A 5G-based intelligent portable WiFi traffic monitoring method and system

Abstract

The application provides a 5G-based intelligent portable WiFi traffic monitoring method and system, which comprises the following steps: real-time capturing of data packets, extraction of traffic data when the data packets pass through the key nodes of the kernel protocol stack; transmission of the traffic data to the local edge computing node, processing by using a streaming processing framework, storage by using a data compression algorithm, and generation of a traffic data subset; identification by combining a traffic identification model, prewarning by the device when abnormal traffic is identified, and activation of a hierarchical traffic control mechanism to limit or block the abnormal traffic; allocation of an independent network slice for traffic monitoring to realize business isolation; encryption of the traffic data and identification results by using quantum encryption technology, and construction of a block chain ledger by using a distributed ledger technology; and fusion analysis of the environmental data of surrounding Internet of Things devices and the traffic data to dynamically adjust a traffic distribution strategy. The application not only improves the monitoring efficiency and resource utilization rate, but also improves the intelligence and security.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of 5G, in particular to a 5G-based intelligent personal WiFi traffic monitoring method and system. BACKGROUND

[0002] In recent years, 5G-based intelligent personal WiFi devices have gradually become popular, providing users with more convenient and high-speed network experience. 5G-based personal WiFi devices can provide faster data transmission speed than traditional 4G devices, with a theoretical downlink rate of 10 Gbps, and actual use of several hundred Mbps or even higher, easily supporting high-definition video playback, 4K live streaming and large file downloads; these devices are usually designed to be lightweight and portable, without the need for installation and wiring, providing WiFi signals anytime and anywhere; many 5G personal WiFi devices support large traffic packages, with monthly traffic up to 1500G or even more, meeting the user's long-term and high-traffic usage needs; most devices can connect to multiple devices at the same time, usually around 32, meeting the needs of multiple people or multiple devices accessing the Internet at the same time. The above characteristics of 5G personal WiFi devices also lead to the problem of abnormal traffic, and the existing intelligent personal WiFi traffic monitoring method does not perform well in monitoring efficiency, security protection, etc., and needs to be improved. SUMMARY

[0003] The present application is based on the above problems, and proposes a 5G-based intelligent personal WiFi traffic monitoring method and system. Through the present application, the monitoring efficiency and resource utilization are improved, and the intelligence and security are also improved.

[0004] Therefore, one aspect of the present application proposes a 5G-based intelligent personal WiFi traffic monitoring method, comprising:

[0005] A traffic statistics module is provided in the chipset of the first 5G intelligent personal WiFi device, which uses an adaptive sampling rate mechanism to capture data packets in real time; wherein the adaptive sampling rate mechanism dynamically adjusts the data packet capture frequency according to the network load state and traffic characteristics;

[0006] When the data packet flows through the kernel protocol stack key node, the traffic data including timestamp, source and destination IP address, port number, protocol type, data size is extracted;

[0007] The traffic data is transmitted to the edge computing node deployed locally on the first 5G intelligent personal WiFi device;

[0008] The flow data is cleaned in real time by using a flow processing framework to remove repeated, incorrect and invalid flow records, compressed and stored by using a data compression algorithm, and standardized by using a preset classification rule to generate a flow data subset;

[0009] A flow recognition result is obtained according to the flow data subset and a preset first flow recognition model;

[0010] When abnormal flow is identified, a warning message is sent through a plurality of user interfaces associated with the device, and a hierarchical flow control mechanism built in the first 5G smart portable WiFi device is activated to limit or block the abnormal flow;

[0011] Abnormal flow characteristics are extracted and fed back to the first flow recognition model for model optimization;

[0012] An independent network slice is allocated for flow monitoring to achieve business isolation, and slice configuration parameters are automatically adjusted based on a smart contract;

[0013] Flow data interconnection between different operators is realized through cross-chain interoperation mechanism;

[0014] The flow data, flow recognition result and warning record are encrypted by using quantum encryption technology, and the encrypted data is packaged into blocks by using distributed ledger technology to build a block chain ledger containing a timestamp, realizing data tamper-proofing;

[0015] The environment data of surrounding Internet of Things devices is collected, the environment data and flow data are fused for comprehensive analysis, and the flow distribution strategy is dynamically adjusted based on the analysis result.

[0016] Optionally, the step of capturing data packets in real time by using an adaptive sampling rate mechanism through the flow statistics module arranged in the chip set of the first 5G smart portable WiFi device, comprising:

[0017] The initialization configuration step includes: arranging a flow statistics module in the chip set of the first 5G smart portable WiFi device; configuring initial sampling rate parameters in the flow statistics module, including a reference sampling interval and a sampling window size; setting flow threshold values, including high load threshold values and low load threshold values; initializing a sampling rate adjustment factor and an adjustment step;

[0018] The network state monitoring step includes: monitoring the network interface state of the first 5G smart portable WiFi device in real time; obtaining the current network bandwidth utilization; detecting the data packet queue length; recording the network delay and packet loss rate;

[0019] The load assessment steps include: calculating network load metrics within the current time window; comparing the calculated load metrics with preset thresholds; determining whether the current network status is high load, normal load, or low load; and generating load assessment results.

[0020] The adaptive sampling rate adjustment steps include: dynamically calculating the optimal sampling rate based on the load assessment results; appropriately reducing the sampling rate to alleviate system pressure when the load is higher than the high load threshold; increasing the sampling rate to obtain more detailed traffic information when the load is lower than the low load threshold; and ensuring that the sampling rate adjustment is within the preset maximum and minimum range.

[0021] The packet capture steps include: setting a packet filter in the network interface driver layer; sampling the passing packets according to the current sampling rate; extracting the header information of the sampled packets; and recording the timestamp information of the packets.

[0022] The sampling optimization steps include: adopting differentiated sampling strategies for different types of network protocols; increasing the sampling priority for critical business traffic; adopting a predictive sampling mechanism for periodic traffic; and dynamically adjusting the sampling window size.

[0023] The resource monitoring steps include: monitoring the CPU utilization of the traffic statistics module; monitoring memory buffer usage; triggering protection mechanisms when system resources approach thresholds; and automatically adjusting sampling parameters to balance system load.

[0024] The sampling quality assessment steps include: calculating representativeness indicators of the sampling data; evaluating the accuracy of the sampling results; analyzing sampling bias; and generating a sampling quality report.

[0025] Optionally, the steps of using a streaming processing framework to clean the traffic data in real time, removing duplicate, erroneous, and invalid traffic records, compressing and storing the cleaned traffic data using a data compression algorithm, and standardizing the compressed traffic data according to preset classification rules to generate a subset of traffic data include:

[0026] The initialization steps for a streaming processing environment include: deploying the streaming processing framework on edge computing nodes; configuring data stream inlet and outlet nodes; setting the parallelism parameters of the data processing pipeline; and initializing the data buffer and processing queue.

[0027] The data stream access steps include: establishing a data transmission channel with the traffic statistics module; fragmenting the received traffic data and adding it to the processing queue; assigning a unique identifier to each data fragment; and recording the data access timestamp.

[0028] The real-time cleaning steps include: detecting and deleting duplicate data packet records: calculating the feature hash value of the data packet, using a sliding time window to determine duplicates, and retaining the earliest valid record; identifying and filtering erroneous data: verifying the integrity of the data packet, validating the legality of the protocol field, and checking the validity of the address format; and removing invalid traffic records: filtering timed-out data packets, deleting incomplete session records, and removing abnormally long data.

[0029] The data compression steps include: classifying and packaging the cleaned data: grouping by protocol type, batch processing by time series, and establishing a data index structure; performing multi-level compression: first performing field-level compression, then block-level compression, and finally applying global compression; generating compression metadata: recording compression algorithm parameters, saving information required for decompression, and establishing a compressed data index.

[0030] The standardized processing steps include: unifying data formats: standardizing timestamp formats, address representations, and protocol identifiers; normalizing numerical values: calculating statistical values ​​of traffic characteristics, performing minimum-maximum normalization, and applying Z-score standardization; and establishing a standardized mapping table: recording transformation parameters, saving normalization ranges, and maintaining feature mapping relationships.

[0031] The steps for generating traffic data subsets include: classifying data according to preset rules: dividing based on time dimension, grouping according to protocol type, and clustering according to business characteristics; building a data subset index: creating a multi-dimensional index structure, establishing a fast retrieval table, and generating subset association relationships; and optimizing the subset storage structure: implementing an incremental update mechanism, designing a caching strategy, and building a hierarchical storage structure.

[0032] The quality control steps include: real-time monitoring of processing quality: tracking data loss rate, monitoring processing latency, and evaluating compression efficiency; execution of anomaly handling: detecting processing anomalies, triggering recovery mechanisms, and recording anomaly logs; and generation of quality reports: statistically analyzing processing metrics, identifying performance bottlenecks, and providing optimization suggestions.

[0033] Optionally, the method for constructing the first traffic identification model includes:

[0034] The model initialization steps include: initializing the global model architecture on the central server, which includes a convolutional neural network module and a recurrent neural network module; the convolutional neural network module is used to extract spatial features of traffic data, including multiple convolutional layers, pooling layers and fully connected layers; the recurrent neural network module is used to extract temporal features of traffic data, including LSTM or GRU units; and distributing the initialized global model parameters to each 5G smart portable WiFi device participating in the training.

[0035] The local training steps include: training the model on each 5G smart portable WiFi device based on the local traffic dataset; using batch normalization to process the local data and eliminate differences in data distribution between devices; using differential privacy mechanism to protect the privacy of the training process; and calculating the gradient update values ​​of the local model parameters.

[0036] The parameter aggregation step includes: each 5G smart portable WiFi device encrypts and transmits the calculated gradient update value to the central server; the central server aggregates the gradient update values ​​of all devices using a weighted average algorithm; updates the global model parameters; and distributes the updated global model parameters to each participating device.

[0037] The model optimization steps include: setting a dynamic learning rate adjustment mechanism to adaptively adjust the learning rate according to the training progress; introducing an early stopping mechanism to stop training when the model performance no longer improves significantly; using Dropout technology to prevent model overfitting; and using residual connections to optimize gradient propagation.

