A self-adaptive adjustment system and method for portable WiFi network

Abstract

The present invention relates to the field of wireless communication technology, and in particular to a self-adaptive adjustment system and method for a portable wifi network, comprising a dynamic environment perception module, an intelligent network evaluation module, a user behavior analysis module, an optimization decision engine, a network automatic adjustment module, and a self-learning module; wherein: the dynamic environment perception module: real-time collection of the strength of surrounding wireless signals, the geographical location of user equipment, and network congestion; the intelligent network evaluation module: network quality evaluation; the user behavior analysis module: used to monitor the user's network usage behavior and predict the user's future network needs; the optimization decision engine: used to generate specific network optimization strategies; the network automatic adjustment module: used to perform specific adjustment operations. The present invention, by real-time monitoring of the network environment and user behavior, intelligently generates optimization strategies, and uses deep learning to continuously optimize, significantly improving network performance and user experience.

Description

Technical Field

[0001] The present invention relates to the field of wireless communication technology, and in particular to a system and method for adaptively adjusting a portable Wi-Fi network. Background Art

[0002] With the rapid development of mobile Internet, portable WiFi devices have become the main tool for users to obtain network connection on the move. These devices can provide convenient network access services, support the connection of multiple terminal devices, and meet users' Internet access needs in different scenarios. However, with the complexity of the network environment and the diversification of user needs, traditional portable WiFi devices often face many challenges, such as unstable signals, low data transmission rate and network congestion. These problems seriously affect users' network experience.

[0003] Existing portable WiFi devices usually use fixed network settings, which are difficult to dynamically adjust according to the actual network environment and user needs, resulting in the inability to provide optimal network services when the network conditions are complex and changeable. Traditional methods lack the perception and intelligent evaluation of the real-time network environment, lack the ability to analyze and predict user behavior, and cannot generate effective network optimization strategies. At the same time, the existing technology lacks self-learning and optimization mechanisms, making it difficult to continuously improve network performance during use.

[0004] Therefore, there is an urgent need for a new method that can solve these technical problems, achieve adaptive adjustment of portable WiFi networks, and improve network performance and user experience. Summary of the invention

[0005] Based on the above objectives, the present invention provides a system and method for adaptively adjusting a portable WiFi network.

[0006] An adaptive adjustment system for a portable wifi network includes a dynamic environment perception module, an intelligent network evaluation module, a user behavior analysis module, an optimization decision engine, a network automatic adjustment module, and a self-learning module; wherein:

[0007] Dynamic environment perception module: Through a variety of preset sensors, it collects the strength of surrounding wireless signals, the geographical location of user devices, and network congestion in real time, and transmits the collected data to the intelligent network evaluation module;

[0008] Intelligent network evaluation module: receives data provided by the dynamic environment perception module, uses the relevant vector machine algorithm to evaluate the network quality, outputs the evaluation results of signal stability, data transmission rate and network delay, and sends the evaluation results to the user behavior analysis module and the optimization decision engine;

[0009] User behavior analysis module: used to monitor users' network usage behavior, including streaming media consumption, data download volume, and online time, and predict users' future network needs, and transmit the prediction results to the optimization decision engine;

[0010] Optimization decision engine: used to receive data provided by the intelligent network evaluation module and the user behavior analysis module, and generate specific network optimization strategies based on network quality evaluation results and user demand predictions, and transmit the optimization strategies to the network automatic adjustment module;

[0011] Network automatic adjustment module: receives the network optimization strategy generated by the optimization decision engine, automatically adjusts the network parameters of the portable WiFi device, and performs specific adjustment operations, including channel switching, signal enhancement, and load balancing;

[0012] Self-learning module: obtains adjusted network parameters and user experience feedback from the network automatic adjustment module, optimizes the intelligent network evaluation module and optimization decision engine using deep learning technology, and continuously improves network evaluation and optimization strategies.

[0013] Optionally, the dynamic environment perception module includes a signal strength sensor unit, a location sensor unit and a network congestion sensor unit; wherein:

[0014] Signal strength sensor unit: including RSSI sensor, which is used to collect the strength of surrounding wireless signals in real time. The RSSI sensor outputs the value of signal strength by measuring the received signal power;

[0015] Position sensor unit: including GPS submodule and WiFi positioning submodule, used to locate the geographical location of the user device in real time. The GPS submodule is used to receive satellite signals to calculate the longitude and latitude of the device, and the WiFi positioning submodule is used to scan the surrounding WiFi signals and match them with the known locations in the database to calibrate the device location;

[0016] Network congestion sensor unit: includes flow monitoring sensor and packet delay detection sensor, which are used to monitor the current network congestion. The flow monitoring sensor determines the network load by counting the data flow per unit time; the packet delay detection sensor evaluates the real-time congestion status of the network by measuring the delay time from sending to receiving the data packet.

