Multi-device shared WiFi network optimization method and system

Abstract

According to the multi-device shared WiFi network optimization method and system provided by the invention, the router dynamically adjusts the frequency band and the channel by monitoring the interference source, the signal strength and the channel occupation condition of the WiFi network, so that the signal quality and the network stability are improved; the edge server generates an optimization strategy by using the terminal attribute, the service type and the historical data to ensure that the communication equipment obtains the required network resources and improve the overall use efficiency; the router detects and prevents access of illegal equipment, performs security vulnerability scanning, and takes isolation or repair measures in time to guarantee network security; the state monitoring and feedback module of the terminal equipment feeds back the network use condition to the edge server to form a closed-loop feedback mechanism so as to ensure that the network performance is continuously improved; through intelligent flow management and optimization strategies, a user can enjoy smoother network experience when using a plurality of devices. According to the invention, not only can the performance and security of sharing the WiFi network by multiple devices be effectively improved, but also the overall network experience of the user can be improved.

Description

Technical Field

[0001] The present invention relates to the field of network technologies, and in particular, to a method and system for optimizing multi-device shared WiFi networks. Background Art

[0002] In modern society, using mobile intelligent terminals to access the network through WiFi (Wireless Fidelity) has become a basic operation in digital life. In this network connection scenario, although the traditional sharing method meets the basic network access requirements, in the increasingly complex multi-terminal interconnection ecosystem, there are deficiencies in ensuring stable network performance, security, and timely response, resulting in a poor user experience. Summary of the Invention

[0003] Based on the above problems, the present invention proposes a method and system for optimizing multi-device shared WiFi networks. Through the solution of the present invention, not only can the performance and security of multi-device shared WiFi networks be effectively improved, but also continuous optimization can be achieved through intelligent management, ultimately enhancing the overall network experience of users.

[0004] In view of this, one aspect of the present invention proposes a method for optimizing multi-device shared WiFi networks, including: An intelligent router monitors the surrounding interference sources, signal strength, and channel occupancy of the WiFi network in real time, obtains monitoring data, and transmits the monitoring data to an Internet of Things edge server; The Internet of Things edge server analyzes the monitoring data to obtain a first data analysis result; The Internet of Things edge server obtains the terminal attribute data, service type data, and historical working data of communication terminals connected to the intelligent router; The Internet of Things edge server generates a first optimization strategy according to a preset network optimization model, the first data analysis result, the terminal attribute data, the service type data, and the historical working data, and transmits the first optimization strategy to the intelligent router; The intelligent router switches the working frequency band and channel according to the first optimization strategy, and allocates and controls the network traffic of each communication device; The intelligent router detects and blocks illegal devices from accessing the WiFi network, and performs a security vulnerability scan on the connected communication devices; When a security threat is detected, isolation or repair measures are taken, and security event data is transmitted to the Internet of Things edge server; The IoT edge server generates communication device control instructions and updates the security protection policy based on the security event data, sends the updated policy back to the intelligent router, and sends the communication device control instructions to the communication device; The communication device receives the communication device control instructions and controls the background network activities of its own applications according to the communication device control instructions, including: restricting or allowing network access permissions for specific applications, and adjusting the data transmission priorities of the applications; The communication device transmits the network usage data of the application to the IoT edge server; The IoT edge server generates a correction plan for the network optimization model according to the network usage data of the application.

[0005] Optionally, the steps for the IoT edge server to analyze the monitoring data to obtain the first data analysis result include: After receiving the monitoring data, the IoT edge server preprocesses the monitoring data according to preset data cleaning rules, including: removing outliers, filling in missing values, and data standardization; wherein, the determination of the outliers is based on the statistical characteristics of historical data, and the missing values are obtained by interpolating data at adjacent time points; The IoT edge server extracts features from the preprocessed monitoring data to obtain feature data, specifically including: extracting the number of interference sources, signal strength, and occupied channel distribution characteristics from the surrounding interference source data; extracting the signal attenuation trend and signal fluctuation pattern from the WiFi signal strength data; extracting the average occupancy rate, peak occupancy period, and idle period distribution of each channel from the channel occupancy data; The IoT edge server performs classification and clustering analysis on the feature data based on a pre-trained deep learning model, including: classifying the current network environment state as "congested", "normal", or "idle"; identifying the types of main interference sources and their influence degrees; grading the channel quality; The IoT edge server combines the temporal characteristics of the feature data and uses a time series analysis method to predict the network environment change trend in the next period of time, including: predicting the occupancy rate change of each channel; predicting the activity pattern of interference sources; predicting the change pattern of signal strength; The IoT edge server integrates the above analysis results to form the first data analysis result, including: the current network environment state assessment report; the channel quality score and ranking; the interference source impact analysis report; the network environment prediction report.

[0006] Optionally, the step of the Internet of Things edge server generating a first optimization strategy according to a preset network optimization model, the first data analysis result, the terminal attribute data, the service type data, and the historical work data, and transmitting the first optimization strategy to the intelligent router includes: The Internet of Things edge server determines a first optimization target for the current network environment based on the first data analysis result, including: when the network environment status is "congested", setting load balancing and interference avoidance as the main optimization targets; when the network environment status is "normal", setting service quality improvement as the main optimization target; when the network environment status is "idle", setting energy consumption optimization as the main optimization target; The Internet of Things edge server analyzes and integrates the terminal attribute data, service type data, and historical work data to obtain a first analysis result, including: classifying devices according to terminal attribute data, including: mobile terminals, fixed terminals, and Internet of Things devices; grading applications according to service type data, including: real-time services, interactive services, and background services; calculating the average bandwidth requirements and peak and valley periods of various terminals based on historical work data; The Internet of Things edge server calls a preset network optimization model, which includes: a resource allocation model based on deep reinforcement learning; a channel allocation model based on genetic algorithms; a QoS control model based on fuzzy logic; The Internet of Things edge server inputs the first analysis result and the first optimization target into the network optimization model, performs target optimization calculations to obtain a first calculation result, including: calculating an optimal channel allocation scheme; calculating the bandwidth allocation quotas for each terminal; calculating a service priority scheduling strategy; The Internet of Things edge server generates a first optimization strategy according to the first calculation result, including: a channel switching instruction for specifying the working channels of each terminal; a bandwidth allocation instruction for specifying the bandwidth upper limit of each terminal; a QoS control instruction for setting the priorities and resource quotas of various services; a load balancing instruction for determining the distribution of terminals among multiple frequency bands; The Internet of Things edge server verifies the executability of the first optimization strategy, including: checking whether the strategy complies with terminal hardware constraints; verifying the expected network performance after the implementation of the strategy; evaluating the impact of the strategy on existing services; The Internet of Things edge server encodes the verified first optimization strategy into an instruction set recognizable by the router and transmits it to the intelligent router through a secure channel.

[0007] Optionally, the step of the intelligent router switching the working frequency band and channel according to the first optimization strategy and allocating and controlling the network traffic of each communication device includes: After receiving the first optimization policy, the intelligent router performs policy parsing and extracts the following control instructions: frequency band switching instruction; channel allocation instruction; traffic control instruction; Before performing frequency band and channel switching, the intelligent router sends a switching notice to all connected communication devices, including: broadcasting switching time window information; sending new frequency band and channel parameters; setting the reconnection waiting time threshold; Within the preset time window, the intelligent router performs frequency band and channel switching according to the following steps, including: pausing new device access; saving the current network connection status; switching to the target frequency band and channel according to the instruction; waiting for the device to reconnect; resuming the device access function; The intelligent router performs grouped management on the reconnected communication devices, including: preferentially allocating dual-band supported devices to the 5GHz frequency band; allocating devices at fixed positions to channels with stronger signals; allocating mobile devices to channels with lighter loads; The intelligent router configures the QoS policy based on the traffic control instruction, including: setting the bandwidth upper limit and guaranteed bandwidth for each device; configuring the service priority queue; enabling the traffic shaping algorithm; The intelligent router monitors the optimization effect in real time, including: recording the device reconnection success rate; counting the actual usage of each channel; measuring the key network performance indicators; When the intelligent router detects the following abnormal situations, it triggers emergency handling, including: automatically reverting to the original configuration when the device reconnection failure rate exceeds the threshold; temporarily adjusting the traffic control parameters when the network performance significantly decreases; starting the standby channel mechanism when a new interference source appears.

