5G on-body wi-fi fault diagnosis and recovery method and system

Abstract

The application provides a 5G personal WiFi fault diagnosis and recovery method and system, which comprises the following steps: collecting network connection data, system information and running logs from a communication terminal connected to a 5G personal WiFi device; analyzing the data to generate a fault diagnosis report; selecting and executing corresponding recovery operations from a recovery scheme library according to the report; monitoring the device state and network connection in real time to determine whether the recovery is successful; if the fault cannot be solved, providing an advanced solution and sending device information, program attributes, scheme library information, network connection data, system information and running logs to an edge server; the edge server obtains fault data and diagnosis reports of multiple similar devices as references, mines potential fault rules through big data analysis, and generates reference analysis data; and optimizes the intelligent diagnosis program and the recovery scheme library according to the reference analysis data and other information. The application can accurately identify the fault type, significantly shorten the fault recovery time and improve the user experience.

Description

Technical Field

[0001] This invention relates to the field of 5G technology, specifically to a method and system for diagnosing and recovering 5G portable WiFi faults. Background Technology

[0002] 5G smart portable WiFi devices have become increasingly popular in recent years, providing users with a more convenient and faster network experience. These devices offer faster data transmission speeds than traditional 4G devices, with theoretical downlink speeds reaching 10Gbps and commonly reaching several hundred Mbps or even higher in actual use, easily supporting high-definition video playback, 4K live streaming, and large file downloads. These devices are typically lightweight and portable, requiring no installation or cables, providing WiFi signals anytime, anywhere. Many 5G portable WiFi devices support large data plans, offering up to 1500GB or more per month, meeting users' needs for long-term, high-data usage. Most devices can connect multiple devices simultaneously, typically around 32, satisfying the needs of multiple users or devices accessing the internet at the same time. However, due to structural limitations and varying usage environments, 5G portable WiFi devices are prone to malfunctions; and existing fault diagnosis methods for 5G portable WiFi devices are not accurate, efficient, or intelligent enough. Summary of the Invention

[0003] Based on the above-mentioned problems, this invention proposes a method and system for 5G portable WiFi fault diagnosis and recovery. Through the solution of this invention, the fault type can be identified more accurately, misjudgment can be reduced, and the reliability of diagnosis can be improved; the fault recovery time can be significantly shortened, and the user experience can be improved; the effect of recovery operation can be judged in a timely manner, and the intelligence level of the system can be improved.

[0004] In view of this, one aspect of the present invention proposes a method for diagnosing and recovering 5G portable WiFi faults, comprising:

[0005] Network connection data, as well as system information and operation logs of the communication terminal, are collected from the communication terminal connected to the 5G portable WiFi device.

[0006] The network connection data, system information, and operation log are analyzed using the pre-set intelligent diagnostic program of the 5G portable WiFi device to obtain a first analysis result;

[0007] A fault diagnosis report is generated based on the first analysis results. The fault diagnosis report includes the fault type, fault severity, and possible fault causes.

[0008] Based on the fault diagnosis report, select and execute the corresponding recovery operation from the pre-stored recovery plan library;

[0009] During the recovery operation, the current device status and current network connection status of the 5G portable WiFi device are monitored in real time, and the recovery operation is judged to have successfully resolved the fault based on the current device status and current network connection status.

[0010] If the recovery operation fails to resolve the fault, an advanced solution is provided, and the device information of the 5G portable WiFi device, the program attribute information of the intelligent diagnostic program, the solution library information of the recovery solution library, the network connection data, the system information, and the operation log are sent to the edge server.

[0011] The edge server obtains fault data and diagnostic reports from multiple similar portable WiFi devices as reference data.

[0012] The reference data is analyzed using big data analytics to uncover potential fault patterns and trends, resulting in reference analysis data.

[0013] The intelligent diagnostic program and the recovery solution library are optimized based on the reference analysis data, the device information, the program attribute information, the solution library information, the network connection data, the system information, and the operation log.

[0014] Optionally, the step of analyzing the network connection data, the system information, and the operation log using the pre-set intelligent diagnostic program of the 5G portable WiFi device to obtain a first analysis result includes:

[0015] The intelligent diagnostic program preprocesses the network connection data, specifically including: standardizing the signal strength data and converting the raw dBm value into a percentage; performing time-series analysis on the connection speed data to calculate speed fluctuation rate and stability indicators; validating the IP address and DNS configuration to check for conflicts or misconfigurations; statistically analyzing the temporal distribution characteristics of packet loss rate to generate a packet loss pattern feature vector; and calculating the mean, variance, and peak value of network latency to construct latency feature indicators.

[0016] Feature extraction of the system information specifically includes: analyzing hardware resource status such as CPU utilization, memory usage, and storage space; detecting the compatibility of driver and firmware versions; extracting physical status parameters such as device temperature and power supply voltage; and obtaining network protocol stack configuration parameters and operating status.

[0017] Semantic analysis of the operation logs includes: extracting key event information using natural language processing techniques; establishing an event sequence graph to identify fault triggering chains; statistically analyzing the frequency and distribution characteristics of error codes; and extracting the severity levels of system warnings and error messages.

[0018] The data obtained after the above processing is input into a pre-trained multimodal fault recognition model, specifically including: using a convolutional neural network to process time-series feature data; using a recurrent neural network to analyze event sequence data; using an attention mechanism to fuse multi-source feature information; and outputting the probability distribution of fault types.

[0019] The decision-making reasoning based on the model output results specifically includes: determining the main fault types according to the fault probability threshold; analyzing the correlation and causal relationship between fault types; assessing the severity and urgency of the fault; and generating the first analysis result containing detailed fault information.

[0020] Optionally, the step of generating a fault diagnosis report based on the first analysis result, wherein the fault diagnosis report includes the fault type, fault severity, and possible fault causes, includes:

[0021] Parsing the fault feature data in the first analysis result specifically includes: extracting the fault type probability distribution output by the fault identification model; obtaining the anomaly score of each performance indicator; reading the fault-related time-series event chain; and collecting system status and resource usage data.

[0022] Prioritizing fault types involves: sorting multiple possible fault types based on their probability values; analyzing the causal relationships between fault types and constructing a fault propagation tree; identifying root cause faults and derived faults; and marking critical faults that require priority handling.

[0023] Assessing the severity of a fault specifically includes: calculating the impact of the fault on network performance; evaluating the negative impact of the fault on user experience; analyzing the duration and development trend of the fault; and generating a fault severity level based on preset scoring rules.

[0024] The analysis of possible causes of failure includes: matching similar cases based on a historical failure database; deriving possible failure triggering conditions using an expert rule system; analyzing the correlation between environmental factors and failures; and assessing the confidence level of various possible causes.

[0025] Generate structured diagnostic reports, including: an overview of the fault, including device identification and timestamps; a description of the specific manifestations and scope of impact of the fault; a list of possible causes of the fault and their probability weights; the addition of relevant diagnostic data and performance indicator charts; and the generation of report views tailored to different user roles.

[0026] Optionally, the step of selecting and executing a corresponding recovery operation from a pre-stored recovery scheme library based on the fault diagnosis report includes:

[0027] The fault diagnosis report is feature-mapped, specifically including: extracting fault type identifiers and severity levels;

[0028] Prioritize and analyze the causes of failures; obtain relevant abnormal performance data; read the current operating status parameters of the device;

[0029] Matching solutions within a pre-stored recovery solution library involves: constructing query conditions based on fault characteristics; retrieving historical cases with similar fault characteristics; evaluating the applicability scores of each candidate recovery solution; and ranking the recovery solutions according to their scores.