[0038] The model evaluation steps include: evaluating model performance on a validation dataset; calculating several evaluation metrics such as accuracy, recall, and F1 score; generating a confusion matrix to analyze the model's prediction performance; determining whether further training is needed based on the evaluation results; and obtaining the first traffic identification model.

[0039] The anomaly detection steps include: inputting real-time traffic data into a trained model; extracting spatial features using a convolutional neural network; analyzing temporal patterns using a recurrent neural network; and fusing the two types of features to determine abnormal traffic.

[0040] The model deployment steps include: converting the trained model into a lightweight format; deploying it to various 5G smart portable WiFi devices; configuring model inference parameters; and starting the online anomaly detection service.

[0041] Optionally, the step of issuing warning information through multiple user interfaces associated with the device when abnormal traffic is detected, and simultaneously activating the built-in hierarchical traffic control mechanism of the first 5G smart portable WiFi device to limit or block the abnormal traffic, includes:

[0042] The abnormal traffic feature extraction steps include: acquiring abnormal traffic data identified by the deep learning model; extracting key feature parameters of the abnormal traffic: traffic surge magnitude and duration, number of abnormal connections and port usage, and packet content characteristics; determining the severity level of the abnormal traffic; and generating an abnormal feature description report.

[0043] The steps for generating early warning information include: constructing an early warning information template based on the anomaly level; integrating the specific manifestations of abnormal traffic: anomaly type description, impact scope assessment, and potential risk analysis; generating early warning recommended measures; and adding timestamps and unique identifiers.

[0044] The multi-interface early warning push steps include: Device display push: displaying an early warning icon, outputting a warning sound, and triggering indicator light flashing; Mobile APP notification: sending push notifications, updating the APP interface status, and displaying detailed abnormal information; Web management interface prompt: updating the dashboard status, displaying early warning pop-ups, and providing detailed log viewing.

[0045] The initialization steps of the hierarchical flow control mechanism include: establishing a flow control policy table: defining control level thresholds, setting control action types, and configuring control duration; and initializing the flow control module: loading control rules, setting priority order, and preparing control resources.

[0046] Traffic control execution steps include: Minor anomaly handling: limiting bandwidth of suspicious IPs, reducing the priority of abnormal traffic, and logging abnormal behavior; Moderate anomaly handling: blocking traffic on specific ports, limiting traffic of suspicious protocols, and initiating traffic redirection; Severe anomaly handling: disconnecting abnormal connections, blocking related IP ranges, and activating emergency response mechanisms.

[0047] The steps for evaluating the effectiveness of control measures include: monitoring traffic changes after control: analyzing the downward trend of traffic, assessing bandwidth recovery, and checking whether the anomaly has been eliminated; recording the effectiveness of control measures: statistically analyzing the blocking success rate, calculating response latency, and assessing the possibility of misjudgment; and generating a control effectiveness report.

[0048] The adaptive optimization steps include: dynamically adjusting the strategy based on the control effect: updating control rules, optimizing threshold settings, and adjusting control intensity; and optimizing the early warning mechanism: improving the content of early warning information, adjusting the push frequency, and optimizing the display method.

[0049] Optionally, the step of allocating independent network slices for traffic monitoring to achieve service isolation and automatically adjusting slice configuration parameters based on smart contracts includes:

[0050] The network slicing initialization steps include: creating a dedicated network slice for traffic monitoring in the 5G core network: allocating slice identifiers, setting slice priorities, and defining slice resource quotas; configuring slice isolation parameters: setting resource isolation levels, configuring service isolation policies, and establishing security isolation mechanisms; and initializing basic quality of service parameters: configuring bandwidth limits, setting latency requirements, and defining reliability indicators.

[0051] The smart contract deployment steps include: deploying the slice management smart contract in the blockchain network: writing contract code, setting trigger conditions, and defining execution rules; initializing contract parameters: configuring adjustment thresholds, setting decision rules, and defining reward and punishment mechanisms; and establishing the contract call interface: configuring interface permissions, setting call methods, and defining data formats.

[0052] The slice monitoring steps include: real-time collection of slice performance indicators: monitoring resource utilization, recording service quality parameters, and statistical analysis of business traffic; analysis of slice operation status: evaluating performance trends, detecting anomalies, and predicting resource requirements; and generation of monitoring reports: summarizing performance data, marking abnormal events, and calculating health indicators.

[0053] The smart contract triggering steps include: checking triggering conditions: determining performance thresholds, verifying time conditions, and confirming triggering permissions; collecting decision information: acquiring historical data, analyzing the current state, and predicting future trends; and executing contract logic: calculating adjustment plans, verifying feasibility, and recording the execution process.

[0054] The steps for adjusting slice parameters include: generating adjustment instructions: determining the adjustment items, calculating the adjustment range, and setting the execution time; executing parameter updates: modifying bandwidth configuration, adjusting priority settings, and updating resource quotas; and verifying the adjustment effect: checking that the parameters are effective, monitoring performance changes, and evaluating the impact of the adjustment.

[0055] The business migration steps include: preparing the migration environment: assessing the target slice capacity, planning the migration path, and preparing a rollback plan; executing the business migration: establishing data channels, transferring business traffic, and synchronizing status information; and verifying the migration results: checking business continuity, confirming data integrity, and evaluating service quality.

[0056] Continuous optimization steps include: collecting optimization data: statistically analyzing the effects of adjustments, evaluating performance improvements, and recording feedback on issues; updating smart contracts: optimizing decision-making rules, adjusting triggering conditions, and improving execution logic; and improving management strategies: optimizing resource allocation, updating isolation strategies, and improving security mechanisms.

[0057] Optionally, the step of achieving traffic data interoperability between different operators through a cross-chain interoperability mechanism includes:

[0058] The cross-chain network initialization steps include: deploying cross-chain protocols on each operator node: configuring consensus mechanisms, setting communication protocols, and initializing key pairs; establishing cross-chain gateways: deploying gateway nodes, configuring routing rules, and setting security policies; and initializing inter-chain communication channels: establishing P2P connections, configuring transmission protocols, and setting bandwidth parameters.

[0059] Data standardization steps include: establishing cross-chain data format specifications: defining data structures, standardizing field naming, and setting data types; establishing data mapping relationships: configuring field mappings, setting conversion rules, and defining verification methods; and implementing data format conversion: processing data encoding, converting data formats, and verifying conversion results.

[0060] The identity authentication steps include: deploying a distributed identity system: generating identity identifiers, configuring permission levels, and setting authentication rules; achieving multi-chain identity mutual recognition: exchanging identity credentials, verifying identity validity, and establishing trust relationships; and managing access permissions: setting access policies, controlling data permissions, and recording access logs.

[0061] The cross-chain data transfer steps include: initiating a data transfer request: constructing a transfer request, signing the request data, and selecting a target chain; executing the cross-chain transfer: verifying the legality of the request, encrypting the data packet, and transferring the data content; and confirming data reception: verifying data integrity, sending confirmation information, and recording the transfer status.

[0062] The steps for maintaining data consistency include: achieving atomic operations: setting transaction boundaries, defining rollback mechanisms, and ensuring operation integrity; maintaining data consistency: synchronizing data states, handling conflicts, and keeping data synchronized; and managing version control: recording version information, tracking data changes, and maintaining update history.

[0063] The steps for cross-chain smart contract calls include: Deploying the cross-chain contract: writing contract code, setting call rules, and configuring the execution environment; Implementing contract interoperability: defining interface specifications, implementing call methods, and handling return results; Managing contract state: synchronizing contract state, handling execution exceptions, and recording call logs.

[0064] Performance optimization steps include: optimizing transmission efficiency: implementing data fragmentation, compressing transmission content, and optimizing routing; improving processing performance: processing requests in parallel, optimizing query efficiency, and implementing caching mechanisms; and monitoring system performance: collecting performance metrics, analyzing bottlenecks, and optimizing system configuration.

[0065] Optionally, the step of encrypting the traffic data, the traffic identification result, and the early warning record using quantum encryption technology, and packaging the encrypted data into blocks using distributed ledger technology to construct a blockchain ledger containing timestamps to achieve data tamper-proofing includes:

[0066] The quantum key distribution steps include: initializing the quantum key distribution system: configuring quantum communication equipment, establishing a quantum channel, and setting key generation parameters; performing quantum key negotiation: generating a sequence of qubits, measuring quantum states, and performing basis vector verification; and generating a shared key: performing error correction coding, refining the key, and verifying the key's availability.

[0067] The data preprocessing steps include: organizing raw data: classifying traffic data, integrating traffic identification results, and summarizing early warning records; building data structure: defining data format, setting field attributes, and establishing index relationships; generating data summary: calculating hash values, adding timestamps, and recording data sources.

[0068] The quantum encryption steps include: encrypting data based on quantum keys: selecting an encryption algorithm, encrypting data in blocks, and generating ciphertext; performing integrity protection: calculating an authentication code, adding verification information, and generating a signature; and managing key status: updating key usage status, recording key version, and setting key validity period.

[0069] The block construction steps include: packaging encrypted data: organizing the block structure, setting the block header, and adding transaction content; generating block identifiers: calculating the block hash, linking previous blocks, and recording the block height; and adding time proofs: obtaining a trusted timestamp, signing the time proof, and verifying the time validity.

[0070] The consensus verification steps include: initiating a consensus request: broadcasting block information, submitting a verification request, and waiting for node responses; executing the consensus process: verifying block validity, checking data integrity, and confirming the time sequence; and reaching a consensus result: collecting verification results, tallying consensus votes, and confirming the block status.

[0071] Ledger maintenance steps include: updating the blockchain state: adding new blocks, updating link relationships, and maintaining the state tree; managing the data index: creating a search table, updating the index structure, and optimizing query performance; and performing ledger synchronization: broadcasting update information, synchronizing block data, and verifying synchronization results.

[0072] The audit traceability steps include: providing a query interface: designing a query language, implementing retrieval methods, and configuring access permissions; supporting proof generation: constructing proof paths, generating verification proofs, and providing audit reports; and maintaining historical records: recording operation logs, saving status snapshots, and supporting version backtracking.