[0008] Optionally, the steps for the intelligent router to detect and prevent illegal devices from accessing the WiFi network and perform security vulnerability scanning on the connected communication devices include: The intelligent router authenticates the devices attempting to access the WiFi network, including: obtaining the MAC address and device type identifier of the device; extracting the access time and geographical location information of the device; checking whether the device is in the authorized device white list; verifying the validity of the access credentials provided by the device; When detecting the following situations, the intelligent router will determine it as illegal access: the device MAC address is repeated with the connected device; the device MAC address exists in the blacklist database; multiple incorrect password access attempts are made within a short period of time; the device access behavior characteristics match the attack characteristics library; The intelligent router takes preventive measures against illegally accessed devices, including: adding the device to the temporary blacklist; prohibiting subsequent access requests for this MAC address; recording the detailed information of illegal access events; sending a security warning to legitimate users; The intelligent router periodically performs security scans on connected communication devices, including: scanning for known vulnerabilities in the device operating system; detecting whether the device has installed the latest security patches; identifying whether there are abnormal network behaviors in the device; checking whether the network protocol configuration of the device is secure; The intelligent router monitors the network behaviors of communication devices in real time, including: analyzing whether the traffic patterns of the device are abnormal; detecting whether the device accesses malicious websites; monitoring whether there are unauthorized port openings in the device; identifying whether the device generates abnormal network requests; The intelligent router classifies the security risks discovered by the scan, including: Emergency level: Vulnerabilities that can lead to system intrusion; High-risk level: Vulnerabilities that can leak sensitive data; Medium-risk level: Vulnerabilities that can affect system performance; Low-risk level: Configurations with potential security risks; The intelligent router takes corresponding measures according to the security risk levels, including: implementing device isolation for emergency-level risks; restricting network access permissions for high-risk-level risks; making security configuration adjustments for medium-risk-level risks; sending repair suggestions for low-risk-level risks.

[0009] Optionally, the steps of the IoT edge server generating communication device control instructions and updating the security protection policy based on the security event data, and sending the updated policy back to the intelligent router, and sending the communication device control instructions to the communication device, include: After receiving the security event data, the IoT edge server conducts security event analysis, including: extracting the type, occurrence time, and involved devices of the security event; analyzing the severity and impact scope of the event; determining the potential hazards and urgency of the event; associating historical security event data for threat tracing; Based on the security event analysis results, the IoT edge server determines response strategies, including: matching a preset protection plan for known type attacks; starting an adaptive protection mechanism for unknown type attacks; formulating a repair plan for system vulnerabilities; determining control measures for abnormal behaviors; The IoT edge server generates communication device control instructions, including: generating application access control instructions; generating network connection restriction instructions; generating system configuration modification instructions; generating data transmission policy instructions; The IoT edge server updates the security protection policy, including: updating device access rules; updating traffic monitoring rules; updating vulnerability scanning rules; updating security warning thresholds; The IoT edge server verifies the updated security protection policy, including: checking for conflicts between policies; evaluating the effectiveness of the policies; predicting the impact of policy implementation; and confirming the compatibility of the policies. The IoT edge server performs policy distribution, including: sending the updated security protection policy to the intelligent router; sending communication device control instructions to the corresponding communication devices respectively; setting a policy effective time window; and establishing a policy execution feedback mechanism. The IoT edge server monitors the policy execution effect, including: collecting policy execution status feedback; evaluating the security protection effect; recording the policy update log; and maintaining the policy version information.

[0010] Optionally, the steps for the IoT edge server to generate a correction plan for the network optimization model based on the network usage data of the application include: The IoT edge server preprocesses the network usage data of the application, including: counting the bandwidth usage and time distribution of each application; extracting the network behavior characteristics of the application; identifying the quality of service requirements of the application; and analyzing the resource competition relationship between applications. The IoT edge server constructs an application portrait based on the preprocessed data, including: determining the business priority category of the application; establishing a resource demand model of the application; predicting the bandwidth usage trend of the application; and identifying the typical working mode of the application. The IoT edge server evaluates the network optimization model, including: calculating the error between the model prediction value and the actual value; analyzing the performance of the model in different scenarios; identifying the optimization space of the model; and determining the model parameters that need to be corrected. The IoT edge server generates a model correction plan based on the application portrait, including: adjusting the resource allocation weight coefficient; updating the quality of service evaluation index; optimizing the load balancing algorithm; and modifying the bandwidth reservation policy. The IoT edge server performs model verification, including: verifying the corrected model using historical data; conducting multi-scenario simulation tests; evaluating the generalization ability of the model; and calculating the improvement degree of the optimization effect. The IoT edge server implements incremental learning, including: integrating new application features into the model; updating the training data set of the model; adjusting the learning parameters of the model; and optimizing the prediction accuracy of the model. The IoT edge server deploys the updated model, including: generating a model deployment package; setting a model switching time point; establishing model version management; and saving the model update record.

[0011] Optionally, the construction method of the network optimization model includes: Construct the input layer of the model, including: collecting network environment feature data, including signal strength, interference level, and channel occupancy rate; collecting terminal device feature data, including device type, hardware capabilities, and location information; collecting application feature data, including bandwidth requirements, latency sensitivity, and service priority; performing normalization processing and encoding conversion on the collected feature data; Construct the hidden layer of the deep neural network, including: designing a multi-layer perceptron structure for feature extraction and representation learning; configuring an attention mechanism to highlight the impact of important features; adding recurrent neural network units to capture temporal dependencies; setting up convolutional layers to extract local feature patterns; Construct a reinforcement learning module, including: defining a state space that includes the network environment and device states; designing an action space that includes operations such as frequency band selection, bandwidth allocation, and priority scheduling; constructing a reward function that comprehensively considers metrics such as network throughput, latency, and fairness; implementing an experience replay mechanism to improve learning efficiency; Construct a decision output layer, including: designing a frequency band and channel allocation policy generator; designing a bandwidth allocation policy generator; designing a QoS control policy generator; adding a policy feasibility constraint checking mechanism; Execute model training, including: performing supervised pre-training based on historical data; performing online training through reinforcement learning; implementing experience replay and target network update; dynamically adjusting the learning rate and exploration rate; Implement model evaluation and tuning, including: setting performance evaluation metrics, including throughput, latency, and fairness; performing cross-validation to evaluate the model's generalization ability; performing sensitivity analysis to identify key parameters; optimizing the model structure and parameters based on the evaluation results; Establish a model application mechanism, including: implementing model inference acceleration; designing a model compression scheme; constructing a model update mechanism; implementing anomaly detection and fault tolerance processing.

[0012] Optionally, the steps of constructing the hidden layer of the deep neural network include: Specifically, constructing a multi-layer perceptron structure is as follows: setting the number of nodes in the first hidden layer to twice the input feature dimension and using the ReLU activation function; setting the number of nodes in the second hidden layer to 1 / 2 of the first layer and using the ReLU activation function; setting the number of nodes in the third hidden layer to 1 / 2 of the second layer and using the ReLU activation function; adding batch normalization layers between adjacent layers to improve training stability; using the Dropout mechanism to prevent overfitting, with the dropout rate set to 0.3; Specifically, constructing an attention mechanism layer is as follows: calculating the correlation matrix between feature vectors; using the softmax function to convert the correlation into attention weights; performing weighted summation on the features based on the attention weights; concatenating the weighted results with the original features; fusing the concatenated features through a fully connected layer; Specifically, the construction of the recurrent neural network unit is as follows: Use LSTM units to process the time series feature sequence; Set the dimension of the LSTM hidden state to 128; Configure a bidirectional LSTM structure to capture bidirectional time series dependencies; Add residual connections to alleviate the problem of gradient vanishing; Use sequence masking to process variable-length sequences; Specifically, the construction of the convolutional layer structure is as follows: Set the size of the first convolutional kernel to 3×3, the stride to 1, and the paddling to same; Set the size of the second convolutional kernel to 3×3 and the stride to 2 to achieve feature dimensionality reduction; Add a BatchNormalization layer and a ReLU activation function after each convolutional layer; Use a max pooling layer for feature screening; Add skip connections to retain fine-grained features; Specifically, the implementation of the feature fusion mechanism is as follows: Concatenate the outputs of the multi-layer perceptron and the attention mechanism; Perform feature fusion on the concatenated result and the LSTM output; Input the fused result into the convolutional layer for feature extraction; Use 1×1 convolution to adjust the number of feature channels; Generate the final feature representation through a fully connected layer; Specifically, the configuration of the inter-layer connection mechanism is as follows: Add residual connections between key layers; Implement multi-scale feature fusion; Set the feature pyramid structure; Add a gated update mechanism; Implement a dynamic routing mechanism; Specifically, the addition of the regularization and optimization mechanism is as follows: Apply L2 regularization to constrain the weights; Implement gradient clipping to prevent gradient explosion; Use a learning rate decay strategy; Configure an early stopping mechanism; Implement sparsification of model parameters.