[0017] Optionally, the intelligent network evaluation module includes a data receiving unit, a preprocessing unit, an evaluation unit and an output unit; wherein:

[0018] Data receiving unit: used to receive real-time data from the dynamic environment perception module, including wireless signal strength, geographic location of user equipment and network congestion;

[0019] Preprocessing unit: used to preprocess the received data, including denoising, normalization and feature extraction, and generate a feature vector V for evaluation;

[0020] Evaluation unit: Use the relevance vector machine algorithm to evaluate the network quality of the preprocessed feature vector V. Specifically, the network quality evaluation result is calculated by the following formula: Among them, Q represents the network quality assessment result, w i represents the weight, represents the kernel function mapping of the feature vector, b represents the bias, and m represents the dimension of the feature vector;

[0021] Output unit: splits the network quality evaluation results generated by the evaluation unit into three parts: signal stability R, data transmission rate D and network delay E, and sends the split results to the user behavior analysis module and the optimization decision engine.

[0022] Optionally, the user behavior analysis module includes a data monitoring unit, a data storage unit, a data processing unit and a demand prediction unit; wherein:

[0023] Data monitoring unit: used to monitor and collect users' network usage behavior data in real time, including streaming media consumption, data download volume and online time;

[0024] The data monitoring unit specifically includes:

[0025] Streaming Monitoring Subunit: used to monitor the data consumption of users on the streaming platform, and to generate streaming consumption data by recording the data usage of each streaming playback;

[0026] Download volume monitoring subunit: used to monitor the user's data download activities and generate data download volume by recording the size of each data download;

[0027] Online duration monitoring subunit: used to monitor the user's online time and generate online duration data by recording the duration of each time the user connects to the network;

[0028] Data storage unit: used to store the user network usage behavior data collected by the data monitoring unit, and the data storage unit includes a database for storing the behavior data;

[0029] Data processing unit: processes the stored user network usage behavior data, including data cleaning, normalization and feature extraction, to generate feature vectors for demand forecasting;

[0030] Demand forecasting unit: Based on the feature vector output by the data processing unit, it uses historical behavior data and machine learning algorithms to predict users' future network needs and transmits the forecast results to the optimization decision engine.

[0031] Optionally, the demand forecasting unit specifically includes:

[0032] Data preprocessing: receiving the preprocessed feature vector from the data processing unit and normalizing the feature vector;

[0033] Build a historical behavior database: collect and store users' historical network usage behavior data to form a historical behavior database; historical behavior data includes past streaming media consumption, data downloads, and online time;

[0034] Feature matching: Match the current feature vector with the feature vector in the historical behavior database. Specifically, the nearest neighbor algorithm is used to calculate the similarity between the current feature vector and the historical feature vector. The formula is:

[0035] Among them, Sim(V, V′) represents the similarity between the feature vector V and the historical feature vector V′, v i and v i ′ represents the i-th eigenvalue of the eigenvectors V and V′, respectively, and n represents the dimension of the eigenvector;

[0036] Machine learning model training: Use decision tree algorithms to train historical behavior data and build prediction models. Decision tree models recursively segment feature spaces to establish decision rules for predicting users’ future network needs.

[0037] Predicting users’ future network needs: Input the current feature vector into the trained decision tree model to predict the user’s streaming consumption, data download volume, and online time in a predetermined time period in the future.

[0038] Optionally, the optimization decision engine includes a data receiving unit, a strategy generating unit and a strategy customizing unit; wherein:

[0039] Data receiving unit: used to receive data from the intelligent network evaluation module and the user behavior analysis module;

[0040] Strategy generation unit: generates specific network optimization strategies based on the received network quality assessment results and user demand predictions;

[0041] The strategy generation unit specifically includes:

[0042] Evaluation and analysis subunit: used to analyze network quality evaluation results and identify current network performance bottlenecks;

[0043] Demand analysis subunit: Analyzes the user demand forecast results to determine the user's future network usage peak period, streaming media consumption trends, and data download needs;

[0044] Policy customization unit: customizes optimization strategies that adapt to current network conditions and predict user needs based on the outputs of the evaluation and analysis subunit and the demand analysis subunit.

[0045] Optionally, the policy customization unit specifically includes:

[0046] Resource allocation strategy customization: Comprehensive network quality assessment results and user demand forecast results are used to formulate resource allocation plans, giving priority to resource allocation in high-demand areas and high-usage time periods. The formula is:

[0047] ResourceAllocation represents the resources allocated to the scheduled time period t, U t Indicates the user demand forecast value for this time period, represents the sum of user demands in all time periods, and R represents the total available resources;

[0048] Parameter adjustment strategy customization: Develop specific parameter adjustment plans for identified network performance bottlenecks, including wireless channel switching, transmission power adjustment, and access point optimization operations. The specific adjustment formula is:

[0049] P new =Pc urrent +ΔP, where P new represents the adjusted transmission power, P current represents the current transmission power, and ΔP represents the adjustment amplitude;

[0050] Generate comprehensive optimization strategy: Integrate resource allocation strategy and parameter adjustment strategy to generate comprehensive optimization strategy.

