Fault processing system and method of wireless router
By introducing a fault diagnosis model and solution sequence into the wireless router fault handling system, users can handle the faults themselves, solving the problem of low processing efficiency in traditional methods, and improving the efficiency of fault handling and the ability of users to handle independently.
Patent Information
- Application Number
- CN202411882927.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-19
- Publication Date
- 2025-02-18
AI Technical Summary
When an existing wireless router fails, it is difficult for users to handle it by themselves. They need to contact technical support or on-site repairs, resulting in low processing efficiency.
A fault processing system for wireless routers is designed, including data acquisition module, data analysis module, early warning module, interaction module and database. Through the fault diagnosis model, artificial intelligence is used to identify fault tags and generate solution sequences. Users can handle them themselves according to the sequence. Fault.
It improves the efficiency of wireless router fault handling, reduces the work burden of maintenance personnel, and prioritizes simple solutions, improving users' ability to solve problems by themselves.
Smart Images
Figure CN119484248A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of network communication technology, and specifically relates to a fault handling system and method for a wireless router. Background Art
[0002] A wireless router is a network device that can convert wired network signals into wireless signals for reception by computers, mobile phones, PDAs and other devices that support its technology. It is mainly used for users to access the Internet and provide wireless coverage. There are many types of wireless routers, which can be divided into home wireless routers, enterprise-level wireless routers and portable wireless routers. Wireless routers play a vital role in modern society. They not only provide convenient wireless network coverage and resource sharing functions, but also promote the development of smart homes, promote the innovation of Internet applications, and change people's lifestyles. At the same time, the popularity of wireless routers also brings network security challenges and opportunities for digital transformation. Therefore, we need to strengthen the troubleshooting methods of wireless routers to better serve people's lives.
[0003] With the popularization of wireless networks and the deepening of Internet applications, wireless routers, as core devices of home and enterprise networks, have a direct impact on users' network experience due to their operational stability and fault handling capabilities. When a traditional wireless router fails, users often do not understand the cause of the failure and need to contact technical support or on-site repair services, resulting in low efficiency in handling the failure. For example, when users encounter simple methods to handle the failure, they can handle it according to the solution. At this time, if users contact maintenance personnel for on-site service, the maintenance personnel's work efficiency will be low. Therefore, the fault handling system of wireless routers still needs further improvement. Summary of the invention
[0004] The present application aims to solve at least one of the technical problems existing in the prior art; to this end, the present application proposes a fault handling system and method for a wireless router, which is used to solve the technical problem that in the prior art, when a fault occurs, the user often contacts technical support or requests on-site repair services, resulting in low handling efficiency when a fault occurs.
[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a wireless router fault handling system, comprising: a data acquisition module, a data analysis module, an early warning module, an interaction module and a database;
[0006] The data acquisition module: acquires environmental data, parameter data and device information through data acquisition equipment; and integrates the environmental data, parameter data and device information into comprehensive data;
[0007] The data analysis module: inputs the comprehensive data into the fault diagnosis model to obtain the fault label and its corresponding confidence, and the fault diagnosis model is constructed by the artificial intelligence model; generates a corresponding solution according to the fault label; generates a solution sequence according to the fault label and the solution; processes the solution sequence in sequence according to the corresponding solution number threshold and generates a feedback score; generates an alarm signal according to the feedback score;
[0008] The early warning module: gives a prompt according to the alarm signal and contacts the management personnel;
[0009] The interactive module provides solutions for users to view.
[0010] This application obtains the fault label of the device through the fault diagnosis model in the above steps, and finds possible solutions for it, then notifies the user to deal with the fault problem in advance according to the solution sequence, and generates a feedback score after processing, and issues an alarm based on the score. When the user encounters a device failure, he or she can consider solving the problem by himself or herself, which improves the efficiency of solving router failures and the work efficiency of maintenance personnel.
[0011] Furthermore, the fault diagnosis model is constructed by an artificial intelligence model, including:
[0012] Acquire a number of historical environmental data, historical parameter data, and historical equipment information and their corresponding fault labels; and integrate the historical environmental data, historical parameter data, and historical equipment information into a number of historical comprehensive data;
[0013] Divide a number of historical comprehensive data into training data, verification data, and test data according to fault labels; perform data preprocessing on the training data, verification data, and test data to obtain a training set, a verification set, and a test set;
[0014] Select an AI model as the base model;
[0015] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;
[0016] By verifying the pre-trained model on the test set, we finally obtain a fault diagnosis model whose input is comprehensive data and output is confidence and its corresponding fault label.