[0013] Another aspect of the present invention provides a multi-device shared WiFi network optimization system for executing a multi-device shared WiFi network optimization method, including: a smart router, a communication device, and an Internet of Things edge server; The smart router is configured to: Real-time monitor the surrounding interference sources, signal strength, and channel occupancy of the WiFi network to obtain monitoring data, and transmit the monitoring data to the Internet of Things edge server; The Internet of Things edge server is configured to: Analyze the monitoring data to obtain a first data analysis result; Obtain the terminal attribute data, service type data, and historical working data of the communication terminals connected to the smart router; Generate a first optimization strategy according to a preset network optimization model, the first data analysis result, the terminal attribute data, the service type data, and the historical working data, and transmit the first optimization strategy to the smart router; The smart router is further configured to: Switch the working frequency band and channels according to the first optimization strategy, and allocate and control the network traffic of each communication device; Detect and prevent illegal devices from accessing the WiFi network, and perform security vulnerability scanning on the connected communication devices; When a security threat is detected, take isolation or repair measures, and transmit the security incident data to the IoT edge server; The IoT edge server is further configured to: Generate communication device control instructions and updated security protection policies according to the security incident data, send the updated policies back to the intelligent router, and send the communication device control instructions to the communication device; The communication device is configured to: Receive the communication device control instructions, and control the background network activities of its own applications according to the communication device control instructions, including: restricting or allowing the network access permissions of specific applications, and adjusting the data transmission priorities of applications; Transmit the network usage data of the application to the IoT edge server; The IoT edge server is further configured to: generate a correction plan for the network optimization model according to the network usage data of the application.

[0014] Adopting the technical solution of the present invention, by the intelligent router, the interference sources, signal strength and channel occupancy of the WiFi network are monitored in real time, the frequency band and channels can be dynamically adjusted, thereby reducing interference, improving signal quality and network stability; the IoT edge server generates targeted optimization strategies according to the terminal attribute data, service type data and historical working data to ensure that each communication device obtains the required network resources and improves the overall network usage efficiency; through the security protection module of the intelligent router, illegal devices can be detected and prevented from accessing the WiFi network in real time, and security vulnerability scanning can be performed, and isolation or repair measures can be taken in time to ensure network security; the status monitoring and feedback module of the terminal device can feedback the network usage data of the application to the IoT edge server to form a closed-loop feedback mechanism, so that the network optimization strategy can be dynamically adjusted according to the actual usage situation to ensure the continuous improvement of network performance; through intelligent traffic management and optimization strategies, users can enjoy a smoother network experience when using multiple devices, reduce latency and stuttering phenomena, and meet the requirements of high-bandwidth applications. In summary, the solution of this embodiment can not only effectively improve the performance and security of multi-device shared WiFi networks, but also achieve continuous optimization through intelligent management, and ultimately improve the overall network experience of users. Description of the Drawings

[0015] Figure 1It is a flowchart of a multi-device shared WiFi network optimization method provided by an embodiment of the present invention; Figure 2 It is a schematic block diagram of a multi-device shared WiFi network optimization system provided by an embodiment of the present invention. Detailed implementation manners

[0016] In order to more clearly understand the above objects, 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 implementation manners. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0017] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0018] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0019] Referring to "embodiment" herein means that a specific feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0020] Next, refer to Figures 1 to 2 to describe a multi-device shared WiFi network optimization method and system provided according to some embodiments of the present invention.

[0021] As Figure 1 shown, an embodiment of the present invention provides a multi-device shared WiFi network optimization method, including: The intelligent router monitors the surrounding interference sources, signal strength, and channel occupancy of the WiFi network in real time, obtains monitoring data, and transmits the monitoring data to the Internet of Things edge server; It is understandable that the intelligent router is built-in with a network environment monitoring module, a frequency band and channel switching module, a traffic allocation and control module, a security protection module, etc. When the built-in network environment monitoring module of the intelligent router is activated, it starts to monitor the surrounding environment of the WiFi network in real time, including interference sources, signal strength, and channel occupancy; the monitoring module regularly collects the surrounding signal strength data, interference source information (such as other WiFi signals, electronic device interference, etc.), and the occupancy of the current channel. These data are processed through sensors and signal analysis algorithms to ensure the accuracy and real-time nature of the data; the collected monitoring data is preliminarily processed inside the intelligent router to generate a format that can be used for analysis. This process may include data cleaning, noise removal, and data integration to ensure the effectiveness of subsequent analysis; the processed monitoring data is transmitted to the Internet of Things edge server through a network connection (such as WiFi or wired network) to ensure that the data can reach the edge server in a timely manner for more in-depth analysis; after receiving the monitoring data, the Internet of Things edge server analyzes the data using the configured artificial intelligence algorithm and network optimization model to generate the first data analysis result, which will provide a basis for subsequent network optimization strategies; according to the analysis result, the edge server can generate an optimization strategy and feedback it to the intelligent router for frequency band and channel adjustment to optimize network performance. In this step, through the real-time monitoring function of the intelligent router, the changes in the network environment can be identified in a timely manner to ensure the stability and reliability of the network; after transmitting the monitoring data to the Internet of Things edge server and analyzing it using the artificial intelligence algorithm, targeted optimization strategies can be generated to improve network performance; by reducing interference and optimizing channel allocation, users can enjoy a smoother network experience when using multiple devices, reducing latency and stuttering; real-time monitoring of surrounding interference sources and signal strength helps to identify potential security threats and enhance the network's security protection ability.

[0022] The Internet of Things edge server analyzes the monitoring data to obtain the first data analysis result; It is understandable that the Internet of Things edge server is configured with a network optimization model based on artificial intelligence algorithms, a network optimization strategy database, and a device information database.

[0023] The Internet of Things edge server obtains the terminal attribute data, service type data, and historical working data (used to determine the network resource requirements of the communication terminal) of the communication terminals connected to the intelligent router; It can be understood that in this step, each communication terminal connected to the intelligent router regularly collects its own terminal attribute data through its built-in status monitoring and feedback module. These data include information such as device type, operating system, hardware configuration, and current connection status. When the terminal device runs an application, it monitors its service type data, which can be achieved by analyzing the characteristics of the application being used (such as video stream, online game, file download, etc.), ensuring that different types of network requirements can be identified. The terminal device records its historical work data, including past network usage, traffic consumption, connection duration, application performance, etc. These data can help the IoT edge server understand the usage patterns and resource requirements of the terminal device. The terminal device transmits the collected terminal attribute data, service type data, and historical work data to the IoT edge server through a network connection (such as WiFi or wired network) to ensure that the edge server can obtain the latest terminal information. After receiving the data, the IoT edge server integrates and analyzes this information to determine the network resource requirements of each communication terminal. This process may involve technologies such as data cleaning, feature extraction, and pattern recognition. According to the analysis results, the edge server generates a network resource requirement report, specifying the bandwidth requirements, latency requirements, and priorities of each terminal. This information will be used for subsequent network optimization strategy formulation. In this step, by obtaining terminal attribute data, service type data, and historical work data, the IoT edge server can more accurately evaluate the network resource requirements of each communication terminal, thereby achieving more reasonable resource allocation. Dynamically adjusting according to the actual needs of the terminal can effectively improve the overall performance of the network, reduce latency and stuttering. By identifying the requirements of different service types, it ensures that high-priority applications obtain sufficient bandwidth, improving the user experience when using multiple devices. The network resource requirement report generated by the edge server based on terminal data provides data support for network management, helping to formulate more effective optimization strategies.

[0024] The IoT edge server generates a first optimization strategy according to a preset network optimization model, the first data analysis result, the terminal attribute data, the service type data, and the historical work data, and transmits the first optimization strategy to the intelligent router; The intelligent router switches the working frequency band and channel according to the first optimization strategy, and allocates and controls the network traffic of each communication device; It can be understood that the device status monitoring and feedback module installed on each communication device monitors its own network usage status and application running situation, and feeds back the relevant data to the IoT edge server for continuous optimization.

[0025] The intelligent router detects and blocks illegal devices from accessing the WiFi network, and performs a security vulnerability scan on the connected communication devices; When a security threat is detected, isolation or repair measures are taken, and the security event data is transmitted to the IoT edge server; It can be understood that in this step, the system continuously monitors network traffic and device behavior, uses behavior analysis and anomaly detection technologies to identify potential security threats. Once suspicious activities or known attack patterns are detected, the system will trigger an alarm; after detecting a security threat, the system evaluates the threat to determine its severity and scope of impact, which includes analyzing the affected devices, data, and network parts in order to formulate corresponding response measures; according to the threat assessment results, the system will implement isolation measures. Specifically, the affected devices or network segments will be isolated to prevent the threat from spreading laterally in the network, which can be achieved by disconnecting the network connection or restricting access permissions; for threats that can be repaired, the system will initiate an automatic repair program, which may include restoring the security configuration of the affected device, updating patches, or rolling back to a secure state to eliminate the threat; during the whole process, the system will collect data related to security events, including information such as the detected threat type, affected devices, measures taken, and their effects; the collected security event data will be encrypted and transmitted to the IoT edge server to ensure the security of the data during transmission and facilitate subsequent analysis and processing; on the IoT edge server, the security event data will be further analyzed to identify potential security trends and vulnerabilities, and the system will generate a security report for the security team to review and take further measures. In this step, by detecting and isolating security threats in a timely manner, the system can respond quickly, reducing potential losses and impacts; the isolation and repair measures effectively prevent the spread of threats, protecting the security of the network and data; transmitting the security event data to the edge server facilitates in-depth analysis and long-term trend monitoring, improving the intelligent level of security management; the automated repair measures and data collection process reduce manual intervention, improving the response efficiency and accuracy.