[0051] Optionally, the network automatic adjustment module includes a policy receiving unit, a channel switching unit, a signal enhancement unit and a load balancing unit; wherein:

[0052] Strategy receiving unit: used for receiving the network optimization strategy generated by the optimization decision engine;

[0053] Channel switching unit: used to automatically select and switch to a wireless channel with less interference according to the channel switching instructions in the optimization strategy;

[0054] The channel switching unit comprises:

[0055] Channel scanning subunit: used to scan all currently available wireless channels, evaluate the interference and signal strength of each channel, and select the channel with the least interference and the strongest signal;

[0056] Channel switching control subunit: used to perform channel switching operation according to the selection result of the channel scanning subunit, and switch to the channel recommended in the optimization strategy;

[0057] Signal enhancement unit: adjusts the transmission power and antenna direction of the WiFi device according to the signal enhancement instructions in the optimization strategy;

[0058] The signal enhancement unit comprises:

[0059] Transmission power adjustment subunit: used to adjust the transmission power of the WiFi device according to the instructions in the optimization strategy;

[0060] Antenna direction control subunit: used to adjust the antenna direction according to the instructions in the optimization strategy;

[0061] Load balancing unit: used to dynamically allocate network resources according to the load balancing instructions in the optimization strategy;

[0062] The load balancing unit specifically includes:

[0063] Traffic monitoring subunit: used to monitor the data traffic and network usage of each connected device in real time and collect traffic data;

[0064] Load distribution subunit: It is used to dynamically allocate network resources and balance the load between devices based on the data of the traffic monitoring subunit. The formula is: Among them, L new represents the new load assigned to device j, R represents the total available resources, and U i represents the current network requirements of device i, Represents the total demand of all devices.

[0065] Optionally, the self-learning module includes a data collection unit, a data processing unit, a model training unit and a strategy optimization unit; wherein:

[0066] Data collection unit: used to obtain adjusted network parameters and user experience feedback from the network automatic adjustment module, including adjusted channels, transmission power, load distribution results and their corresponding user experience feedback;

[0067] Data processing unit: pre-process the collected data, including data cleaning, normalization and labeling;

[0068] Model training unit: Use deep learning technology to train models on processed data and learn the impact of network parameter adjustment on user experience;

[0069] Strategy optimization unit: used to generate improved network evaluation and optimization strategies based on model training results.

[0070] A method for adaptively adjusting a portable WiFi network comprises the following steps:

[0071] S1: Use multiple sensors to collect real-time data on the strength of surrounding wireless signals, the geographic location of user devices, and network congestion.

[0072] S2: receives the data provided by S1, and uses the correlation vector machine algorithm to evaluate the network quality, and outputs the evaluation results of signal stability, data transmission rate and network delay;

[0073] S3: monitors users’ network usage behavior in real time, including streaming consumption, data downloads, and online time, and predicts users’ future network needs through historical data and machine learning algorithms;

[0074] S4: Generate specific network optimization strategies, including resource allocation and parameter adjustment, based on the network quality evaluation results in S2 and the user demand prediction in S3;

[0075] S5: After receiving the optimization strategy, the network parameters of the portable WiFi device are automatically adjusted and specific adjustment operations are performed, including channel switching, signal enhancement and load balancing;

[0076] S5: Obtain adjusted network parameters and user experience feedback, use deep learning technology to optimize network quality assessment and optimization strategies, and continuously improve network assessment and optimization strategies.

[0077] Beneficial effects of the present invention:

[0078] The present invention, through user behavior analysis and optimization strategy generation, can formulate a more reasonable network resource allocation plan based on a deep understanding of user needs, which not only includes balanced distribution of network load, but also involves adjusting network parameters according to user behavior trends, such as channel switching and signal strength adjustment. The implementation of this strategy effectively solves the problem of insufficient response of traditional portable WiFi devices when user needs change, greatly improves the personalization of network services and user satisfaction. Through this method, the portable WiFi device can automatically adjust the settings to adapt to the changing network conditions and user needs, so as to continuously provide the best network services.

[0079] The present invention continuously optimizes network evaluation and optimization strategies through deep learning technology. After obtaining adjusted network parameters and user experience feedback, it can continuously learn and improve to maintain the best state in a dynamic and complex network environment. Through this continuous learning and optimization, the effectiveness and real-time performance of network adjustment measures are ensured, and the system's adaptive ability and user satisfaction are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0081] Figure 1 A schematic diagram of a network adaptive adjustment system according to an embodiment of the present invention;

[0082] Figure 2 Schematic diagram of a method for adaptively adjusting a portable WiFi network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0083] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0084] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0085] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0086] like Figure 1 As shown, a self-adaptive adjustment system for a portable WiFi network includes a dynamic environment perception module, an intelligent network evaluation module, a user behavior analysis module, an optimization decision engine, a network automatic adjustment module, and a self-learning module; wherein:

[0087] Dynamic environment perception module: Through a variety of preset sensors, it collects the strength of surrounding wireless signals, the geographical location of user devices, and network congestion in real time, and transmits the collected data to the intelligent network evaluation module;

[0088] Intelligent network evaluation module: receives data provided by the dynamic environment perception module, uses the relevance vector machine (RVM) algorithm to evaluate network quality, outputs evaluation results of signal stability, data transmission rate and network delay, and sends the evaluation results to the user behavior analysis module and optimization decision engine;

[0089] User behavior analysis module: used to monitor users' network usage behavior, including streaming media consumption, data download volume, and online time, and predict users' future network needs, and transmit the prediction results to the optimization decision engine;

[0090] Optimization decision engine: used to receive data provided by the intelligent network evaluation module and the user behavior analysis module, and generate specific network optimization strategies based on network quality evaluation results and user demand predictions, and transmit the optimization strategies to the network automatic adjustment module;

[0091] Network automatic adjustment module: receives the network optimization strategy generated by the optimization decision engine, automatically adjusts the network parameters of the portable WiFi device, and performs specific adjustment operations, including channel switching, signal enhancement, and load balancing, to achieve network optimization;

[0092] Self-learning module: obtains adjusted network parameters and user experience feedback from the network automatic adjustment module, optimizes the intelligent network evaluation module and optimization decision engine using deep learning technology, continuously improves network evaluation and optimization strategies, and realizes self-evolution of the system.

