model.

[0047] There are a lot of abnormal traffic caused by misoperation in the existing network, and there are also a lot of traffic from malicious attacks. When a large amount of abnormal traffic appears, it usually takes a certain amount of time to investigate, and finally find out which terminals are coming from the traffic, and then deal with it. In this application, the access controller uses an AI model to monitor terminal traffic, and responds promptly when abnormal traffic and abnormal terminals are found. For example, based on terminal identification such as five-tuples, the abnormal terminal is kicked offline or the abnormal traffic is limited to ensure that the network is not congested.

[0048] In summary, this embodiment provides the following solutions to the problem of abnormal terminal traffic:

[0049] The access controller inputs the terminal traffic data into the AI ​​model to perform an anomaly detection operation, and obtains an operation and maintenance operation identifier and a terminal identifier, wherein the anomaly detection operation includes determining whether the terminal traffic data is abnormal traffic, and when the judgment result is yes, determining the operation and maintenance operation identifier of the first operation and maintenance operation and the terminal identifier of the abnormal terminal based on the terminal traffic data. Afterwards, the access controller performs the first operation and maintenance operation on the abnormal terminal according to the operation and maintenance operation identifier and the terminal identifier. The first operation and maintenance operation is speed limiting or offline.

[0050] In terms of device management, the access controller in this embodiment can use AI models to implement fault prevention and fault handling. Specifically, when encountering irreversible problems, the access controller calls the AI ​​model to make operation and maintenance decisions based on the device status data, and executes avoidance measures without affecting customer use to ensure stable operation of the device problem, for example, restarting the process suspected of memory leakage and recording it; for dual-link, cloud cluster and other networking environments, actively triggering the master-slave switch or the original master restarting itself.

[0051] In summary, this embodiment provides the following solutions for irreversible equipment failures:

[0052] The access controller inputs the device status data into the AI ​​model to perform an irreversible problem detection operation and obtain an operation and maintenance operation identifier, wherein the irreversible problem detection operation includes judging whether an irreversible error occurs in the device according to the device status data, and determining the operation and maintenance operation identifier of the second operation and maintenance operation according to the device status data when the judgment result is yes. Finally, the access controller performs the second operation and maintenance operation according to the operation and maintenance operation identifier. The second operation and maintenance operation is restart or master-slave switching.

[0053] Considering that the AI ​​model update process has high CPU requirements, as a preferred implementation, the access controller of the present application selectively starts the update function of the AI ​​model. Specifically, for different networking environments, this embodiment provides multiple AI model update methods. Each update method is described below.

[0054] Update method 1: In a relatively simple networking environment, such as a single-machine environment, the access controller will update the AI ​​model only when it is idle. Specifically, each time the AI ​​model outputs the operation and maintenance decision result based on the local operation and maintenance data, the access controller will judge the status of its own equipment and then follow the Figure 2 Follow the steps shown to update:

[0055] Step 210: The access controller determines its own device status;

[0056] Step 220: If the device status is idle, the AI ​​model is updated using the historical operation and maintenance data, the current local operation and maintenance data, and the operation and maintenance decision result;

[0057] Step 230: If the device status is busy, only the local operation and maintenance data and operation and maintenance results of this time are retained as historical operation and maintenance data.

[0058] Update method 2: If the networking environment in which the access controller is located is a multi-machine environment, the access controller first determines its own device role in the networking environment. If it is a backup device, the access controller uses historical operation and maintenance data to update its own AI model, and synchronizes the updated AI model to the access controller whose device role is the primary device in the current network; if it is the primary device, it updates its own AI model based on the AI ​​model of the access controller whose device role is the backup device in the current network. In this way, only the backup device in the network needs to update the AI ​​model, and the primary device does not need to update the AI ​​model. After each update of its own AI model, the backup device can synchronize the updated AI model to the primary device.

[0059] Update method three: if the access controller implements the above operation and maintenance method based on an external AI chip, that is, hardware, since the AI ​​chip card is generally directly connected to the CPU through PCIE, it is more convenient to manage and easy to obtain historical operation and maintenance data on the access controller without occupying forwarding performance. Therefore, in this networking environment, you do not need to consider the device status and directly set the access controller to update the AI ​​model regularly.

[0060] Finally, this embodiment can also perform operation and maintenance records. Specifically, the access controller will record locally each time the AI ​​model outputs the operation and maintenance decision result, and generate a log in the memory flash 24 hours a day to facilitate daily inspections by operation and maintenance personnel.

[0061] The operation and maintenance method of this embodiment is introduced above. The operation and maintenance method provided by this application is further described below by taking actual application as an example. This embodiment divides the entire operation and maintenance solution into three parts, and each part is described below.

