5G portable WiFi signal enhancement method and system

Abstract

According to the 5G portable WiFi signal enhancement method and system provided by the invention, surrounding environment data are collected through an environment sensing sensor, and a device placement scheme is optimized in combination with a deep learning algorithm, so that the signal coverage range is expanded; the strategy of dynamically adjusting the transmitting power, the signal frequency and the modulation mode can optimize the signal strength according to the environmental change; interference signals are analyzed through quantum calculation, null is formed through the beam forming technology, interference signal receiving is effectively restrained, and the signal strength in the target direction is enhanced. In combination with the Internet of Things technology, uploading equipment state data to an edge server in real time for big data analysis, and pushing a personalized signal enhancement scheme according to different user use environments; through precise placement guidance and a dynamic frequency band switching strategy, a user can enjoy smoother network connection in a use process, and good signal quality is ensured to be kept in a complex environment. According to the invention, not only can the signal quality of 5G portable WiFi be improved, but also more intelligent and personalized network experience can be provided for users.

Description

Technical Field

[0001] The present invention relates to the field of 5G technology, and in particular to a 5G portable WiFi signal enhancement method and system. Background Art

[0002] 5G smart portable WiFi devices have gradually become popular in recent years, providing users with a more convenient and high-speed network experience. 5G portable WiFi devices can provide faster data transmission speeds than traditional 4G devices, with a theoretical downlink rate of up to 10Gbps, and in actual use, it is generally several hundred Mbps or even higher, easily supporting high-definition video playback, 4K live broadcast and large file downloads; these devices are usually lightweight and easy to carry, without the need for installation and wiring, and provide WiFi signals anytime and anywhere; many 5G portable WiFi devices support large-volume packages, with monthly traffic of up to 1500G or more, meeting the user's long-term, large-volume usage needs; most devices can connect to multiple devices at the same time, usually around 32, to meet the needs of multiple people or multiple devices to access the Internet at the same time. Existing 5G portable WiFi devices have problems such as poor signal and lack of intelligence due to their changing working locations and simple structures. Summary of the invention

[0003] Based on the above problems, the present invention proposes a 5G portable WiFi signal enhancement method and system. Through the solution of the present invention, not only the signal quality of 5G portable WiFi can be improved, but also a more intelligent and personalized network experience can be provided for users.

[0004] In view of this, one aspect of the present invention proposes a 5G portable WiFi signal enhancement method, comprising: Enable multiple types of environment perception sensors built into the first 5G portable WiFi device to collect first data; Acquire in real time a first surrounding environment image within a first preset range of a location where a first terminal connected to the first 5G portable WiFi device is located, and a second surrounding environment image within a second preset range of a location where the first 5G portable WiFi device is located; Using a deep learning-based target detection algorithm, signal obstruction data is identified from the first surrounding environment image and the second surrounding environment image, and a placement scheme of the first 5G portable WiFi device is determined according to the signal obstruction data, the first data, and a preset device placement model; Activate the network monitoring program built into the first 5G portable WiFi device to scan the entire frequency band, and continuously collect signal data such as signal strength, phase, polarization characteristics, and noise spectrum distribution of each frequency band to construct an original data sample set; For the original data sample set, an adaptive filtering algorithm is used to dynamically adjust the filtering parameters to remove noise interference, a high-order statistical analysis method is used to mine the nonlinear characteristics in the signal data, and a time-frequency analysis tool is used to extract the time-varying characteristics of the frequency band and the frequency domain distribution characteristics; Use ensemble learning algorithms to fuse multiple weak classifiers and use historical frequency band features as input to build a frequency band quality assessment model; Combining the frequency band quality assessment model, the time-varying characteristics and the frequency domain distribution characteristics, to obtain a frequency band quality assessment result; According to the frequency band quality assessment result, based on a deep reinforcement learning algorithm, the frequency band switching action of the first 5G portable WiFi device is expanded to a continuous space; With the help of the parallel computing capability of quantum computing, a quantum neural network is constructed for interference signal analysis; The first 5G portable WiFi device uses coding technology based on the interference analysis results to dynamically adjust the coding rate according to the interference intensity; Combined with orthogonal frequency division multiplexing technology, subcarriers are allocated, and subcarriers in frequency bands with severe interference are used to transmit redundant information to ensure the correct transmission of key data; Introducing beamforming technology, using a multi-antenna array to form a null in the interference direction, suppressing the reception of interference signals and enhancing the signal strength in the target direction; Continue to use the semantic segmentation algorithm in image recognition and processing technology to segment the latest environmental images acquired in real time, identify the location, outline, and material of new obstructions, and evaluate their degree of signal obstruction; Based on the evaluation results of the degree of signal obstruction caused by the newly appeared obstructions, combined with the temperature, humidity and electromagnetic environment change data fed back by the IoT sensors in real time, the first 5G portable WiFi device dynamically adjusts the transmission power, signal frequency and modulation mode, and maintains high-frequency interaction with the mobile communication base station, uploads the local environment and signal status, downloads the latest optimization instructions, forms a closed-loop optimization link, and continuously and adaptively optimizes the signal enhancement effect; The key status data of the first 5G portable WiFi device is encrypted and uploaded to the edge server through the Internet of Things. The edge server performs big data analysis based on the data of multiple 5G portable WiFi devices, and pushes personalized signal enhancement solutions to different users based on the data analysis results.

[0005] Optionally, the step of using a deep learning-based target detection algorithm to identify signal obstruction data from the first surrounding environment image and the second surrounding environment image, and determining a placement solution for the first 5G portable WiFi device according to the signal obstruction data, the first data and a preset device placement model includes: The first surrounding environment image and the second surrounding environment image are subjected to standardization processing to obtain a third surrounding environment image and a fourth surrounding environment image; Using a deep learning-based target detection algorithm to perform target detection and instance segmentation on the third surrounding environment image and the fourth surrounding environment image, specifically including: extracting image features and generating candidate regions; classifying the candidate regions and identifying the types of occluders; generating pixel-level masks of occluders; and calculating the precise contours and spatial position information of the occluders; Based on the binocular vision principle, the third surrounding environment image and the fourth surrounding environment image are subjected to three-dimensional reconstruction, specifically including: extracting image feature points and matching them; calculating feature point parallax and constructing a depth map; generating a three-dimensional point cloud model of the occluder; and analyzing the surface features of the occluder and determining the material properties based on the material recognition model; In combination with the first environmental parameter in the first data, a signal propagation model is constructed, including: calculating the signal attenuation coefficient according to the three-dimensional position and material of the obstruction; considering the influence of temperature and humidity on signal propagation; simulating multipath effects and signal reflection and diffraction phenomena; Based on the preset device placement model, multi-objective optimization calculations are performed, including: inputting obstruction data, first environmental parameters, and signal propagation models; considering the device's heat dissipation requirements and operational convenience; using reinforcement learning algorithms to iteratively optimize placement positions and angles; and outputting the optimal placement plan, including specific coordinates and placement postures.

[0006] Optionally, the step of using an ensemble learning algorithm to fuse multiple weak classifiers and using historical frequency band features as input to construct a frequency band quality assessment model includes: Construct a multidimensional feature vector based on historical frequency band characteristics, including: extracting statistical features of signal strength, including mean, variance, skewness, and kurtosis; calculating signal stability indicators, including signal jitter rate and disconnection frequency; generating spectrum features such as spectrum occupancy rate and bandwidth utilization rate; normalizing feature data and detecting outliers; Construct multiple basic classifiers for different feature subspaces, including: deploying gradient boosting decision trees to process continuous features; configuring AdaBoost classifiers to process categorical features; applying random forests to process the correlation of high-dimensional features; assigning initial weights to each weak classifier; Design an adaptive integration strategy to dynamically adjust the classifier weights, including: calculating the prediction accuracy of each weak classifier; dynamically updating the classifier weights based on the accuracy; using a weighted voting mechanism to fuse the prediction results of each classifier; introducing a time decay factor to reduce the weight of historical data; Deploy a generative adversarial network to expand training data, including: building a generator network to simulate various interference scenarios; designing a discriminator network to distinguish between real and generated data; iteratively training the GAN network to generate high-quality samples; adding generated samples to the training set to improve model robustness; Realize refined grading of frequency band quality, including: establishing multi-level evaluation standards, including main classification and sub-classification; dynamically updating threshold parameters at each level; predicting frequency band quality change trends in combination with time series analysis; and continuously optimizing evaluation model parameters.

[0007] Optionally, the step of obtaining a frequency band quality assessment result by combining the frequency band quality assessment model, the time-varying feature and the frequency domain distribution characteristic includes: The input multi-source features are standardized, specifically including: normalizing the evaluation index output by the frequency band quality evaluation model; performing time window segmentation processing on the time-varying features; converting the frequency domain distribution characteristics into a unified feature vector; and constructing a feature fusion matrix; Dynamic evaluation based on time-varying characteristics, including: calculating the time series fluctuation index of signal strength; extracting the periodic change pattern of signal quality; analyzing the mutation feature points of signal parameters; generating time series evaluation scores; Conduct in-depth analysis of frequency domain distribution characteristics, including: calculating spectrum energy distribution density; identifying frequency domain interference characteristics; evaluating frequency band utilization efficiency; generating frequency domain evaluation scores; A weighted fusion strategy is used to integrate the evaluation results of each dimension, including: designing an adaptive weight calculation method; considering reliability indicators with different characteristics; integrating the evaluation scores of each dimension; and generating a comprehensive evaluation indicator; Generate the final frequency band quality assessment results based on comprehensive assessment indicators, including: establishing multi-threshold assessment standards; calculating quality level confidence; generating an assessment result report; and providing optimization suggestion instructions.