[0073] Optionally, the step of collecting environmental data from surrounding IoT devices, integrating environmental data with traffic data for comprehensive analysis, and dynamically adjusting the traffic allocation strategy based on the analysis results includes:

[0074] Collect environmental data from nearby IoT devices;

[0075] Collect network traffic data, including user access volume, data transmission rate, and latency;

[0076] The collected environmental data and traffic data are merged to form a comprehensive dataset;

[0077] A comprehensive analysis of the dataset was conducted, and data analysis algorithms were used to identify the relationship between environmental factors and traffic changes.

[0078] Based on the results of comprehensive analysis, dynamically adjust the traffic allocation strategy;

[0079] Implement the adjusted traffic allocation strategy and continuously monitor its effectiveness. Based on real-time feedback, optimize the traffic allocation strategy to adapt to the ever-changing environment and user needs.

[0080] Another aspect of the present invention provides a 5G-based intelligent portable WiFi traffic monitoring system for executing a 5G-based intelligent portable WiFi traffic monitoring method, characterized in that it includes: a first 5G intelligent portable WiFi device equipped with a traffic statistics module, an edge computing node, and a server;

[0081] The traffic statistics module located within the chipset of the first 5G smart portable WiFi device is configured as follows:

[0082] An adaptive sampling rate mechanism is used to capture data packets in real time; wherein, the adaptive sampling rate mechanism dynamically adjusts the data packet capture frequency according to the network load status and traffic characteristics;

[0083] When data packets flow through key nodes of the kernel protocol stack, traffic data including timestamps, source and destination IP addresses, port numbers, protocol types, and data size are extracted.

[0084] The traffic data is transmitted to the edge computing node deployed locally on the first 5G smart portable WiFi device;

[0085] The edge computing node is configured as follows:

[0086] The streaming data is cleaned in real time using a streaming processing framework to remove duplicate, erroneous and invalid data records. The cleaned data is compressed and stored using a data compression algorithm. The compressed data is then standardized according to a preset classification rule to generate a subset of the data.

[0087] Based on the subset of traffic data and the preset first traffic identification model, the traffic identification result is obtained;

[0088] When abnormal traffic is detected, warning messages are issued through multiple user interfaces associated with the device, and the built-in hierarchical traffic control mechanism of the first 5G smart portable WiFi device is activated to restrict or block the abnormal traffic.

[0089] Abnormal traffic features are extracted and fed back to the first traffic identification model for model optimization.

[0090] Allocate independent network slices for traffic monitoring to achieve service isolation, and automatically adjust slice configuration parameters based on smart contracts;

[0091] Achieve data interoperability between different operators through cross-chain interoperability mechanisms;

[0092] The traffic data, traffic identification results, and early warning records are encrypted using quantum encryption technology, and distributed ledger technology is used to package the encrypted data into blocks to construct a blockchain ledger containing timestamps, thereby achieving data tamper-proofing.

[0093] Collect environmental data from surrounding IoT devices, integrate environmental data with traffic data for comprehensive analysis, and dynamically adjust traffic allocation strategies based on the analysis results.

[0094] The present invention provides a 5G-based intelligent portable WiFi traffic monitoring method, comprising: capturing data packets in real time using an adaptive sampling rate mechanism via a traffic statistics module installed in the chipset of a first 5G intelligent portable WiFi device; wherein the adaptive sampling rate mechanism dynamically adjusts the data packet capture frequency according to network load status and traffic characteristics; extracting traffic data, including timestamp, source and destination IP addresses, port numbers, protocol types, and data size, when the data packets flow through key nodes of the kernel protocol stack; transmitting the traffic data to an edge computing node deployed locally on the first 5G intelligent portable WiFi device; performing real-time cleaning of the traffic data using a streaming processing framework to remove duplicate, erroneous, and invalid traffic records; compressing and storing the cleaned traffic data using a data compression algorithm; and standardizing the compressed traffic data according to preset classification rules to generate a traffic data subset; and then, based on the traffic data subset... The system integrates a pre-defined first traffic identification model to obtain traffic identification results. When abnormal traffic is identified, it issues warning messages through multiple user interfaces associated with the device, and simultaneously activates the built-in hierarchical traffic control mechanism of the first 5G smart portable WiFi device to restrict or block abnormal traffic. Abnormal traffic features are extracted and fed back to the first traffic identification model for model optimization. Independent network slices are allocated for traffic monitoring to achieve service isolation, and slice configuration parameters are automatically adjusted based on smart contracts. Traffic data interoperability between different operators is achieved through a cross-chain interoperability mechanism. The traffic data, traffic identification results, and warning records are encrypted using quantum encryption technology, and the encrypted data is packaged into blocks using distributed ledger technology to construct a blockchain ledger containing timestamps, achieving data tamper-proofing. Environmental data from surrounding IoT devices is collected, and environmental data is integrated with traffic data for comprehensive analysis. Based on the analysis results, the traffic allocation strategy is dynamically adjusted. Adaptive sampling and federated learning improve the accuracy of traffic monitoring, enabling multi-device collaborative learning, enhancing anomaly detection efficiency, and supporting intelligent traffic management and resource allocation. Streaming processing and data compression reduce system overhead, edge computing architecture reduces data transmission latency, and network slicing technology ensures monitoring service quality. Quantum encryption protects data security, blockchain technology ensures data immutability, and multi-layered anomaly protection mechanisms enhance network security. Cross-chain interoperability supports a wider range of business scenarios, and IoT collaboration enables more comprehensive monitoring. Attached Figure Description

[0095] Fig. 1 This is a flowchart of a 5G-based intelligent portable WiFi traffic monitoring method provided in one embodiment of the present invention;

[0096] Fig. 2 This is a schematic block diagram of a 5G-based intelligent portable WiFi traffic monitoring system provided in one embodiment of the present invention. Detailed Implementation

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] The following reference Figs. 1-2 This invention describes a 5G-based smart portable WiFi traffic monitoring method and system provided by some embodiments of the present invention.

[0102] like Fig. 1 As shown, one embodiment of the present invention provides a 5G-based intelligent portable WiFi traffic monitoring method, including:

[0103] By using a traffic statistics module located within the chipset of the first 5G smart portable WiFi device, data packets are captured in real time using an adaptive sampling rate mechanism; wherein, the adaptive sampling rate mechanism dynamically adjusts the data packet capture frequency according to network load status and traffic characteristics.

[0104] When data packets flow through key nodes of the kernel protocol stack, traffic data including timestamps, source and destination IP addresses, port numbers, protocol types, and data size are extracted.

[0105] Understandably, in this step, the first 5G smart portable WiFi device activates a packet capture module to ensure that the device can monitor all data packets flowing through the kernel protocol stack; it identifies key nodes in the kernel protocol stack, such as the network interface layer, transport layer, and application layer, and ensures that data packets are extracted at these nodes; it monitors the flow of data packets through the kernel network module to ensure that data is extracted in a timely manner when data packets pass through key nodes; when data packets pass through key nodes, it extracts the following traffic data: timestamp (recording the time when the data packet arrives at the key node), source IP address (the source IP address of the extracted data packet), destination IP address (the destination IP address of the extracted data packet), source port number (the source port number of the extracted data packet), destination port number (the destination port number of the extracted data packet), protocol type (identifying the transport protocol used by the data packet (such as TCP, UDP, etc.)), and data size (calculating the size of the data packet (in bytes)); it stores the extracted traffic data in a local database or sends it to an edge computing node for further processing and analysis for subsequent traffic monitoring and anomaly detection; it implements a real-time monitoring mechanism, periodically checks the extracted data, generates traffic reports, and dynamically adjusts and optimizes based on traffic characteristics. This step extracts traffic data from key nodes in the kernel protocol stack, enabling comprehensive acquisition of crucial packet information and providing a rich data foundation for subsequent traffic analysis. Extracted timestamps, IP addresses, port numbers, and other information help analyze traffic patterns, distinguish between normal and abnormal traffic, and improve the accuracy of traffic analysis. Real-time monitoring and data extraction allow for the timely detection of abnormal traffic and potential security threats, enhancing network security. Furthermore, analysis of traffic data identifies network bottlenecks and performance issues, enabling optimization and improving overall network performance and user experience.

[0106] The traffic data is transmitted to the edge computing node deployed locally on the first 5G smart portable WiFi device;

[0107] Understandably, in this step, after the traffic data extraction is completed, it is ensured that the extracted data (including timestamps, source and destination IP addresses, port numbers, protocol types, data size, etc.) has undergone preliminary processing and meets the transmission format requirements. In the first 5G smart portable WiFi device, the communication module with the edge computing node is activated to establish a reliable network connection. The stability and security of the communication channel are ensured for subsequent data transmission. The prepared traffic data is packaged using an appropriate data format (such as JSON, XML, etc.) for parsing and processing at the edge computing node. The packaged traffic data is sent to the edge computing node through the established communication channel (this process can use TCP / UDP protocols for data transmission to ensure data integrity and accuracy). After receiving the data, the edge computing node sends an acknowledgment message back to the first 5G smart portable WiFi device to ensure successful data transmission. If no acknowledgment message is received, the data is retransmitted. After receiving the traffic data, the edge computing node stores and further processes it, including data cleaning, analysis, and storage, for subsequent traffic monitoring and anomaly detection. This step enables real-time data processing and analysis by transmitting traffic data to edge computing nodes, improving system response speed. Processing data on local edge computing nodes reduces latency in data transmission to remote servers, improving overall system efficiency. Local data processing reduces the risk of data leakage during transmission, enhancing data security. Edge computing nodes can make intelligent decisions and allocate resources based on real-time traffic data, optimizing network resource usage and improving network performance.

[0108] The streaming data is cleaned in real time using a streaming processing framework to remove duplicate, erroneous and invalid data records. The cleaned data is compressed and stored using a data compression algorithm. The compressed data is then standardized according to a preset classification rule to generate a subset of the data.