[0026] The IoT edge server generates communication device control instructions and updates the security protection policy according to the security event data, and transmits the updated policy back to the intelligent router, and sends the communication device control instructions to the communication device; The communication device receives the communication device control instructions and controls the background network activities of its own applications according to the communication device control instructions, including: restricting or allowing network access permissions for specific applications, adjusting the data transmission priority of applications; It is understandable that in this step, the communication device receives communication device control instructions from the IoT edge server or the smart router through the network interface. These instructions contain specific instructions on how to manage the network activities of the applications. The communication device parses the received control instructions to identify the specific operations included in the instructions, such as restricting or allowing the network access rights of specific applications, and adjusting the data transmission priorities of the applications. According to the parsing results, the communication device checks the list of currently running application programs and adjusts the network access rights of each application: restrict access (that is, for the applications restricted by the instructions, the communication device will block their access to the network, possibly by closing the network connection or modifying the firewall rules), allow access (for the applications allowed by the instructions, the communication device will restore their network access rights to ensure that the applications can connect to the Internet normally). The communication device adjusts the data transmission priorities of each application according to the control instructions, including: increasing the priority (for applications that require quick response (such as video calls or online games), the communication device will give priority to processing their data packets to ensure their smooth operation), decreasing the priority (for less important applications (such as background updates or file downloads), the communication device will reduce their data transmission priorities to free up bandwidth for more important applications). After the communication device implements the above changes, it continuously monitors the network activities of the applications to ensure that the effects of the control instructions are verified. If problems are found, the device will record the relevant information and may request further instructions. The communication device feeds back the implementation results to the IoT edge server or the smart router, reporting the execution status of the control instructions and the network activity status of the applications for subsequent adjustment and optimization. In this step, by restricting or allowing the network access rights of specific applications, the communication device can effectively manage the bandwidth to ensure that critical applications obtain the required network resources. Adjusting the data transmission priorities of the applications can improve the user experience when using real-time applications (such as video conferencing or online games), reducing latency and stuttering. By controlling the network access rights of the applications, the communication device can prevent potential malicious applications or unnecessary network activities, enhancing the overall network security. The communication device can flexibly adjust the network activities according to real-time control instructions to ensure the best performance in different network environments and usage scenarios.

[0027] The communication device transmits the network usage data of the application to the IoT edge server; It is understandable that in this step, the communication device first monitors and collects the network usage data of each application running on it. This data includes information such as the bandwidth usage, data transfer rate, and connection status of each application. The collected network usage data needs to be formatted to ensure that it conforms to the data transfer format required by the Internet of Things edge server. This may involve converting the data into JSON or XML format for subsequent processing. The communication device establishes a connection with the Internet of Things edge server through a pre-configured network protocol (such as HTTP, MQTT, etc.). This step ensures that the data can be transmitted securely and reliably. Before data transmission, the communication device encrypts the network usage data to protect the privacy and security of the data. This can be achieved by using encryption protocols such as SSL / TLS. The communication device sends the formatted and encrypted network usage data to the Internet of Things edge server through the established connection to ensure that the data can reach the server in a timely manner for processing. After receiving the data, the Internet of Things edge server sends a confirmation message to the communication device indicating that the data has been successfully received. This feedback mechanism helps to ensure the reliability of data transmission. The communication device records the status and results of data transmission, including information such as success or failure and transmission time, for subsequent troubleshooting and performance monitoring. By transmitting the network usage data of the application to the Internet of Things edge server in this step, the system can monitor the network performance of each application in real time, detect and solve potential problems in a timely manner. The edge server can analyze the network usage of the application based on the collected data, thereby optimizing the allocation of network resources and improving the overall network efficiency. The data is encrypted during transmission to ensure the security of the network usage data and reduce the risk of data leakage. By analyzing the network usage data, the edge server can provide data support for network management and optimization, helping to formulate more effective network strategies.

[0028] The Internet of Things edge server generates a correction plan for the network optimization model based on the network usage data of the application (more refined sharing WiFi network optimization according to the network usage data of the applications running on each communication terminal).

[0029] The solution of this embodiment can dynamically adjust the frequency band and channel by the intelligent router to monitor the interference sources, signal strength, and channel occupancy of the WiFi network in real time, thereby reducing interference, improving signal quality, and network stability. The Internet of Things edge server generates targeted optimization strategies based on terminal attribute data, service type data, and historical working data to ensure that each communication device obtains the required network resources and improves the overall network usage efficiency. Through the security protection module of the intelligent router, it can detect and prevent illegal devices from accessing the WiFi network in real time, perform security vulnerability scans, and take isolation or repair measures in a timely manner to ensure network security. The status monitoring and feedback module of the terminal device can feedback the network usage data of the application to the Internet of Things edge server to form a closed-loop feedback mechanism, enabling the network optimization strategy to be dynamically adjusted according to the actual usage situation to ensure the continuous improvement of network performance. Through intelligent traffic management and optimization strategies, users can enjoy a smoother network experience when using multiple devices, reduce latency and stuttering phenomena, and meet the requirements of high-bandwidth applications. In summary, the solution of this embodiment can not only effectively improve the performance and security of multi-device shared WiFi networks, but also achieve continuous optimization through intelligent management, ultimately enhancing the overall network experience of users.

[0030] In some possible embodiments of the present invention, the step of the Internet of Things edge server analyzing the monitoring data to obtain the first data analysis result includes: After receiving the monitoring data, the Internet of Things edge server preprocesses the monitoring data according to preset data cleaning rules, including: removing outliers, filling in missing values, and data standardization; wherein, the determination of outliers is based on the statistical characteristics of historical data, and the missing values are obtained by interpolating data at adjacent time points; The Internet of Things edge server extracts features from the preprocessed monitoring data to obtain feature data, specifically including: extracting the number, signal strength, and occupied channel distribution characteristics of interference sources from the surrounding interference source data; extracting the signal attenuation trend and signal fluctuation law from the WiFi signal strength data; extracting the average occupancy rate, peak occupancy period, and idle period distribution of each channel from the channel occupancy data; The Internet of Things edge server performs classification and clustering analysis on the feature data based on a pre-trained deep learning model, including: classifying the current network environment status as "congested", "normal", or "idle"; identifying the types and influence degrees of main interference sources; grading the channel quality; The Internet of Things edge server combines the temporal characteristics of the feature data and uses time series analysis methods to predict the network environment change trend in a future period of time (a period of time with a preset duration), including: predicting the change in the occupancy rate of each channel; predicting the activity pattern of interference sources; predicting the change pattern of signal strength; The IoT edge server integrates the above analysis results to form a first data analysis result, including: a current network environment status assessment report; a channel quality score and ranking; an interference source impact analysis report; a network environment prediction report.

[0031] The solution of this embodiment improves the accuracy and reliability of subsequent analysis through data preprocessing; comprehensively depicts the characteristics of the network environment through multi-dimensional feature extraction, providing a sufficient basis for subsequent optimization decisions; realizes the accurate assessment and problem location of the network environment through the classification analysis of the deep learning model; predicts the network environment change through time series analysis to support the formulation of anticipatory optimization decisions; the integrated analysis results provide comprehensive data support for formulating network optimization strategies, improving the scientificity and effectiveness of optimization decisions.