[0008] Optionally, the step of extending the frequency band switching action of the first 5G portable WiFi device to a continuous space based on a deep reinforcement learning algorithm according to the frequency band quality assessment result includes: Constructing the state representation of deep reinforcement learning, including: encoding the current frequency band quality assessment results; integrating historical frequency band switching records; collecting network environment parameters; constructing a multi-dimensional state vector; Expand the discrete frequency band switching into a continuous action space, including: defining the continuous value range of frequency and bandwidth; designing the action space mapping function; establishing action constraints; and realizing the action smooth transition mechanism; Deploy a dual network architecture to implement policy learning, including: building an Actor network to output continuous action values; deploying a Critic network to evaluate action values; designing an experience replay buffer pool; and implementing a soft update mechanism for the target network. Establish a multi-objective reward function, including: evaluating the effect of frequency band switching; considering the switching time cost; calculating the energy consumption penalty; integrating user experience indicators; Realize online learning and strategy updating, including: collecting interactive experience data; calculating temporal difference error; updating Actor-Critic network parameters; optimizing exploration-exploitation balance.

[0009] Optionally, the step of constructing a quantum neural network for interference signal analysis by means of the parallel computing capability of quantum computing includes: Encoding interference signal data into quantum states, including: using amplitude encoding method to map signal features to quantum bits; constructing quantum state superposition to represent multi-dimensional features; realizing quantum entanglement of feature space; and establishing quantum data preprocessing pipeline; Design a dedicated quantum neural network architecture, including: deploying a parameterized quantum circuit layer; building a quantum convolution layer to process time-frequency features; designing quantum pooling operation compression features; and implementing a quantum-classical hybrid computing interface. Using quantum parallelism to perform feature analysis, including: processing interference features of multiple frequency bands simultaneously; parallel calculation of time-frequency correlation; extracting hidden features from quantum state evolution; and constructing quantum feature maps; Realize quantum classification of interference patterns, including: design quantum measurement operators; construct quantum decision trees; realize quantum ensemble learning; output interference type probability distribution; Optimize the prediction model based on quantum feedback, including: designing a quantum gradient descent algorithm; realizing quantum acceleration of parameter updates; optimizing quantum-classical data conversion; and dynamically adjusting the model structure.

[0010] Optionally, the first 5G portable WiFi device adopts a coding technology based on the interference analysis result to dynamically adjust the coding rate according to the interference intensity, including: Multi-dimensional evaluation is performed based on the interference analysis results, including: calculating the dynamic range of signal-to-noise ratio; analyzing the time-frequency characteristics of the interference signal; evaluating the impact of interference on channel capacity; and generating quantitative indicators of interference intensity; Select the optimal coding scheme according to the interference intensity, including: constructing a hybrid coding library of LDPC codes and polar codes; designing coding scheme evaluation criteria; calculating the performance indicators of different coding schemes; and selecting the coding scheme that best suits the current interference environment; Dynamically adjust the coding parameter configuration, including: calculating the target coding rate based on the interference intensity; optimizing the codeword length and check bit distribution; adjusting the interleaving depth and pattern structure; generating optimized coding parameters; Realize real-time switching of coding schemes, including: designing a coding switching buffer mechanism; achieving smooth transition of coding parameters; monitoring coding performance indicators; and executing dynamic updates of coding schemes; Establish a coding effect feedback mechanism, including: collecting decoding error statistics; analyzing throughput change trends; evaluating coding overhead and gain ratio; and optimizing the coding strategy decision model.

[0011] Optionally, the step of combining orthogonal frequency division multiplexing technology to allocate subcarriers, using subcarriers in a frequency band that is severely interfered with to transmit redundant information, and ensuring correct transmission of key data includes: Dynamically evaluate the subcarriers in the OFDM system, including: measuring the signal-to-noise ratio of each subcarrier; evaluating the degree of interference between subcarriers; calculating the subcarrier channel capacity; generating subcarrier quality scores; Classify the data to be transmitted, including: identifying key data packets; calculating data transmission priority; estimating the required transmission reliability; generating data transmission strategies; Intelligent allocation based on subcarrier status, including: allocating high-quality subcarriers to critical data; using interfered subcarriers for redundant transmission; optimizing subcarrier combination schemes; and achieving dynamic bandwidth allocation; Design an adaptive redundant transmission mechanism, including: calculating the redundant data ratio; selecting a redundant coding scheme; determining the redundant data distribution; and implementing redundant transmission scheduling; Establish a real-time monitoring and adjustment mechanism, including: tracking data transmission success rate; analyzing transmission delay changes; evaluating resource utilization efficiency; and dynamically optimizing allocation strategies.

[0012] Optionally, the step of introducing beamforming technology, using a multi-antenna array, forming a null in the interference direction, suppressing reception of interference signals, and enhancing signal strength in the target direction includes: Channel characteristic analysis using multi-antenna arrays, including: obtaining the received signal characteristics of each antenna; calculating the signal correlation between antennas; estimating the signal arrival angle; and constructing a spatial channel matrix; Accurately identify the spatial location of interference sources, including: performing spatial spectrum scanning; calculating the signal arrival angle distribution; identifying the direction of the main interference source; generating a spatial distribution map of the interference source; Designing optimal beamforming weights, including: constructing an adaptive beamforming algorithm; calculating constraints on the null direction; optimizing the main lobe direction gain; generating a weight vector; Achieve precise beam control, including: configuring antenna array phase relationships; adjusting the transmit power of each antenna; synchronizing antenna array timing; and performing beamforming operations; Establish a real-time optimization feedback mechanism, including: monitoring beamforming effects; analyzing signal-to-interference ratio changes; evaluating system performance indicators; and adjusting beamforming strategies.

[0013] Another aspect of the present invention provides a 5G portable WiFi signal enhancement system for performing a 5G portable WiFi signal enhancement method, including: a first 5G portable WiFi device, a first terminal, and an edge server; The first 5G portable WiFi device is configured to: enable multiple types of environment perception sensors built into the first 5G portable WiFi device to collect first data; The edge server is configured as: Acquire in real time a first surrounding environment image within a first preset range of a location where a first terminal connected to the first 5G portable WiFi device is located, and a second surrounding environment image within a second preset range of a location where the first 5G portable WiFi device is located; Using a deep learning-based target detection algorithm, signal obstruction data is identified from the first surrounding environment image and the second surrounding environment image, and a placement scheme of the first 5G portable WiFi device is determined according to the signal obstruction data, the first data, and a preset device placement model; Activate the network monitoring program built into the first 5G portable WiFi device to scan the entire frequency band, and continuously collect signal data such as signal strength, phase, polarization characteristics, and noise spectrum distribution of each frequency band to construct an original data sample set; For the original data sample set, an adaptive filtering algorithm is used to dynamically adjust the filtering parameters to remove noise interference, a high-order statistical analysis method is used to mine the nonlinear characteristics in the signal data, and a time-frequency analysis tool is used to extract the time-varying characteristics of the frequency band and the frequency domain distribution characteristics; Use ensemble learning algorithms to fuse multiple weak classifiers and use historical frequency band features as input to build a frequency band quality assessment model; Combining the frequency band quality assessment model, the time-varying characteristics and the frequency domain distribution characteristics, to obtain a frequency band quality assessment result; According to the frequency band quality assessment result, based on a deep reinforcement learning algorithm, the frequency band switching action of the first 5G portable WiFi device is expanded to a continuous space; With the help of the parallel computing capability of quantum computing, a quantum neural network is constructed for interference signal analysis; The first 5G portable WiFi device is further configured as: Based on the interference analysis results, the coding technology is used to dynamically adjust the coding rate according to the interference intensity; Combined with orthogonal frequency division multiplexing technology, subcarriers are allocated, and subcarriers in frequency bands with severe interference are used to transmit redundant information to ensure the correct transmission of key data; Introducing beamforming technology, using a multi-antenna array to form a null in the interference direction, suppressing the reception of interference signals and enhancing the signal strength in the target direction; The edge server is also configured to: Continue to use the semantic segmentation algorithm in image recognition and processing technology to segment the latest environmental images acquired in real time, identify the location, outline, and material of new obstructions, and evaluate their degree of signal obstruction; According to the evaluation results of the degree of signal obstruction by the newly appeared obstructions, combined with the temperature, humidity, and electromagnetic environment change data fed back by the IoT sensors in real time, the first 5G portable WiFi device is controlled to dynamically adjust the transmission power, signal frequency, and modulation mode, and maintain high-frequency interaction with the mobile communication base station, upload the local environment and signal status, download the latest optimization instructions, form a closed-loop optimization link, and continuously and adaptively optimize the signal enhancement effect; The key status data of the first 5G portable WiFi device is received through the Internet of Things, and big data analysis is performed based on the data of multiple 5G portable WiFi devices. Based on the data analysis results, personalized signal enhancement solutions are pushed to different users.