[0109] Based on the traffic data subset and the preset first traffic identification model (a distributed deep learning model based on a federated learning framework, which integrates convolutional neural networks and recurrent neural networks), the traffic identification result is obtained;

[0110] Understandably, in this step, a cleaned and standardized subset of traffic data is extracted from the storage system to ensure that the data format matches the input requirements of the first traffic identification model. Under the federated learning framework, a pre-defined first traffic identification model, which combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs), is loaded for traffic identification. Necessary preprocessing is performed on the extracted traffic data subset, including feature extraction (using CNNs to extract features from the traffic data and identify key features) and sequence processing (using RNNs to process the extracted feature sequences to capture temporal information in the traffic data). The preprocessed data is then input into the loaded traffic identification model for inference calculations to obtain the traffic identification results. This process should ensure the model's inference efficiency and accuracy. The traffic identification results output by the model are analyzed to evaluate the accuracy and effectiveness of the identification. Subsequent result optimization or model parameter adjustments can be performed as needed. The traffic identification results are stored in a database for subsequent querying and analysis. Simultaneously, the identification results are fed back to the federated learning framework for continuous model optimization and updates. This step combines CNN and RNN model architectures to effectively extract spatial and temporal features from traffic data, thereby improving the accuracy of traffic identification. The distributed deep learning model based on the federated learning framework can share learning results among different data sources, enhancing the model's adaptability to new traffic patterns. Through the federated learning mechanism, data is processed locally, avoiding centralized data storage and transmission, and enhancing data privacy protection. The rapid traffic identification capability enables the system to monitor network traffic in real time and promptly detect abnormal traffic and potential security threats.

[0111] When abnormal traffic is detected, warning messages are issued through multiple user interfaces associated with the device, and the built-in hierarchical traffic control mechanism of the first 5G smart portable WiFi device is activated to restrict or block the abnormal traffic.

[0112] Abnormal traffic features are extracted and fed back to the first traffic identification model for model optimization.

[0113] Understandably, after identifying abnormal traffic, the first step is to extract features from the traffic. These extracted features should include key traffic attributes such as source, destination, packet size, protocol type, and timestamp. The extracted abnormal traffic features are then formatted to ensure they meet the input requirements of the first traffic identification model (this may include data type conversion and feature standardization to facilitate model processing). A feedback mechanism is established to transmit the formatted abnormal traffic feature data to the first traffic identification model (this process can be achieved through API calls or direct data transmission to ensure data timeliness and accuracy). Upon receiving the feedback abnormal traffic features, the first traffic identification model receives and stores the data. The model will then use these new features for training to optimize its identification capabilities. Upon receiving new feature data... Next, the model training process is initiated. By using these feature data, the model will adjust its parameters to improve the accuracy and efficiency of identifying abnormal traffic. After training is complete, the model is validated and evaluated. The optimized model is tested using a test set to assess its performance improvement in identifying abnormal traffic. This step feeds abnormal traffic features back to the traffic identification model, enabling it to learn new traffic patterns and improve its identification accuracy. The model can self-optimize based on constantly changing network environments and traffic characteristics, enhancing its adaptability to new types of abnormal traffic. Through continuous feature feedback and model updates, the traffic identification model is ensured to always remain in optimal condition, capable of responding to new security threats in real time. The optimized model can more effectively identify and respond to abnormal traffic, improving the overall network security and stability.

[0114] Allocate independent network slices for traffic monitoring to achieve service isolation, and automatically adjust slice configuration parameters based on smart contracts;

[0115] Achieve data interoperability between different operators through cross-chain interoperability mechanisms;

[0116] The traffic data, traffic identification results, and early warning records are encrypted using quantum encryption technology, and distributed ledger technology is used to package the encrypted data into blocks to construct a blockchain ledger containing timestamps, thereby achieving data tamper-proofing.

[0117] Collect environmental data from surrounding IoT devices, integrate environmental data with traffic data for comprehensive analysis, and dynamically adjust traffic allocation strategies based on the analysis results.

[0118] This invention improves the accuracy of traffic monitoring through adaptive sampling and federated learning, enables multi-device collaborative learning, enhances anomaly detection efficiency, and supports intelligent traffic management and resource allocation. It reduces system overhead through streaming processing and data compression, reduces data transmission latency through edge computing architecture, and ensures monitoring service quality through network slicing technology. Quantum encryption protects data security, blockchain technology ensures data immutability, and a multi-layered anomaly protection mechanism enhances network security. Cross-chain interoperability supports a wider range of business scenarios, and IoT collaboration enables more comprehensive monitoring.

[0119] In some possible embodiments of the present invention, visualization and interaction steps are also included, specifically: generating a 3D dynamic traffic visualization interface using image processing technology; integrating a voice recognition module to support voice command query and control; and displaying the specific causes of abnormal traffic through an interpretability module. In this solution, multimodal interaction improves system usability, visualization enhances data comprehension, and interpretability design increases user trust.

[0120] In some possible embodiments of the present invention, a continuous optimization step is also included, specifically comprising: periodically collecting user feedback and new network attack characteristics, using data analysis techniques to evaluate the effectiveness of existing monitoring, and updating model parameters and monitoring strategies based on the evaluation results. This continuous optimization mechanism ensures the long-term performance of the system.

[0121] In some possible embodiments of the present invention, the step of capturing data packets in real time using an adaptive sampling rate mechanism through a traffic statistics module disposed within the chipset of the first 5G smart portable WiFi device includes:

[0122] The initialization configuration steps include: setting a traffic statistics module in the chipset of the first 5G smart portable WiFi device; configuring initial sampling rate parameters in the traffic statistics module, including the baseline sampling interval and the sampling window size; setting traffic thresholds, including high load thresholds and low load thresholds; and initializing the sampling rate adjustment factor and adjustment step size.

[0123] The network status monitoring steps include: real-time monitoring of the network interface status of the first 5G smart portable WiFi device; obtaining the current network bandwidth utilization; detecting the data packet queue length; and recording network latency and packet loss rate.

[0124] The load assessment steps include: calculating network load metrics within the current time window; comparing the calculated load metrics with preset thresholds; determining whether the current network status is high load, normal load, or low load; and generating load assessment results.

[0125] The adaptive sampling rate adjustment steps include: dynamically calculating the optimal sampling rate based on the load assessment results; appropriately reducing the sampling rate to alleviate system pressure when the load is higher than the high load threshold; increasing the sampling rate to obtain more detailed traffic information when the load is lower than the low load threshold; and ensuring that the sampling rate adjustment is within the preset maximum and minimum range.

[0126] The packet capture steps include: setting a packet filter in the network interface driver layer; sampling the passing packets according to the current sampling rate; extracting the header information of the sampled packets; and recording the timestamp information of the packets.

[0127] The sampling optimization steps include: adopting differentiated sampling strategies for different types of network protocols; increasing the sampling priority for critical business traffic; adopting a predictive sampling mechanism for periodic traffic; and dynamically adjusting the sampling window size.

[0128] The resource monitoring steps include: monitoring the CPU utilization of the traffic statistics module; monitoring memory buffer usage; triggering protection mechanisms when system resources approach thresholds; and automatically adjusting sampling parameters to balance system load.

[0129] The sampling quality assessment steps include: calculating representativeness indicators of the sampling data; evaluating the accuracy of the sampling results; analyzing sampling bias; and generating a sampling quality report.

[0130] The solution in this embodiment adjusts the sampling strategy in real time according to the network load, avoiding resource waste or data loss caused by a fixed sampling rate, and achieving a dynamic balance between the sampling rate and the network status; it reduces system resource consumption, optimizes packet processing efficiency, and reduces unnecessary data storage; it ensures the representativeness of the sampled data, improves the accuracy of traffic statistics, and supports fine-grained traffic analysis; it optimizes system resource allocation, avoids performance bottlenecks, and improves the overall operating efficiency of the device; it supports multi-protocol traffic monitoring, adapts to different network environments, and facilitates functional expansion and optimization.

[0131] In some possible embodiments of the present invention, the steps of using a streaming processing framework to clean the traffic data in real time, removing duplicate, erroneous, and invalid traffic records, compressing and storing the cleaned traffic data using a data compression algorithm, and standardizing the compressed traffic data according to a preset classification rule to generate a subset of traffic data include:

[0132] The initialization steps for a streaming processing environment include: deploying the streaming processing framework on edge computing nodes; configuring data stream inlet and outlet nodes; setting the parallelism parameters of the data processing pipeline; and initializing the data buffer and processing queue.

[0133] The data stream access steps include: establishing a data transmission channel with the traffic statistics module; fragmenting the received traffic data and adding it to the processing queue; assigning a unique identifier to each data fragment; and recording the data access timestamp.

[0134] The real-time cleaning steps include: detecting and deleting duplicate data packet records: calculating the feature hash value of the data packet, using a sliding time window to determine duplicates, and retaining the earliest valid record; identifying and filtering erroneous data: verifying the integrity of the data packet, validating the legality of the protocol field, and checking the validity of the address format; and removing invalid traffic records: filtering timed-out data packets, deleting incomplete session records, and removing abnormally long data.

[0135] The data compression steps include: classifying and packaging the cleaned data: grouping by protocol type, batch processing by time series, and establishing a data index structure; performing multi-level compression: first performing field-level compression, then block-level compression, and finally applying global compression; generating compression metadata: recording compression algorithm parameters, saving information required for decompression, and establishing a compressed data index.

[0136] The standardized processing steps include: unifying data formats: standardizing timestamp formats, address representations, and protocol identifiers; normalizing numerical values: calculating statistical values ​​of traffic characteristics, performing minimum-maximum normalization, and applying Z-score standardization; and establishing a standardized mapping table: recording transformation parameters, saving normalization ranges, and maintaining feature mapping relationships.

[0137] The steps for generating traffic data subsets include: classifying data according to preset rules: dividing based on time dimension, grouping according to protocol type, and clustering according to business characteristics; building a data subset index: creating a multi-dimensional index structure, establishing a fast retrieval table, and generating subset association relationships; and optimizing the subset storage structure: implementing an incremental update mechanism, designing a caching strategy, and building a hierarchical storage structure.

[0138] The quality control steps include: real-time monitoring of processing quality: tracking data loss rate, monitoring processing latency, and evaluating compression efficiency; execution of anomaly handling: detecting processing anomalies, triggering recovery mechanisms, and recording anomaly logs; and generation of quality reports: statistically analyzing processing metrics, identifying performance bottlenecks, and providing optimization suggestions.