[0030] Develop a recovery operation execution strategy, which includes: classifying candidate recovery schemes into different execution levels; setting the execution order and triggering conditions for each level of scheme; configuring the timeout and retry rules for scheme execution; and defining a rollback mechanism in case of execution failure.

[0031] Perform the selected recovery operation, which includes: performing a security check on the execution environment; backing up the current system configuration and critical data; executing recovery instructions in the order of preset strategies; and recording status changes during the execution process.

[0032] Evaluate the effectiveness of recovery operations, specifically including: monitoring the changing trends of key performance indicators; verifying whether fault symptoms have been alleviated; checking for any new abnormal conditions; and generating a recovery operation execution report.

[0033] Optionally, the step of monitoring the current device status and current network connection status of the 5G portable WiFi device in real time during the recovery operation, and determining whether the recovery operation has successfully resolved the fault based on the current device status and current network connection status, includes:

[0034] Establish a real-time monitoring indicator system, which specifically includes: setting equipment status monitoring indicators, including hardware parameters such as CPU utilization, memory usage, temperature, and voltage; determining network connection monitoring indicators, including network parameters such as signal strength, transmission rate, packet loss rate, and latency; configuring the sampling period and threshold range for each indicator; and establishing correlation rules between indicators.

[0035] Collect current device status data, specifically including: reading real-time device parameters through hardware interfaces; obtaining system resource usage; detecting driver and service running status; recording system logs and alarm information; and storing the collected data in a temporary cache queue.

[0036] Acquire current network connection data, specifically including: measuring current network signal quality; performing network speed tests; detecting network protocol stack status; verifying data transmission stability; and recording network connection events.

[0037] Data analysis and status assessment are performed, including: real-time filtering and preprocessing of the collected current device status and current network connection status; calculation of trend changes of various indicators; detection of abnormal fluctuations and exceeding limits; and assessment of the overall operational health score.

[0038] Judging the effectiveness of the recovery operation includes: comparing the state changes before and after the fault occurred; verifying whether the fault symptoms have been eliminated; assessing whether the system stability has improved; checking for any new anomalies; and generating an evaluation conclusion on the recovery effect.

[0039] Optionally, the step of providing an advanced solution and sending the device information of the 5G portable WiFi device, the program attribute information of the intelligent diagnostic program, the solution library information of the recovery solution library, the network connection data, the system information, and the operation log to the edge server if the recovery operation fails to resolve the fault includes:

[0040] Generate advanced solutions, specifically including: analyzing the reasons for the failure of the initial recovery operation; matching higher-level solutions based on the persistent characteristics of the fault; generating user-guided processes that include hardware inspection steps; and developing alternative solutions for network repair.

[0041] Organize the device information of the 5G portable WiFi device, specifically including: collecting the hardware configuration information of the 5G portable WiFi device; extracting firmware version and driver information; obtaining the device's unique identification code; recording the device's usage time and operating environment parameters; and packaging the device's warranty status information.

[0042] This involves summarizing program attribute information and solution library information, specifically including: extracting configuration parameters of the intelligent diagnostic program; collecting execution records of diagnostic algorithms; organizing version information of the recovery solution library; statistically analyzing solution usage frequency and success rate data; and recording the detailed execution process of the solutions.

[0043] Processing the network connection data, the system information, and the operation logs specifically includes: compressing the network connection data; extracting key system event logs; filtering abnormal state records; organizing performance monitoring data; and summarizing fault-related alarm information.

[0044] The data that has undergone the above processing is then encrypted and transmitted. Specifically, this includes: de-identifying sensitive data; using encryption algorithms to protect data security; establishing a secure connection with the edge server; transmitting large amounts of data in chunks; and verifying the integrity of the data transmission.

[0045] Optionally, the step of the edge server obtaining fault data and diagnostic reports from multiple similar portable WiFi devices as reference data includes:

[0046] Determining the matching range of similar devices to obtain the similar portable WiFi devices specifically includes: establishing a product family classification system based on the device models of the 5G portable WiFi devices; identifying hardware architecture similarity; comparing software version compatibility; evaluating the similarity of functional features; and establishing a device grouping index.

[0047] Building a distributed data acquisition network specifically includes: deploying data acquisition agents on edge servers; establishing a device node registration mechanism; configuring data acquisition priority strategies; setting acquisition frequency and data volume thresholds; and achieving adaptive load balancing.

[0048] Acquiring fault data from similar portable WiFi devices specifically includes: receiving fault information actively reported by similar portable WiFi devices; periodically synchronizing the operating status data of similar portable WiFi devices; acquiring on-site data when a fault occurs in a similar portable WiFi device; collecting fault handling process records; and saving the fault resolution result data.

[0049] Collect diagnostic reports from similar portable WiFi devices, specifically including: obtaining the analysis results of the corresponding intelligent diagnostic program on the similar portable WiFi devices; collecting expert opinions from manual diagnosis; recording the process of determining the cause of the fault; saving the execution record of the repair plan; and statistically evaluating the effectiveness of the fault handling.

[0050] Data preprocessing is performed on the fault data and the diagnostic report to obtain reference data, specifically including: format conversion of the raw data; cleaning of abnormal and redundant data; supplementation of missing data items; standardization of data representation; and establishment of data association index.

[0051] Optionally, the step of analyzing the reference data using big data analytics to uncover potential fault patterns and trends to obtain reference analysis data includes:

[0052] The reference data is classified and preprocessed, specifically including: establishing data subsets according to fault type; extracting time series feature data; constructing equipment behavior feature vectors; labeling key attribute tags of the data; and handling missing and outlier values ​​in the data.

[0053] Perform multi-dimensional correlation analysis, specifically including: calculating the temporal correlation of failure occurrence; analyzing the correlation between failures and environmental factors; assessing the propagation relationship between failures; identifying combinations of failure triggering conditions; and constructing a failure correlation network model.

[0054] The application of machine learning algorithms for pattern recognition specifically includes: using clustering algorithms to discover fault patterns; using classification algorithms to predict fault types; using regression analysis to predict fault trends; using anomaly detection to identify novel faults; and establishing fault prediction models.

[0055] Temporal feature mining specifically includes: analyzing the periodicity of faults; identifying the seasonality of faults; extracting the evolution patterns of fault development; predicting potential fault inflection points; and assessing the persistence characteristics of faults.

[0056] Generate reference analysis data, specifically including: summarizing the statistical characteristics of fault patterns; outputting a probabilistic model for fault prediction; generating a decision tree for fault diagnosis; forming best practices for fault handling; and constructing a fault knowledge graph.

[0057] Optionally, the step of optimizing the intelligent diagnostic program and the recovery solution library based on the reference analysis data, the device information, the program attribute information, the solution library information, the network connection data, the system information, and the operation log includes:

[0058] Evaluate the performance metrics of the existing system, specifically including: statistically analyzing the accuracy and recall of diagnostic procedures; calculating the success rate and efficiency of recovery plans; analyzing system response time and resource consumption; evaluating user feedback and satisfaction data; and generating a performance evaluation report.