[0032] In some possible implementation manners of the present invention, the step that the IoT edge server generates a first optimization strategy according to a preset network optimization model, the first data analysis result, the terminal attribute data, the service type data, and the historical working data, and transmits the first optimization strategy to the intelligent router includes: The IoT edge server determines a first optimization target for the current network environment based on the first data analysis result, including: when the network environment status is "congested", setting load balancing and interference avoidance as the main optimization targets; when the network environment status is "normal", setting service quality improvement as the main optimization target; when the network environment status is "idle", setting energy consumption optimization as the main optimization target; The IoT edge server analyzes and integrates the terminal attribute data, service type data, and historical working data to obtain a first analysis result, including: classifying devices according to terminal attribute data, including: mobile terminals, fixed terminals, IoT devices; grading applications according to service type data, including: real-time services, interactive services, background services; calculating the average bandwidth requirements and peak and valley periods of various types of terminals based on historical working data. The IoT edge server calls a preset network optimization model, which includes: a resource allocation model based on deep reinforcement learning; a channel allocation model based on genetic algorithms; a QoS control model based on fuzzy logic. The IoT edge server inputs the first analysis result and the first optimization target into the network optimization model, and performs target optimization calculations to obtain a first calculation result, including: calculating an optimal channel allocation scheme; calculating the bandwidth allocation quota for each terminal; calculating a service priority scheduling strategy. The IoT edge server generates a first optimization policy based on the first calculation result, including: a channel switching instruction for specifying the working channels of each terminal; a bandwidth allocation instruction for specifying the bandwidth upper limit of each terminal; a QoS control instruction for setting the priorities and resource quotas of various services; a load balancing instruction for determining the distribution of terminals among multiple frequency bands; The IoT edge server verifies the executability of the first optimization policy, including: checking whether the policy conforms to the terminal hardware constraints; verifying the expected network performance after the implementation of the policy; evaluating the impact of the policy on existing services; The IoT edge server encodes the first optimization policy that passes the verification into an instruction set recognizable by the router and transmits it to the intelligent router through a secure channel.

[0033] The solution of this embodiment improves the adaptability of the optimization policy through the dynamic adjustment of the optimization objectives of environmental perception; realizes differentiated resource allocation through terminal classification and service grading, and improves the user experience; finds a better solution in complex scenarios through multi-model collaborative optimization; ensures the actual effect of the optimization policy through policy executability verification; overall, it realizes the intelligent and refined management of network resources, improves network performance and user satisfaction.

[0034] In some possible implementation manners of the present invention, the steps for the intelligent router to switch the working frequency band and channel according to the first optimization policy and allocate and control the network traffic of each communication device include: After receiving the first optimization policy, the intelligent router performs policy parsing and extracts the following control instructions: a frequency band switching instruction (determining the usage configuration of the 2.4GHz and 5GHz frequency bands); a channel allocation instruction (determining the target working channels under each frequency band); a traffic control instruction (including bandwidth allocation and QoS parameters); Before performing the frequency band and channel switching, the intelligent router sends a switching notice to all connected communication devices, including: broadcasting switching time window information; sending new frequency band and channel parameters; setting a reconnection waiting time threshold; The intelligent router performs frequency band and channel switching within a preset time window according to the following steps, including: pausing the access of new devices; saving the current network connection status; switching to the target frequency band and channel according to the instruction; waiting for the device to reconnect; resuming the device access function; The intelligent router performs grouped management on the reconnected communication devices, including: preferentially allocating dual-band supported devices to the 5GHz frequency band; allocating fixed-position devices to channels with stronger signals; allocating mobile devices to channels with lighter loads; The intelligent router configures the QoS policy based on the traffic control instruction, including: setting the bandwidth ceiling and guaranteed bandwidth for each device; configuring the service priority queue; enabling the traffic shaping algorithm; The intelligent router monitors the optimization effect in real time, including: recording the device reconnection success rate; counting the actual usage of each channel; measuring the key network performance indicators; When the intelligent router detects the following abnormal situations, it triggers emergency handling, including: automatically reverting to the original configuration when the device reconnection failure rate exceeds the threshold; temporarily adjusting the traffic control parameters when the network performance significantly decreases; starting the standby channel mechanism when a new interference source appears.

[0035] The solution of this embodiment reduces the impact of frequency band and channel switching on the user experience through prior notification and step-by-step switching; optimizes the network resource utilization efficiency through grouped management and differential configuration; ensures the reliability of network optimization through real-time monitoring and emergency handling; meets the service quality requirements of different devices and services through the refined configuration of the QoS policy; and overall realizes the smooth adjustment of network parameters and the efficient utilization of network resources.

[0036] In some possible embodiments of the present invention, the steps of the intelligent router detecting and preventing illegal devices from accessing the WiFi network and performing a security vulnerability scan on the connected communication devices include: The intelligent router authenticates the devices attempting to access the WiFi network, including: obtaining the MAC address and device type identifier of the device; extracting the access time and geographical location information of the device; checking whether the device is in the authorized device white list; verifying the validity of the access credentials provided by the device; When detecting the following situations, the intelligent router will determine it as illegal access: the device MAC address is repeated with the connected device; the device MAC address exists in the blacklist database; multiple incorrect password access attempts are made within a short period of time; the device access behavior characteristics match the attack characteristics library; The intelligent router takes preventive measures against illegal access devices, including: adding the device to the temporary blacklist; prohibiting subsequent access requests for this MAC address; recording the detailed information of the illegal access event; sending a security warning to legitimate users; The intelligent router regularly performs a security scan on the connected communication devices, including: scanning the known vulnerabilities of the device operating system; detecting whether the device installs the latest security patches; identifying whether there are abnormal network behaviors on the device; checking whether the network protocol configuration of the device is secure; The intelligent router monitors the network behaviors of the communication devices in real time, including: analyzing whether the traffic pattern of the device is abnormal; detecting whether the device accesses malicious websites; monitoring whether there are unauthorized port openings on the device; identifying whether the device generates abnormal network requests; The intelligent router classifies the security risks discovered by scanning, including: Emergency level: Vulnerabilities that can lead to system intrusion; High-risk level: Vulnerabilities that can leak sensitive data; Medium-risk level: Vulnerabilities that can affect system performance; Low-risk level: Configurations with potential security risks; The intelligent router takes corresponding measures according to the security risk levels, including: implementing device isolation for emergency-level risks; restricting network access permissions for high-risk-level risks; adjusting security configurations for medium-risk-level risks; and sending repair suggestions for low-risk-level risks.

[0037] The solution of this embodiment effectively prevents illegal devices from accessing through multi-dimensional authentication; discovers network security threats in a timely manner through real-time behavior monitoring; realizes precise control of security protection through a hierarchical processing mechanism; reduces network security risks through proactive security scanning; and overall constructs an active defense and multi-level network security protection system.

[0038] In some possible implementation manners of the present invention, the steps of the IoT edge server generating communication device control instructions and updating security protection policies according to the security event data, and transmitting the updated policies back to the intelligent router, and sending the communication device control instructions to the communication device include: After receiving the security event data, the IoT edge server performs security event analysis, including: extracting the type, occurrence time, and involved devices of the security event; analyzing the severity and impact range of the event; determining the potential harm and urgency of the event; and tracing the threat by associating historical security event data; Based on the security event analysis results, the IoT edge server determines response strategies, including: matching a preset protection plan for known type attacks; starting an adaptive protection mechanism for unknown type attacks; formulating a repair plan for system vulnerabilities; and determining control measures for abnormal behaviors; The IoT edge server generates communication device control instructions, including: generating application access control instructions; generating network connection restriction instructions; generating system configuration modification instructions; generating data transmission policy instructions; The IoT edge server updates security protection policies, including: updating device access rules; updating traffic monitoring rules; updating vulnerability scanning rules; updating security warning thresholds; The IoT edge server verifies the updated security protection policies, including: checking for conflicts between policies; evaluating the effectiveness of the policies; predicting the impact of policy implementation; and confirming the compatibility of the policies; The IoT edge server performs policy distribution, including: sending the updated security protection policy to the smart router; sending communication device control instructions to the corresponding communication devices respectively; setting a policy effective time window; establishing a policy execution feedback mechanism; The IoT edge server monitors the policy execution effect, including: collecting policy execution status feedback; evaluating the security protection effect; recording policy update logs; maintaining policy version information.

[0039] The solution of this embodiment realizes accurate threat identification and response through multi-dimensional security event analysis; improves the pertinence of security protection through differentiated response strategies; ensures the coordination of security measures through unified policy management; guarantees the effectiveness of security protection through policy execution monitoring; and overall realizes the rapid response to security events and the dynamic optimization of security protection.

[0040] In some possible implementation manners of the present invention, the step in which the IoT edge server generates a correction solution for the network optimization model according to the network usage data of the application includes: The IoT edge server preprocesses the network usage data of the application, including: counting the bandwidth usage and time distribution of each application; extracting the network behavior characteristics of the application; identifying the quality of service requirements of the application; analyzing the resource competition relationship between applications; The IoT edge server constructs an application portrait based on the preprocessed data, including: determining the business priority category of the application; establishing a resource demand model of the application; predicting the bandwidth usage trend of the application; identifying the typical working mode of the application; The IoT edge server evaluates the network optimization model, including: calculating the error between the model prediction value and the actual value; analyzing the performance of the model in different scenarios; identifying the optimization space of the model; determining the model parameters that need to be corrected; The IoT edge server generates a model correction solution based on the application portrait, including: adjusting the resource allocation weight coefficient; updating the quality of service evaluation index; optimizing the load balancing algorithm; modifying the bandwidth reservation policy; The IoT edge server performs model verification, including: verifying the corrected model using historical data; conducting multi-scenario simulation tests; evaluating the generalization ability of the model; calculating the improvement degree of the optimization effect; The IoT edge server implements incremental learning, including: integrating new application features into the model; updating the training data set of the model; adjusting the learning parameters of the model; optimizing the prediction accuracy of the model; The IoT edge server deploys the updated model, including: generating a model deployment package; setting a model switching time point; establishing model version management; saving model update records.