[0139] The solution in this embodiment achieves real-time data cleaning through streaming processing, significantly reduces storage space through multi-level compression strategies, and improves system throughput through parallel processing. It effectively removes duplicate and erroneous data, ensures data consistency through standardized processing, and improves data availability through categorized storage. It also reduces storage space usage, lowers data transmission load, and improves query and retrieval efficiency.

[0140] In some possible embodiments of the present invention, the method for constructing the first traffic identification model includes:

[0141] The model initialization steps include: initializing the global model architecture on the central server, which includes a convolutional neural network module and a recurrent neural network module; the convolutional neural network module is used to extract spatial features of traffic data, including multiple convolutional layers, pooling layers and fully connected layers; the recurrent neural network module is used to extract temporal features of traffic data, including LSTM or GRU units; and distributing the initialized global model parameters to each 5G smart portable WiFi device participating in the training.

[0142] The local training steps include: training the model on each 5G smart portable WiFi device based on the local traffic dataset; using batch normalization to process the local data and eliminate differences in data distribution between devices; using differential privacy mechanism to protect the privacy of the training process; and calculating the gradient update values ​​of the local model parameters.

[0143] The parameter aggregation step includes: each 5G smart portable WiFi device encrypts and transmits the calculated gradient update value to the central server; the central server aggregates the gradient update values ​​of all devices using a weighted average algorithm; updates the global model parameters; and distributes the updated global model parameters to each participating device.

[0144] The model optimization steps include: setting a dynamic learning rate adjustment mechanism to adaptively adjust the learning rate according to the training progress; introducing an early stopping mechanism to stop training when the model performance no longer improves significantly; using Dropout technology to prevent model overfitting; and using residual connections to optimize gradient propagation.

[0145] The model evaluation steps include: evaluating model performance on a validation dataset; calculating several evaluation metrics such as accuracy, recall, and F1 score; generating a confusion matrix to analyze the model's prediction performance; determining whether further training is needed based on the evaluation results; and obtaining the first traffic identification model.

[0146] The anomaly detection steps include: inputting real-time traffic data into a trained model; extracting spatial features using a convolutional neural network; analyzing temporal patterns using a recurrent neural network; and fusing the two types of features to determine abnormal traffic.

[0147] The model deployment steps include: converting the trained model into a lightweight format; deploying it to various 5G smart portable WiFi devices; configuring model inference parameters; and starting the online anomaly detection service.

[0148] The solution in this embodiment enables collaborative learning between devices, making full use of distributed data resources; protects user privacy, as raw data does not need to leave the local device; reduces the computational load and storage pressure on individual devices; the combination of spatial and temporal features improves anomaly detection accuracy, while dynamic learning rate and early stopping mechanism optimize model convergence; residual connections and Dropout technology enhance model generalization ability; supports the dynamic addition of new participating devices, allowing the model to be continuously optimized and updated to adapt to traffic characteristics in different scenarios; lightweight model deployment reduces device resource consumption, batch training improves computational efficiency, and the optimized parameter aggregation mechanism reduces communication overhead; differential privacy protects user data security, encrypted transmission ensures the security of the model update process, and the distributed architecture enhances the system's fault tolerance.

[0149] In some possible embodiments of the present invention, the step of issuing warning information through multiple user interfaces associated with the device when abnormal traffic is identified, and simultaneously activating the hierarchical traffic control mechanism built into the first 5G smart portable WiFi device to limit or block the abnormal traffic, includes:

[0150] The abnormal traffic feature extraction steps include: acquiring abnormal traffic data identified by the deep learning model; extracting key feature parameters of the abnormal traffic: traffic surge magnitude and duration, number of abnormal connections and port usage, and packet content characteristics; determining the severity level of the abnormal traffic; and generating an abnormal feature description report.

[0151] It is understood that, in this embodiment of the invention, historical traffic data can be analyzed, and the severity of abnormal traffic can be classified into mild, moderate, and severe anomalies based on the analysis results. Of course, the severity of abnormal traffic can also be classified into other types using other methods, and the implementation of this invention does not limit this.

[0152] The steps for generating early warning information include: constructing an early warning information template based on the anomaly level; integrating the specific manifestations of abnormal traffic: anomaly type description, impact scope assessment, and potential risk analysis; generating early warning recommended measures; and adding timestamps and unique identifiers.

[0153] The multi-interface early warning push steps include: Device display push: displaying an early warning icon, outputting a warning sound, and triggering indicator light flashing; Mobile APP notification: sending push notifications, updating the APP interface status, and displaying detailed abnormal information; Web management interface prompt: updating the dashboard status, displaying early warning pop-ups, and providing detailed log viewing.

[0154] The initialization steps of the hierarchical flow control mechanism include: establishing a flow control policy table: defining control level thresholds, setting control action types, and configuring control duration; and initializing the flow control module: loading control rules, setting priority order, and preparing control resources.

[0155] Traffic control execution steps include: Minor anomaly handling: limiting bandwidth of suspicious IPs, reducing the priority of abnormal traffic, and logging abnormal behavior; Moderate anomaly handling: blocking traffic on specific ports, limiting traffic of suspicious protocols, and initiating traffic redirection; Severe anomaly handling: disconnecting abnormal connections, blocking related IP ranges, and activating emergency response mechanisms.

[0156] Understandably, a suspicious IP refers to an IP address that exhibits abnormal or potentially threatening network activity. Its characteristics include, but are not limited to: frequent login failures (multiple failed login attempts from the same IP address may indicate a brute-force attack); abnormal data traffic (significantly higher traffic than normal for this IP address, potentially involving data breaches or DDoS attacks); communication with known malicious addresses (communication records between this IP address and known malicious IP addresses may indicate involvement in malicious activities); use of uncommon ports or protocols (a suspicious IP may use uncommon ports or protocols for communication, which could be characteristic of attackers); and so on. A suspicious protocol refers to a protocol that exhibits abnormal or potentially threatening behavior in network communication. Its characteristics include, but are not limited to: use of outdated or insecure protocols (such as older protocols like POP3, IMAP, and SMTP, which may be exploited by attackers for password spraying attacks); abnormal protocol usage patterns (e.g., a protocol is frequently used within unusual timeframes or invoked without normal business logic); association with a suspicious IP (if the use of a protocol is combined with the activity of a suspicious IP, it may indicate that the protocol is being used for malicious purposes); and so on.

[0157] The steps for evaluating the effectiveness of control measures include: monitoring traffic changes after control: analyzing the downward trend of traffic, assessing bandwidth recovery, and checking whether the anomaly has been eliminated; recording the effectiveness of control measures: statistically analyzing the blocking success rate, calculating response latency, and assessing the possibility of misjudgment; and generating a control effectiveness report.

[0158] The adaptive optimization steps include: dynamically adjusting the strategy based on the control effect: updating control rules, optimizing threshold settings, and adjusting control intensity; and optimizing the early warning mechanism: improving the content of early warning information, adjusting the push frequency, and optimizing the display method.

[0159] The solution in this embodiment achieves real-time early warning of abnormal traffic, supports simultaneous notification through multiple channels, and ensures that control measures take effect in a timely manner; it achieves hierarchical and precise control, reduces the impact of misjudgments, and improves control efficiency; it provides collaborative display across multiple interfaces, making early warning information clear and intuitive, and minimizes the impact of the control process on normal business; the control mechanism is stable and reliable, supports automatic recovery from failures, and has emergency handling capabilities; the control strategy is adaptively adjusted, the early warning mechanism is continuously optimized, and it supports handling complex scenarios.

[0160] In some possible embodiments of the present invention, the step of allocating independent network slices for traffic monitoring to achieve service isolation and automatically adjusting slice configuration parameters based on smart contracts includes:

[0161] The network slicing initialization steps include: creating a dedicated network slice for traffic monitoring in the 5G core network: allocating slice identifiers, setting slice priorities, and defining slice resource quotas; configuring slice isolation parameters: setting resource isolation levels, configuring service isolation policies, and establishing security isolation mechanisms; and initializing basic quality of service parameters: configuring bandwidth limits, setting latency requirements, and defining reliability indicators.

[0162] The smart contract deployment steps include: deploying the slice management smart contract in the blockchain network: writing contract code, setting trigger conditions, and defining execution rules; initializing contract parameters: configuring adjustment thresholds, setting decision rules, and defining reward and punishment mechanisms; and establishing the contract call interface: configuring interface permissions, setting call methods, and defining data formats.

[0163] The slice monitoring steps include: real-time collection of slice performance indicators: monitoring resource utilization, recording service quality parameters, and statistical analysis of business traffic; analysis of slice operation status: evaluating performance trends, detecting anomalies, and predicting resource requirements; and generation of monitoring reports: summarizing performance data, marking abnormal events, and calculating health indicators.

[0164] The smart contract triggering steps include: checking triggering conditions: determining performance thresholds, verifying time conditions, and confirming triggering permissions; collecting decision information: acquiring historical data, analyzing the current state, and predicting future trends; and executing contract logic: calculating adjustment plans, verifying feasibility, and recording the execution process.

[0165] The steps for adjusting slice parameters include: generating adjustment instructions: determining the adjustment items, calculating the adjustment range, and setting the execution time; executing parameter updates: modifying bandwidth configuration, adjusting priority settings, and updating resource quotas; and verifying the adjustment effect: checking that the parameters are effective, monitoring performance changes, and evaluating the impact of the adjustment.

[0166] The business migration steps include: preparing the migration environment: assessing the target slice capacity, planning the migration path, and preparing a rollback plan; executing the business migration: establishing data channels, transferring business traffic, and synchronizing status information; and verifying the migration results: checking business continuity, confirming data integrity, and evaluating service quality.

[0167] Continuous optimization steps include: collecting optimization data: statistically analyzing the effects of adjustments, evaluating performance improvements, and recording feedback on issues; updating smart contracts: optimizing decision-making rules, adjusting triggering conditions, and improving execution logic; and improving management strategies: optimizing resource allocation, updating isolation strategies, and improving security mechanisms.