[0014] By adopting the technical solution of the present invention, the surrounding environment data is collected by the environment perception sensor, and the placement scheme of the device is optimized by the deep learning algorithm, which can effectively improve the coverage of the signal and ensure that users can obtain stronger signals in different environments; the strategy of dynamically adjusting the transmission power, signal frequency and modulation mode can be adopted to optimize the signal strength according to the real-time environmental changes, reduce signal attenuation and interference, thereby improving the user's network experience; by analyzing the interference signal through quantum computing, and using the beamforming technology to form a zero-stuck, the reception of the interference signal can be effectively suppressed, the signal strength in the target direction can be enhanced, and the stable transmission of key data can be ensured; combined with the Internet of Things technology, the device status data is uploaded to the edge server in real time for big data analysis, and personalized signal enhancement schemes can be pushed according to the use environment of different users to achieve continuous adaptive optimization; through precise placement guidance and dynamic frequency band switching strategies, users can enjoy smoother network connections during use, reducing connection interruptions and delays caused by poor signals; according to the static characteristics and dynamic changes of the environment, the working state of the device can be adjusted in real time to ensure that good signal quality can be maintained in complex environments. In summary, the scheme of the embodiment of the present invention can not only improve the signal quality of 5G portable WiFi, but also provide users with a more intelligent and personalized network experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a 5G portable WiFi signal enhancement method provided by an embodiment of the present invention; Figure 2It is a schematic block diagram of a 5G portable WiFi signal enhancement system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

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

[0018] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. 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 includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0019] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0020] Refer to the following Figure 1 to Figure 2 To describe a 5G portable WiFi signal enhancement method and system provided according to some embodiments of the present invention.

[0021] like Figure 1 As shown, an embodiment of the present invention provides a 5G portable WiFi signal enhancement method, comprising: Enable multiple types of environment perception sensors built into the first 5G portable WiFi device to collect first data; It is understandable that multiple types of environmental perception sensors include infrared, ultrasonic, light sensors, etc., as well as micro-electromechanical systems (MEMS) accelerometers, gyroscopes, etc.; accelerometers and gyroscopes can sense the inclination of the plane on which the device is placed, and assist in determining whether the device is in a stable placement that is conducive to signal diffusion; the first data collected includes not only the material properties of nearby objects and the distance to obstacles, but also the ambient temperature, humidity, and even the direction and speed of air flow, because temperature and humidity will affect the characteristics of the signal transmission medium, and airflow may also cause signal perturbations. It is understandable that the device has a built-in basic intelligent analysis module, which is responsible for collecting and analyzing its own operating data such as device temperature, signal transmission power, and real-time connection speed.

[0022] Acquire in real time a first surrounding environment image within a first preset range of a location where a first terminal connected to the first 5G portable WiFi device is located, and a second surrounding environment image within a second preset range of a location where the first 5G portable WiFi device is located; It can be understood that in this step, first, ensure that the first terminal (such as a smart phone or tablet) is successfully connected to the first 5G portable WiFi device (including scanning of WiFi signals, sending of connection requests and connection confirmation); use the built-in positioning system of the first terminal (such as GPS, Wi-Fi positioning or Bluetooth positioning) to obtain its current geographical location in real time (the location data will be used to determine the first preset range); after determining the location of the first terminal, start the environmental image acquisition module (the module can use a built-in camera or an external camera device) to capture the surrounding environment image of the first terminal in real time; process and analyze the collected first surrounding environment image; use the image recognition algorithm to recognize the image objects, obstacles and other important features in the first 5G portable WiFi device for subsequent signal optimization and environmental adaptation; at the same time, the first 5G portable WiFi device should also obtain the environmental image within the second preset range of its own position (this step is similar to the image acquisition of the first terminal, ensuring that the environment around the device can be fully understood); the environmental image data collected by the first terminal and the first 5G portable WiFi device are integrated to form a comprehensive environmental data set. Using this data, the system can provide real-time feedback to optimize signal transmission and connection quality; according to the analysis results, the signal transmission parameters (such as frequency, power, etc.) of the first 5G portable WiFi device are dynamically adjusted to adapt to the current environmental conditions and ensure the best network connection quality. The solution of this step can obtain the surrounding environment image in real time, so that the system can better understand and adapt to environmental changes; through the analysis and dynamic adjustment of the environment, the stability and coverage of the WiFi signal are improved, and the signal interference is reduced; users can enjoy a smoother network connection during use, reducing connection interruptions and delays caused by environmental factors; provide personalized network optimization solutions according to different environmental conditions to meet the needs of users in different scenarios.

[0023] Using a deep learning-based target detection algorithm, signal obstruction data is identified from the first surrounding environment image and the second surrounding environment image, and a placement scheme of the first 5G portable WiFi device is determined according to the signal obstruction data, the first data, and a preset device placement model; It is understandable that signal obstructions, such as large metal cabinets, thick walls, etc., the signal obstruction data includes but is not limited to the three-dimensional data, position data, material data, etc. of the signal obstruction. In an embodiment of the present invention, the collected environmental data for training is transmitted to the edge server in advance, and processed by deep fusion of edge computing and artificial intelligence algorithms to train a device placement model; the device placement model based on deep learning on the edge server can be a complex architecture that integrates convolutional neural networks (CNN) and long short-term memory networks (LSTM), comprehensively considering the static characteristics and dynamic changes of the environment, simulating the propagation path and attenuation of the signal in the current environment, and through the training mechanism of reinforcement learning, continuous trial and error optimization, generating the most suitable device placement strategy (including: placement location, such as placing windows, empty desktops, etc.; placement angle; number and angle of external antennas; etc.), to maximize the signal coverage and strength, and finally accurately push placement guidance information to users to guide users to complete the placement.

[0024] Activate the network monitoring program built into the first 5G portable WiFi device (using a high-sensitivity, high-resolution RF receiving module) to perform full-band scanning (covering not only the authorized bands but also monitoring potential unauthorized bands), and continuously collect signal data such as signal strength, phase, polarization characteristics, and noise spectrum distribution of each band to construct an original data sample set; It is understandable that the network monitoring program built into the first 5G portable WiFi device is started (ensuring that the device is in normal working condition and connected to a power source to support continuous monitoring operations); initialization settings are performed using a high-sensitivity, high-resolution RF receiving module (this includes calibrating the receiving module to ensure that it can accurately capture signals in different frequency bands); configuration of scanning parameters to ensure coverage of all authorized frequency bands and potential unauthorized frequency bands (setting the frequency range and time interval of the scan for subsequent data collection); start full-band scanning and continuously collect signal data from each frequency band. Specifically including: signal strength (recording the signal strength value of each frequency band), phase (measuring and recording the phase information of the signal), polarization characteristics (analyzing the polarization state of the signal and obtaining relevant data), noise spectrum distribution (monitoring and recording the spectrum distribution of background noise); storing the collected signal data in real time in the device's memory or external storage medium, constructing a raw data sample set, ensuring the integrity and accuracy of the data for subsequent analysis; conducting a preliminary analysis of the constructed raw data sample set to identify the trend of signal strength changes, phase stability, the influence of polarization characteristics, and the characteristics of the noise spectrum. These analysis results will provide a basis for subsequent network optimization. In this step, all authorized frequency bands and potential unlicensed frequency bands can be covered to ensure a comprehensive understanding of the signal environment. A high-sensitivity, high-resolution RF receiving module is used to ensure the accuracy and reliability of signal data. Multi-dimensional data such as signal strength, phase, polarization characteristics, and noise spectrum distribution are collected to provide a rich information basis for subsequent network optimization and troubleshooting. Through continuous data collection and analysis, network problems can be discovered and optimized in a timely manner to improve users' network experience.

[0025] For the original data sample set, an adaptive filtering algorithm is used to dynamically adjust the filtering parameters to remove noise interference, a high-order statistical analysis method (such as high-order cumulant analysis) is used to mine the nonlinear characteristics in the signal data, and a time-frequency analysis tool (such as short-time Fourier transform and wavelet packet transform) is used to extract the time-varying characteristics and frequency domain distribution characteristics of the frequency band; It can be understood that in this step, the original data sample set obtained from the previous step, including information such as signal strength, phase, polarization characteristics and noise spectrum distribution, is sorted and preprocessed for subsequent analysis; a suitable adaptive filtering algorithm (such as LMS algorithm or RLS algorithm) is selected to process the original data sample set; the filtering parameters are dynamically adjusted to remove noise interference and ensure the clarity and accuracy of the signal data; high-order statistical analysis methods (such as high-order cumulant analysis) are used to analyze the denoised signal data; nonlinear features in the signal are extracted to identify the complexity and change pattern of the signal; combined with time-frequency analysis tools ( The signal data is analyzed in the time and frequency domain using a method such as short-time Fourier transform or wavelet packet transform. The specific steps include: short-time Fourier transform (segmenting the signal, calculating the Fourier transform of each segment, and obtaining the distribution characteristics of the signal in time and frequency), wavelet packet transform (performing multi-scale analysis on the signal, extracting the time-varying characteristics and frequency-domain distribution characteristics of the signal, and identifying the changes of the signal in different frequency bands); extracting key features from the time-frequency analysis results, including the time-varying characteristics of the frequency band, the frequency-domain distribution characteristics, etc., and integrating these features into a feature vector for subsequent model training and analysis; verifying the extracted features to ensure their accuracy and effectiveness. According to the verification results, adjust the analysis parameters and methods to optimize the signal feature extraction process. In this step, the adaptive filtering algorithm can dynamically adjust parameters, effectively remove noise interference in the signal, and improve the clarity of the signal; the high-order statistical analysis method can mine the nonlinear characteristics in the signal data and reveal the complexity and potential patterns of the signal; combined with the time-frequency analysis tool, it can extract the time-varying characteristics and frequency domain distribution characteristics of the signal, providing rich information for subsequent signal processing and optimization; by extracting and integrating multi-dimensional features, the system's ability to understand signal characteristics is improved, providing data support for intelligent decision-making and optimization.