[0017] Furthermore, generating a corresponding solution according to the fault label includes:
[0018] Obtain device information, several confidence levels and their corresponding fault labels;
[0019] Using the device information and the plurality of fault tags as a plurality of query conditions;
[0020] A plurality of solutions that are consistent with a plurality of query conditions are obtained from a solution database.
[0021] Furthermore, generating a solution sequence according to the fault label and the solution includes:
[0022] Get the confidence ZXD corresponding to several fault labels i , solutions, and the ease of operation of the solutions CJD i ; The operation simplicity is calculated by the operation difficulty level and the operation time;
[0023] By formula YX i =α1×ZXD i +α2×CJD i Calculate the priority coefficient YX of the corresponding fault label solution; where α1 and α2 are weight coefficients, α1 and α2∈(0,1);
[0024] The solutions are sorted from large to small according to the priority coefficient to obtain the solution sequence.
[0025] The present application generates corresponding solutions and forms a solution sequence by considering various possibilities of failure. It gives priority to failure problems with greater possibility and solutions with simple operation when users handle them. It also considers user operation and the possibility of failure, thereby improving the efficiency of problem solving and the comprehensiveness of problem consideration.
[0026] Furthermore, the operation simplicity is calculated by the difficulty level of the operation steps and the operation step time, including:
[0027] Obtaining an operation difficulty level CND and an operation time CT; the operation difficulty level is assessed by an expert based on the amount of knowledge required for the operation;
[0028] By formula Calculate the operational simplicity CJD of the solution; where α3 and α4 are weight coefficients, α3 and α4∈(0,1); DT is the unit time.
[0029] Furthermore, the processing in sequence according to the solution sequence and the corresponding solution number threshold and generating feedback scores include:
[0030] Step 1: Obtain the solutions corresponding to the maximum value of the priority coefficient and their corresponding solution times thresholds in turn;
[0031] Step 2: Process the fault label according to the solution based on the number of solutions threshold, and obtain the feedback score by processing the scoring model, wherein the processing scoring model is constructed by an artificial intelligence model; determine whether the feedback score is greater than the scoring threshold; if yes, end the operation; if no, remove the solution corresponding to the current priority coefficient from the solution sequence; determine whether the solution sequence is an empty sequence; if yes, end the operation; if no, proceed to step 1.
[0032] The present application implements the complete processing of the solution sequence through the above steps. Once the feedback score exceeds the score threshold or the solution sequence is empty, the processing process is stopped, which improves the efficiency of solution use and further improves the efficiency of equipment failure processing.
[0033] Furthermore, the threshold of the number of solutions is obtained by the number of successful solutions of historical solutions, including:
[0034] Get the same device information, the same fault label, and the number of historical successful solutions for the same solution CJC j ;
[0035] By formula Calculate the solution times threshold JCY; where, The round-up symbol.
[0036] Furthermore, the processing scoring model is constructed by an artificial intelligence model, including:
[0037] Obtaining a number of historical environmental data, historical parameter data, and historical equipment information before, after, and after a solution is provided, and their corresponding feedback scores; and integrating a number of historical environmental data, historical parameter data, and historical equipment information before, after, and after a solution is provided into a number of historical comprehensive processing data;
[0038] Dividing a number of historical comprehensive processing data into training data, verification data and test data according to feedback scores; performing data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set;
[0039] Select an AI model as the base model;
[0040] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;
[0041] By verifying the pre-trained model on the test set, we finally obtain a processing scoring model whose input is comprehensive processing data and output is feedback score.
[0042] Further, generating an alarm signal according to the feedback score includes:
[0043] Get feedback ratings;
[0044] Determine whether the feedback score is less than D times the score threshold;
[0045] Yes, a serious fault alarm signal is generated for the router;
[0046] If no, determine whether the feedback score is less than the score threshold; if yes, generate a router fault alarm signal; if no, do nothing; wherein D is the proportionality coefficient, D∈(0,1).