[0041] The solution of this embodiment realizes more accurate resource demand prediction through the construction of portraits; improves the adaptability of network optimization through model dynamic correction; continuously improves the model performance through the incremental learning mechanism; ensures the reliability of model updates through multi-dimensional verification; overall, it realizes the continuous evolution of the network optimization model and the steady improvement of the optimization effect.

[0042] In some possible implementation manners of the present invention, the construction method of the network optimization model includes: Construct a model input layer, including: collecting network environment feature data, including signal strength, interference level, and channel occupancy rate; collecting terminal device feature data, including device type, hardware capabilities, and location information; collecting application feature data, including bandwidth requirements, latency sensitivity, and service priority; performing normalization processing and encoding conversion on the collected feature data; Construct a hidden layer of a deep neural network, including: designing a multi-layer perceptron structure for feature extraction and representation learning; configuring an attention mechanism to highlight the influence of important features; adding a recurrent neural network unit to capture temporal dependencies; setting up a convolutional layer to extract local feature patterns; Construct a reinforcement learning module, including: defining a state space, including network environment and device states; designing an action space, including operations such as frequency band selection, bandwidth allocation, and priority scheduling; constructing a reward function, comprehensively considering indicators such as network throughput, latency, and fairness; implementing an experience replay mechanism to improve learning efficiency; Construct a decision output layer, including: designing a frequency band and channel allocation policy generator; designing a bandwidth allocation policy generator; designing a QoS control policy generator; adding a policy feasibility constraint check mechanism; Perform model training, including: performing supervised pre-training based on historical data; performing online training through reinforcement learning; implementing experience replay and target network update; dynamically adjusting the learning rate and exploration rate; Realize model evaluation and tuning, including: setting performance evaluation indicators, including throughput, latency, and fairness; performing cross-validation to evaluate the generalization ability of the model; performing sensitivity analysis to identify key parameters; optimizing the model structure and parameters based on the evaluation results; Establish a model application mechanism, including: realizing model inference acceleration; designing a model compression scheme; constructing a model update mechanism; realizing anomaly detection and fault tolerance processing.

[0043] The solution of this embodiment improves the model's understanding ability of the network environment through multi-level feature learning; realizes the autonomous learning and continuous improvement of network optimization strategies through a reinforcement learning mechanism; balances multiple dimensions of network performance through multi-objective optimization design; ensures the reliability and stability of the optimization effect through model evaluation and tuning; and overall constructs an adaptive and scalable network optimization decision-making system.

[0044] In some possible implementation manners of the present invention, the step of constructing the hidden layer of the deep neural network includes: Specifically, constructing a multi-layer perceptron structure: setting the number of nodes in the first hidden layer to be 2 times the input feature dimension, and using the ReLU activation function; setting the number of nodes in the second hidden layer to be 1 / 2 of the first layer, and using the ReLU activation function; setting the number of nodes in the third hidden layer to be 1 / 2 of the second layer, and using the ReLU activation function; adding a batch normalization layer between adjacent layers to improve training stability; using the Dropout mechanism to prevent overfitting, and setting the dropout rate to 0.3; Specifically, constructing an attention mechanism layer: calculating the correlation matrix between feature vectors; using the softmax function to convert the correlation into attention weights; performing weighted summation on the features based on the attention weights; concatenating the weighted result with the original features; and fusing the concatenated features through a fully connected layer; Specifically, constructing a recurrent neural network unit: using an LSTM unit to process the time series feature sequence; setting the dimension of the LSTM hidden state to 128; configuring a bidirectional LSTM structure to capture bidirectional time series dependencies; adding a residual connection to alleviate the problem of gradient disappearance; and using a sequence mask to process variable-length sequences; Specifically, constructing a convolutional layer structure: setting the size of the convolutional kernel in the first layer to 3×3, the stride to 1, and the paddling to same (Padding refers to adding additional pixels to the edge of the input data to control the size of the output feature map; setting it to "same" means adding padding to the edge of the input so that the size of the output feature map is the same as that of the input feature map; this is usually achieved by adding an appropriate number of zeros to each side of the input to ensure that the convolutional operation does not lose edge information); setting the size of the convolutional kernel in the second layer to 3×3, the stride to 2, to achieve feature dimensionality reduction; adding a BatchNormalization layer and a ReLU activation function after each convolutional layer; using a max pooling layer for feature screening; adding a skip connection to retain fine-grained features; Specifically, implementing a feature fusion mechanism: concatenating the output of the multi-layer perceptron and the output of the attention mechanism; fusing the concatenated result with the output of the LSTM; inputting the fused result into the convolutional layer for feature extraction; using a 1×1 convolution to adjust the number of feature channels; and generating the final feature representation through a fully connected layer; The specific configuration of the inter-layer connection mechanism is as follows: adding residual connections between key layers; achieving multi-scale feature fusion; setting up a feature pyramid structure; adding a gated update mechanism; implementing a dynamic routing mechanism; The specific addition of regularization and optimization mechanisms is as follows: applying L2 regularization to constrain the weights; implementing gradient clipping to prevent gradient explosion; using a learning rate decay strategy; configuring an early stopping mechanism; achieving sparsification of model parameters.

[0045] The solution of this embodiment realizes the high-order abstract representation of features through a multi-layer perceptron structure, improving the expression ability of the model; highlights the influence of important features through the attention mechanism, improving the recognition accuracy of the model; effectively captures temporal dependence relationships through a recurrent neural network, enhancing the temporal modeling ability of the model; realizes the automatic extraction of local features through a convolutional layer, improving the efficiency of feature extraction; and constructs a deep neural network structure with strong feature learning ability through the synergistic effect of multiple mechanisms.

[0046] Please refer to Figure 2 , another embodiment of the present invention provides a multi-device shared WiFi network optimization system for executing a multi-device shared WiFi network optimization method, including: an intelligent router, a communication device, and an Internet of Things edge server; The intelligent router is configured to: Real-time monitor the surrounding interference sources, signal strength, and channel occupancy of the WiFi network, obtain monitoring data, and transmit the monitoring data to the Internet of Things edge server; The Internet of Things edge server is configured to: Analyze the monitoring data to obtain a first data analysis result; Obtain the terminal attribute data, service type data, and historical working data of the communication terminals connected to the intelligent router; Generate a first optimization strategy according to a preset network optimization model, the first data analysis result, the terminal attribute data, the service type data, and the historical working data, and transmit the first optimization strategy to the intelligent router; The intelligent router is further configured to: Switch the working frequency band and channel according to the first optimization strategy, and allocate and control the network traffic of each communication device; Detect and prevent illegal devices from accessing the WiFi network, and perform security vulnerability scanning on the connected communication devices; When a security threat is detected, take isolation or repair measures, and transmit the security event data to the Internet of Things edge server; The Internet of Things edge server is further configured to: Generate communication device control instructions and update security protection policies based on the security event data, send the updated policies back to the intelligent router, and send the communication device control instructions to the communication device; The communication device is configured to: Receive the communication device control instructions and control the background network activities of its own applications according to the communication device control instructions, including: restricting or allowing network access permissions for specific applications, and adjusting the data transmission priorities of applications; Transmit the network usage data of the applications to the Internet of Things edge server; The Internet of Things edge server is further configured to: generate a correction scheme for the network optimization model according to the network usage data of the applications.

[0047] It should be known that Figure 2 The block diagram of the multi-device shared WiFi network optimization system shown is only for illustration, and the number of each module shown does not limit the protection scope of the present invention. The multi-device shared WiFi network optimization system provided in this embodiment can be used to execute the implementation schemes of the corresponding multi-device shared WiFi network optimization methods. For the specific implementation process, please refer to the descriptions of the method embodiments, which will not be elaborated here.

[0048] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be adopted in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0049] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0050] In several embodiments provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the above division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0051] The units described above as separate components may or may not be physically separated. 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 according to actual needs to achieve the purpose of the solution of this embodiment.

[0052] In addition, each functional unit in various embodiments of the present application may be integrated into a processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0053] If the above integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this 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 for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the above methods in various embodiments of the present application. The aforementioned memory includes: USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs and other media that can store program codes.

[0054] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory. The memory may include: flash drives, read-only memories (abbreviation: ROM), random access memories (abbreviation: RAM), magnetic disks, or optical discs, etc.