[0026] Use ensemble learning algorithms to fuse multiple weak classifiers and use historical frequency band features as input to build a frequency band quality assessment model; It can be understood that in this step, an integrated learning algorithm is used to fuse multiple weak classifiers (such as gradient boosting tree, AdaBoost algorithm), and historical frequency band features are used as input to construct a frequency band quality assessment model. This model not only distinguishes between high-quality, medium, and low-quality frequency bands, but can also further subdivide them into more detailed frequency band categories such as temporary availability, long-term stable availability, and availability in specific scenarios. Combined with the generative adversarial network (GAN) in deep learning, simulated interference scenario data is continuously generated to expand the training set and improve the assessment capability of the frequency band quality assessment model in extreme environments.

[0027] Combining the frequency band quality assessment model, the time-varying characteristics and the frequency domain distribution characteristics, to obtain a frequency band quality assessment result; According to the frequency band quality assessment result, based on a deep reinforcement learning algorithm (such as a deep deterministic policy gradient (DDPG) algorithm), the frequency band switching action of the first 5G portable WiFi device is expanded to a continuous space; It can be understood that in this step, the current environmental status, historical frequency band switching effects, and predicted future interference changes are comprehensively considered to continuously optimize the frequency band switching strategy; when signal fluctuations are monitored, a frequency band switching attempt is immediately initiated, and the optimal frequency band is quickly converged based on real-time feedback. The switching process uses intelligent pre-synchronization technology to ensure uninterrupted data transmission at the moment of switching and maintain the ultimate smoothness of signal transmission.

[0028] With the help of the parallel computing capability of quantum computing, a quantum neural network is constructed for interference signal analysis; It is understandable that the superposition state characteristics of quantum bits allow the simultaneous processing of massive interference signal samples, accelerating the neural network training process. Through quantum entanglement, the interference signal data in different time and space are associated, the hidden laws and mutation points of the interference signal are accurately captured, and the complex model of the interference signal is quickly updated. It can not only predict the short-term interference change trend, but also predict the medium- and long-term interference evolution, providing a basis for subsequent response strategies.

[0029] The first 5G portable WiFi device uses coding technology based on the interference analysis results to dynamically adjust the coding rate according to the interference intensity; Combined with orthogonal frequency division multiplexing technology, subcarriers are allocated, and subcarriers in frequency bands with severe interference are used to transmit redundant information to ensure the correct transmission of key data; Introducing beamforming technology, using a multi-antenna array to form a null in the interference direction, suppressing the reception of interference signals and enhancing the signal strength in the target direction; It can be understood that in this embodiment, the adaptive modulation and demodulation module built into the first 5G portable WiFi device adopts intelligent coding technology (such as a hybrid coding scheme of low-density parity check code (LDPC) and polarization code) based on the interference analysis results, and dynamically adjusts the coding rate according to the interference intensity; combined with orthogonal frequency division multiplexing (OFDM) technology, intelligently allocates subcarriers, and uses the subcarriers of the frequency band that is severely interfered (that is, the interference intensity exceeds the preset intensity) to transmit redundant information, thereby ensuring the correct transmission of key data; at the same time, introduces intelligent beamforming technology, uses a multi-antenna array to form a null in the interference direction, suppresses the reception of interference signals, and enhances the signal strength in the target direction; Continue to use the semantic segmentation algorithm in image recognition and processing technology to segment the latest environmental images acquired in real time, identify the location, outline, and material of new obstructions, and evaluate their degree of signal obstruction; It can be understood that in this step, a camera or other sensor can be used to acquire environmental images in real time, and these images will be used as input data for subsequent processing; the acquired images are preprocessed, including denoising, contrast enhancement and image resizing, to improve the effect of the subsequent semantic segmentation algorithm; a suitable semantic segmentation algorithm (such as FCN, U-Net or DeepLab, etc.) is selected to segment the preprocessed images, which assigns a category label to each pixel in the image to identify different objects and regions; in the segmentation results, newly appeared occluders are identified, and the outline and position of the occluders are extracted by analyzing the segmented images, which can be achieved by contour detection algorithms (such as Canny edge detection). Now; use image feature extraction technology (such as texture analysis or color histogram) to classify the materials of the identified occluders. This step can help determine the nature of the occluders (such as metal, wood, plastic, etc.); evaluate the degree of signal occlusion based on the position and outline of the occluder, which can be achieved by establishing an occlusion model and analyzing the relative position and size between the occluder and the signal source; output the recognition results (including the position, outline, material and degree of signal occlusion of the occluder) to the user interface or other system modules for subsequent processing or decision-making; optimize the semantic segmentation model and occluder recognition algorithm by continuously acquiring new images and feedback results, and use machine learning technology to improve the system's adaptability to new environments. In this step, the system can recognize and process new occluders in the environment in real time, and enhance its responsiveness to environmental changes; through the semantic segmentation algorithm, the position, outline and material of the occluder are accurately identified, which improves the recognition accuracy; it can effectively evaluate the impact of the occluder on the signal, providing a basis for subsequent signal processing and optimization; through continuous learning and optimization, the system can adapt to different environmental changes and improve overall performance and reliability.

[0030] Based on the evaluation results of the degree of signal obstruction caused by the newly appeared obstructions, combined with the temperature, humidity and electromagnetic environment change data fed back by the IoT sensors in real time, the first 5G portable WiFi device dynamically adjusts the transmission power, signal frequency and modulation mode, and maintains high-frequency interaction with the mobile communication base station, uploads the local environment and signal status, downloads the latest optimization instructions, forms a closed-loop optimization link, and continuously and adaptively optimizes the signal enhancement effect; It can be understood that according to the newly appeared obstructions identified in the previous step, the degree of obstruction of the signal is analyzed (this includes evaluating the size, position and material of the obstructions) to determine its impact on signal propagation; the IoT sensor is used to feedback environmental data in real time, including temperature, humidity and electromagnetic environment changes, which will provide an important basis for subsequent signal adjustment; the obstruction degree assessment results of the obstructions are integrated and analyzed with the environmental data fed back by the IoT sensor, and the quality and stability of the current signal are determined by comprehensively considering these factors; according to the analysis results, the transmission power, signal frequency and modulation mode of the first 5G portable WiFi device are dynamically adjusted: transmission power (when the signal is severely obstructed, increase the transmission power to enhance the signal penetration ability), signal frequency (according to environmental changes, select a suitable frequency to reduce interference and improve transmission efficiency), modulation mode (according to signal quality, select a suitable modulation mode to optimize the reliability of data transmission); maintain high-frequency interaction with the mobile communication base station, and upload the local environment and signal status in real time. This process ensures that the base station can obtain the status information of the device in time and perform corresponding network optimization; according to the uploaded environment and signal status, the mobile communication base station will issue the latest optimization instructions. These instructions may include adjusting network configuration, optimizing resource allocation, etc.; the uploaded environmental data, signal status and downloaded optimization instructions form a closed-loop optimization link. Through this mechanism, the system can continuously monitor and adjust signal parameters to adapt to the changing environment; through the above steps, the first 5G portable WiFi device can continuously and adaptively optimize the signal enhancement effect to ensure that good signal quality and transmission efficiency can be maintained under different environmental conditions. In this implementation, dynamic adjustment of transmission power and signal frequency can effectively respond to environmental changes and ensure that the signal can still be transmitted stably under the influence of obstructions; real-time feedback of environmental data and signal status analysis enables the system to quickly adapt to different environmental conditions and optimize signal quality; through high-frequency interaction with mobile communication base stations, efficient use of network resources can be achieved and overall communication performance can be improved; the establishment of a closed-loop optimization link enables the system to continuously learn and optimize, improving user experience and the level of intelligence of the system.

[0031] The key status data of the first 5G portable WiFi device is encrypted and uploaded to the edge server through the Internet of Things. The edge server performs big data analysis based on the data of multiple 5G portable WiFi devices, and based on the data analysis results, pushes personalized signal enhancement solutions to different users (for example, more aggressive anti-interference settings are provided for users who are often in densely built-up areas).