[0168] The solution in this embodiment achieves complete isolation of traffic monitoring services, ensuring the stability of monitoring services and avoiding mutual interference between services; it enables automatic adjustment of slice parameters, reducing the need for manual intervention and improving management efficiency; it guarantees the service quality of monitoring services, improves resource utilization efficiency, and supports dynamic load balancing.

[0169] In some possible embodiments of the present invention, the step of achieving traffic data interoperability between different operators through a cross-chain interoperability mechanism includes:

[0170] The cross-chain network initialization steps include: deploying cross-chain protocols on each operator node: configuring consensus mechanisms, setting communication protocols, and initializing key pairs; establishing cross-chain gateways: deploying gateway nodes, configuring routing rules, and setting security policies; and initializing inter-chain communication channels: establishing P2P connections, configuring transmission protocols, and setting bandwidth parameters.

[0171] Data standardization steps include: establishing cross-chain data format specifications: defining data structures, standardizing field naming, and setting data types; establishing data mapping relationships: configuring field mappings, setting conversion rules, and defining verification methods; and implementing data format conversion: processing data encoding, converting data formats, and verifying conversion results.

[0172] The identity authentication steps include: deploying a distributed identity system: generating identity identifiers, configuring permission levels, and setting authentication rules; achieving multi-chain identity mutual recognition: exchanging identity credentials, verifying identity validity, and establishing trust relationships; and managing access permissions: setting access policies, controlling data permissions, and recording access logs.

[0173] The cross-chain data transfer steps include: initiating a data transfer request: constructing a transfer request, signing the request data, and selecting a target chain; executing the cross-chain transfer: verifying the legality of the request, encrypting the data packet, and transferring the data content; and confirming data reception: verifying data integrity, sending confirmation information, and recording the transfer status.

[0174] The steps for maintaining data consistency include: achieving atomic operations: setting transaction boundaries, defining rollback mechanisms, and ensuring operation integrity; maintaining data consistency: synchronizing data states, handling conflicts, and keeping data synchronized; and managing version control: recording version information, tracking data changes, and maintaining update history.

[0175] The steps for cross-chain smart contract calls include: Deploying the cross-chain contract: writing contract code, setting call rules, and configuring the execution environment; Implementing contract interoperability: defining interface specifications, implementing call methods, and handling return results; Managing contract state: synchronizing contract state, handling execution exceptions, and recording call logs.

[0176] Performance optimization steps include: optimizing transmission efficiency: implementing data fragmentation, compressing transmission content, and optimizing routing; improving processing performance: processing requests in parallel, optimizing query efficiency, and implementing caching mechanisms; and monitoring system performance: collecting performance metrics, analyzing bottlenecks, and optimizing system configuration.

[0177] The solution in this embodiment enables data interoperability between different operators, supports the connection of heterogeneous blockchain systems, and ensures the reliability of data exchange; ensures the security of cross-chain data transmission, achieves complete identity authentication, and protects the privacy of sensitive data; improves data transmission efficiency, optimizes processing performance, and reduces system overhead; supports the access of new operators, adapts to different protocol standards, and facilitates functional expansion; ensures data consistency, supports atomic operations, and provides reliable state synchronization.

[0178] In some possible embodiments of the present invention, the step of encrypting the traffic data, the traffic identification result, and the early warning record using quantum encryption technology, and packaging the encrypted data into blocks using distributed ledger technology to construct a blockchain ledger containing timestamps to achieve data tamper-proofing includes:

[0179] The quantum key distribution steps include: initializing the quantum key distribution system: configuring quantum communication equipment, establishing a quantum channel, and setting key generation parameters; performing quantum key negotiation: generating a sequence of qubits, measuring quantum states, and performing basis vector verification; and generating a shared key: performing error correction coding, refining the key, and verifying the key's availability.

[0180] The data preprocessing steps include: organizing raw data: classifying traffic data, integrating traffic identification results, and summarizing early warning records; building data structure: defining data format, setting field attributes, and establishing index relationships; generating data summary: calculating hash values, adding timestamps, and recording data sources.

[0181] The quantum encryption steps include: encrypting data based on quantum keys: selecting an encryption algorithm, encrypting data in blocks, and generating ciphertext; performing integrity protection: calculating an authentication code, adding verification information, and generating a signature; and managing key status: updating key usage status, recording key version, and setting key validity period.

[0182] The block construction steps include: packaging encrypted data: organizing the block structure, setting the block header, and adding transaction content; generating block identifiers: calculating the block hash, linking previous blocks, and recording the block height; and adding time proofs: obtaining a trusted timestamp, signing the time proof, and verifying the time validity.

[0183] The consensus verification steps include: initiating a consensus request: broadcasting block information, submitting a verification request, and waiting for node responses; executing the consensus process: verifying block validity, checking data integrity, and confirming the time sequence; and reaching a consensus result: collecting verification results, tallying consensus votes, and confirming the block status.

[0184] Ledger maintenance steps include: updating the blockchain state: adding new blocks, updating link relationships, and maintaining the state tree; managing the data index: creating a search table, updating the index structure, and optimizing query performance; and performing ledger synchronization: broadcasting update information, synchronizing block data, and verifying synchronization results.

[0185] The audit traceability steps include: providing a query interface: designing a query language, implementing retrieval methods, and configuring access permissions; supporting proof generation: constructing proof paths, generating verification proofs, and providing audit reports; and maintaining historical records: recording operation logs, saving status snapshots, and supporting version backtracking.

[0186] The solution in this embodiment achieves quantum-level encryption protection, ensuring data integrity and preventing data tampering; it provides trusted time proof, achieving data non-repudiation and supporting complete audit traceability; it improves data processing efficiency, optimizes storage structure, and enhances query performance; it supports dynamic node access, adapts to business scale expansion, and facilitates function upgrades.

[0187] In some possible embodiments of the present invention, the step of collecting environmental data from surrounding IoT devices, integrating environmental data with traffic data for comprehensive analysis, and dynamically adjusting the traffic allocation strategy based on the analysis results includes:

[0188] Collect environmental data from surrounding IoT devices (such as sensors, cameras, etc.). This data may include information such as temperature, humidity, air quality, and light intensity.

[0189] Collect network traffic data, including user access volume, data transmission rate, and latency (this data will be used for subsequent analysis).

[0190] The collected environmental data and traffic data are merged to form a comprehensive dataset (this step requires data standardization and formatting to ensure that data from different sources can be effectively combined).

[0191] A comprehensive analysis of the dataset is conducted, and data analysis algorithms (such as machine learning models) are used to identify the relationship between environmental factors and traffic changes (this analysis will help to understand the trend of traffic changes under different environmental conditions).

[0192] Based on the results of comprehensive analysis, traffic allocation strategies are dynamically adjusted (for example, in high temperature or high humidity environments, it may be necessary to prioritize the traffic of certain critical applications, or adjust bandwidth allocation according to user needs).

[0193] Implement the adjusted traffic allocation strategy and continuously monitor its effectiveness. Based on real-time feedback, optimize the traffic allocation strategy to adapt to the ever-changing environment and user needs.

[0194] This embodiment's solution, through the fusion analysis of environmental and traffic data, can more rationally allocate network resources and improve overall resource utilization efficiency. Dynamically adjusting traffic allocation strategies can optimize network performance and enhance user experience based on environmental changes and user needs. The system can respond to environmental changes in real time and quickly adjust strategies, enhancing network adaptability and flexibility. Insights provided by data analysis support smarter decision-making, helping operators better manage network traffic. By collecting environmental data from surrounding IoT devices, fusing environmental and traffic data for comprehensive analysis, and dynamically adjusting traffic allocation strategies based on the analysis results, the implementation steps not only improve resource utilization and user experience but also enhance the system's flexibility and intelligent decision-making capabilities.

[0195] Please see Fig. 2 Another embodiment of the present invention provides a 5G-based intelligent portable WiFi traffic monitoring system for executing a 5G-based intelligent portable WiFi traffic monitoring method, comprising: a first 5G intelligent portable WiFi device equipped with a traffic statistics module, an edge computing node, and a server;

[0196] The traffic statistics module located within the chipset of the first 5G smart portable WiFi device is configured as follows:

[0197] An adaptive sampling rate mechanism is used to capture data packets in real time; wherein, the adaptive sampling rate mechanism dynamically adjusts the data packet capture frequency according to the network load status and traffic characteristics;

[0198] When data packets flow through key nodes of the kernel protocol stack, traffic data including timestamps, source and destination IP addresses, port numbers, protocol types, and data size are extracted.

[0199] The traffic data is transmitted to the edge computing node deployed locally on the first 5G smart portable WiFi device;

[0200] The edge computing node is configured as follows:

[0201] The streaming data is cleaned in real time using a streaming processing framework to remove duplicate, erroneous and invalid data records. The cleaned data is compressed and stored using a data compression algorithm. The compressed data is then standardized according to a preset classification rule to generate a subset of the data.

[0202] Based on the traffic data subset and the preset first traffic identification model (a distributed deep learning model based on a federated learning framework, which integrates convolutional neural networks and recurrent neural networks), the traffic identification result is obtained;

[0203] When abnormal traffic is detected, warning messages are issued through multiple user interfaces associated with the device, and the built-in hierarchical traffic control mechanism of the first 5G smart portable WiFi device is activated to restrict or block the abnormal traffic.

[0204] Abnormal traffic features are extracted and fed back to the first traffic identification model for model optimization.

[0205] Allocate independent network slices for traffic monitoring to achieve service isolation, and automatically adjust slice configuration parameters based on smart contracts;

[0206] Achieve data interoperability between different operators through cross-chain interoperability mechanisms;

[0207] The traffic data, traffic identification results, and early warning records are encrypted using quantum encryption technology, and distributed ledger technology is used to package the encrypted data into blocks to construct a blockchain ledger containing timestamps, thereby achieving data tamper-proofing.

[0208] Collect environmental data from surrounding IoT devices, integrate environmental data with traffic data for comprehensive analysis, and dynamically adjust traffic allocation strategies based on the analysis results.