[0047] Another aspect of the present invention provides a method for troubleshooting a wireless router, comprising:
[0048] S0: Acquire environmental data, parameter data and equipment information; and integrate the environmental data, parameter data and equipment information into comprehensive data;
[0049] S1: Inputting the comprehensive data into a fault diagnosis model to obtain a fault label and its corresponding confidence level, wherein the fault diagnosis model is constructed by an artificial intelligence model;
[0050] S2: Generate corresponding solutions according to the fault labels, and visualize the solutions for users to view; generate solution sequences according to the fault labels and solutions;
[0051] S3: Process the solution sequence in sequence according to the corresponding solution number threshold and generate feedback scores; generate an alarm signal according to the feedback scores;
[0052] S4: Provide prompts based on alarm signals and contact management.
[0053] Compared with the prior art, the beneficial effects of this application are:
[0054] 1. The present application obtains fault labels and their corresponding confidence levels by inputting comprehensive data into a fault diagnosis model; generates corresponding solutions according to the fault labels, and visualizes the solutions for users to view; generates a solution sequence according to the fault labels and solutions; processes the solution sequence in sequence according to the corresponding solution number threshold and generates a feedback score; generates an alarm signal according to the feedback score. Once a fault occurs, the user can handle it in advance according to the solution sequence, reducing the process of requiring maintenance personnel to come to the door to handle simple faults. At the same time, priority is given to fault types that are likely to cause faults and have simple corresponding solutions for users to handle, thereby improving the efficiency of solving router faults and the work efficiency of maintenance personnel.
[0055] 2. The present application generates a priority coefficient of a solution according to the confidence level corresponding to the fault type and the operational simplicity of the solution to the fault type, and sorts the solutions according to the priority coefficient to obtain a solution sequence. The user processes the solution according to the solution sequence, taking into account the interactivity between the user and the system and the operational complexity of the user when handling the fault, thereby improving the efficiency of problem solving and the comprehensiveness of problem consideration.
[0056] 3. This application processes the solution sequence in sequence according to the corresponding solution number threshold and generates a feedback score. If the feedback score exceeds the score threshold, it means that the corresponding solution has been successfully solved. When the solution sequence is empty and the feedback score is lower than the score threshold, it means that an unknown fault has occurred in the equipment, prompting maintenance personnel to come to the site for processing, thereby improving the processing efficiency when equipment failure occurs. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0058] Figure 1 A schematic diagram of the principle of a wireless router fault handling system of the present application;
[0059] Figure 2 A process flow chart of the processing solution sequence for this application;
[0060] Figure 3 The present invention is a flowchart of a method for troubleshooting a wireless router. DETAILED DESCRIPTION
[0061] The technical solution of the present application will be described clearly and completely in conjunction with the embodiments below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.
[0062] See also Figure 1 , the first aspect of the present application provides a wireless router fault handling system, including: a data acquisition module, a data analysis module, an early warning module, an interaction module and a database;
[0063] Data acquisition module: obtains environmental data, parameter data and equipment information through data acquisition equipment; and integrates environmental data, parameter data and equipment information into comprehensive data; data acquisition equipment includes various sensors, etc.; parameter data includes packet loss rate, throughput and flow data, etc.;
[0064] Data analysis module: input comprehensive data into the fault diagnosis model to obtain fault labels and their corresponding confidence levels. The fault diagnosis model is constructed through an artificial intelligence model. Generate corresponding solutions based on the fault labels, including solution videos, etc. Generate a solution sequence based on the fault labels and solutions. Process the solution sequence in sequence according to the corresponding solution count threshold and generate feedback scores. The feedback score refers to the solution effect after processing. Generate an alarm signal based on the feedback score.
[0065] Early warning module: Prompts are given according to alarm signals and the management personnel are contacted; the alarm signals include alarm signals indicating serious faults in the router and alarm signals indicating faults in the router, etc.;
[0066] Interactive module: provides solutions for users to view.
[0067] This embodiment uses a pre-built fault diagnosis model to accurately identify the fault label corresponding to the device, and then further searches for the corresponding solution. It notifies the user based on the confidence of the fault label and the complexity of the operation when solving the fault, and guides the user to deal with the fault problem in advance according to the solution sequence. When the user faces a device failure, he can confidently try to solve the problem by himself, which not only improves the efficiency of router fault handling, but also effectively speeds up the work pace and efficiency of maintenance personnel.