[0032] It can be understood that in this step, the first 5G portable WiFi device monitors and collects key status data in real time, including signal strength, connection quality, user location, environmental changes and other information; encrypts the collected key status data to ensure the security and privacy of the data during transmission (common encryption algorithms may include AES (Advanced Encryption Standard) etc.); uploads the encrypted data to the edge server through the Internet of Things communication protocol (such as MQTT or HTTP) to ensure the stability and reliability of data transmission; the edge server receives and stores encrypted data from multiple 5G portable WiFi devices, and establishes a data warehouse for subsequent analysis; uses big data analysis technology to process and analyze the stored data. The analysis includes user usage habits, signal quality changes, environmental factors, etc., to identify the needs and patterns of different users; based on the data analysis results, the edge server generates a personalized signal enhancement plan, for example, for users who are often in densely built-up areas, it provides more aggressive anti-interference settings, or optimizes signal parameters for specific environmental conditions; the generated personalized signal enhancement plan is pushed to different users' devices through applications or notifications to ensure that users can obtain optimization suggestions in a timely manner; collect user feedback on the push plan, further optimize the signal enhancement strategy, and improve the accuracy and effectiveness of personalized services through continuous data collection and analysis. In this step, the personalized signal enhancement plan can significantly improve the signal quality and network connection stability according to the actual needs and environmental conditions of the user; by encrypting the uploaded data, it ensures user privacy and data security and reduces the risk of data leakage; the personalized solution push based on big data analysis makes the service more intelligent and can adapt to the usage scenarios and needs of different users; through user feedback and data analysis, the system can continuously optimize the signal enhancement strategy and improve the overall service quality.

[0033] In the embodiment of the present invention, the surrounding environment data is collected by the environment perception sensor, and the placement scheme of the device is optimized by the deep learning algorithm, which can effectively improve the coverage of the signal and ensure that users can obtain stronger signals in different environments; the strategy of dynamically adjusting the transmission power, signal frequency and modulation mode can optimize the signal strength according to the real-time environmental changes, reduce signal attenuation and interference, and thus improve the user's network experience; through quantum computing to analyze the interference signal, and using the beamforming technology to form a zero sink, it can effectively suppress the reception of the interference signal, enhance the signal strength in the target direction, and ensure the stable transmission of key data; combined with the Internet of Things technology, the device status data is uploaded to the edge server in real time for big data analysis, and personalized signal enhancement schemes can be pushed according to the use environment of different users to achieve continuous adaptive optimization; through precise placement guidance and dynamic frequency band switching strategies, users can enjoy smoother network connections during use, reduce connection interruptions and delays caused by poor signals; can adjust the working state of the device in real time according to the static characteristics and dynamic changes of the environment, and ensure that good signal quality can be maintained in complex environments. In summary, the scheme of the embodiment of the present invention can not only improve the signal quality of 5G portable WiFi, but also provide users with a more intelligent and personalized network experience.

[0034] In some possible implementations of the present invention, the step of using a deep learning-based target detection algorithm to identify signal obstruction data from the first surrounding environment image and the second surrounding environment image, and determining a placement solution for the first 5G portable WiFi device based on the signal obstruction data, the first data, and a preset device placement model includes: The first surrounding environment image and the second surrounding environment image are subjected to standardization processing (including: performing illumination compensation and color balance on the images; uniformly adjusting the image resolution to a preset size; removing image noise and distortion) to obtain a third surrounding environment image and a fourth surrounding environment image; Using a deep learning-based target detection algorithm (such as an improved Mask R-CNN network model) to perform target detection and instance segmentation on the third surrounding environment image and the fourth surrounding environment image, specifically including: extracting image features and generating candidate regions; classifying the candidate regions and identifying the types of occluders; generating pixel-level masks of occluders; and calculating the precise contours and spatial position information of the occluders; Based on the binocular vision principle, the third surrounding environment image and the fourth surrounding environment image are subjected to three-dimensional reconstruction, specifically including: extracting image feature points and matching them; calculating feature point parallax and constructing a depth map; generating a three-dimensional point cloud model of the occluder; and analyzing the surface features of the occluder and determining the material properties based on the material recognition model; In combination with the first environmental parameter in the first data, a signal propagation model is constructed, including: calculating the signal attenuation coefficient according to the three-dimensional position and material of the obstruction; considering the influence of temperature and humidity on signal propagation; simulating multipath effects and signal reflection and diffraction phenomena; Based on the preset device placement model, multi-objective optimization calculations are performed, including: inputting obstruction data, first environmental parameters, and signal propagation models; considering the device's heat dissipation requirements and operational convenience; using reinforcement learning algorithms to iteratively optimize placement positions and angles; and outputting the optimal placement plan, including specific coordinates and placement postures.

[0035] The solution of this embodiment uses deep learning to achieve sub-pixel level obstruction contour recognition, accurately evaluates the impact of different materials on signals, and achieves centimeter-level device placement optimization; it can adjust the placement strategy in real time according to environmental changes, adapt to the layout characteristics of different indoor scenes, and have the ability to dynamically compensate for environmental factors such as temperature and humidity; it reduces the difficulty of user operation and provides intuitive placement guidance; it optimizes the heat dissipation conditions of the equipment and extends its service life; it balances signal strength and ease of use; it supports online learning of new types of obstructions, can update optimization algorithms and models through edge servers, and has the ability to coordinate optimization of multiple devices.

[0036] In some possible implementations of the present invention, the step of using an ensemble learning algorithm to fuse multiple weak classifiers and using historical frequency band features as input to construct a frequency band quality assessment model includes: Construct a multidimensional feature vector based on historical frequency band characteristics, including: extracting statistical features of signal strength, including mean, variance, skewness, and kurtosis; calculating signal stability indicators, including signal jitter rate and disconnection frequency; generating spectrum features such as spectrum occupancy rate and bandwidth utilization rate; normalizing feature data and detecting outliers; Construct multiple basic classifiers for different feature subspaces, including: deploying gradient boosted decision tree (GBDT) to process continuous features; configuring AdaBoost classifier to process categorical features; applying random forest to process the correlation of high-dimensional features; assigning initial weights to each weak classifier; Design an adaptive integration strategy to dynamically adjust the classifier weights, including: calculating the prediction accuracy of each weak classifier; dynamically updating the classifier weights based on the accuracy; using a weighted voting mechanism to fuse the prediction results of each classifier; introducing a time decay factor to reduce the weight of historical data; Deploy a generative adversarial network to expand training data, including: building a generator network to simulate various interference scenarios; designing a discriminator network to distinguish between real and generated data; iteratively training the GAN network to generate high-quality samples; adding generated samples to the training set to improve model robustness; Realize refined grading of frequency band quality, including: establishing multi-level evaluation standards, including main classification and sub-classification; dynamically updating threshold parameters at each level; predicting frequency band quality change trends in combination with time series analysis; and continuously optimizing evaluation model parameters.

[0037] The scheme of this embodiment constructs a frequency band quality assessment model that can accurately distinguish frequency bands of different qualities and subdivide them into multiple categories to meet the needs of different application scenarios; by integrating multiple weak classifiers, the robustness and accuracy of the model are improved, and it can adapt to complex signal environments; the training set is expanded by using interference scenario data generated by GAN, so that the model's assessment ability in extreme environments is significantly enhanced, and the generalization ability of the model is improved; the deployed model can evaluate the frequency band quality in real time, provide users with timely frequency band usage suggestions, and optimize the configuration of network resources.

[0038] In some possible implementations of the present invention, the step of combining the frequency band quality assessment model, the time-varying feature and the frequency domain distribution characteristic to obtain a frequency band quality assessment result includes: The input multi-source features are standardized, specifically including: normalizing the evaluation index output by the frequency band quality evaluation model; performing time window segmentation processing on the time-varying features; converting the frequency domain distribution characteristics into a unified feature vector; and constructing a feature fusion matrix; Dynamic evaluation based on time-varying characteristics, including: calculating the time series fluctuation index of signal strength; extracting the periodic change pattern of signal quality; analyzing the mutation feature points of signal parameters; generating time series evaluation scores; Conduct in-depth analysis of frequency domain distribution characteristics, including: calculating spectrum energy distribution density; identifying frequency domain interference characteristics; evaluating frequency band utilization efficiency; generating frequency domain evaluation scores; A weighted fusion strategy is used to integrate the evaluation results of each dimension, including: designing an adaptive weight calculation method; considering reliability indicators with different characteristics; integrating the evaluation scores of each dimension; and generating a comprehensive evaluation indicator; Generate the final frequency band quality assessment results based on comprehensive assessment indicators, including: establishing multi-threshold assessment standards; calculating quality level confidence; generating an assessment result report; and providing optimization suggestion instructions.

[0039] The scheme of this embodiment combines the time-varying characteristics and frequency domain distribution characteristics, and the frequency band quality assessment model can provide more accurate and detailed assessment results to help users better understand the use of the frequency band; the assessment results provide a scientific basis for the use and management of the frequency band, and can effectively support the optimal configuration and dynamic adjustment of network resources; through regular updates and iterations, the model can adapt to the ever-changing environment and needs and maintain efficient assessment capabilities; accurate frequency band quality assessment results can enhance the user experience when using the frequency band and ensure communication quality and service stability.

[0040] In some possible implementations of the present invention, the step of extending the frequency band switching action of the first 5G portable WiFi device to a continuous space based on the frequency band quality evaluation result and based on a deep reinforcement learning algorithm includes: Constructing the state representation of deep reinforcement learning, including: encoding the current frequency band quality assessment results; integrating historical frequency band switching records; collecting network environment parameters; constructing a multi-dimensional state vector; Expand the discrete frequency band switching into a continuous action space, including: defining the continuous value range of frequency and bandwidth; designing the action space mapping function; establishing action constraints; and realizing the action smooth transition mechanism; Deploy a dual network architecture to implement policy learning, including: building an Actor network to output continuous action values; deploying a Critic network to evaluate action values; designing an experience replay buffer pool; and implementing a soft update mechanism for the target network. Establish a multi-objective reward function, including: evaluating the effect of frequency band switching; considering the switching time cost; calculating the energy consumption penalty; integrating user experience indicators; Realize online learning and strategy updating, including: collecting interactive experience data; calculating temporal difference error; updating Actor-Critic network parameters; optimizing exploration-exploitation balance.