[0209] It should be known that, Fig. 2 The block diagram of the 5G-based smart portable WiFi traffic monitoring 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-based smart portable WiFi traffic monitoring system provided in this embodiment can be used to execute various embodiments of the corresponding 5G-based smart portable WiFi traffic monitoring method. For specific implementation details, please refer to the descriptions of the respective method embodiments, which will not be repeated here.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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 5G-based intelligent personal WiFi traffic monitoring method, characterized in that, The application comprises the following steps: Through the traffic statistics module set in the chipset of the first 5G smart portable WiFi device, real-time data packets are captured using an adaptive sampling rate mechanism; wherein the adaptive sampling rate mechanism dynamically adjusts the data packet capture frequency according to the network load state and traffic characteristics; When the data packets pass through the kernel protocol stack key nodes, traffic data including timestamps, source and destination IP addresses, port numbers, protocol types, and data size are extracted; The traffic data is transmitted to the edge computing node deployed locally in the first 5G smart portable WiFi device; Real-time cleaning of the traffic data is performed using a stream processing framework to remove duplicate, error, and invalid traffic records. Data compression algorithms are used to compress and store the cleaned traffic data, and standardized processing is performed on the compressed traffic data according to the pre-set classification rules to generate a traffic data subset; According to the traffic data subset and the pre-set first traffic identification model, the traffic identification result is obtained; When abnormal traffic is identified, warning information is sent through multiple user interfaces associated with the device, and the built-in hierarchical traffic control mechanism of the first 5G smart portable WiFi device is activated to limit or block abnormal traffic; Abnormal traffic characteristics are extracted and fed back to the first traffic identification model for model optimization; An independent network slice is allocated for traffic monitoring to achieve business isolation, and the slice configuration parameters are automatically adjusted based on smart contracts; Through cross-chain interoperability mechanism, traffic data interconnection between different operators is realized; The traffic data, traffic identification results, and warning records are encrypted using quantum encryption technology, and the encrypted data is packaged into blocks using distributed ledger technology to build a blockchain ledger containing timestamps, achieving data tamper-proofing; Collect environmental data from surrounding IoT devices, integrate environmental data with traffic data for comprehensive analysis, and dynamically adjust traffic distribution strategies based on analysis results; The steps of collecting environmental data from surrounding IoT devices, integrating environmental data with traffic data for comprehensive analysis, and dynamically adjusting traffic distribution strategies based on analysis results comprise: Collecting environmental data from surrounding IoT devices, including temperature, humidity, air quality, and light intensity; Collecting network traffic data, including user access volume, data transmission rate, and delay; Fusing the collected environmental data and traffic data to form a comprehensive data set; Performing comprehensive analysis on the comprehensive data set to identify the relationship between environmental factors and traffic changes using data analysis algorithms; Based on the results of comprehensive analysis, dynamically adjust the traffic distribution strategy; Implement the adjusted traffic distribution strategy and continuously monitor its effectiveness. According to real-time feedback, optimize the traffic distribution strategy to adapt to changing environments and user needs. 2.The 5G-based smart on-the-go WiFi traffic monitoring method of claim 1, wherein, The step of capturing data packets in real time through the traffic statistics module set in the chipset of the first 5G smart portable WiFi device using an adaptive sampling rate mechanism comprises: The initialization configuration step includes: setting a traffic statistics module in the chipset of the first 5G smart portable WiFi device; configuring initial sampling rate parameters in the traffic statistics module, including a reference sampling interval and a sampling window size; setting traffic thresholds, including a high load threshold and a low load threshold; initializing a sampling rate adjustment factor and an adjustment step; The network state monitoring step includes: monitoring the network interface state of the first 5G smart portable WiFi device in real time; obtaining the current network bandwidth utilization; detecting the data packet queue length; recording the network delay and packet loss rate; The load evaluation step includes: calculating the network load indicator in the current time window; comparing the calculated load indicator with the preset threshold; determining whether the current network state belongs to a high load, normal load or low load situation; generating a load evaluation result; The sampling rate adaptive adjustment step includes: dynamically calculating the optimal sampling rate according to the load evaluation result; appropriately reducing the sampling rate to reduce system pressure when the load is higher than the high load threshold; increasing the sampling rate to obtain more detailed traffic information when the load is lower than the low load threshold; ensuring that the sampling rate adjustment is within the preset maximum and minimum range; The data packet capture step includes: setting a data packet filter at the network interface driver program layer; sampling the passing data packets according to the current sampling rate; extracting the header information of the sampled data packets; recording the timestamp information of the data packets; The sampling optimization step includes: adopting differentiated sampling strategies for different types of network protocols; increasing the sampling priority for critical business traffic; using a predictive sampling mechanism for periodic traffic; dynamically adjusting the sampling window size; The resource monitoring step includes: monitoring the CPU usage of the traffic statistics module; monitoring the memory buffer occupancy; triggering a protection mechanism when the system resources approach the threshold; automatically adjusting the sampling parameters to balance the system load; The sampling quality evaluation step includes: calculating the representativeness indicator of the sampling data; evaluating the accuracy of the sampling result; analyzing the sampling bias; generating a sampling quality report. 3.The 5G-based smart on-the-go WiFi traffic monitoring method of claim 2, wherein, The step of using a stream processing framework to perform real-time cleaning on the traffic data, removing duplicate, error and invalid traffic records, using a data compression algorithm to compress and store the cleaned traffic data, and performing standardized processing on the compressed traffic data according to a preset classification rule to generate a traffic data subset includes: The stream processing environment initialization step includes: deploying a stream processing framework on an edge computing node; configuring data stream inlet and outlet nodes; setting the parallelism parameter of the data processing pipeline; initializing the data buffer and processing queue; The data stream access step includes: establishing a data transmission channel with the traffic statistics module; dividing and adding the received traffic data into the processing queue; assigning a unique identifier to each data fragment; recording the data access timestamp; The real-time cleaning step includes: detecting and deleting duplicate packet records; calculating packet feature hash values, using a sliding time window to determine duplicates, and retaining the earliest valid record; identifying and filtering error data; verifying packet integrity, verifying protocol field legality, and checking address format validity; removing invalid traffic records; filtering out timeout packets, deleting incomplete session records, and removing abnormal length data; The data compression step includes: classifying and packaging the cleaned data; grouping by protocol type, batch processing by time sequence, and establishing a data index structure; performing multi-level compression processing: first, field-level compression, then block-level compression, and finally global compression; generating compressed metadata: recording compression algorithm parameters, saving information required for decompression, and establishing a compressed data index; The standardization processing step includes: performing data format unification: unifying timestamp format, standardizing address representation, and normalizing protocol identification; performing numerical normalization: calculating statistical values of traffic features, performing min-max normalization, and applying Z-score standardization; establishing a standardization mapping table: recording conversion parameters, saving normalization ranges, and maintaining feature mapping relationships; The traffic data subset generation step includes: classifying data according to pre-set rules: dividing based on time dimension, grouping by protocol type, and clustering by service characteristics; constructing a data subset index: creating a multi-dimensional index structure, establishing a fast retrieval table, and generating subset association relationships; optimizing subset storage structure: implementing incremental update mechanism, designing cache strategy, and constructing hierarchical storage structure; The quality control step includes: real-time monitoring of processing quality: tracking data loss rate, monitoring processing delay, and evaluating compression efficiency; performing abnormal processing: detecting processing abnormalities, triggering recovery mechanism, and recording abnormal logs; generating quality reports: statistical processing indicators, performance bottleneck analysis, and optimization suggestions. 4.The 5G-based smart on-the-go WiFi traffic monitoring method of claim 3, wherein, The method for constructing the first traffic identification model includes: The model initialization step includes: initializing the global model architecture on the central server side, including a convolutional neural network module and a recurrent neural network module; the convolutional neural network module is used to extract spatial features of traffic data, including multiple convolutional layers, pooling layers, and fully connected layers; the recurrent neural network module is used to extract time sequence features of traffic data, including LSTM or GRU units; distributing the initialized global model parameters to each 5G smart portable WiFi device participating in training; The local training step includes: each 5G smart portable WiFi device performs model training based on local traffic data sets; using batch normalization to process local data and eliminate data distribution differences between devices; using differential privacy mechanism to protect privacy during training; calculating gradient update values of local model parameters; The parameter aggregation step includes: each 5G smart portable WiFi device encrypts and transmits the calculated gradient update values to the central server; the central server aggregates the gradient update values of all devices using a weighted average algorithm; updates the global model parameters; distributes the updated global model parameters to each participating device; The model optimization step comprises: setting a dynamic learning rate adjustment mechanism to adaptively adjust the learning rate according to the training progress; introducing an early stopping mechanism to stop training when the model performance no longer significantly improves; adopting the Dropout technology to prevent model overfitting; and using residual connection to optimize gradient propagation; The model evaluation step comprises: evaluating the model performance on the validation dataset; calculating several evaluation indicators such as accuracy, recall rate and F1 score; generating a confusion matrix to analyze the model prediction effect; deciding whether to continue training according to the evaluation result; and obtaining the first traffic identification model; The anomaly detection step comprises: inputting real-time traffic data into the trained model; extracting spatial features through a convolutional neural network; analyzing time series patterns through a recurrent neural network; and fusing the two types of features to determine abnormal traffic; The model deployment step comprises: converting the trained model into a lightweight format; deploying it to each 5G intelligent portable WiFi device; configuring model inference parameters; and starting the online anomaly detection service. 