[0062] Part 1: The overall structure and operation and maintenance process of the access controller

[0063] The overall structure of the access controller in this embodiment is as follows Figure 3 As shown, it includes an operating system module, a product driver module and an AI module.

[0064] The overall operation and maintenance process is as follows Figure 4 As shown, first, the product driver module collects operation and maintenance data from the operating system module, and summarizes it together with the operation and maintenance data counted by the product driver module to obtain local operation and maintenance data; the product driver module sends the local operation and maintenance data to the AI ​​module for operation and maintenance decision-making; the AI ​​module sends the operation and maintenance decision results to the product driver module; the product driver module performs relevant operation and maintenance operations according to the operation and maintenance decision results to ensure network stability.

[0065] Part 2: How to train AI models

[0066] Due to the limitation of AC hardware computing power, the AI ​​model of this embodiment is mainly composed of multiple rules. For example, in response to the problem of uneven distribution of network traffic, a rule of the AI ​​model in this embodiment can be set as follows: when the actual value of a CPU utilization on the access controller exceeds the threshold, it is determined that the access controller has the problem of uneven network traffic distribution, thereby realizing the monitoring of network traffic distribution. Specifically, this embodiment first initializes the AI ​​model with standard operation and maintenance data to initialize the CPU utilization threshold, and then the access controller uses historical operation and maintenance data to update the AI ​​model and continuously adjust the threshold to make the threshold value more reasonable and more in line with network site needs.

[0067] It should be noted that the initialization of the AI ​​model mentioned in this application refers to the process of pre-training the AI ​​model using standard operation and maintenance data such as laboratory data. This embodiment collects and organizes equipment operation and maintenance data in different industry usage scenarios, and uses these equipment operation and maintenance data as standard operation and maintenance data to initialize the AI ​​model. Project test data and acceptance test data can also be used as standard operation and maintenance data to initialize the AI ​​model.

[0068] Part 3: How to update the AI ​​model

[0069] In this embodiment, the AI ​​model is selectively updated according to different networking environments. Specifically, the access controller updates the AI ​​model when the following conditions are met: the device status is idle, the device role is a backup device in a networking environment with a master and a backup device, and the device type is a device with an external AI chip. In short, this embodiment divides the networking environment into three categories: a single-machine environment, a multi-machine environment, and an access controller containing an AI chip. Each environment is introduced below.

[0070] In a stand-alone environment, when the access controller is in idle state, it uses the retained historical operation and maintenance data to update the AI ​​model.

[0071] For multi-machine environments such as dual-link, IRF (Intelligent Resilient Framework), and cloud clusters, the access controller first determines whether its networking environment is a multi-machine environment. If it is a multi-machine environment, it starts the information transmission module and establishes a heartbeat link with the information transmission modules of other access controllers in the network. Figure 5 If one party is disconnected suddenly, it is considered that the networking environment of the access controller is changed to a stand-alone environment, and it runs in the stand-alone environment mode until the heartbeat is restored.

[0072] The operation and maintenance process in a multi-machine environment is as follows Figure 5 As shown, the active device sends the historical operation and maintenance data to the standby device through (1)(2)(3) to update the AI ​​model. The standby device updates its own AI model based on the received historical operation and maintenance data, and then synchronizes the updated AI model to the active device through (4)(2)(5).

[0073] It is worth mentioning that if the CPU pressure of the backup device is high, the access controller acting as a backup device can stop updating its own AI model until it is idle again. The access controller acting as a backup device wakes up the information transmission module and obtains the historical operation and maintenance data of the active device, and updates its own AI model based on the historical operation and maintenance data.

[0074] Access controllers containing AI chips are mainly divided into two categories: AI chip cards and access controllers with integrated AI chips. This type of solution will be more expensive, but with the support of AI chip hardware, the access controller can make more complex operation and maintenance decisions. For example, when a user uses the command line to configure a command, it checks in real time whether the command combination configured by the user is incorrect, and promptly provides prompts and other functions. Therefore, for access controllers containing AI chips, this embodiment sets the update mode of the AI ​​model to regular updates to ensure the optimal performance of the AI ​​model.

[0075] It can be seen from the above technical solutions that this application applies AI technology to the operation and maintenance solution of the access controller. Network maintenance and network optimization based on the AI ​​model have the following main advantages: the granularity of operation and maintenance data is controllable, which facilitates timely response when problems occur; it can prevent equipment failure or network congestion in advance and ensure network stability; there is no need to upload device data, which can ensure the privacy of users; it can better help operation and maintenance personnel understand the status of the equipment in the existing network, such as the overall performance of the equipment under the business traffic model.