[0093] The dynamic environment perception module includes a signal strength sensor unit, a location sensor unit and a network congestion sensor unit; wherein:

[0094] Signal strength sensor unit: including RSSI (Received Signal Strength Indicator) sensor, which is used to collect the strength of surrounding wireless signals in real time. The RSSI sensor measures the received signal power and outputs the signal strength value, providing accurate data of wireless signal strength;

[0095] Position sensor unit: includes GPS submodule and WiFi positioning submodule, which are used to locate the geographical location of the user's device in real time. The GPS submodule is used to receive satellite signals to calculate the longitude and latitude of the device, and the WiFi positioning submodule is used to scan the surrounding WiFi signals and match them with the known locations in the database to calibrate the device location;

[0096] Network congestion sensor unit: includes flow monitoring sensor and packet delay detection sensor, which are used to monitor the current network congestion. The flow monitoring sensor determines the network load by counting the data flow in a unit time; the packet delay detection sensor evaluates the real-time congestion status of the network by measuring the delay time from sending to receiving the data packet. The specific process includes:

[0097] The formula for calculating data flow per unit time is: Among them, F represents the data flow per unit time, P i represents the size of the ith data packet, and T represents the length of the statistical period;

[0098] The formula for calculating the average delay time is: Where L represents the average delay time, S i represents the sending time of the ith data packet, R i represents the receiving time of the ith data packet, and n represents the number of data packets in the statistical period;

[0099] Taking traffic and latency into consideration, the network congestion index is calculated using the following formula: N = αF + βL, where N represents the network congestion index, and α and β are weight coefficients, which are set according to specific application scenarios. Through the coordinated work of the signal strength sensor unit, the geographic location sensor unit, and the network congestion sensor unit, the dynamic environment perception module can comprehensively and real-time collect the strength of the surrounding wireless signals, the geographic location of the user device, and the network congestion situation, providing accurate data support for the adaptive adjustment of the portable WiFi network. Through the precise measurement and real-time monitoring of these sensors, the system can quickly respond to environmental changes to ensure the optimization of network quality and user experience.

[0100] The intelligent network evaluation module includes a data receiving unit, a preprocessing unit, an evaluation unit and an output unit; wherein:

[0101] Data receiving unit: used to receive real-time data from the dynamic environment perception module, including wireless signal strength, geographic location of user equipment and network congestion;

[0102] Preprocessing unit: used to preprocess the received data, including denoising, normalization and feature extraction, and generate a feature vector V for evaluation;

[0103] Evaluation unit: Use the relevance vector machine algorithm to evaluate the network quality of the preprocessed feature vector V. Specifically, the network quality evaluation result is calculated by the following formula: Among them, Q represents the network quality assessment result, w i represents the weight, represents the kernel function mapping of the feature vector, b represents the bias, and m represents the dimension of the feature vector;

[0104] Output unit: splits the network quality evaluation results generated by the evaluation unit into three parts: signal stability R, data transmission rate D, and network delay E, and sends the split results to the user behavior analysis module and the optimization decision engine;

[0105] The specific splitting formula is as follows:

[0106] Signal stability R: Among them, S i represents the wireless signal strength collected for the i-th time, and n represents the total number of collections;

[0107] Data transfer rate D: Among them, P i represents the size of the ith data packet, T i represents the transmission time of the ith data packet, and n represents the total number of data packets;

[0108] Network delay E: Among them, R i represents the receiving time of the ith data packet, S i represents the sending time of the i-th data packet, and n represents the total number of data packets;

[0109] Through the design of the above-mentioned intelligent network evaluation module, the system can make full use of the advantages of the correlation vector machine algorithm to perform accurate network quality evaluation. The data receiving unit, preprocessing unit, evaluation unit and output unit in the module cooperate with each other to realize the automation of the entire process from data reception to the output of evaluation results, improve the accuracy and real-time performance of the evaluation, and thus provide reliable data support for network optimization.

[0110] The user behavior analysis module includes a data monitoring unit, a data storage unit, a data processing unit and a demand prediction unit; wherein:

[0111] Data monitoring unit: used to monitor and collect users' network usage behavior data in real time, including streaming media consumption, data download volume and online time;

[0112] The data monitoring unit specifically includes:

[0113] Streaming Monitoring Subunit: used to monitor the data consumption of users on the streaming platform, and to generate streaming consumption data by recording the data usage of each streaming playback;

[0114] Download volume monitoring subunit: used to monitor the user's data download activities and generate data download volume by recording the size of each data download;

[0115] Online duration monitoring subunit: used to monitor the user's online time and generate online duration data by recording the duration of each time the user connects to the network;

[0116] Data storage unit: used to store the user network usage behavior data collected by the data monitoring unit to ensure the integrity and security of the data. The data storage unit includes an efficient database for storing the behavior data;

[0117] Data processing unit: processes the stored user network usage behavior data, including data cleaning, normalization and feature extraction, to generate feature vectors for demand forecasting; data cleaning is used to remove noise and outliers in monitoring data to ensure data accuracy; normalization is used to standardize data from different sources so that they can be compared and analyzed on the same scale; feature extraction is used to extract key features from the cleaned and normalized data to generate feature vectors;

[0118] Demand forecasting unit: Based on the feature vector output by the data processing unit, the unit uses historical behavior data and machine learning algorithms to forecast the user's future network demand and transmits the forecast results to the optimization decision engine. The unit analyzes the user's historical network usage patterns and forecasts the user's network usage in a predetermined time period in the future.