[0068] The fault diagnosis model in this embodiment is constructed by an artificial intelligence model, including:
[0069] Acquire a number of historical environmental data, historical parameter data, and historical equipment information and their corresponding fault labels; and integrate the historical environmental data, historical parameter data, and historical equipment information into a number of historical comprehensive data;
[0070] Divide a number of historical comprehensive data into training data, verification data and test data according to fault labels; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; the ratio between the training set, the test set and the verification set is 7:2:1;
[0071] Select an artificial intelligence model as the basic model; artificial intelligence models include VGGNet and ResNet models, etc.;
[0072] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;
[0073] By verifying the pre-trained model on the test set, we finally obtain a fault diagnosis model whose input is comprehensive data and output is confidence and its corresponding fault label.
[0074] In this embodiment, generating a corresponding solution according to the fault label includes:
[0075] Obtain device information, several confidence levels, and their corresponding fault labels. The solutions to the same fault labels of different devices may be different, so when querying solutions, limit the query to the same device information.
[0076] Use device information and several fault tags as several query conditions;
[0077] A plurality of solutions consistent with a plurality of query conditions are obtained in a solution database; the solution database is generated based on a plurality of historical fault types of the same device.
[0078] In this embodiment, generating a solution sequence according to the fault label and the solution includes:
[0079] Get the confidence ZXD corresponding to several fault labels i , solutions, and the ease of operation of the solutions CJD i ; The simplicity of operation is calculated by the difficulty level and operation time;
[0080] By formula YX i =α1×ZXD i +α2×CJD i Calculate the priority coefficient YX of the corresponding fault label solution; where α1 and α2 are weight coefficients, α1 and α2∈(0,1), and the specific values are set based on experience. The higher the confidence, the greater the possibility of the occurrence of the fault label. Therefore, in this embodiment, α1>α2; the higher the confidence of the fault label, the greater the possibility that the problem of the device is caused by the fault, and the solution of the fault label is given priority; under the same confidence, the higher the operation simplicity, the easier it is for the user to operate to handle the fault, and the solution with high operation simplicity is given priority; therefore, the priority coefficient of the fault label solution increases accordingly;
[0081] The solutions are sorted from large to small according to the priority coefficient to obtain the solution sequence.
[0082] The operation simplicity in this embodiment is calculated by the difficulty level of the operation steps and the operation step time, including:
[0083] Obtain the operation difficulty level CND and operation time CT; the operation difficulty level is assessed by experts based on the amount of knowledge required for the operation;
[0084] By formula Calculate the operational simplicity CJD of the solution; wherein α3 and α4 are weight coefficients, α3 and α4∈(0,1), and the specific values are set based on experience. In this embodiment, it is believed that the higher the operational difficulty level, the greater the impact on the operational simplicity, so α3>α4; if it is believed that the longer the operation time, the greater the impact on the operational simplicity, then α3<α4; DT is the unit time, and the specific value is set based on experience. In this embodiment, DT is set to 1 minute; the higher the difficulty level of the operation step and the longer the operation step time, the more complicated the operation; therefore, the operational simplicity of the solution decreases accordingly.
[0085] See also Figure 2 In this embodiment, the solution sequence is processed in sequence according to the corresponding solution number threshold and feedback scores are generated, including:
[0086] Step 1: Obtain the solutions corresponding to the maximum value of the priority coefficient and their corresponding solution times thresholds in turn;
[0087] Step 2: Process the fault label according to the solution based on the threshold of the number of solutions, and obtain the feedback score by processing the scoring model, which is constructed through the artificial intelligence model; determine whether the feedback score is greater than the scoring threshold, which is set based on experience; if yes, end the operation; if no, remove the solution corresponding to the current priority coefficient from the solution sequence; determine whether the solution sequence is an empty sequence; if yes, end the operation; if no, proceed to step 1.
[0088] This embodiment implements the complete processing of the solution sequence through the above steps. When the feedback score exceeds the score threshold or the solution sequence is empty, the processing process is terminated and the solution corresponding to the maximum value of the priority coefficient in the solution sequence is given priority. Processing in this way can not only quickly identify the cause of the fault, but also improve the efficiency of users in solving problems.
[0089] The solution number threshold in this embodiment is obtained by the number of successful solutions of historical solutions, including:
[0090] Get the same device information, the same fault label, and the number of historical successful solutions for the same solution CJC j ;
[0091] By formula Calculate the solution times threshold JCY; where, The rounding up symbol is used to ensure that the number of solution thresholds is an integer; the number of solution thresholds increases as the number of historical successful solutions increases.