[0076] Based on the same inventive concept, the present application also provides an operation and maintenance device, which is applied to the access controller, and its structural diagram is as follows: Figure 6 As shown, the device comprises:

[0077] Data acquisition module 610, used to acquire local operation and maintenance data;

[0078] A decision module 620, configured to input the local operation and maintenance data into an AI model to obtain an operation and maintenance decision result, wherein the input data of the AI ​​model in the initialization phase is standard operation and maintenance data, and the access controller is updated according to historical operation and maintenance data in the operation and maintenance phase;

[0079] The operation and maintenance module 630 is used to perform operation and maintenance operations according to the operation and maintenance decision result.

[0080] As a specific implementation, it also includes:

[0081] The model update module is used to determine the device status of the access controller, and when the device status is idle, update the AI ​​model using historical operation and maintenance data.

[0082] As a specific implementation, a model updating module is also included, and the model updating module includes:

[0083] An environment determination unit, configured to determine a device role of the access controller in the current network if the network environment in which the access controller is located is a multi-machine environment;

[0084] An updating unit, configured to update its own AI model using historical operation and maintenance data if the device role of the access controller in the current network is a backup device, and synchronize the updated AI model to the access controller whose device role is a primary device in the current network;

[0085] The synchronization unit is used to update its own AI model according to the AI ​​model of the access controller whose device role is a backup device in the current networking if the device role of the access controller in the current networking is a master device.

[0086] As a specific implementation, the decision module 620 and the operation and maintenance module 630 are specifically used for:

[0087] Inputting the local network traffic data into the AI ​​model to perform a first traffic diversion operation to obtain a target traffic diversion algorithm identifier, wherein the first traffic diversion operation includes predicting a traffic trend based on the local network traffic data and determining the target traffic diversion algorithm identifier based on the traffic trend;

[0088] A traffic diversion algorithm switching operation is performed according to the target traffic diversion algorithm identifier to switch the current traffic diversion algorithm to the target traffic diversion algorithm.

[0089] As a specific implementation, the decision module 620 and the operation and maintenance module 630 are specifically used for:

[0090] Inputting the local network traffic data into the AI ​​model to perform a second traffic diversion operation to obtain target traffic diversion algorithm parameters, wherein the second traffic diversion operation includes predicting a traffic trend based on the local network traffic data and determining the target traffic diversion algorithm parameters based on the traffic trend;

[0091] According to the target diversion algorithm parameters, the parameters of the current diversion algorithm are updated to the target diversion algorithm parameters.

[0092] As a specific implementation, the decision module 620 and the operation and maintenance module 630 are specifically used for:

[0093] Input the terminal traffic data into the AI ​​model to perform an anomaly detection operation, and obtain an operation and maintenance operation identifier and a terminal identifier, wherein the anomaly detection operation includes determining whether the terminal traffic data is abnormal traffic, and when the judgment result is yes, determining an operation and maintenance operation identifier of a first operation and maintenance operation and a terminal identifier of an abnormal terminal according to the terminal traffic data, wherein the first operation and maintenance operation is speed limiting or offline;

[0094] A first operation and maintenance operation is performed on the abnormal terminal according to the operation and maintenance operation identifier and the terminal identifier.

[0095] As a specific implementation, the decision module 620 and the operation and maintenance module 630 are specifically used for:

[0096] Input the device status data into the AI ​​model to perform an irreversible problem detection operation to obtain an operation and maintenance operation identifier, wherein the irreversible problem detection operation includes judging whether an irreversible error occurs in the device according to the device status data, and determining an operation and maintenance operation identifier of a second operation and maintenance operation according to the device status data when the judgment result is yes, wherein the second operation and maintenance operation is restart or active-standby switching;

[0097] A second operation and maintenance operation is performed according to the operation and maintenance operation identifier.

[0098] The embodiment of the present application also provides an access controller, including: an operating system module, a product driver module and an AI module;

[0099] The product driving module is used to obtain local operation and maintenance data from the operating system module, and send the local operation and maintenance data to the AI ​​module, the AI ​​module uses the AI ​​model to analyze the local operation and maintenance data and outputs an operation and maintenance decision result, and the product driving module calls the operating system module to perform an operation and maintenance operation according to the operation and maintenance decision result;

[0100] Among them, the input data of the AI ​​model in the initialization stage is standard operation and maintenance data, and in the operation and maintenance stage, the access controller is updated according to historical operation and maintenance data.

[0101] The above access controller can implement the steps of the above operation and maintenance method.

[0102] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. An operation and maintenance method, characterized in that: The method is applied to an access controller, and the method comprises: Obtain local operation and maintenance data; Inputting the local operation and maintenance data into the AI ​​model to obtain an operation and maintenance decision result, wherein the input data of the AI ​​model in the initialization phase is standard operation and maintenance data, and the access controller is updated according to historical operation and maintenance data in the operation and maintenance phase; Execute operation and maintenance operations according to the operation and maintenance decision result.