[0059] The intelligent diagnostic program is optimized, specifically including: updating the fault feature model based on reference analysis data; adjusting the weight parameters for fault identification; adding newly discovered fault modes; optimizing the decision logic of the diagnostic process; and updating the fault rule knowledge base.

[0060] The upgrade of the recovery solution library includes: filtering efficient and reliable recovery solutions; removing inefficient or outdated solutions; adding new solutions; optimizing the execution order of solutions; and updating the applicable conditions for solutions.

[0061] Performing adaptive optimization specifically includes: adjusting diagnostic parameters based on device characteristics; optimizing execution strategies based on the network environment; adjusting resource allocation according to system load; customizing solutions based on user scenarios; and achieving dynamic performance tuning.

[0062] Verifying the optimization effect specifically includes: conducting offline testing; performing small-scale field trials; collecting optimized performance data; comparing the effects before and after optimization; and generating an optimization effect report.

[0063] Another aspect of the present invention provides a 5G portable WiFi fault diagnosis and recovery system for performing a 5G portable WiFi fault diagnosis and recovery method, comprising: a 5G portable WiFi device, a communication terminal connected to the 5G portable WiFi device, and an edge server;

[0064] The 5G portable WiFi device is configured as follows:

[0065] Collect network connection data, system information, and operation logs of the communication terminal from the communication terminal;

[0066] The network connection data, system information, and operation log are analyzed using a preset intelligent diagnostic program to obtain a first analysis result;

[0067] A fault diagnosis report is generated based on the first analysis results. The fault diagnosis report includes the fault type, fault severity, and possible fault causes.

[0068] Based on the fault diagnosis report, select and execute the corresponding recovery operation from the pre-stored recovery plan library;

[0069] During the recovery operation, the current device status and current network connection status of the 5G portable WiFi device are monitored in real time, and the recovery operation is judged to have successfully resolved the fault based on the current device status and current network connection status.

[0070] If the recovery operation fails to resolve the fault, an advanced solution is provided, and the device information of the 5G portable WiFi device, the program attribute information of the intelligent diagnostic program, the solution library information of the recovery solution library, the network connection data, the system information, and the operation log are sent to the edge server.

[0071] The edge server is configured as follows:

[0072] Obtain fault data and diagnostic reports from multiple similar portable WiFi devices as reference data;

[0073] The reference data is analyzed using big data analytics to uncover potential fault patterns and trends, resulting in reference analysis data.

[0074] The intelligent diagnostic program and the recovery solution library are optimized based on the reference analysis data, the device information, the program attribute information, the solution library information, the network connection data, the system information, and the operation log.

[0075] By employing the technical solution of this invention, network connection data, system information, and operation logs can be analyzed using artificial intelligence algorithms to more accurately identify fault types. This analysis method based on historical data and fault patterns reduces misjudgments and improves diagnostic reliability. The system can automatically select and execute recovery operations, such as restarting the device or updating firmware, based on the fault diagnosis report. This automated process significantly shortens fault recovery time and improves the user experience. During the recovery operation, the device status and network connection status are monitored in real time, allowing for timely assessment of the recovery operation's effectiveness. This dynamic feedback mechanism ensures the timeliness and effectiveness of fault handling. When the initial recovery operation fails to resolve the fault, the system can provide advanced solutions, such as guiding users to perform hardware checks or contact after-sales service. This multi-layered solution can more comprehensively address various fault situations. By collecting and analyzing fault data from multiple similar devices, the system can uncover potential fault patterns and trends, thereby optimizing the intelligent diagnostic program and recovery solution library. This data-driven optimization process continuously improves the system's intelligence level. Attached Figure Description

[0076] Figure 1 This is a flowchart of a 5G portable WiFi fault diagnosis and recovery method provided in one embodiment of the present invention;

[0077] Figure 2 This is a schematic block diagram of a 5G portable WiFi fault diagnosis and recovery system provided in one embodiment of the present invention. Detailed Implementation

[0078] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0079] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0080] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0081] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0082] The following reference Figures 1 to 2 This invention describes a 5G portable WiFi fault diagnosis and recovery method and system provided by some embodiments of the present invention.

[0083] like Figure 1 As shown, one embodiment of the present invention provides a method for diagnosing and recovering 5G portable WiFi faults, including:

[0084] Network connection data (including signal strength, connection speed, IP address, DNS configuration, packet loss rate, latency data) and system information and operation logs of the communication terminal are collected from the communication terminal connected to the 5G portable WiFi device.

[0085] Understandably, in this step, it is crucial to ensure a successful connection between the communication terminal (such as a smartphone, tablet, or laptop) and the 5G portable WiFi device. Once connected, the communication terminal sends a request to the 5G portable WiFi device via API or network protocols (such as HTTP or MQTT) to collect the following network connection data: signal strength (obtained through the device's wireless interface), connection speed (measured upload and download speeds), IP address (obtained from the IP address assigned to the communication terminal), DNS configuration (collected from the currently used DNS server address), packet loss rate (calculated using statistics on sent and received data packets), and latency data (measured from the time a data packet is sent to the point of reception). The communication terminal accesses its system information (such as operating system version, device model, etc.) and operational logs (such as network connection history, error logs, etc.) through the system API. This information is then packaged together with the network connection data to form a complete dataset. The collected network connection data, system information, and operational logs are sent to the 5G portable WiFi device's intelligent diagnostic program for analysis via a secure communication protocol (such as HTTPS). After receiving the data, the 5G portable WiFi device stores it in its local database and prepares it for subsequent intelligent analysis. This step allows for the comprehensive collection of various data related to network connectivity, ensuring sufficient foundational information for fault diagnosis. The collected data, such as signal strength and connection speed, provides crucial information for subsequent fault analysis, helping to identify the root cause of network problems. Through continuous data collection and transmission, real-time monitoring of network status is achieved, enabling timely detection and response to potential faults. Accurate fault diagnosis and rapid recovery operations significantly improve the user experience when using 5G portable WiFi devices, reducing usage interruptions caused by network issues.

[0086] The network connection data, system information, and operation log are analyzed using the pre-set intelligent diagnostic program of the 5G portable WiFi device to obtain a first analysis result;

[0087] It is understood that the intelligent diagnostic program is based on artificial intelligence algorithms and can identify the types of faults that may exist at present based on historical fault data and preset fault modes. The fault types include, but are not limited to, equipment hardware faults, software faults, network signal problems, configuration errors, and external interference.

[0088] A fault diagnosis report is generated based on the first analysis results. The fault diagnosis report includes the fault type, fault severity, and possible fault causes.

[0089] Based on the fault diagnosis report, select and execute the corresponding recovery operation from the pre-stored recovery plan library;

[0090] It is understood that the recovery operations include, but are not limited to, automatically restarting the device, updating firmware, adjusting network configuration parameters, switching network frequency bands, and clearing cached data;

[0091] During the recovery operation, the current device status and current network connection status of the 5G portable WiFi device are monitored in real time, and the recovery operation is judged to have successfully resolved the fault based on the current device status and current network connection status.

[0092] If the recovery operation fails to resolve the fault, an advanced solution is provided, and the device information of the 5G portable WiFi device, the program attribute information of the intelligent diagnostic program, the solution library information of the recovery solution library, the network connection data, the system information, and the operation log are sent to the edge server.

[0093] Understandably, the advanced solutions include guiding users to perform hardware checks, contact after-sales service, or perform network repair operations.