[0119] Through the design of the above-mentioned user behavior analysis module, the system can comprehensively monitor the user's network usage behavior, including streaming media consumption, data download volume and online time. The mutual collaboration of the data monitoring unit, data storage unit, data processing unit and demand forecasting unit realizes the automation of the entire process from data monitoring to demand forecasting, improves the accuracy and real-time performance of the forecast, and thus provides reliable data support for network optimization.

[0120] The demand forecasting unit predicts the user's future network demand, including:

[0121] Data preprocessing: receiving the preprocessed feature vector from the data processing unit and normalizing the feature vector so that the data can be compared and analyzed on the same scale;

[0122] Build a historical behavior database: collect and store users' historical network usage behavior data to form a historical behavior database; historical behavior data includes past streaming media consumption, data downloads, and online time;

[0123] Feature matching: Match the current feature vector with the feature vector in the historical behavior database. Specifically, the K-Nearest Neighbors (KNN) algorithm is used to calculate the similarity between the current feature vector and the historical feature vector. The formula is:

[0124] Among them, Sim(V, V′) represents the similarity between the feature vector V and the historical feature vector V′, v i and v i ′ represents the i-th eigenvalue of the eigenvectors V and V′, respectively, and n represents the dimension of the eigenvector;

[0125] Machine learning model training: Use the decision tree algorithm to train historical behavior data and build a prediction model. The decision tree model recursively splits the feature space to establish decision rules for predicting users' future network needs. The training process of the decision tree includes selecting the best split point and creating branches. The goal is to maximize information gain. The formula is: Among them, IG(D, A) represents the information gain of feature A to data set D, H(D) represents the entropy of data set D, Values(A) represents all possible values ​​of feature A, and D v represents the data subset with value v on feature A;

[0126] Predicting users' future network needs: Input the current feature vector into the trained decision tree model to make predictions about the user's streaming media consumption, data download volume, and online time in a predetermined time period in the future. By integrating the above steps, the demand prediction unit can accurately predict users' future network needs based on the feature vector output by the data processing unit, using historical behavior data and the decision tree algorithm, providing key data support for the system's network optimization.

[0127] The optimization decision engine includes a data receiving unit, a strategy generating unit and a strategy customizing unit; wherein:

[0128] Data receiving unit: used to receive data from the intelligent network evaluation module and the user behavior analysis module. This unit ensures that the received network quality evaluation results and user demand prediction data are complete and real-time;

[0129] Strategy generation unit: generates specific network optimization strategies based on the received network quality assessment results and user demand predictions;

[0130] The strategy generation unit specifically includes:

[0131] Evaluation and analysis subunit: used to analyze network quality evaluation results and identify current network performance bottlenecks, such as unstable signals, low data transmission rates, or high network latency;

[0132] Demand analysis subunit: Analyzes the user demand forecast results to determine the user's future network usage peak period, streaming media consumption trends, and data download needs;

[0133] Strategy customization unit: customizes optimization strategies that adapt to current network conditions and predict user needs based on the outputs of the evaluation and analysis subunit and the demand analysis subunit;

[0134] By optimizing the design of the decision engine, it is possible to combine network performance data and user behavior predictions to intelligently generate customized network optimization strategies. Through meticulous strategy customization and parameter adjustment, the system ensures that network optimization measures can be effectively implemented, significantly improves network performance and user satisfaction, and effectively responds to network bottlenecks and changes in user needs.

[0135] The strategy customization unit specifically includes:

[0136] Resource allocation strategy customization: Comprehensive network quality assessment results and user demand forecast results are used to formulate resource allocation plans, giving priority to resource allocation in high-demand areas and high-usage time periods. The formula is:

[0137] ResourceAllocation represents the resources allocated to the scheduled time period t, U t Indicates the user demand forecast value for this time period, represents the sum of user demands in all time periods, and R represents the total available resources;

[0138] Parameter adjustment strategy customization: Develop specific parameter adjustment plans for identified network performance bottlenecks, including wireless channel switching, transmission power adjustment, and access point optimization operations. The specific adjustment formula is:

[0139] P new =P current +ΔP, where P new represents the adjusted transmission power, P current represents the current transmission power, and ΔP represents the adjustment amplitude;

[0140] Generate comprehensive optimization strategy: Integrate resource allocation strategy and parameter adjustment strategy to generate comprehensive optimization strategy, ensure that optimization strategies can cooperate with each other during implementation and improve overall network performance; by integrating the above steps, the strategy customization unit can customize optimization strategies that adapt to current network conditions and predict user needs based on the outputs of the evaluation and analysis subunit and the demand analysis subunit, thereby optimizing network performance.