[0041] The solution of this embodiment expands the frequency band switching action to a continuous space, so that the device can switch between frequency bands more flexibly and smoothly, thereby improving the user experience; based on the deep reinforcement learning algorithm, the device can make intelligent frequency band switching decisions based on the real-time frequency band quality assessment results, thereby optimizing the use of network resources; through continuous learning and model updating, the device can adapt to the ever-changing network environment and user needs, and maintain efficient frequency band switching capabilities; the optimized frequency band switching strategy will help improve the overall network performance and ensure that users can obtain stable connection quality in different environments.

[0042] In some possible implementations of the present invention, the step of constructing a quantum neural network for interference signal analysis by means of the parallel computing capability of quantum computing includes: Encoding interference signal data into quantum states, including: using amplitude encoding method to map signal features to quantum bits; constructing quantum state superposition to represent multi-dimensional features; realizing quantum entanglement of feature space; and establishing quantum data preprocessing pipeline; Design a dedicated quantum neural network architecture, including: deploying a parameterized quantum circuit layer; building a quantum convolution layer to process time-frequency features; designing quantum pooling operation compression features; and implementing a quantum-classical hybrid computing interface. Using quantum parallelism to perform feature analysis, including: processing interference features of multiple frequency bands simultaneously; parallel calculation of time-frequency correlation; extracting hidden features from quantum state evolution; and constructing quantum feature maps; Realize quantum classification of interference patterns, including: design quantum measurement operators; construct quantum decision trees; realize quantum ensemble learning; output interference type probability distribution; Optimize the prediction model based on quantum feedback, including: designing a quantum gradient descent algorithm; realizing quantum acceleration of parameter updates; optimizing quantum-classical data conversion; and dynamically adjusting the model structure.

[0043] In the solution of this embodiment, with the help of the parallel computing capability of quantum computing, the quantum neural network can significantly improve the computing speed and efficiency when processing complex interference signals; the quantum neural network can utilize the characteristics of the quantum state to extract richer signal features, thereby improving the accuracy of interference signal analysis; through the flexibility of quantum computing, the model can quickly adapt to different types of interference signals, enhancing its application capabilities in dynamic environments.

[0044] In some possible implementations of the present invention, the first 5G portable WiFi device uses a coding technology based on the interference analysis result to dynamically adjust the coding rate according to the interference intensity, including: Multi-dimensional evaluation is performed based on the interference analysis results, including: calculating the dynamic range of signal-to-noise ratio; analyzing the time-frequency characteristics of the interference signal; evaluating the impact of interference on channel capacity; and generating quantitative indicators of interference intensity; Select the optimal coding scheme according to the interference intensity, including: constructing a hybrid coding library of LDPC codes and polar codes; designing coding scheme evaluation criteria; calculating the performance indicators of different coding schemes; and selecting the coding scheme that best suits the current interference environment; Dynamically adjust the coding parameter configuration, including: calculating the target coding rate based on the interference intensity; optimizing the codeword length and check bit distribution; adjusting the interleaving depth and pattern structure; generating optimized coding parameters; Realize real-time switching of coding schemes, including: designing a coding switching buffer mechanism; achieving smooth transition of coding parameters; monitoring coding performance indicators; and executing dynamic updates of coding schemes; Establish a coding effect feedback mechanism, including: collecting decoding error statistics; analyzing throughput change trends; evaluating coding overhead and gain ratio; and optimizing the coding strategy decision model.

[0045] The solution of this embodiment dynamically adjusts the coding rate to effectively cope with different interference environments and ensure reliable transmission of data under high interference conditions; increasing the coding rate in a low interference environment can increase the data transmission rate and optimize the use of network resources; the device can automatically adjust the coding strategy according to the real-time interference situation, enhancing the adaptability in complex network environments; through optimized data transmission performance, users can obtain a more stable and fast network experience when using the first 5G portable WiFi device.

[0046] In some possible implementations of the present invention, the step of combining orthogonal frequency division multiplexing technology, allocating subcarriers, and using subcarriers in a frequency band with severe interference to transmit redundant information to ensure correct transmission of key data includes: Dynamically evaluate the subcarriers in the OFDM system, including: measuring the signal-to-noise ratio of each subcarrier; evaluating the degree of interference between subcarriers; calculating the subcarrier channel capacity; generating subcarrier quality scores; Classify the data to be transmitted, including: identifying key data packets; calculating data transmission priority; estimating the required transmission reliability; generating data transmission strategies; Intelligent allocation based on subcarrier status, including: allocating high-quality subcarriers to critical data; using interfered subcarriers for redundant transmission; optimizing subcarrier combination schemes; and achieving dynamic bandwidth allocation; Design an adaptive redundant transmission mechanism, including: calculating the redundant data ratio; selecting a redundant coding scheme; determining the redundant data distribution; and implementing redundant transmission scheduling; Establish a real-time monitoring and adjustment mechanism, including: tracking data transmission success rate; analyzing transmission delay changes; evaluating resource utilization efficiency; and dynamically optimizing allocation strategies.

[0047] The solution of this embodiment ensures that key data is not easily lost or damaged during transmission by transmitting redundant information on the interfered subcarriers; reasonably allocates subcarriers so that spectrum resources are effectively utilized while ensuring the transmission quality of key data; even in a severely interfered environment, the system can still restore key data through redundant information to improve the stability of the overall communication; users can enjoy higher transmission reliability and less data loss during use, thereby improving the overall user experience.

[0048] In some possible implementations of the present invention, the step of introducing beamforming technology, using a multi-antenna array, forming a null in the interference direction, suppressing reception of interference signals, and enhancing signal strength in the target direction includes: Channel characteristic analysis using multi-antenna arrays, including: obtaining the received signal characteristics of each antenna; calculating the signal correlation between antennas; estimating the signal arrival angle; and constructing a spatial channel matrix; Accurately identify the spatial location of interference sources, including: performing spatial spectrum scanning; calculating the signal arrival angle distribution; identifying the direction of the main interference source; generating a spatial distribution map of the interference source; Designing optimal beamforming weights, including: constructing an adaptive beamforming algorithm; calculating constraints on the null direction; optimizing the main lobe direction gain; generating a weight vector; Achieve precise beam control, including: configuring antenna array phase relationships; adjusting the transmit power of each antenna; synchronizing antenna array timing; and performing beamforming operations; Establish a real-time optimization feedback mechanism, including: monitoring beamforming effects; analyzing signal-to-interference ratio changes; evaluating system performance indicators; and adjusting beamforming strategies.

[0049] The solution of this embodiment significantly reduces the impact of interference signals on the receiving system by forming a null in the interference direction, thereby improving the signal quality; enhances the signal strength in the direction of the target signal to ensure that the target signal can be clearly received in a complex environment; the system can maintain stable performance in a variety of interference environments, thereby enhancing the reliability of communication; and through beamforming technology, rationally utilizes spectrum resources to improve the overall efficiency of the system.

[0050] See also Figure 2 , another embodiment of the present invention provides a 5G portable WiFi signal enhancement system for performing a 5G portable WiFi signal enhancement method, including: a first 5G portable WiFi device, a first terminal and an edge server; The first 5G portable WiFi device is configured to: enable multiple types of environment perception sensors built into the first 5G portable WiFi device to collect first data; The edge server is configured as: Acquire in real time a first surrounding environment image within a first preset range of a location where a first terminal connected to the first 5G portable WiFi device is located, and a second surrounding environment image within a second preset range of a location where the first 5G portable WiFi device is located; Using a deep learning-based target detection algorithm, signal obstruction data is identified from the first surrounding environment image and the second surrounding environment image, and a placement scheme of the first 5G portable WiFi device is determined according to the signal obstruction data, the first data, and a preset device placement model; Activate the network monitoring program built into the first 5G portable WiFi device to scan the entire frequency band, and continuously collect signal data such as signal strength, phase, polarization characteristics, and noise spectrum distribution of each frequency band to construct an original data sample set; For the original data sample set, an adaptive filtering algorithm is used to dynamically adjust the filtering parameters to remove noise interference, a high-order statistical analysis method is used to mine the nonlinear characteristics in the signal data, and a time-frequency analysis tool is used to extract the time-varying characteristics of the frequency band and the frequency domain distribution characteristics; Use ensemble learning algorithms to fuse multiple weak classifiers and use historical frequency band features as input to build a frequency band quality assessment model; Combining the frequency band quality assessment model, the time-varying characteristics and the frequency domain distribution characteristics, to obtain a frequency band quality assessment result; According to the frequency band quality assessment result, based on a deep reinforcement learning algorithm, the frequency band switching action of the first 5G portable WiFi device is expanded to a continuous space; With the help of the parallel computing capability of quantum computing, a quantum neural network is constructed for interference signal analysis; The first 5G portable WiFi device is further configured as: Based on the interference analysis results, the coding technology is used to dynamically adjust the coding rate according to the interference intensity; Combined with orthogonal frequency division multiplexing technology, subcarriers are allocated, and subcarriers in frequency bands with severe interference are used to transmit redundant information to ensure the correct transmission of key data; Introducing beamforming technology, using a multi-antenna array to form a null in the interference direction, suppressing the reception of interference signals and enhancing the signal strength in the target direction; The edge server is also configured to: Continue to use the semantic segmentation algorithm in image recognition and processing technology to segment the latest environmental images acquired in real time, identify the location, outline, and material of new obstructions, and evaluate their degree of signal obstruction; According to the evaluation results of the degree of signal obstruction by the newly appeared obstructions, combined with the temperature, humidity, and electromagnetic environment change data fed back by the IoT sensors in real time, the first 5G portable WiFi device is controlled to dynamically adjust the transmission power, signal frequency, and modulation mode, and maintain high-frequency interaction with the mobile communication base station, upload the local environment and signal status, download the latest optimization instructions, form a closed-loop optimization link, and continuously and adaptively optimize the signal enhancement effect; The key status data of the first 5G portable WiFi device is received through the Internet of Things, and big data analysis is performed based on the data of multiple 5G portable WiFi devices. Based on the data analysis results, personalized signal enhancement solutions are pushed to different users.