[0094] The edge server obtains fault data and diagnostic reports from multiple similar portable WiFi devices (which are the same or similar products as the 5G portable WiFi device) as reference data.

[0095] The reference data is analyzed using big data analytics to uncover potential fault patterns and trends, resulting in reference analysis data.

[0096] The intelligent diagnostic program and the recovery solution library are optimized based on the reference analysis data, the device information, the program attribute information, the solution library information, the network connection data, the system information, and the operation log.

[0097] Understandably, the computing resources of edge servers, including high-performance quantum computing capabilities, can be used for more in-depth analysis and diagnosis to accelerate the fault diagnosis process.

[0098] In this embodiment, analyzing network connection data, system information, and operational logs using artificial intelligence algorithms can more accurately identify fault types. This analysis method based on historical data and fault patterns reduces misjudgments and improves diagnostic reliability. The system can automatically select and execute recovery operations based on fault diagnosis reports, such as restarting the device or updating firmware. This automated process significantly shortens fault recovery time and improves the user experience. During the recovery operation, real-time monitoring of device and network connection status allows for timely assessment of the recovery operation's effectiveness. This dynamic feedback mechanism ensures the timeliness and effectiveness of fault handling. When initial recovery operations fail to resolve the fault, the system can provide advanced solutions, such as guiding users to perform hardware checks or contact after-sales service. This multi-layered solution can more comprehensively address various fault situations. By collecting and analyzing fault data from multiple similar devices, the system can uncover potential fault patterns and trends, thereby optimizing the intelligent diagnostic program and recovery solution library. This data-driven optimization process continuously improves the system's intelligence level.

[0099] To provide more accurate, safer, and more personalized services, some possible embodiments of the present invention may also include the following steps:

[0100] Provide users with a remote diagnostic service interface, enabling technical support personnel to remotely access information about faulty equipment and perform remote assistance operations through terminals, including but not limited to remotely controlling terminals to execute diagnostic commands, view equipment settings, and modify network configurations;

[0101] During the data collection, transmission, and storage process, encryption technology is used to encrypt device information, user data, and diagnostic results to prevent data leakage.

[0102] The system is monitored in real time to prevent malicious attacks and intrusions. Blockchain technology is used to ensure the integrity and immutability of data, and all diagnostic and recovery operation logs are recorded for traceability and auditing.

[0103] Display fault diagnosis results, recovery operation progress and status information to users through an intuitive graphical interface or voice prompts;

[0104] It receives user feedback and operation instructions, guides users to perform necessary manual operations (such as inserting or removing SIM cards, replacing power adapters, etc.), and feeds back the user operation results to the corresponding fault diagnosis module and fault recovery module for further analysis and processing.

[0105] In some possible embodiments of the present invention, the step of analyzing the network connection data, the system information, and the operation log using the smart diagnostic program preset in the 5G portable WiFi device to obtain a first analysis result includes:

[0106] The intelligent diagnostic program preprocesses the network connection data, specifically including: standardizing the signal strength data and converting the raw dBm value into a percentage; performing time-series analysis on the connection speed data to calculate speed fluctuation rate and stability indicators; validating the IP address and DNS configuration to check for conflicts or misconfigurations; statistically analyzing the temporal distribution characteristics of packet loss rate to generate a packet loss pattern feature vector; and calculating the mean, variance, and peak value of network latency to construct latency feature indicators.

[0107] Feature extraction of the system information specifically includes: analyzing hardware resource status such as CPU utilization, memory usage, and storage space; detecting the compatibility of driver and firmware versions; extracting physical status parameters such as device temperature and power supply voltage; and obtaining network protocol stack configuration parameters and operating status.

[0108] Semantic analysis of the operation logs includes: extracting key event information using natural language processing techniques; establishing an event sequence graph to identify fault triggering chains; statistically analyzing the frequency and distribution characteristics of error codes; and extracting the severity levels of system warnings and error messages.

[0109] The data obtained after the above processing is input into a pre-trained multimodal fault recognition model, specifically including: using a convolutional neural network to process time-series feature data; using a recurrent neural network to analyze event sequence data; using an attention mechanism to fuse multi-source feature information; and outputting the probability distribution of fault types.

[0110] Understandably, CNNs excel at processing image and temporal data, extracting local features through convolutional layers to effectively capture spatial and temporal patterns in the data, which is crucial for analyzing changes in device status at different points in time. RNNs are well-suited for processing sequential data, remembering previous input information to analyze dependencies in time series, enabling them to identify temporal relationships between events and making them suitable for time series analysis of fault occurrences. Attention mechanisms allow models to focus on the most relevant information when processing data, effectively fusing feature information from different sources. This mechanism improves the sensitivity of multimodal fault identification models to important features and enhances the accuracy of fault identification. Finally, the multimodal fault identification model outputs a probability distribution for each fault type, meaning it not only identifies the fault type but also provides the probability of each type occurring. This probability output helps decision-makers assess the severity of the fault and the order of priority for handling it.

[0111] The decision-making reasoning based on the model output results specifically includes: determining the main fault types according to the fault probability threshold; analyzing the correlation and causal relationship between fault types; assessing the severity and urgency of the fault; and generating the first analysis result containing detailed fault information.

[0112] The solution in this embodiment improves the accuracy of fault identification through multi-dimensional feature analysis; reduces false alarm and false negative rates, thereby improving diagnostic reliability; adopts a pipelined parallel processing mechanism; optimizes the allocation of computing resources to improve processing efficiency; comprehensively considers hardware, software, and network-level issues to establish a correlation analysis mechanism between faults; and its modular design facilitates functional expansion and supports the dynamic addition of new fault types.

[0113] In some possible embodiments of the present invention, a method for constructing a multimodal fault identification model includes:

[0114] Collect data from different modalities, such as sensor data, log files, network connectivity information, etc. This data needs to be cleaned and standardized to ensure its quality and consistency.

[0115] Using different deep learning models to extract features from various types of data:

[0116] Convolutional Neural Networks (CNNs): Suitable for processing image and temporal feature data, capable of extracting local features;

[0117] Recurrent Neural Networks (RNNs): Suitable for analyzing time series data, they can capture the temporal dependencies between events;

[0118] Attention mechanism: used to fuse feature information from different sources to enhance the model's ability to focus on important features;

[0119] The extracted features are input into a multimodal model, which is usually a deep learning framework that integrates CNN, RNN and attention mechanisms. This model can handle multiple types of data and perform effective feature fusion.

[0120] The model is trained using labeled fault data, and its parameters are adjusted to improve its recognition accuracy. After training, the model's performance is evaluated using a validation set to ensure its generalization ability on unseen data.

[0121] Once the model is trained, it can be used for real-time fault identification; based on the fault type probability distribution output by the model, a fault diagnosis report is generated, providing information such as fault type, severity, and possible causes.

[0122] Based on feedback from real-world applications and newly collected data, the model is regularly retrained and optimized to improve its accuracy and adaptability.

[0123] The solution in this embodiment can construct an efficient multimodal fault identification model, which can comprehensively analyze multiple data features, thereby improving the accuracy and efficiency of fault identification.

[0124] In some possible embodiments of the present invention, the step of generating a fault diagnosis report based on the first analysis result, wherein the fault diagnosis report includes the fault type, the fault severity, and possible causes of the fault, includes:

[0125] Parsing the fault feature data in the first analysis result specifically includes: extracting the fault type probability distribution output by the fault identification model; obtaining the anomaly score of each performance indicator; reading the fault-related time-series event chain; and collecting system status and resource usage data.