[0141] The network automatic adjustment module includes a strategy receiving unit, a channel switching unit, a signal enhancement unit and a load balancing unit; wherein:

[0142] Policy receiving unit: used to receive the network optimization policy generated by the optimization decision engine, and ensure that the received policy data is complete and real-time;

[0143] Channel switching unit: used to automatically select and switch to a wireless channel with less interference according to the channel switching instructions in the optimization strategy;

[0144] The channel switching unit includes:

[0145] Channel scanning subunit: used to scan all currently available wireless channels, evaluate the interference and signal strength of each channel, and select the channel with the least interference and the strongest signal;

[0146] Channel switching control subunit: used to perform channel switching operations according to the selection results of the channel scanning subunit, and switch to the channel recommended in the optimization strategy to ensure the connection stability during the switching process;

[0147] Signal enhancement unit: adjusts the transmission power and antenna direction of the WiFi device according to the signal enhancement instructions in the optimization strategy to enhance the signal strength;

[0148] The signal booster unit includes:

[0149] Transmission power adjustment subunit: used to adjust the transmission power of the WiFi device according to the instructions in the optimization strategy. The formula is: P new =P current +ΔP, where P new represents the adjusted transmission power, P current represents the current transmission power, and ΔP represents the adjustment amplitude;

[0150] Antenna direction control subunit: used to adjust the antenna direction to optimize signal coverage and strength according to the instructions in the optimization strategy;

[0151] Load balancing unit: used to dynamically allocate network resources to optimize data transmission efficiency and user experience according to the load balancing instructions in the optimization strategy;

[0152] The load balancing unit specifically includes:

[0153] Traffic monitoring subunit: used to monitor the data traffic and network usage of each connected device in real time and collect traffic data;

[0154] Load distribution subunit: It is used to dynamically allocate network resources and balance the load between devices based on the data of the traffic monitoring subunit. The formula is: Among them, L new represents the new load assigned to device j, R represents the total available resources, and U i represents the current network requirements of device i, Represents the total demand of all devices; by integrating the above units, the network automatic adjustment module can automatically adjust the network parameters of the portable WiFi device according to the network optimization strategy generated by the optimization decision engine, and perform specific adjustment operations, including channel switching, signal enhancement and load balancing, to ensure the optimization of network performance and improvement of user experience.

[0155] The self-learning module includes a data collection unit, a data processing unit, a model training unit, and a strategy optimization unit; wherein:

[0156] Data collection unit: used to obtain adjusted network parameters and user experience feedback from the network automatic adjustment module, including adjusted channels, transmission power, load distribution results and their corresponding user experience feedback;

[0157] Data processing unit: pre-processes the collected data, including data cleaning, normalization and labeling, in preparation for training deep learning models;

[0158] The data processing unit includes:

[0159] Data cleaning subunit: used to remove invalid, erroneous or incomplete data records to ensure data quality;

[0160] Normalization subunit: used to convert data of different scales to a unified scale to facilitate model training;

[0161] Annotation subunit: used to annotate data, distinguish the before and after states of data and the improvement of user experience, and provide supervision signals;

[0162] Model training unit: Use deep learning technology to train models on processed data and learn the impact of network parameter adjustments on user experience; including designing deep learning network structures suitable for this system, such as convolutional neural networks (CNN) or recurrent neural networks (RNN) to process time series data and feature association analysis; and perform model training processes, using optimization algorithms such as gradient descent to adjust network weights to minimize prediction errors;

[0163] Strategy optimization unit: used to generate improved network evaluation and optimization strategies based on model training results;

[0164] Based on the trained model output, possible network optimization points are identified and new network optimization strategies are generated. The generated optimization strategies are fed back to the intelligent network evaluation module and the optimization decision engine for future network adjustment decisions.

[0165] like Figure 2 As shown, a method for adaptively adjusting a portable WiFi network includes the following steps:

[0166] S1: Use multiple sensors to collect real-time data on the strength of surrounding wireless signals, the geographic location of user devices, and network congestion.

[0167] S2: receives the data provided by S1, and uses the correlation vector machine algorithm to evaluate the network quality, and outputs the evaluation results of signal stability, data transmission rate and network delay;

[0168] S3: monitors users’ network usage behavior in real time, including streaming consumption, data downloads, and online time, and predicts users’ future network needs through historical data and machine learning algorithms;

[0169] S4: Generate specific network optimization strategies, including resource allocation and parameter adjustment, based on the network quality evaluation results in S2 and the user demand prediction in S3;

[0170] S5: After receiving the optimization strategy, the network parameters of the portable WiFi device are automatically adjusted and specific adjustment operations are performed, including channel switching, signal enhancement and load balancing;

[0171] S5: Obtain adjusted network parameters and user experience feedback, use deep learning technology to optimize network quality assessment and optimization strategies, and continuously improve network assessment and optimization strategies;

[0172] Through the above method, it is possible to perceive the network environment and user behavior in real time, intelligently evaluate network quality, accurately predict user needs, generate and implement optimization strategies, and conduct continuous learning and optimization, thereby significantly improving network performance and user experience.