[0055] The above has introduced the embodiments of the present application in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

[0056] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily conceive of changes or substitutions without departing from the spirit and scope of the present invention, and can make various modifications and alterations, including combinations of the above different functions and implementation steps, including software and hardware implementation manners, all within the protection scope of the present invention.

Claims

1. A method for optimizing a WiFi network shared by multiple devices, characterized in that: include: The smart router monitors the surrounding interference sources, signal strength and channel occupancy of the WiFi network in real time, obtains monitoring data, and transmits the monitoring data to the IoT edge server; The IoT edge server analyzes the monitoring data to obtain a first data analysis result; The IoT edge server obtains terminal attribute data, service type data, and historical work data of the communication terminal connected to the smart router; The IoT edge server generates a first optimization strategy according to a preset network optimization model, the first data analysis result, the terminal attribute data, the service type data and the historical work data, and transmits the first optimization strategy to the smart router; The intelligent router switches the working frequency band and channel according to the first optimization strategy, and distributes and controls the network traffic of each of the communication devices; The intelligent router detects and blocks illegal devices from accessing the WiFi network, and scans the connected communication devices for security vulnerabilities; When a security threat is detected, isolation or repair measures are taken, and security event data is transmitted to the IoT edge server; The IoT edge server generates a communication device control instruction and updates a security protection strategy based on the security event data, transmits the updated strategy back to the smart router, and sends the communication device control instruction to the communication device; The communication device receives the communication device control instruction, and controls the background network activities of its own application according to the communication device control instruction, including: limiting or allowing network access rights of specific applications, and adjusting the data transmission priority of applications; The communication device transmits the network usage data of the application to the IoT edge server; The IoT edge server generates a correction scheme for the network optimization model based on the network usage data of the application.

2. The multi-device shared WiFi network optimization method according to claim 1, characterized in that: The IoT edge server analyzes the monitoring data to obtain a first data analysis result, comprising: After receiving the monitoring data, the IoT edge server pre-processes the monitoring data according to preset data cleaning rules, including: removing outliers, supplementing missing values, and data standardization; wherein the determination of the outliers is based on the statistical characteristics of historical data, and the missing values ​​are obtained by interpolating data from adjacent time points; The IoT edge server extracts features from the preprocessed monitoring data to obtain feature data, specifically including: extracting the number of interference sources, signal strength, and occupied channel distribution characteristics from the surrounding interference source data; extracting the signal attenuation trend and signal fluctuation law from the WiFi signal strength data; extracting the average occupancy rate, peak occupancy period, and idle period distribution of each channel from the channel occupancy data; The IoT edge server classifies and clusters the feature data based on a pre-trained deep learning model, including: classifying the current network environment status as "congested", "normal" or "idle"; identifying the type of the main interference source and its impact; and grading the channel quality; The IoT edge server combines the time series characteristics of the feature data and uses a time series analysis method to predict the trend of network environment changes in the future, including: predicting the occupancy rate changes of each channel; predicting the activity rules of interference sources; predicting the change pattern of signal strength; The IoT edge server integrates the above analysis results to form a first data analysis result, including: a current network environment status assessment report; channel quality scoring and ranking; an interference source impact analysis report; and a network environment prediction report.

3. The multi-device shared WiFi network optimization method according to claim 2, characterized in that: The IoT edge server generates a first optimization strategy according to a preset network optimization model, the first data analysis result, the terminal attribute data, the service type data, and the historical work data, and transmits the first optimization strategy to the smart router, including: The IoT edge server determines a first optimization target of the current network environment based on the first data analysis result, including: when the network environment state is "congested", setting load balancing and interference avoidance as the main optimization target; when the network environment state is "normal", setting service quality improvement as the main optimization target; when the network environment state is "idle", setting energy consumption optimization as the main optimization target; The IoT edge server analyzes and integrates the terminal attribute data, the service type data and the historical work data to obtain a first analysis result, including: classifying devices according to the terminal attribute data, including: mobile terminals, fixed terminals, IoT devices; grading applications according to the service type data, including: real-time services, interactive services, and background services; and calculating the average bandwidth requirements and peak and trough periods of various types of terminals based on the historical work data; The IoT edge server calls a preset network optimization model, which includes: a resource allocation model based on deep reinforcement learning; a channel allocation model based on genetic algorithm; and a QoS control model based on fuzzy logic; The IoT edge server inputs the first analysis result and the first optimization target into the network optimization model, and performs target optimization calculation to obtain a first calculation result, including: calculating an optimal channel allocation scheme; calculating a bandwidth allocation quota for each terminal; and calculating a service priority scheduling strategy; The IoT edge server generates a first optimization strategy including the following contents according to the first calculation result: a channel switching instruction for specifying a working channel of each terminal; a bandwidth allocation instruction for specifying a bandwidth upper limit of each terminal; a QoS control instruction for setting a priority and resource quota for each type of service; and a load balancing instruction for determining the distribution of terminals among multiple frequency bands; The IoT edge server verifies the feasibility of the first optimization strategy, including: checking whether the strategy complies with the terminal hardware constraints; verifying the expected network performance after the strategy is implemented; and evaluating the impact of the strategy on existing services; The IoT edge server encodes the verified first optimization strategy into an instruction set recognizable by the router, and transmits it to the smart router through a secure channel.

4. The method for optimizing a multi-device shared WiFi network according to claim 3, characterized in that: The step of the intelligent router switching the working frequency band and channel according to the first optimization strategy and distributing and controlling the network traffic of each of the communication devices includes: After receiving the first optimization strategy, the intelligent router performs strategy analysis and extracts the following control instructions: frequency band switching instruction; channel allocation instruction; flow control instruction; Before executing the frequency band and channel switching, the intelligent router sends a switching notice to all connected communication devices, including: broadcasting the switching time window information; sending the new frequency band and channel parameters; setting the reconnection waiting time threshold; The intelligent router performs frequency band and channel switching in the preset time window according to the following steps, including: suspending new device access; saving the current network connection status; switching to the target frequency band and channel according to the instruction; waiting for the device to reconnect; and restoring the device access function; The intelligent router manages the reconnected communication devices in groups, including: allocating dual-band devices to the 5GHz band first; allocating fixed-position devices to channels with stronger signals; and allocating mobile devices to channels with lighter loads. The intelligent router configures QoS policies based on traffic control instructions, including: setting bandwidth upper and lower limits for each device; configuring service priority queues; and enabling traffic shaping algorithms; The intelligent router monitors the optimization effect in real time, including: recording the device reconnection success rate; counting the actual usage of each channel; measuring key indicators of network performance; The intelligent router triggers emergency processing when detecting the following abnormal situations, including: automatically falling back to the original configuration when the device reconnection failure rate exceeds a threshold; temporarily adjusting the flow control parameters when the network performance is significantly reduced; and starting the backup channel mechanism when a new interference source appears.

5. The method for optimizing a multi-device shared WiFi network according to claim 4, characterized in that: The steps of the intelligent router detecting and preventing illegal devices from accessing the WiFi network and scanning the connected communication devices for security vulnerabilities include: The smart router authenticates the device attempting to access the WiFi network, including: obtaining the MAC address and device type identification of the device; extracting the access time and geographic location information of the device; checking whether the device is in the authorized device whitelist; and verifying the validity of the access credentials provided by the device; The smart router will determine illegal access when the following situations are detected: the device MAC address is the same as the connected device; the device MAC address exists in the blacklist database; multiple attempts to access with the wrong password in a short period of time; the device access behavior characteristics match the attack feature library; The intelligent router takes blocking measures against illegal access devices, including: adding the device to a temporary blacklist; prohibiting subsequent access requests from the MAC address; recording detailed information of illegal access events; and sending security warnings to legitimate users; The smart router regularly performs security scans on connected communication devices, including: scanning known vulnerabilities of the device operating system; detecting whether the device has the latest security patches installed; identifying whether the device has abnormal network behavior; and checking whether the device's network protocol configuration is secure. The intelligent router monitors the network behavior of the communication device in real time, including: analyzing whether the traffic pattern of the device is abnormal; detecting whether the device visits malicious websites; monitoring whether the device has unauthorized ports open; identifying whether the device generates abnormal network requests; The intelligent router classifies the potential security risks found by the scan, including: Emergency level: vulnerabilities that can lead to system intrusion; High-risk: vulnerabilities that can leak sensitive data; Medium-risk: vulnerabilities that can affect system performance; Low risk: configurations with potential security risks; The intelligent router takes corresponding measures according to the level of security risks, including: implementing equipment isolation for emergency-level risks; restricting network access rights for high-risk risks; adjusting security configuration for medium-risk risks; and sending repair suggestions for low-risk risks.