[0126] Prioritizing fault types involves: sorting multiple possible fault types based on their probability values; analyzing the causal relationships between fault types and constructing a fault propagation tree; identifying root cause faults and derived faults; and marking critical faults that require priority handling.

[0127] Assessing the severity of a fault specifically includes: calculating the impact of the fault on network performance; evaluating the negative impact of the fault on user experience; analyzing the duration and development trend of the fault; and generating a fault severity level based on preset scoring rules.

[0128] The analysis of possible causes of failure includes: matching similar cases based on a historical failure database; deriving possible failure triggering conditions using an expert rule system; analyzing the correlation between environmental factors and failures; and assessing the confidence level of various possible causes.

[0129] Generate structured diagnostic reports, including: an overview of the fault, including device identification and timestamps; a description of the specific manifestations and scope of impact of the fault; a list of possible causes of the fault and their probability weights; the addition of relevant diagnostic data and performance indicator charts; and the generation of report views tailored to different user roles.

[0130] The solution in this embodiment adopts a hierarchical and structured information organization method, supports multi-dimensional data visualization, and adaptively adjusts the content depth according to the user role; it fully records the reasoning process of fault judgment, retains key diagnostic data and evidence, and facilitates subsequent fault analysis and optimization; it clearly identifies fault priorities, intuitively displays the scope of fault impact, and accelerates the formulation of fault solutions; and it uses a standardized fault description format to facilitate the construction of a fault knowledge base and promote the reuse of fault handling experience.

[0131] In some possible embodiments of the present invention, the step of selecting and executing a corresponding recovery operation from a pre-stored recovery scheme library based on the fault diagnosis report includes:

[0132] The fault diagnosis report is feature-mapped, specifically including: extracting fault type identifiers and severity levels;

[0133] Prioritize and analyze the causes of failures; obtain relevant abnormal performance data; read the current operating status parameters of the device;

[0134] Matching solutions within a pre-stored recovery solution library involves: constructing query conditions based on fault characteristics; retrieving historical cases with similar fault characteristics; evaluating the applicability scores of each candidate recovery solution; and ranking the recovery solutions according to their scores.

[0135] Develop a recovery operation execution strategy, which includes: classifying candidate recovery schemes into different execution levels; setting the execution order and triggering conditions for each level of scheme; configuring the timeout and retry rules for scheme execution; and defining a rollback mechanism in case of execution failure.

[0136] Perform the selected recovery operation, which includes: performing a security check on the execution environment; backing up the current system configuration and critical data; executing recovery instructions in the order of preset strategies; and recording status changes during the execution process.

[0137] Evaluate the effectiveness of recovery operations, specifically including: monitoring the changing trends of key performance indicators; verifying whether fault symptoms have been alleviated; checking for any new abnormal conditions; and generating a recovery operation execution report.

[0138] The solution in this embodiment is based on accurate matching of multi-dimensional features, takes into account feedback from historical execution results, and dynamically adjusts the priority of the solution; it conducts risk assessment before execution, sets up a sound rollback mechanism to protect critical data and configurations; it adopts a progressive recovery strategy, executes independent recovery operations in parallel, optimizes the execution order to reduce waiting time; it adaptively selects the optimal recovery solution, dynamically adjusts the execution strategy, and accumulates optimization experience to improve accuracy.

[0139] In some possible embodiments of the present invention, the step of monitoring the current device status and current network connection status of the 5G portable WiFi device in real time during the recovery operation, and determining whether the recovery operation has successfully resolved the fault based on the current device status and current network connection status, includes:

[0140] Establish a real-time monitoring indicator system, which specifically includes: setting equipment status monitoring indicators, including hardware parameters such as CPU utilization, memory usage, temperature, and voltage; determining network connection monitoring indicators, including network parameters such as signal strength, transmission rate, packet loss rate, and latency; configuring the sampling period and threshold range for each indicator; and establishing correlation rules between indicators.

[0141] Collect current device status data, specifically including: reading real-time device parameters through hardware interfaces; obtaining system resource usage; detecting driver and service running status; recording system logs and alarm information; and storing the collected data in a temporary cache queue.

[0142] Acquire current network connection data, specifically including: measuring current network signal quality; performing network speed tests; detecting network protocol stack status; verifying data transmission stability; and recording network connection events.

[0143] Data analysis and status assessment are performed, including: real-time filtering and preprocessing of the collected current device status and current network connection status; calculation of trend changes of various indicators; detection of abnormal fluctuations and exceeding limits; and assessment of the overall operational health score.

[0144] Judging the effectiveness of the recovery operation includes: comparing the state changes before and after the fault occurred; verifying whether the fault symptoms have been eliminated; assessing whether the system stability has improved; checking for any new anomalies; and generating an evaluation conclusion on the recovery effect.

[0145] The solution in this embodiment, through a multi-dimensional indicator monitoring system, real-time data collection and analysis, and a precise status assessment mechanism, can promptly detect abnormal situations, dynamically adjust recovery strategies, and prevent secondary failures. It can continuously monitor system status, provide timely warnings of potential risks, and ensure network service quality. It also features automated effect evaluation, objective success criteria, and complete process record archiving.

[0146] In some possible embodiments of the present invention, the step of providing an advanced solution if the recovery operation fails to resolve the fault, and sending the device information of the 5G portable WiFi device, the program attribute information of the intelligent diagnostic program, the solution library information of the recovery solution library, the network connection data, the system information, and the operation log to the edge server includes:

[0147] Generate advanced solutions, specifically including: analyzing the reasons for the failure of the initial recovery operation; matching higher-level solutions based on the persistent characteristics of the fault; generating user-guided processes that include hardware inspection steps; and developing alternative solutions for network repair.

[0148] Organize the device information of the 5G portable WiFi device, specifically including: collecting the hardware configuration information of the 5G portable WiFi device; extracting firmware version and driver information; obtaining the device's unique identification code; recording the device's usage time and operating environment parameters; and packaging the device's warranty status information.

[0149] This involves summarizing program attribute information and solution library information, specifically including: extracting configuration parameters of the intelligent diagnostic program; collecting execution records of diagnostic algorithms; organizing version information of the recovery solution library; statistically analyzing solution usage frequency and success rate data; and recording the detailed execution process of the solutions.

[0150] Processing the network connection data, the system information, and the operation logs specifically includes: compressing the network connection data; extracting key system event logs; filtering abnormal state records; organizing performance monitoring data; and summarizing fault-related alarm information.

[0151] The data that has undergone the above processing is then encrypted and transmitted. Specifically, this includes: de-identifying sensitive data; using encryption algorithms to protect data security; establishing a secure connection with the edge server; transmitting large amounts of data in chunks; and verifying the integrity of the data transmission.

[0152] The solution in this embodiment provides a multi-layered approach to ensure effective fault handling; it enhances the standardization of data management through a complete data acquisition mechanism, standardized data organization format, and reliable data transmission mechanism; and it guarantees the security of data transmission through strict data encryption measures, a robust privacy protection mechanism, and a reliable transmission verification mechanism.