[0092] The processing scoring model in this embodiment is constructed by an artificial intelligence model, including:
[0093] Obtaining a number of historical environmental data, historical parameter data, and historical equipment information before, after, and after a solution is provided, and their corresponding feedback scores; and integrating a number of historical environmental data, historical parameter data, and historical equipment information before, after, and after a solution is provided into a number of historical comprehensive processing data;
[0094] Divide a number of historical comprehensive processing data into training data, verification data and test data according to feedback scores; perform data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; the ratio between the training set, the test set and the verification set is 7:2:1;
[0095] Select an artificial intelligence model as the basic model; the artificial intelligence model includes a neural network model, etc.;
[0096] Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model;
[0097] By verifying the pre-trained model on the test set, we finally obtain a processing scoring model whose input is comprehensive processing data and output is feedback score.
[0098] In this embodiment, generating an alarm signal according to the feedback score includes:
[0099] Get feedback ratings;
[0100] Determine whether the feedback score is less than D times the score threshold;
[0101] Yes, a serious fault alarm signal is generated for the router;
[0102] No, determine whether the feedback score is less than the score threshold; Yes, generate a router fault alarm signal; No, do nothing; wherein D is the proportional coefficient, D∈(0,1), the specific value is set according to experience, and in this embodiment, D is set to 0.7.
[0103] See also Figure 3 Another aspect of the present application provides a method for troubleshooting a wireless router, including:
[0104] S0: Acquire environmental data, parameter data and equipment information; and integrate the environmental data, parameter data and equipment information into comprehensive data;
[0105] S1: Input the comprehensive data into the fault diagnosis model to obtain the fault label and its corresponding confidence level. The fault diagnosis model is constructed through the artificial intelligence model;
[0106] S2: Generate corresponding solutions according to the fault labels, and visualize the solutions for users to view; generate solution sequences according to the fault labels and solutions;
[0107] S3: Process the solution sequence in sequence according to the corresponding solution number threshold and generate feedback scores; generate an alarm signal according to the feedback scores;
[0108] S4: Provide prompts based on alarm signals and contact management.
[0109] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.
[0110] The working principle of this application is as follows: by acquiring environmental data, parameter data and equipment information, and integrating them into comprehensive data; inputting the comprehensive data into the fault diagnosis model to obtain the fault label and its corresponding confidence level; generating the corresponding solution according to the fault label, and visualizing the solution for users to view; generating a solution sequence according to the fault label and the solution; processing the solution sequence in sequence according to the corresponding solution number threshold and generating a feedback score; generating an alarm signal according to the feedback score; making a prompt according to the alarm signal and contacting the management personnel, once a fault occurs, the user can handle it in advance according to the solution sequence, reducing the process of requiring maintenance personnel to come to the door to handle simple faults, and giving priority to the fault types that are likely to cause the fault and the corresponding solutions that are simple to operate for users to handle, thereby improving the efficiency of solving router faults and the work efficiency of maintenance personnel.
[0111] The above embodiments are only used to illustrate the technical method of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical method of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present application.
Claims
1. A wireless router fault handling system, characterized in that: include: Data collection module, data analysis module, early warning module, interactive module and database; The data acquisition module: acquires environmental data, parameter data and device information through data acquisition equipment; and integrates the environmental data, parameter data and device information into comprehensive data; The data analysis module: inputs the comprehensive data into the fault diagnosis model to obtain the fault label and its corresponding confidence, and the fault diagnosis model is constructed by the artificial intelligence model; generates the corresponding solution according to the fault label; generates a solution sequence according to the fault label and the solution; processes the solution sequence in sequence according to the corresponding solution number threshold and generates a feedback score; Generate alert signals based on feedback scores; The early warning module: gives a prompt according to the alarm signal and contacts the management personnel; The interactive module provides solutions for users to view.
2. A wireless router fault handling system according to claim 1, characterized in that: The fault diagnosis model is constructed by an artificial intelligence model, including: Acquire a number of historical environmental data, historical parameter data, and historical equipment information and their corresponding fault labels; and integrate the historical environmental data, historical parameter data, and historical equipment information into a number of historical comprehensive data; Divide a number of historical comprehensive data into training data, verification data, and test data according to fault labels; perform data preprocessing on the training data, verification data, and test data to obtain a training set, a verification set, and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtain a fault diagnosis model whose input is comprehensive data and output is confidence and its corresponding fault label.