5.The 5G-based smart on-the-go WiFi traffic monitoring method of claim 4, wherein, The step of issuing warning information through multiple user interfaces associated with the device when abnormal traffic is identified, and activating the built-in hierarchical traffic control mechanism of the first 5G intelligent portable WiFi device to limit or block abnormal traffic, comprises: The abnormal traffic feature extraction step comprises: obtaining abnormal traffic data identified by the deep learning model; extracting key feature parameters of abnormal traffic: traffic surge amplitude and duration, abnormal connection number and port usage, and data packet content features; determining the damage level of abnormal traffic; and generating an abnormal feature description report; The warning information generation step comprises: constructing a warning information template according to the abnormal level; integrating the specific performance of abnormal traffic: abnormal type description, impact range evaluation and potential risk analysis; generating warning measures; and adding a timestamp and a unique identifier; The multi-interface warning push step comprises: device display screen push: display warning icon, output warning sound, trigger indicator light blinking; mobile APP notification: send push notification, update APP interface state, display detailed abnormal information; Web management interface prompt: update dashboard state, display warning popup, provide detailed log viewing; The hierarchical traffic control mechanism initialization step comprises: establishing a traffic control policy table: defining control level threshold, setting control action type, configuring control duration; initializing the traffic control module: loading control rules, setting priority order, preparing control resources; The traffic control execution step comprises: mild abnormality processing: limiting the bandwidth of suspicious IP, reducing the priority of abnormal traffic, recording abnormal behavior; moderate abnormality processing: blocking specific port traffic, limiting suspicious protocol traffic, starting traffic redirection; severe abnormality processing: disconnecting abnormal connections, blocking related IP segments, activating emergency response mechanism; The control effect evaluation step comprises: monitoring the traffic changes after control: analyzing the traffic decline trend, evaluating the bandwidth recovery situation, checking whether the anomaly is eliminated; recording the control measure effect: calculating the blocking success rate, calculating the response time delay, evaluating the misjudgment situation; generating a control effect report; The adaptive optimization step includes dynamically adjusting the strategy according to the control effect: updating the control rules, optimizing the threshold settings, and adjusting the control strength; and optimizing the early warning mechanism: improving the early warning information content, adjusting the push frequency, and optimizing the display method. 6.The 5G-based smart on-the-go WiFi traffic monitoring method of claim 5, wherein, The step of allocating independent network slices for traffic monitoring to achieve service isolation and automatically adjusting slice configuration parameters based on smart contracts includes: The network slice initialization step includes creating a network slice dedicated to traffic monitoring in the 5G core network: allocating a slice identifier, setting a slice priority, and defining a slice resource quota; configuring slice isolation parameters: setting resource isolation levels, configuring service isolation strategies, and establishing a secure isolation mechanism; initializing basic quality of service parameters: configuring bandwidth limits, setting latency requirements, and defining reliability indicators; The smart contract deployment step includes deploying a slice management smart contract in the blockchain network: writing contract code, setting trigger conditions, and defining execution rules; initializing contract parameters: configuring adjustment thresholds, setting decision rules, and defining reward and punishment mechanisms; establishing contract invocation interfaces: configuring interface permissions, setting invocation methods, and defining data formats; The slice monitoring step includes real-time collection of slice performance indicators: monitoring resource utilization, recording service quality parameters, and statistical business traffic; analyzing slice running status: evaluating performance trends, detecting abnormal conditions, and predicting resource demand; generating monitoring reports: aggregating performance data, marking abnormal events, and calculating health indicators; The smart contract triggering step includes checking trigger conditions: judging performance thresholds, verifying time conditions, and confirming trigger permissions; collecting decision information: obtaining historical data, analyzing current status, and predicting future trends; executing contract logic: calculating adjustment schemes, verifying feasibility, and recording execution process; The slice parameter adjustment step includes generating adjustment instructions: determining adjustment items, calculating adjustment amplitude, and setting execution time; executing parameter updates: modifying bandwidth configurations, adjusting priority settings, and updating resource quotas; verifying adjustment effects: checking parameter effectiveness, monitoring performance changes, and evaluating adjustment impacts; The business migration step includes preparing the migration environment: evaluating target slice capacity, planning migration paths, and preparing rollback schemes; executing business migration: establishing data channels, transferring business traffic, and synchronizing state information; verifying migration results: checking business continuity, confirming data integrity, and evaluating service quality; The continuous optimization step includes collecting optimization data: statistical adjustment effects, performance improvement analysis, and problem feedback records; updating smart contracts: optimizing decision rules, adjusting trigger conditions, and improving execution logic; improving management strategies: optimizing resource allocation, updating isolation strategies, and perfecting security mechanisms. 7.The 5G-based smart on-the-go WiFi traffic monitoring method of claim 6, wherein, The step of realizing traffic data interconnection between different operators through cross-chain interoperation mechanism includes: The cross-chain network initialization step includes deploying cross-chain protocols on each operator node: configuring consensus mechanisms, setting communication protocols, and initializing key pairs; establishing cross-chain gateways: deploying gateway nodes, configuring routing rules, and setting security strategies; initializing inter-chain communication channels: establishing P2P connections, configuring transmission protocols, and setting bandwidth parameters; The data standardization step includes: formulating a cross-chain data format specification: defining data structures, specifying field naming, and setting data types; establishing data mapping relationships: configuring field mapping, setting conversion rules, and defining verification methods; implementing data format conversion: processing data encoding, converting data formats, and verifying conversion results; The identity authentication step includes: deploying a distributed identity system: generating identity identifiers, configuring permission levels, and setting authentication rules; implementing multi-chain identity mutual authentication: exchanging identity credentials, verifying identity validity, and establishing trust relationships; managing access permissions: setting access policies, controlling data permissions, and recording access logs; The cross-chain data transmission step includes: initiating a data transmission request: building a transmission request, signing the request data, and selecting a target chain; executing cross-chain transmission: verifying the legality of the request, encrypting data packets, and transmitting data content; confirming data reception: checking data integrity, sending confirmation information, and recording transmission status; The data consistency maintenance step includes: implementing atomic operations: setting transaction boundaries, defining rollback mechanisms, and ensuring operation integrity; maintaining data consistency: synchronizing data states, handling conflict situations, and keeping data synchronized; managing version control: recording version information, tracking data changes, and maintaining update history; The smart contract cross-chain calling step includes: deploying cross-chain contracts: writing contract code, setting calling rules, and configuring execution environments; implementing contract interoperability: defining interface specifications, implementing calling methods, and handling return results; managing contract status: synchronizing contract status, handling execution exceptions, and recording calling logs; The performance optimization step includes: optimizing transmission efficiency: implementing data sharding, compressing transmission content, and optimizing routing selection; improving processing performance: parallel processing requests, optimizing query efficiency, and implementing caching mechanisms; monitoring system performance: collecting performance indicators, analyzing bottleneck issues, and optimizing system configurations. 8.The 5G-based smart on-the-go WiFi traffic monitoring method of claim 7, wherein, The step of encrypting the traffic data, the traffic identification result and the early warning record by quantum encryption technology, and packaging the encrypted data into blocks by distributed ledger technology to build a block chain ledger containing a time stamp, and realizing data tamper-proofing, comprises: The quantum key distribution step includes: initializing the quantum key distribution system: configuring quantum communication equipment, establishing quantum channels, and setting key generation parameters; performing quantum key agreement: generating quantum bit sequences, measuring quantum states, and performing basis vector verification; generating shared keys: performing error correction coding, key refining, and verifying key usability; The data preprocessing step includes: organizing raw data: classifying traffic data, integrating traffic identification results, and summarizing early warning records; building data structures: defining data formats, setting field attributes, and establishing index relationships; generating data digests: calculating hash values, adding timestamps, and recording data sources; The quantum encryption step includes: encrypting data based on quantum keys: selecting encryption algorithms, block-wise encrypting data, and generating ciphertext; performing integrity protection: calculating authentication codes, adding verification information, and generating signatures; managing key status: updating key usage status, recording key versions, and setting key validity periods; The block construction step includes: packing encrypted data, organizing block structure, setting block header, adding transaction content; generating block identification, calculating block hash, linking previous block, recording block height; adding time proof, obtaining trusted timestamp, signing time proof, verifying time validity; The consensus verification step includes: initiating consensus request, broadcasting block information, submitting verification request, waiting for node response; executing consensus process, verifying block validity, checking data integrity, confirming time sequence; reaching consensus result, collecting verification result, counting consensus vote, confirming block status; The ledger maintenance step includes: updating block chain state, adding new block, updating link relationship, maintaining state tree; managing data index, establishing retrieval table, updating index structure, optimizing query performance; executing ledger synchronization, broadcasting update information, synchronizing block data, verifying synchronization result; The audit traceability step includes: providing query interface, designing query language, implementing retrieval method, configuring access rights; supporting proof generation, building proof path, generating verification proof, providing audit report; maintaining historical record, recording operation log, saving state snapshot, supporting version backtracking. 9.A 5G-based intelligent on-body WiFi traffic monitoring system configured to perform the 5G-based intelligent on-body WiFi traffic monitoring method according to any one of claims 1 to 8. It comprises: A first 5G intelligent portable WiFi device provided with a traffic statistics module, an edge computing node and a server; The traffic statistics module arranged in the chip set of the first 5G intelligent portable WiFi device is configured to: Adopt an adaptive sampling rate mechanism to capture data packets in real time; wherein the adaptive sampling rate mechanism dynamically adjusts the data packet capture frequency according to the network load state and traffic characteristics; When the data packets pass through the kernel protocol stack key nodes, extract traffic data including timestamp, source and destination IP address, port number, protocol type, data size; The traffic data is transmitted to the edge computing node deployed locally on the first 5G intelligent portable WiFi device; The edge computing node is configured to: Adopt a streaming processing framework to clean the traffic data in real time, remove duplicate, error and invalid traffic records, compress the cleaned traffic data using a data compression algorithm, and standardize the compressed traffic data according to a preset classification rule to generate a traffic data subset; According to the traffic data subset and the preset first traffic identification model, a traffic identification result is obtained; When abnormal traffic is identified, warning information is sent through multiple user interfaces associated with the device, and a hierarchical traffic control mechanism built-in the first 5G intelligent portable WiFi device is activated to limit or block abnormal traffic; Abnormal traffic characteristics are extracted and fed back to the first traffic identification model for model optimization; An independent network slice is allocated for traffic monitoring to achieve business isolation, and slice configuration parameters are automatically adjusted based on a smart contract; Through a cross-chain interoperability mechanism, traffic data between different operators can be interchanged; The traffic data, the traffic identification result and the warning record are encrypted through quantum encryption technology, and the encrypted data is packaged into blocks using distributed ledger technology to build a block chain ledger containing timestamps, achieving data tamper-proofing; Collecting environmental data of peripheral Internet of Things devices, fusing the environmental data and traffic data for comprehensive analysis, and dynamically adjusting a traffic distribution strategy based on an analysis result.

Images