[0153] In some possible embodiments of the present invention, the step of the edge server obtaining fault data and diagnostic reports of multiple similar portable WiFi devices as reference data includes:

[0154] Determining the matching range of similar devices to obtain the similar portable WiFi devices specifically includes: establishing a product family classification system based on the device models of the 5G portable WiFi devices; identifying hardware architecture similarity; comparing software version compatibility; evaluating the similarity of functional features; and establishing a device grouping index.

[0155] Building a distributed data acquisition network specifically includes: deploying data acquisition agents on edge servers; establishing a device node registration mechanism; configuring data acquisition priority strategies; setting acquisition frequency and data volume thresholds; and achieving adaptive load balancing.

[0156] Acquiring fault data from similar portable WiFi devices specifically includes: receiving fault information actively reported by similar portable WiFi devices; periodically synchronizing the operating status data of similar portable WiFi devices; acquiring on-site data when a fault occurs in a similar portable WiFi device; collecting fault handling process records; and saving the fault resolution result data.

[0157] Collect diagnostic reports from similar portable WiFi devices, specifically including: obtaining the analysis results of the corresponding intelligent diagnostic program on the similar portable WiFi devices; collecting expert opinions from manual diagnosis; recording the process of determining the cause of the fault; saving the execution record of the repair plan; and statistically evaluating the effectiveness of the fault handling.

[0158] Data preprocessing is performed on the fault data and the diagnostic report to obtain reference data, specifically including: format conversion of the raw data; cleaning of abnormal and redundant data; supplementation of missing data items; standardization of data representation; and establishment of data association index.

[0159] The solution in this embodiment can improve the comprehensiveness of data collection, enhance the reliability of data quality, improve the efficiency of data management, and optimize the utilization of system resources.

[0160] In some possible embodiments of the present invention, the step of analyzing the reference data using big data analytics to uncover potential fault patterns and trends, and obtaining reference analysis data, includes:

[0161] The reference data is classified and preprocessed, specifically including: establishing data subsets according to fault type; extracting time series feature data; constructing equipment behavior feature vectors; labeling key attribute tags of the data; and handling missing and outlier values ​​in the data.

[0162] Perform multi-dimensional correlation analysis, specifically including: calculating the temporal correlation of failure occurrence; analyzing the correlation between failures and environmental factors; assessing the propagation relationship between failures; identifying combinations of failure triggering conditions; and constructing a failure correlation network model.

[0163] The application of machine learning algorithms for pattern recognition specifically includes: using clustering algorithms to discover fault patterns; using classification algorithms to predict fault types; using regression analysis to predict fault trends; using anomaly detection to identify novel faults; and establishing fault prediction models.

[0164] Temporal feature mining specifically includes: analyzing the periodicity of faults; identifying the seasonality of faults; extracting the evolution patterns of fault development; predicting potential fault inflection points; and assessing the persistence characteristics of faults.

[0165] Generate reference analysis data, specifically including: summarizing the statistical characteristics of fault patterns; outputting a probabilistic model for fault prediction; generating a decision tree for fault diagnosis; forming best practices for fault handling; and constructing a fault knowledge graph.

[0166] The solution in this embodiment, based on the analysis of massive historical data, multi-dimensional feature extraction and fusion, and dynamically updated prediction models, can improve the accuracy of fault prediction; by automatically identifying fault modes, accurately locating fault causes, and intelligently recommending solutions, it can enhance the intelligence of fault diagnosis; and by quickly matching historical cases, optimizing processing procedures, and reducing fault handling time, it can improve the efficiency of fault handling.

[0167] In some possible embodiments of the present invention, the step of optimizing the intelligent diagnostic program and the recovery solution library based on the reference analysis data, the device information, the program attribute information, the solution library information, the network connection data, the system information, and the operation log includes:

[0168] Evaluate the performance metrics of the existing system, specifically including: statistically analyzing the accuracy and recall of diagnostic procedures; calculating the success rate and efficiency of recovery plans; analyzing system response time and resource consumption; evaluating user feedback and satisfaction data; and generating a performance evaluation report.

[0169] The intelligent diagnostic program is optimized, specifically including: updating the fault feature model based on reference analysis data; adjusting the weight parameters for fault identification; adding newly discovered fault modes; optimizing the decision logic of the diagnostic process; and updating the fault rule knowledge base.

[0170] The upgrade of the recovery solution library includes: filtering efficient and reliable recovery solutions; removing inefficient or outdated solutions; adding new solutions; optimizing the execution order of solutions; and updating the applicable conditions for solutions.

[0171] Performing adaptive optimization specifically includes: adjusting diagnostic parameters based on device characteristics; optimizing execution strategies based on the network environment; adjusting resource allocation according to system load; customizing solutions based on user scenarios; and achieving dynamic performance tuning.

[0172] Verifying the optimization effect specifically includes: conducting offline testing; performing small-scale field trials; collecting optimized performance data; comparing the effects before and after optimization; and generating an optimization effect report.

[0173] The solution in this embodiment can improve diagnostic accuracy, increase repair success rate, and reduce processing response time; it can support new fault types, adapt to different usage scenarios, and be compatible with multiple device models; it can improve fault resolution efficiency, reduce the need for manual intervention, and improve service satisfaction; and it can achieve continuous improvement through automated optimization mechanisms, dynamic performance tuning, and continuous knowledge accumulation.

[0174] Please see Figure 2Another embodiment of the present invention provides a 5G portable WiFi fault diagnosis and recovery system for performing a 5G portable WiFi fault diagnosis and recovery method, comprising: a 5G portable WiFi device, a communication terminal connected to the 5G portable WiFi device, and an edge server;

[0175] The 5G portable WiFi device is configured as follows:

[0176] Collect network connection data, system information, and operation logs of the communication terminal from the communication terminal;

[0177] The network connection data, system information, and operation log are analyzed using a preset intelligent diagnostic program to obtain a first analysis result;

[0178] A fault diagnosis report is generated based on the first analysis results. The fault diagnosis report includes the fault type, fault severity, and possible fault causes.

[0179] Based on the fault diagnosis report, select and execute the corresponding recovery operation from the pre-stored recovery plan library;

[0180] During the recovery operation, the current device status and current network connection status of the 5G portable WiFi device are monitored in real time, and the recovery operation is judged to have successfully resolved the fault based on the current device status and current network connection status.

[0181] If the recovery operation fails to resolve the fault, an advanced solution is provided, and the device information of the 5G portable WiFi device, the program attribute information of the intelligent diagnostic program, the solution library information of the recovery solution library, the network connection data, the system information, and the operation log are sent to the edge server.

[0182] The edge server is configured as follows:

[0183] Obtain fault data and diagnostic reports from multiple similar portable WiFi devices as reference data;

[0184] The reference data is analyzed using big data analytics to uncover potential fault patterns and trends, resulting in reference analysis data.

[0185] The intelligent diagnostic program and the recovery solution library are optimized based on the reference analysis data, the device information, the program attribute information, the solution library information, the network connection data, the system information, and the operation log.

[0186] It should be known that, Figure 2The block diagram of the 5G portable WiFi fault diagnosis and recovery system shown is for illustrative purposes only, and the number of modules shown does not limit the scope of protection of this invention. The 5G portable WiFi fault diagnosis and recovery system provided in this embodiment can be used to execute various embodiments of the corresponding 5G portable WiFi fault diagnosis and recovery methods. For specific implementation details, please refer to the descriptions of the respective method embodiments, which will not be repeated here.