[0173] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0174] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An adaptive adjustment system for a portable wifi network, characterized in that: It includes dynamic environment perception module, intelligent network evaluation module, user behavior analysis module, optimization decision engine, network automatic adjustment module and self-learning module; among which: Dynamic environment perception module: Through a variety of preset sensors, it collects the strength of surrounding wireless signals, the geographical location of user devices, and network congestion in real time, and transmits the collected data to the intelligent network evaluation module; Intelligent network evaluation module: receives data provided by the dynamic environment perception module, uses the relevant vector machine algorithm to evaluate the network quality, outputs the evaluation results of signal stability, data transmission rate and network delay, and sends the evaluation results to the user behavior analysis module and the optimization decision engine; User behavior analysis module: used to monitor users' network usage behavior, including streaming media consumption, data download volume, and online time, and predict users' future network needs, and transmit the prediction results to the optimization decision engine; Optimization decision engine: used to receive data provided by the intelligent network evaluation module and the user behavior analysis module, and generate specific network optimization strategies based on network quality evaluation results and user demand predictions, and transmit the optimization strategies to the network automatic adjustment module; Network automatic adjustment module: receives the network optimization strategy generated by the optimization decision engine, automatically adjusts the network parameters of the portable WiFi device, and performs specific adjustment operations, including channel switching, signal enhancement, and load balancing; Self-learning module: obtains adjusted network parameters and user experience feedback from the network automatic adjustment module, optimizes the intelligent network evaluation module and optimization decision engine using deep learning technology, and continuously improves network evaluation and optimization strategies.

2. According to claim 1, the adaptive adjustment system of a portable WiFi network is characterized in that: The dynamic environment perception module includes a signal strength sensor unit, a location sensor unit and a network congestion sensor unit; wherein: Signal strength sensor unit: including RSSI sensor, which is used to collect the strength of surrounding wireless signals in real time. The RSSI sensor outputs the value of signal strength by measuring the received signal power; Position sensor unit: including GPS submodule and WiFi positioning submodule, used to locate the geographical location of the user device in real time. The GPS submodule is used to receive satellite signals to calculate the longitude and latitude of the device, and the WiFi positioning submodule is used to scan the surrounding WiFi signals and match them with the known locations in the database to calibrate the device location; Network congestion sensor unit: includes flow monitoring sensor and packet delay detection sensor, which are used to monitor the current network congestion. The flow monitoring sensor determines the network load by counting the data flow per unit time; the packet delay detection sensor evaluates the real-time congestion status of the network by measuring the delay time from sending to receiving the data packet.

3. The adaptive adjustment system of a portable WiFi network according to claim 1, characterized in that: The intelligent network evaluation module includes a data receiving unit, a preprocessing unit, an evaluation unit and an output unit; wherein: Data receiving unit: used to receive real-time data from the dynamic environment perception module, including wireless signal strength, geographic location of user equipment and network congestion; Preprocessing unit: used to preprocess the received data, including denoising, normalization and feature extraction, and generate a feature vector v for evaluation; Evaluation unit: Use the relevance vector machine algorithm to evaluate the network quality of the preprocessed feature vector V. Specifically, the network quality evaluation result is calculated by the following formula: Among them, Q represents the network quality assessment result, w i represents the weight, represents the kernel function mapping of the feature vector, b represents the bias, and m represents the dimension of the feature vector; Output unit: splits the network quality evaluation results generated by the evaluation unit into three parts: signal stability R, data transmission rate D and network delay E, and sends the split results to the user behavior analysis module and the optimization decision engine.

4. The adaptive adjustment system of a portable WiFi network according to claim 1, characterized in that: The user behavior analysis module includes a data monitoring unit, a data storage unit, a data processing unit and a demand prediction unit; wherein: Data monitoring unit: used to monitor and collect users' network usage behavior data in real time, including streaming media consumption, data download volume and online time; The data monitoring unit specifically includes: Streaming Monitoring Subunit: used to monitor the data consumption of users on the streaming platform, and to generate streaming consumption data by recording the data usage of each streaming playback; Download volume monitoring subunit: used to monitor the user's data download activities and generate data download volume by recording the size of each data download; Online duration monitoring subunit: used to monitor the user's online time and generate online duration data by recording the duration of each time the user connects to the network; Data storage unit: used to store the user network usage behavior data collected by the data monitoring unit, and the data storage unit includes a database for storing the behavior data; Data processing unit: processes the stored user network usage behavior data, including data cleaning, normalization and feature extraction, to generate feature vectors for demand forecasting; Demand forecasting unit: Based on the feature vector output by the data processing unit, it uses historical behavior data and machine learning algorithms to predict users' future network needs and transmits the forecast results to the optimization decision engine.

5. The self-adaptive adjustment system of a portable WiFi network according to claim 4, characterized in that: The demand forecasting unit specifically includes: Data preprocessing: receiving the preprocessed feature vector from the data processing unit and normalizing the feature vector; Build a historical behavior database: collect and store users' historical network usage behavior data to form a historical behavior database; historical behavior data includes past streaming media consumption, data downloads, and online time; Feature matching: Match the current feature vector with the feature vector in the historical behavior database. Specifically, the nearest neighbor algorithm is used to calculate the similarity between the current feature vector and the historical feature vector. The formula is: Among them, Sim(V, V′) represents the similarity between the feature vector V and the historical feature vector V′, vi and vi′ represent the i-th eigenvalues ​​of the feature vectors V and V′ respectively, and n represents the dimension of the feature vector; Machine learning model training: Use decision tree algorithms to train historical behavior data and build prediction models. Decision tree models recursively segment feature spaces to establish decision rules for predicting users’ future network needs. Predicting users’ future network needs: Input the current feature vector into the trained decision tree model to predict the user’s streaming consumption, data download volume, and online time in a predetermined time period in the future.