[0051] It should be known that Figure 2The block diagram of the 5G portable WiFi signal enhancement system shown is for illustration only, and the number of modules shown does not limit the protection scope of the present invention. The 5G portable WiFi signal enhancement system provided in this embodiment can be used to execute the corresponding embodiments of the 5G portable WiFi signal enhancement method. For the specific implementation process, please refer to the description of the embodiments of each method, which will not be repeated here.

[0052] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0053] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0054] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0055] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0056] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0057] If the above-mentioned 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 is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0058] A person skilled 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 related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0059] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0060] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A 5G portable WiFi signal enhancement method, characterized in that: include: Enable multiple types of environment perception sensors built into the first 5G portable WiFi device to collect first data; Acquire in real time a first surrounding environment image within a first preset range of a location where a first terminal connected to the first 5G portable WiFi device is located, and a second surrounding environment image within a second preset range of a location where the first 5G portable WiFi device is located; Using a deep learning-based target detection algorithm, signal obstruction data is identified from the first surrounding environment image and the second surrounding environment image, and a placement scheme of the first 5G portable WiFi device is determined according to the signal obstruction data, the first data, and a preset device placement model; Activate the network monitoring program built into the first 5G portable WiFi device to scan the entire frequency band, and continuously collect signal data such as signal strength, phase, polarization characteristics, and noise spectrum distribution of each frequency band to construct an original data sample set; For the original data sample set, an adaptive filtering algorithm is used to dynamically adjust the filtering parameters to remove noise interference, a high-order statistical analysis method is used to mine the nonlinear characteristics in the signal data, and a time-frequency analysis tool is used to extract the time-varying characteristics of the frequency band and the frequency domain distribution characteristics; Use ensemble learning algorithms to fuse multiple weak classifiers and use historical frequency band features as input to build a frequency band quality assessment model; Combining the frequency band quality assessment model, the time-varying characteristics and the frequency domain distribution characteristics, to obtain a frequency band quality assessment result; According to the frequency band quality assessment result, based on a deep reinforcement learning algorithm, the frequency band switching action of the first 5G portable WiFi device is expanded to a continuous space; With the help of the parallel computing capability of quantum computing, a quantum neural network is constructed for interference signal analysis; The first 5G portable WiFi device uses coding technology based on the interference analysis results to dynamically adjust the coding rate according to the interference intensity; Combined with orthogonal frequency division multiplexing technology, subcarriers are allocated, and subcarriers in frequency bands with severe interference are used to transmit redundant information to ensure the correct transmission of key data; Introducing beamforming technology, using a multi-antenna array to form a null in the interference direction, suppressing the reception of interference signals and enhancing the signal strength in the target direction; Continue to use the semantic segmentation algorithm in image recognition and processing technology to segment the latest environmental images acquired in real time, identify the location, outline, and material of new obstructions, and evaluate their degree of signal obstruction; Based on the evaluation results of the degree of signal obstruction caused by the newly appeared obstructions, combined with the temperature, humidity and electromagnetic environment change data fed back by the IoT sensors in real time, the first 5G portable WiFi device dynamically adjusts the transmission power, signal frequency and modulation mode, and maintains high-frequency interaction with the mobile communication base station, uploads the local environment and signal status, downloads the latest optimization instructions, forms a closed-loop optimization link, and continuously and adaptively optimizes the signal enhancement effect; The key status data of the first 5G portable WiFi device is encrypted and uploaded to the edge server through the Internet of Things. The edge server performs big data analysis based on the data of multiple 5G portable WiFi devices, and pushes personalized signal enhancement solutions to different users based on the data analysis results.

2. The 5G portable WiFi signal enhancement method according to claim 1, characterized in that: The step of using a deep learning-based target detection algorithm to identify signal obstruction data from the first surrounding environment image and the second surrounding environment image, and determining a placement solution for the first 5G portable WiFi device according to the signal obstruction data, the first data, and a preset device placement model includes: The first surrounding environment image and the second surrounding environment image are subjected to standardization processing to obtain a third surrounding environment image and a fourth surrounding environment image; Using a deep learning-based target detection algorithm to perform target detection and instance segmentation on the third surrounding environment image and the fourth surrounding environment image, specifically including: extracting image features and generating candidate regions; classifying the candidate regions and identifying the types of occluders; generating pixel-level masks of occluders; and calculating the precise contours and spatial position information of the occluders; Based on the binocular vision principle, the third surrounding environment image and the fourth surrounding environment image are subjected to three-dimensional reconstruction, specifically including: extracting image feature points and matching them; calculating feature point parallax and constructing a depth map; generating a three-dimensional point cloud model of the occluder; and analyzing the surface features of the occluder and determining the material properties based on the material recognition model; In combination with the first environmental parameter in the first data, a signal propagation model is constructed, including: calculating the signal attenuation coefficient according to the three-dimensional position and material of the obstruction; considering the influence of temperature and humidity on signal propagation; simulating multipath effects and signal reflection and diffraction phenomena; Based on the preset device placement model, multi-objective optimization calculations are performed, including: inputting obstruction data, first environmental parameters, and signal propagation models; considering the device's heat dissipation requirements and operational convenience; using reinforcement learning algorithms to iteratively optimize placement positions and angles; and outputting the optimal placement plan, including specific coordinates and placement postures.

3. The 5G portable WiFi signal enhancement method according to claim 2, characterized in that: The step of using an ensemble learning algorithm to fuse multiple weak classifiers and using historical frequency band features as input to construct a frequency band quality assessment model includes: Construct a multidimensional feature vector based on historical frequency band characteristics, including: extracting statistical features of signal strength, including mean, variance, skewness, and kurtosis; calculating signal stability indicators, including signal jitter rate and disconnection frequency; generating spectrum features such as spectrum occupancy rate and bandwidth utilization rate; normalizing feature data and detecting outliers; Construct multiple basic classifiers for different feature subspaces, including: deploying gradient boosting decision trees to process continuous features; configuring AdaBoost classifiers to process categorical features; applying random forests to process the correlation of high-dimensional features; assigning initial weights to each weak classifier; Design an adaptive integration strategy to dynamically adjust the classifier weights, including: calculating the prediction accuracy of each weak classifier; dynamically updating the classifier weights based on the accuracy; using a weighted voting mechanism to fuse the prediction results of each classifier; introducing a time decay factor to reduce the weight of historical data; Deploy a generative adversarial network to expand training data, including: building a generator network to simulate various interference scenarios; designing a discriminator network to distinguish between real and generated data; iteratively training the GAN network to generate high-quality samples; adding generated samples to the training set to improve model robustness; Realize refined grading of frequency band quality, including: establishing multi-level evaluation standards, including main classification and sub-classification; dynamically updating threshold parameters at each level; predicting frequency band quality change trends in combination with time series analysis; and continuously optimizing evaluation model parameters.

4. The 5G portable WiFi signal enhancement method according to claim 3 is characterized in that: The step of obtaining a frequency band quality assessment result by combining the frequency band quality assessment model, the time-varying feature and the frequency domain distribution characteristic comprises: The input multi-source features are standardized, specifically including: normalizing the evaluation index output by the frequency band quality evaluation model; performing time window segmentation processing on the time-varying features; converting the frequency domain distribution characteristics into a unified feature vector; and constructing a feature fusion matrix; Dynamic evaluation based on time-varying characteristics, including: calculating the time series fluctuation index of signal strength; extracting the periodic change pattern of signal quality; analyzing the mutation feature points of signal parameters; generating time series evaluation scores; Conduct in-depth analysis of frequency domain distribution characteristics, including: calculating spectrum energy distribution density; identifying frequency domain interference characteristics; evaluating frequency band utilization efficiency; generating frequency domain evaluation scores; A weighted fusion strategy is used to integrate the evaluation results of each dimension, including: designing an adaptive weight calculation method; considering reliability indicators with different characteristics; integrating the evaluation scores of each dimension; and generating a comprehensive evaluation indicator; Generate the final frequency band quality assessment results based on comprehensive assessment indicators, including: establishing multi-threshold assessment standards; calculating quality level confidence; generating an assessment result report; and providing optimization suggestion instructions.