[0187] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0188] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0189] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0190] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0191] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0192] If the integrated units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0193] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0194] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0195] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of the present invention, and various modifications and alterations can be made, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of the present invention.

Claims

1. A method for diagnosing and recovering from 5G portable WiFi faults, characterized in that, include: Network connection data, as well as system information and operation logs of the communication terminal, are collected from the communication terminal connected to the 5G portable WiFi device. The network connection data, system information, and operation log are analyzed using the pre-set intelligent diagnostic program of the 5G portable WiFi device to obtain a first analysis result; A fault diagnosis report is generated based on the first analysis results. The fault diagnosis report includes the fault type, fault severity, and possible fault causes. Based on the fault diagnosis report, select and execute the corresponding recovery operation from the pre-stored recovery plan library; During the recovery operation, the current device status and current network connection status of the 5G portable WiFi device are monitored in real time, and the recovery operation is judged to have successfully resolved the fault based on the current device status and current network connection status. If the recovery operation fails to resolve the fault, an advanced solution is provided, and the device information of the 5G portable WiFi device, the program attribute information of the intelligent diagnostic program, the solution library information of the recovery solution library, the network connection data, the system information, and the operation log are sent to the edge server. The edge server obtains fault data and diagnostic reports from multiple similar portable WiFi devices as reference data. The reference data is analyzed using big data analytics to uncover potential fault patterns and trends, resulting in reference analysis data. The intelligent diagnostic program and the recovery solution library are optimized based on the reference analysis data, the device information, the program attribute information, the solution library information, the network connection data, the system information, and the operation log.

2. The 5G portable WiFi fault diagnosis and recovery method according to claim 1, characterized in that, The step of analyzing the network connection data, system information, and operation log using the pre-set intelligent diagnostic program of the 5G portable WiFi device to obtain a first analysis result includes: The intelligent diagnostic program preprocesses the network connection data, specifically including: standardizing the signal strength data and converting the raw dBm value into a percentage; performing time-series analysis on the connection speed data to calculate speed fluctuation rate and stability indicators; validating the IP address and DNS configuration to check for conflicts or misconfigurations; statistically analyzing the temporal distribution characteristics of packet loss rate to generate a packet loss pattern feature vector; and calculating the mean, variance, and peak value of network latency to construct latency feature indicators. Feature extraction of the system information specifically includes: analyzing hardware resource status such as CPU utilization, memory usage, and storage space; detecting the compatibility of driver and firmware versions; extracting physical status parameters such as device temperature and power supply voltage; and obtaining network protocol stack configuration parameters and operating status. Semantic analysis of the operation logs includes: extracting key event information using natural language processing techniques; establishing an event sequence graph to identify fault triggering chains; statistically analyzing the frequency and distribution characteristics of error codes; and extracting the severity levels of system warnings and error messages. The data obtained after the above processing is input into a pre-trained multimodal fault recognition model, specifically including: using a convolutional neural network to process time-series feature data; using a recurrent neural network to analyze event sequence data; using an attention mechanism to fuse multi-source feature information; and outputting the probability distribution of fault types. The decision-making reasoning based on the model output results specifically includes: determining the main fault types according to the fault probability threshold; analyzing the correlation and causal relationship between fault types; assessing the severity and urgency of the fault; and generating the first analysis result containing detailed fault information.

3. The 5G portable WiFi fault diagnosis and recovery method according to claim 2, characterized in that, The step of generating a fault diagnosis report based on the first analysis result, wherein the fault diagnosis report includes the fault type, fault severity, and possible fault causes, includes: Parsing the fault feature data in the first analysis result specifically includes: extracting the fault type probability distribution output by the fault identification model; obtaining the anomaly score of each performance indicator; reading the fault-related time-series event chain; and collecting system status and resource usage data. Prioritizing fault types involves: sorting multiple possible fault types based on their probability values; analyzing the causal relationships between fault types and constructing a fault propagation tree; identifying root cause faults and derived faults; and marking critical faults that require priority handling. Assessing the severity of a fault specifically includes: calculating the impact of the fault on network performance; evaluating the negative impact of the fault on user experience; analyzing the duration and development trend of the fault; and generating a fault severity level based on preset scoring rules. The analysis of possible causes of failure includes: matching similar cases based on a historical failure database; deriving possible failure triggering conditions using an expert rule system; analyzing the correlation between environmental factors and failures; and assessing the confidence level of various possible causes. Generate structured diagnostic reports, including: an overview of the fault, including device identification and timestamps; a description of the specific manifestations and scope of impact of the fault; a list of possible causes of the fault and their probability weights; the addition of relevant diagnostic data and performance indicator charts; and the generation of report views tailored to different user roles.

4. The 5G portable WiFi fault diagnosis and recovery method according to claim 3, characterized in that, The step of selecting and executing the corresponding recovery operation from the pre-stored recovery plan library based on the fault diagnosis report includes: The fault diagnosis report is feature-mapped, specifically including: extracting fault type identifiers and severity levels; Prioritize and analyze the causes of failures; obtain relevant abnormal performance data; read the current operating status parameters of the device; Matching solutions within a pre-stored recovery solution library involves: constructing query conditions based on fault characteristics; retrieving historical cases with similar fault characteristics; evaluating the applicability scores of each candidate recovery solution; and ranking the recovery solutions according to their scores. Develop a recovery operation execution strategy, which includes: classifying candidate recovery schemes into different execution levels; setting the execution order and triggering conditions for each level of scheme; configuring the timeout and retry rules for scheme execution; and defining a rollback mechanism in case of execution failure. Perform the selected recovery operation, which includes: performing a security check on the execution environment; backing up the current system configuration and critical data; executing recovery instructions in the order of preset strategies; and recording status changes during the execution process. Evaluate the effectiveness of recovery operations, specifically including: monitoring the changing trends of key performance indicators; verifying whether fault symptoms have been alleviated; checking for any new abnormal conditions; and generating a recovery operation execution report.

5. The 5G portable WiFi fault diagnosis and recovery method according to claim 4, characterized in that, The steps of monitoring the current device status and current network connection status of the 5G portable WiFi device in real time during the recovery operation, and determining whether the recovery operation has successfully resolved the fault based on the current device status and current network connection status, include: Establish a real-time monitoring indicator system, which specifically includes: setting equipment status monitoring indicators, including hardware parameters such as CPU utilization, memory usage, temperature, and voltage; determining network connection monitoring indicators, including network parameters such as signal strength, transmission rate, packet loss rate, and latency; configuring the sampling period and threshold range for each indicator; and establishing correlation rules between indicators. Collect current device status data, specifically including: reading real-time device parameters through hardware interfaces; obtaining system resource usage; detecting driver and service running status; recording system logs and alarm information; and storing the collected data in a temporary cache queue. Acquire current network connection data, specifically including: measuring current network signal quality; performing network speed tests; detecting network protocol stack status; verifying data transmission stability; and recording network connection events. Data analysis and status assessment are performed, including: real-time filtering and preprocessing of the collected current device status and current network connection status; calculation of trend changes of various indicators; detection of abnormal fluctuations and exceeding limits; and assessment of the overall operational health score. Judging the effectiveness of the recovery operation includes: comparing the state changes before and after the fault occurred; verifying whether the fault symptoms have been eliminated; assessing whether the system stability has improved; checking for any new anomalies; and generating an evaluation conclusion on the recovery effect.