6. The self-adaptive adjustment system of a portable WiFi network according to claim 1, characterized in that: The optimization decision engine includes a data receiving unit, a strategy generating unit and a strategy customizing unit; wherein: Data receiving unit: used to receive data from the intelligent network evaluation module and the user behavior analysis module; Strategy generation unit: generates specific network optimization strategies based on the received network quality assessment results and user demand predictions; The strategy generation unit specifically includes: Evaluation and analysis subunit: used to analyze network quality evaluation results and identify current network performance bottlenecks; Demand analysis subunit: Analyzes the user demand forecast results to determine the user's future network usage peak period, streaming media consumption trends, and data download needs; Policy customization unit: customizes optimization strategies that adapt to current network conditions and predict user needs based on the outputs of the evaluation and analysis subunit and the demand analysis subunit.

7. The self-adaptive adjustment system of a portable WiFi network according to claim 6, characterized in that: The policy customization unit specifically includes: Resource allocation strategy customization: Comprehensive network quality assessment results and user demand forecast results are used to formulate resource allocation plans, giving priority to resource allocation in high-demand areas and high-usage time periods. The formula is: ResourceAllocation represents the resources allocated to the scheduled time period t, U t Indicates the user demand forecast value for this time period, represents the sum of user demands in all time periods, and R represents the total available resources; Parameter adjustment strategy customization: Develop specific parameter adjustment plans for identified network performance bottlenecks, including wireless channel switching, transmission power adjustment, and access point optimization operations. The specific adjustment formula is: P new =P current +ΔP, where P new represents the adjusted transmission power, P current represents the current transmission power, and ΔP represents the adjustment amplitude; Generate comprehensive optimization strategy: Integrate resource allocation strategy and parameter adjustment strategy to generate comprehensive optimization strategy.

8. The self-adaptive adjustment system of a portable WiFi network according to claim 1, characterized in that: The network automatic adjustment module includes a strategy receiving unit, a channel switching unit, a signal enhancement unit and a load balancing unit; wherein: Strategy receiving unit: used for receiving the network optimization strategy generated by the optimization decision engine; Channel switching unit: used to automatically select and switch to a wireless channel with less interference according to the channel switching instructions in the optimization strategy; The channel switching unit comprises: Channel scanning subunit: used to scan all currently available wireless channels, evaluate the interference and signal strength of each channel, and select the channel with the least interference and the strongest signal; Channel switching control subunit: used to perform channel switching operation according to the selection result of the channel scanning subunit, and switch to the channel recommended in the optimization strategy; Signal enhancement unit: adjusts the transmission power and antenna direction of the WiFi device according to the signal enhancement instructions in the optimization strategy; The signal enhancement unit comprises: Transmission power adjustment subunit: used to adjust the transmission power of the WiFi device according to the instructions in the optimization strategy; Antenna direction control subunit: used to adjust the antenna direction according to the instructions in the optimization strategy; Load balancing unit: used to dynamically allocate network resources according to the load balancing instructions in the optimization strategy; The load balancing unit specifically includes: Traffic monitoring subunit: used to monitor the data traffic and network usage of each connected device in real time and collect traffic data; Load distribution subunit: It is used to dynamically allocate network resources and balance the load between devices based on the data of the traffic monitoring subunit. The formula is: Among them, L new represents the new load assigned to device j, R represents the total available resources, and U i represents the current network requirements of device i, Represents the total demand of all devices.

9. The self-adaptive adjustment system of a portable WiFi network according to claim 1, characterized in that: The self-learning module includes a data collection unit, a data processing unit, a model training unit and a strategy optimization unit; wherein: Data collection unit: used to obtain adjusted network parameters and user experience feedback from the network automatic adjustment module, including adjusted channels, transmission power, load distribution results and their corresponding user experience feedback; Data processing unit: pre-process the collected data, including data cleaning, normalization and labeling; Model training unit: Use deep learning technology to train models on processed data and learn the impact of network parameter adjustment on user experience; Strategy optimization unit: used to generate improved network evaluation and optimization strategies based on model training results.

10. A method for adaptively adjusting a portable WiFi network, implemented by an adaptively adjusting system for a portable WiFi network according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1: Use multiple sensors to collect real-time data on the strength of surrounding wireless signals, the geographic location of user devices, and network congestion. S2: receives the data provided by S1, and uses the correlation vector machine algorithm to evaluate the network quality, and outputs the evaluation results of signal stability, data transmission rate and network delay; S3: monitors users’ network usage behavior in real time, including streaming consumption, data downloads, and online time, and predicts users’ future network needs through historical data and machine learning algorithms; S4: Generate specific network optimization strategies, including resource allocation and parameter adjustment, based on the network quality evaluation results in S2 and the user demand prediction in S3; S5: After receiving the optimization strategy, the network parameters of the portable WiFi device are automatically adjusted and specific adjustment operations are performed, including channel switching, signal enhancement and load balancing; S6: Obtain adjusted network parameters and user experience feedback, use deep learning technology to optimize network quality assessment and optimization strategies, and continuously improve network assessment and optimization strategies.

Images