6. The method for optimizing a multi-device shared WiFi network according to claim 5, characterized in that: The IoT edge server generates a communication device control instruction and updates a security protection strategy according to the security event data, and transmits the updated strategy back to the smart router, and sends the communication device control instruction to the communication device, including: After receiving the security event data, the IoT edge server performs security event analysis, including: extracting the type, occurrence time, and involved devices of the security event; analyzing the severity and impact of the event; determining the potential harm and urgency of the event; and correlating historical security event data to trace the threat source; The IoT edge server determines a response strategy based on the security event analysis results, including: matching a preset protection plan for known types of attacks; starting an adaptive protection mechanism for unknown types of attacks; formulating a repair plan for system vulnerabilities; and determining control measures for abnormal behaviors; The IoT edge server generates communication device control instructions, including: generating application access control instructions; generating network connection restriction instructions; generating system configuration modification instructions; generating data transmission strategy instructions; The IoT edge server updates the security protection strategy, including: updating device access rules; updating traffic monitoring rules; updating vulnerability scanning rules; and updating security warning thresholds; The IoT edge server verifies the updated security protection strategy, including: checking conflicts between strategies; evaluating the effectiveness of strategies; predicting the impact of strategy implementation; and confirming the compatibility of strategies; The IoT edge server executes policy distribution, including: sending the updated security protection policy to the smart router; sending the communication device control instructions to the corresponding communication devices respectively; setting the policy effective time window; and establishing a policy execution feedback mechanism; The IoT edge server monitors the policy execution effect, including: collecting policy execution status feedback; evaluating security protection effect; recording policy update logs; and maintaining policy version information.

7. The method for optimizing a multi-device shared WiFi network according to claim 6, characterized in that: The step of the IoT edge server generating a correction scheme for the network optimization model according to the network usage data of the application includes: The IoT edge server pre-processes the network usage data of the applications, including: counting the bandwidth usage and time distribution of each application; extracting the network behavior characteristics of the application; identifying the service quality requirements of the application; and analyzing the resource competition relationship between applications; The IoT edge server constructs an application profile based on the preprocessed data, including: determining the business priority category of the application; establishing a resource demand model for the application; predicting the bandwidth usage trend of the application; and identifying the typical working mode of the application; The IoT edge server evaluates the network optimization model, including: calculating the error between the model prediction value and the actual value; analyzing the performance of the model in different scenarios; identifying the optimization space of the model; and determining the model parameters that need to be corrected; The IoT edge server generates a model correction plan based on the application profile, including: adjusting the resource allocation weight coefficient; updating the service quality evaluation index; optimizing the load balancing algorithm; and modifying the bandwidth reservation strategy; The IoT edge server performs model verification, including: using historical data to verify the revised model; performing multi-scenario simulation tests; evaluating the generalization ability of the model; and calculating the degree of improvement in optimization effect; The IoT edge server implements incremental learning, including: integrating new application features into the model; updating the training data set of the model; adjusting the learning parameters of the model; and optimizing the prediction accuracy of the model; The IoT edge server deploys the updated model, including: generating a model deployment package; setting a model switching time point; establishing model version management; and saving model update records.

8. The method for optimizing a multi-device shared WiFi network according to claim 7, characterized in that: The method for constructing the network optimization model includes: Constructing the model input layer includes: collecting network environment feature data, including signal strength, interference level, and channel occupancy; collecting terminal device feature data, including device type, hardware capabilities, and location information; collecting application feature data, including bandwidth requirements, delay sensitivity, and service priority; and performing standardization and encoding conversion on the collected feature data; Constructing the hidden layers of deep neural networks, including: designing a multi-layer perceptron structure for feature extraction and representation learning; configuring an attention mechanism to highlight the impact of important features; adding recurrent neural network units to capture temporal dependencies; setting up convolutional layers to extract local feature patterns; Constructing a reinforcement learning module, including: defining the state space, including the network environment and device status; designing the action space, including operations such as frequency band selection, bandwidth allocation, and priority scheduling; constructing a reward function, taking into account network throughput, latency, and fairness; implementing an experience replay mechanism to improve learning efficiency; Construct the decision output layer, including: designing the frequency band and channel allocation strategy generator; designing the bandwidth allocation strategy generator; designing the QoS control strategy generator; adding the strategy feasibility constraint checking mechanism; Perform model training, including: supervised pre-training based on historical data; online training through reinforcement learning; implementing experience replay and target network updates; dynamically adjusting learning rate and exploration rate; Implement model evaluation and tuning, including: setting performance evaluation indicators, including throughput, latency, and fairness; performing cross-validation to evaluate model generalization capabilities; performing sensitivity analysis to identify key parameters; and optimizing model structure and parameters based on evaluation results; Establish a model application mechanism, including: realizing model reasoning acceleration; designing a model compression scheme; building a model update mechanism; and realizing anomaly detection and fault-tolerant processing.

9. The method for optimizing a multi-device shared WiFi network according to claim 8, characterized in that: The step of constructing a hidden layer of a deep neural network comprises: The specific steps of constructing the multi-layer perceptron structure are as follows: the number of nodes in the first hidden layer is set to be twice the input feature dimension, and the ReLU activation function is used; the number of nodes in the second hidden layer is set to be 1 / 2 of the first layer, and the ReLU activation function is used; the number of nodes in the third hidden layer is set to be 1 / 2 of the second layer, and the ReLU activation function is used; batch normalization layers are added between adjacent layers to improve training stability; the Dropout mechanism is used to prevent overfitting, and the dropout rate is set to 0.3; The specific steps of constructing the attention mechanism layer are: calculating the correlation matrix between feature vectors; using the softmax function to convert the correlation into attention weights; weighted summing the features based on the attention weights; concatenating the weighted results with the original features; and fusing the concatenated features through the fully connected layer. The specific steps of building a recurrent neural network unit are: using LSTM units to process time series feature sequences; setting the LSTM hidden state dimension to 128; configuring a bidirectional LSTM structure to capture bidirectional time series dependencies; adding residual connections to alleviate the gradient vanishing problem; using sequence masks to process variable-length sequences; The specific steps of building the convolutional layer structure are as follows: set the size of the first convolution kernel to 3×3, the step size to 1, and the padding to the same; set the size of the second convolution kernel to 3×3, the step size to 2 to achieve feature dimensionality reduction; add a BatchNormalization layer and a ReLU activation function after each convolution layer; use a maximum pooling layer for feature screening; add skip connections to retain fine-grained features; The specific implementation of the feature fusion mechanism is as follows: concatenate the multi-layer perceptron output with the attention mechanism output; fuse the concatenation result with the LSTM output; input the fusion result into the convolution layer for feature extraction; use 1×1 convolution to adjust the number of feature channels; generate the final feature representation through the fully connected layer; The inter-layer connection mechanism is specifically configured as follows: adding residual connections between key layers; realizing multi-scale feature fusion; setting up feature pyramid structure; adding gated update mechanism; realizing dynamic routing mechanism; Adding regularization and optimization mechanisms specifically involves: applying L2 regularization to constrain weights; implementing gradient clipping to prevent gradient explosion; using a learning rate decay strategy; configuring an early stopping mechanism; and achieving sparse model parameters.

10. A multi-device shared WiFi network optimization system, used to execute the multi-device shared WiFi network optimization method according to any one of claims 1 to 9, characterized in that: Includes: smart routers, communication equipment and IoT edge servers; The smart router is configured as: Real-time monitoring of the surrounding interference sources, signal strength, and channel occupancy of the WiFi network to obtain monitoring data, and transmit the monitoring data to the IoT edge server; The IoT edge server is configured as: Analyzing the monitoring data to obtain a first data analysis result; Acquire terminal attribute data, service type data and historical work data of a communication terminal connected to the intelligent router; Generate a first optimization strategy according to a preset network optimization model, the first data analysis result, the terminal attribute data, the service type data and the historical work data, and transmit the first optimization strategy to the intelligent router; The intelligent router is also configured as: Switching the working frequency band and channel according to the first optimization strategy, and allocating and controlling the network traffic of each of the communication devices; Detect and prevent illegal devices from accessing the WiFi network, and scan the connected communication devices for security vulnerabilities; When a security threat is detected, isolation or repair measures are taken, and security event data is transmitted to the IoT edge server; The IoT edge server is also configured as: Generate communication device control instructions and update security protection strategies according to the security event data, transmit the updated strategies back to the intelligent router, and send the communication device control instructions to the communication device; The communication device is configured to: Receive the communication device control instruction, and control the background network activities of its own application according to the communication device control instruction, including: limiting or allowing network access rights of specific applications, and adjusting the data transmission priority of applications; Transmitting the application's network usage data to the IoT edge server; The IoT edge server is also configured to generate a correction scheme for the network optimization model based on the network usage data of the application.

Images