3. A wireless router fault handling system according to claim 1, characterized in that: Generating a corresponding solution according to the fault label includes: Obtain device information, several confidence levels and their corresponding fault labels; Using device information and several fault tags as several query conditions; A plurality of solutions that are consistent with a plurality of query conditions are obtained from a solution database.
4. A wireless router fault handling system according to claim 1, characterized in that: The generating of a solution sequence according to the fault label and the solution comprises: Get the confidence ZXD corresponding to several fault labels i , solutions, and the ease of operation of the solutions CJD i ; The operation simplicity is calculated by the operation difficulty level and the operation time; By formula YX i =α1×ZXD i +α2×CJD i Calculate the priority coefficient YX of the corresponding fault label solution; where α1 and α2 are weight coefficients, α1 and α2∈(0,1); The solutions are sorted from large to small according to the priority coefficient to obtain the solution sequence.
5. A wireless router fault handling system according to claim 4, characterized in that: The operation simplicity is calculated by the difficulty level of the operation steps and the operation step time, including: Obtaining an operation difficulty level CND and an operation time CT; the operation difficulty level is assessed by an expert based on the amount of knowledge required for the operation; By formula Calculate the operational simplicity CJD of the solution; where α3 and α4 are weight coefficients, α3 and α4∈(0,1); DT is the unit time.
6. A wireless router fault handling system according to claim 1, characterized in that: The step of processing the solution sequence in accordance with the corresponding solution number threshold and generating feedback scores includes: Step 1: Obtain the solutions corresponding to the maximum value of the priority coefficient and their corresponding solution times thresholds in turn; Step 2: Process the fault label according to the solution based on the number of solutions threshold, and obtain the feedback score by processing the scoring model, wherein the processing scoring model is constructed by an artificial intelligence model; determine whether the feedback score is greater than the scoring threshold; if yes, end the operation; if no, remove the solution corresponding to the current priority coefficient from the solution sequence; determine whether the solution sequence is an empty sequence; if yes, end the operation; if no, proceed to step 1.
7. A wireless router fault handling system according to claim 6, characterized in that: The threshold of the number of resolutions is obtained by the number of successful resolutions of historical solutions, including: Get the same device information, the same fault label, and the number of historical successful solutions for the same solution CJC j ; By formula Calculate the solution times threshold JCY; where, The round-up symbol.
8. A wireless router fault handling system according to claim 6, characterized in that: The processing scoring model is constructed through an artificial intelligence model, including: Obtaining a number of historical environmental data, historical parameter data, and historical equipment information before, after, and after a solution is provided, and their corresponding feedback scores; and integrating a number of historical environmental data, historical parameter data, and historical equipment information before, after, and after a solution is provided into a number of historical comprehensive processing data; Dividing a number of historical comprehensive processing data into training data, verification data and test data according to feedback scores; performing data preprocessing on the training data, verification data and test data to obtain a training set, a verification set and a test set; Select an AI model as the base model; Train the basic model with the training set, and adjust the learning rate and hyperparameters on the validation set to obtain the pre-trained model; By verifying the pre-trained model on the test set, we finally obtain a processing scoring model whose input is comprehensive processing data and output is feedback score.
9. A wireless router fault handling system according to claim 1, characterized in that: The step of generating an alarm signal according to the feedback score comprises: Get feedback ratings; Determine whether the feedback score is less than D times the score threshold; Yes, a serious fault alarm signal is generated for the router; If no, determine whether the feedback score is less than the score threshold; if yes, generate a router fault alarm signal; if no, do nothing; wherein D is the proportionality coefficient, D∈(0,1).
10. A method for handling a wireless router fault, applied to a wireless router fault handling system according to any one of claims 1 to 9, characterized in that: include: S0: Obtain environmental data, parameter data and device information; and integrate environmental data, parameter data and equipment information into comprehensive data; S1: Inputting the comprehensive data into a fault diagnosis model to obtain a fault label and its corresponding confidence level, wherein the fault diagnosis model is constructed by an artificial intelligence model; S2: Generate corresponding solutions according to the fault labels, and visualize the solutions for users to view; generate solution sequences according to the fault labels and solutions; S3: Process the solution sequence in sequence according to the corresponding solution number threshold and generate feedback scores; generate an alarm signal according to the feedback scores; S4: Provide prompts based on alarm signals and contact management.