5. The 5G portable WiFi signal enhancement method according to claim 4 is characterized in that: The step of extending the frequency band switching action of the first 5G portable WiFi device to a continuous space based on the deep reinforcement learning algorithm according to the frequency band quality evaluation result includes: Constructing the state representation of deep reinforcement learning, including: encoding the current frequency band quality assessment results; integrating historical frequency band switching records; collecting network environment parameters; constructing a multi-dimensional state vector; Expand the discrete frequency band switching into a continuous action space, including: defining the continuous value range of frequency and bandwidth; designing the action space mapping function; establishing action constraints; and realizing the action smooth transition mechanism; Deploy a dual network architecture to implement policy learning, including: building an Actor network to output continuous action values; deploying a Critic network to evaluate action values; designing an experience replay buffer pool; and implementing a soft update mechanism for the target network. Establish a multi-objective reward function, including: evaluating the effect of frequency band switching; considering the switching time cost; calculating the energy consumption penalty; integrating user experience indicators; Realize online learning and strategy updating, including: collecting interactive experience data; calculating temporal difference error; updating Actor-Critic network parameters; optimizing exploration-exploitation balance.

6. The 5G portable WiFi signal enhancement method according to claim 5, characterized in that: The step of constructing a quantum neural network for interference signal analysis by using the parallel computing capability of quantum computing includes: Encoding interference signal data into quantum states, including: using amplitude encoding method to map signal features to quantum bits; constructing quantum state superposition to represent multi-dimensional features; realizing quantum entanglement of feature space; and establishing quantum data preprocessing pipeline; Design a dedicated quantum neural network architecture, including: deploying a parameterized quantum circuit layer; building a quantum convolution layer to process time-frequency features; designing quantum pooling operation compression features; and implementing a quantum-classical hybrid computing interface. Using quantum parallelism to perform feature analysis, including: processing interference features of multiple frequency bands simultaneously; parallel calculation of time-frequency correlation; extracting hidden features from quantum state evolution; and constructing quantum feature maps; Realize quantum classification of interference patterns, including: design quantum measurement operators; construct quantum decision trees; realize quantum ensemble learning; output interference type probability distribution; Optimize the prediction model based on quantum feedback, including: designing a quantum gradient descent algorithm; realizing quantum acceleration of parameter updates; optimizing quantum-classical data conversion; and dynamically adjusting the model structure.

7. The 5G portable WiFi signal enhancement method according to claim 6, characterized in that: The first 5G portable WiFi device adopts a coding technology based on the interference analysis result to dynamically adjust the coding rate according to the interference intensity, including: Multi-dimensional evaluation is performed based on the interference analysis results, including: calculating the dynamic range of signal-to-noise ratio; analyzing the time-frequency characteristics of the interference signal; evaluating the impact of interference on channel capacity; and generating quantitative indicators of interference intensity; Select the optimal coding scheme according to the interference intensity, including: constructing a hybrid coding library of LDPC codes and polar codes; designing coding scheme evaluation criteria; calculating the performance indicators of different coding schemes; and selecting the coding scheme that best suits the current interference environment; Dynamically adjust the coding parameter configuration, including: calculating the target coding rate based on the interference intensity; optimizing the codeword length and check bit distribution; adjusting the interleaving depth and pattern structure; generating optimized coding parameters; Realize real-time switching of coding schemes, including: designing a coding switching buffer mechanism; achieving smooth transition of coding parameters; monitoring coding performance indicators; and executing dynamic updates of coding schemes; Establish a coding effect feedback mechanism, including: collecting decoding error statistics; analyzing throughput change trends; evaluating coding overhead and gain ratio; and optimizing the coding strategy decision model.

8. The 5G portable WiFi signal enhancement method according to claim 7, characterized in that: The steps of combining orthogonal frequency division multiplexing technology, allocating subcarriers, and using subcarriers in frequency bands with severe interference to transmit redundant information to ensure accurate transmission of key data include: Dynamically evaluate the subcarriers in the OFDM system, including: measuring the signal-to-noise ratio of each subcarrier; evaluating the degree of interference between subcarriers; calculating the subcarrier channel capacity; generating subcarrier quality scores; Classify the data to be transmitted, including: identifying key data packets; calculating data transmission priority; estimating the required transmission reliability; generating data transmission strategies; Intelligent allocation based on subcarrier status, including: allocating high-quality subcarriers to critical data; using interfered subcarriers for redundant transmission; optimizing subcarrier combination schemes; and achieving dynamic bandwidth allocation; Design an adaptive redundant transmission mechanism, including: calculating the redundant data ratio; selecting a redundant coding scheme; determining the redundant data distribution; and implementing redundant transmission scheduling; Establish a real-time monitoring and adjustment mechanism, including: tracking data transmission success rate; analyzing transmission delay changes; evaluating resource utilization efficiency; and dynamically optimizing allocation strategies.

9. The 5G portable WiFi signal enhancement method according to claim 8, characterized in that: The step of introducing beamforming technology, using a multi-antenna array, forming a null in the interference direction, suppressing the reception of interference signals, and enhancing the signal strength in the target direction includes: Channel characteristic analysis using multi-antenna arrays, including: obtaining the received signal characteristics of each antenna; calculating the signal correlation between antennas; estimating the signal arrival angle; and constructing a spatial channel matrix; Accurately identify the spatial location of interference sources, including: performing spatial spectrum scanning; calculating the signal arrival angle distribution; identifying the direction of the main interference source; generating a spatial distribution map of the interference source; Designing optimal beamforming weights, including: constructing an adaptive beamforming algorithm; calculating constraints on the null direction; optimizing the main lobe direction gain; generating a weight vector; Achieve precise beam control, including: configuring antenna array phase relationships; adjusting the transmit power of each antenna; synchronizing antenna array timing; and performing beamforming operations; Establish a real-time optimization feedback mechanism, including: monitoring beamforming effects; analyzing signal-to-interference ratio changes; evaluating system performance indicators; and adjusting beamforming strategies.

10. A 5G portable WiFi signal enhancement system, used to execute the 5G portable WiFi signal enhancement method according to any one of claims 1 to 9, characterized in that: include: The first 5G portable WiFi device, the first terminal and edge server; The first 5G portable WiFi device is configured to: enable multiple types of environment perception sensors built into the first 5G portable WiFi device to collect first data; The edge server is configured as: Acquire in real time a first surrounding environment image within a first preset range of a location where a first terminal connected to the first 5G portable WiFi device is located, and a second surrounding environment image within a second preset range of a location where the first 5G portable WiFi device is located; Using a deep learning-based target detection algorithm, signal obstruction data is identified from the first surrounding environment image and the second surrounding environment image, and a placement scheme of the first 5G portable WiFi device is determined according to the signal obstruction data, the first data, and a preset device placement model; Activate the network monitoring program built into the first 5G portable WiFi device to scan the entire frequency band, and continuously collect signal data such as signal strength, phase, polarization characteristics, and noise spectrum distribution of each frequency band to construct an original data sample set; For the original data sample set, an adaptive filtering algorithm is used to dynamically adjust the filtering parameters to remove noise interference, a high-order statistical analysis method is used to mine the nonlinear characteristics in the signal data, and a time-frequency analysis tool is used to extract the time-varying characteristics of the frequency band and the frequency domain distribution characteristics; Use ensemble learning algorithms to fuse multiple weak classifiers and use historical frequency band features as input to build a frequency band quality assessment model; Combining the frequency band quality assessment model, the time-varying characteristics and the frequency domain distribution characteristics, to obtain a frequency band quality assessment result; According to the frequency band quality assessment result, based on a deep reinforcement learning algorithm, the frequency band switching action of the first 5G portable WiFi device is expanded to a continuous space; With the help of the parallel computing capability of quantum computing, a quantum neural network is constructed for interference signal analysis; The first 5G portable WiFi device is further configured as: Based on the interference analysis results, the coding technology is used to dynamically adjust the coding rate according to the interference intensity; Combined with orthogonal frequency division multiplexing technology, subcarriers are allocated, and subcarriers in frequency bands with severe interference are used to transmit redundant information to ensure the correct transmission of key data; Introducing beamforming technology, using a multi-antenna array to form a null in the interference direction, suppressing the reception of interference signals and enhancing the signal strength in the target direction; The edge server is also configured to: Continue to use the semantic segmentation algorithm in image recognition and processing technology to segment the latest environmental images acquired in real time, identify the location, outline, and material of new obstructions, and evaluate their degree of signal obstruction; According to the evaluation results of the degree of signal obstruction by the newly appeared obstructions, combined with the temperature, humidity, and electromagnetic environment change data fed back by the IoT sensors in real time, the first 5G portable WiFi device is controlled to dynamically adjust the transmission power, signal frequency, and modulation mode, and maintain high-frequency interaction with the mobile communication base station, upload the local environment and signal status, download the latest optimization instructions, form a closed-loop optimization link, and continuously and adaptively optimize the signal enhancement effect; The key status data of the first 5G portable WiFi device is received through the Internet of Things, and big data analysis is performed based on the data of multiple 5G portable WiFi devices. Based on the data analysis results, personalized signal enhancement solutions are pushed to different users.

Images