2. The method according to claim 1, characterized in that The method specifically updates the AI ​​model in the following ways: Determine the status of its own equipment, and when the equipment status is idle, use historical operation and maintenance data to update the AI ​​model.

3. The method according to claim 1, characterized in that The method specifically updates the AI ​​model in the following ways: If the network environment you are in is a multi-machine environment, determine your device role in the current network; If the device role in the current network is a backup device, the AI ​​model is updated using historical operation and maintenance data, and the updated AI model is synchronized to the access controller whose device role is a primary device in the current network; If the device role of the device in the current network is a master device, the device updates its own AI model according to the AI ​​model on the access controller whose device role is a backup device in the current network.

4. The method according to claim 1, characterized in that The method specifically performs operation and maintenance operations in the following manner: Inputting the local network traffic data into the AI ​​model to perform a first traffic diversion operation to obtain a target traffic diversion algorithm identifier, wherein the first traffic diversion operation includes predicting a traffic trend according to the local network traffic data, and determining the target traffic diversion algorithm identifier according to the traffic trend; A traffic diversion algorithm switching operation is performed according to the target traffic diversion algorithm identifier to switch the current traffic diversion algorithm to the target traffic diversion algorithm.

5. The method according to claim 1, characterized in that The method specifically performs operation and maintenance operations in the following manner: Inputting the local network traffic data into the AI ​​model to perform a second traffic diversion operation to obtain target traffic diversion algorithm parameters, wherein the second traffic diversion operation includes predicting a traffic trend based on the local network traffic data and determining the target traffic diversion algorithm parameters based on the traffic trend; According to the target diversion algorithm parameters, the parameters of the current diversion algorithm are updated to the target diversion algorithm parameters.

6. The method according to claim 1, characterized in that The method specifically performs operation and maintenance operations in the following manner: Input the terminal traffic data into the AI ​​model to perform an anomaly detection operation, and obtain an operation and maintenance operation identifier and a terminal identifier, wherein the anomaly detection operation includes determining whether the terminal traffic data is abnormal traffic, and when the judgment result is yes, determining an operation and maintenance operation identifier of a first operation and maintenance operation and a terminal identifier of an abnormal terminal according to the terminal traffic data, wherein the first operation and maintenance operation is speed limiting or offline; A first operation and maintenance operation is performed on the abnormal terminal according to the operation and maintenance operation identifier and the terminal identifier.

7. The method according to claim 1, characterized in that The method specifically performs operation and maintenance operations in the following manner: Input the device status data into the AI ​​model to perform an irreversible problem detection operation to obtain an operation and maintenance operation identifier, wherein the irreversible problem detection operation includes judging whether an irreversible error occurs in the device according to the device status data, and determining an operation and maintenance operation identifier of a second operation and maintenance operation according to the device status data when the judgment result is yes, wherein the second operation and maintenance operation is restart or active-standby switching; A second operation and maintenance operation is performed according to the operation and maintenance operation identifier.

8. An operation and maintenance device, characterized in that: The device is applied to an access controller, and the device includes: Data acquisition module, used to obtain local operation and maintenance data; A decision module, used to input the local operation and maintenance data into the AI ​​model to obtain an operation and maintenance decision result, wherein the input data of the AI ​​model in the initialization phase is standard operation and maintenance data, and the access controller is updated according to historical operation and maintenance data in the operation and maintenance phase; The operation and maintenance module is used to perform operation and maintenance operations according to the operation and maintenance decision results.

9. The device according to claim 8, characterized in that Also includes: The model update module is used to determine the device status of the access controller, and when the device status is idle, update the AI ​​model of the access controller using historical operation and maintenance data.

10. The device according to claim 8, characterized in that It also includes a model updating module, the model updating module including: An environment determination unit, configured to determine a device role of the access controller in the current network if the network environment in which the access controller is located is a multi-machine environment; An updating unit, configured to update the AI ​​model of the access controller using historical operation and maintenance data if the device role of the access controller in the current networking is a backup device, and synchronize the updated AI model to the access controller whose device role is a primary device in the current networking; The synchronization unit is used to update the AI ​​model of the access controller according to the AI ​​model of the access controller whose device role is a backup device in the current networking if the device role of the access controller in the current networking is a master device.

11. An access controller, characterized in that: include: Operating system module, product driver module and AI module; The product driving module is used to obtain local operation and maintenance data from the operating system module, and send the local operation and maintenance data to the AI ​​module, the AI ​​module uses the AI ​​model to analyze the local operation and maintenance data and outputs an operation and maintenance decision result, and the product driving module calls the operating system module to perform an operation and maintenance operation according to the operation and maintenance decision result; Among them, the input data of the AI ​​model in the initialization stage is standard operation and maintenance data, and in the operation and maintenance stage, the access controller is updated according to historical operation and maintenance data.

Images