6. The 5G portable WiFi fault diagnosis and recovery method according to claim 5, characterized in that, The step of providing an advanced solution if the recovery operation fails to resolve the fault, and sending the device information of the 5G portable WiFi device, the program attribute information of the intelligent diagnostic program, the solution library information of the recovery solution library, the network connection data, the system information, and the operation log to the edge server, includes: Generate advanced solutions, specifically including: analyzing the reasons for the failure of the initial recovery operation; matching higher-level solutions based on the persistent characteristics of the fault; generating user-guided processes that include hardware inspection steps; and developing alternative solutions for network repair. Organize the device information of the 5G portable WiFi device, specifically including: collecting the hardware configuration information of the 5G portable WiFi device; extracting firmware version and driver information; obtaining the device's unique identification code; recording the device's usage time and operating environment parameters; and packaging the device's warranty status information. This involves summarizing program attribute information and solution library information, specifically including: extracting configuration parameters of the intelligent diagnostic program; collecting execution records of diagnostic algorithms; organizing version information of the recovery solution library; statistically analyzing solution usage frequency and success rate data; and recording the detailed execution process of the solutions. Processing the network connection data, the system information, and the operation logs specifically includes: compressing the network connection data; extracting key system event logs; filtering abnormal state records; organizing performance monitoring data; and summarizing fault-related alarm information. The data that has undergone the above processing is then encrypted and transmitted. Specifically, this includes: de-identifying sensitive data; using encryption algorithms to protect data security; establishing a secure connection with the edge server; transmitting large amounts of data in chunks; and verifying the integrity of the data transmission.

7. The 5G portable WiFi fault diagnosis and recovery method according to claim 6, characterized in that, The step of the edge server obtaining fault data and diagnostic reports from multiple similar portable WiFi devices as reference data includes: Determining the matching range of similar devices to obtain the similar portable WiFi devices specifically includes: establishing a product family classification system based on the device models of the 5G portable WiFi devices; identifying hardware architecture similarity; comparing software version compatibility; evaluating the similarity of functional features; and establishing a device grouping index. Building a distributed data acquisition network specifically includes: deploying data acquisition agents on edge servers; establishing a device node registration mechanism; configuring data acquisition priority strategies; setting acquisition frequency and data volume thresholds; and achieving adaptive load balancing. Acquiring fault data from similar portable WiFi devices specifically includes: receiving fault information actively reported by similar portable WiFi devices; periodically synchronizing the operating status data of similar portable WiFi devices; acquiring on-site data when a fault occurs in a similar portable WiFi device; collecting fault handling process records; and saving the fault resolution result data. Collect diagnostic reports from similar portable WiFi devices, specifically including: obtaining the analysis results of the corresponding intelligent diagnostic program on the similar portable WiFi devices; collecting expert opinions from manual diagnosis; recording the process of determining the cause of the fault; saving the execution record of the repair plan; and statistically evaluating the effectiveness of the fault handling. Data preprocessing is performed on the fault data and the diagnostic report to obtain reference data, specifically including: format conversion of the raw data; cleaning of abnormal and redundant data; supplementation of missing data items; standardization of data representation; and establishment of data association index.

8. The 5G portable WiFi fault diagnosis and recovery method according to claim 7, characterized in that, The step of analyzing the reference data using big data analytics to uncover potential fault patterns and trends, and obtaining reference analysis data, includes: The reference data is classified and preprocessed, specifically including: establishing data subsets according to fault type; extracting time series feature data; constructing equipment behavior feature vectors; labeling key attribute tags of the data; and handling missing and outlier values ​​in the data. Perform multi-dimensional correlation analysis, specifically including: calculating the temporal correlation of failure occurrence; analyzing the correlation between failures and environmental factors; assessing the propagation relationship between failures; identifying combinations of failure triggering conditions; and constructing a failure correlation network model. The application of machine learning algorithms for pattern recognition specifically includes: using clustering algorithms to discover fault patterns; using classification algorithms to predict fault types; using regression analysis to predict fault trends; using anomaly detection to identify novel faults; and establishing fault prediction models. Temporal feature mining specifically includes: analyzing the periodicity of faults; identifying the seasonality of faults; extracting the evolution patterns of fault development; predicting potential fault inflection points; and assessing the persistence characteristics of faults. Generate reference analysis data, specifically including: summarizing the statistical characteristics of fault patterns; outputting a probabilistic model for fault prediction; generating a decision tree for fault diagnosis; forming best practices for fault handling; and constructing a fault knowledge graph.

9. The 5G portable WiFi fault diagnosis and recovery method according to claim 8, characterized in that, The step of optimizing the intelligent diagnostic program and the recovery solution library based on the reference analysis data, the device information, the program attribute information, the solution library information, the network connection data, the system information, and the operation log includes: Evaluate the performance metrics of the existing system, specifically including: statistically analyzing the accuracy and recall of diagnostic procedures; calculating the success rate and efficiency of recovery plans; analyzing system response time and resource consumption; evaluating user feedback and satisfaction data; and generating a performance evaluation report. The intelligent diagnostic program is optimized, specifically including: updating the fault feature model based on reference analysis data; adjusting the weight parameters for fault identification; adding newly discovered fault modes; optimizing the decision logic of the diagnostic process; and updating the fault rule knowledge base. The upgrade of the recovery solution library includes: filtering efficient and reliable recovery solutions; removing inefficient or outdated solutions; adding new solutions; optimizing the execution order of solutions; and updating the applicable conditions for solutions. Performing adaptive optimization specifically includes: adjusting diagnostic parameters based on device characteristics; optimizing execution strategies based on the network environment; adjusting resource allocation according to system load; customizing solutions based on user scenarios; and achieving dynamic performance tuning. Verifying the optimization effect specifically includes: conducting offline testing; performing small-scale field trials; collecting optimized performance data; comparing the effects before and after optimization; and generating an optimization effect report.

10. A 5G portable WiFi fault diagnosis and recovery system, used to execute the 5G portable WiFi fault diagnosis and recovery method as described in any one of claims 1 to 9, characterized in that, Includes: a 5G portable WiFi device, a communication terminal connected to the 5G portable WiFi device, and an edge server; The 5G portable WiFi device is configured as follows: Collect network connection data, system information, and operation logs of the communication terminal from the communication terminal; The network connection data, system information, and operation log are analyzed using a preset intelligent diagnostic program to obtain a first analysis result; A fault diagnosis report is generated based on the first analysis results. The fault diagnosis report includes the fault type, fault severity, and possible fault causes. Based on the fault diagnosis report, select and execute the corresponding recovery operation from the pre-stored recovery plan library; During the recovery operation, the current device status and current network connection status of the 5G portable WiFi device are monitored in real time, and the recovery operation is judged to have successfully resolved the fault based on the current device status and current network connection status. If the recovery operation fails to resolve the fault, an advanced solution is provided, and the device information of the 5G portable WiFi device, the program attribute information of the intelligent diagnostic program, the solution library information of the recovery solution library, the network connection data, the system information, and the operation log are sent to the edge server. The edge server is configured as follows: Obtain fault data and diagnostic reports from multiple similar portable WiFi devices as reference data; The reference data is analyzed using big data analytics to uncover potential fault patterns and trends, resulting in reference analysis data. The intelligent diagnostic program and the recovery solution library are optimized based on the reference analysis data, the device information, the program attribute information, the solution library information, the network connection data, the system information, and the operation log.

Images