Intelligent network wireless router control system

Abstract

The invention discloses an intelligent network wireless router control system, which relates to the technical field of data networks and intelligently controls spectrum signal data transmission through a spectrum identification module, a bandwidth distribution module, an intelligent monitoring module, a safety management module and a user terminal. Furthermore, an available channel is obtained by utilizing a channel state through a frequency spectrum identification module, so that the data transmission rate of the frequency spectrum signal is improved, and interference factors suffered by the frequency spectrum signal during transmission are reduced; meanwhile, the frequency spectrum identification module identifies the frequency spectrum signal data and processes the interfered frequency spectrum signal data to obtain non-interference frequency spectrum signal data, and the non-interference frequency spectrum signal data is transmitted by using an available channel, so that the system aims at optimizing the network stability performance and improving the system control efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of data networks, and in particular to an intelligent network wireless routing control system. Background Art

[0002] With the development of network communication technology, traditional router equipment is difficult to meet user needs in large-scale, high-density environments. It is usually prone to frequency band congestion and repeated interference from the same or similar frequency band signals, as well as overlapping interference from the output of the next spectrum signal while the previous spectrum signal is still being transmitted. Therefore, the emergence of intelligent network wireless routing control systems can obtain available channels and interference-free spectrum signals, and transmit the interference-free spectrum signals through available channels;

[0003] The system uses spectrum identification module, bandwidth allocation module, intelligent monitoring module, security management module and user terminal to intelligently control wireless network signal transmission, giving priority to ensuring the connection stability of key equipment. At the same time, the system uses real-time data monitoring of spectrum data transmission through the intelligent monitoring and management function of security risks, and finally uses the user terminal to enable users to independently view the network status and adjust the device settings, thereby promoting the development of intelligent network wireless routing control systems.

[0004] In summary, how to improve the accuracy and stability of spectrum signals is an urgent problem to be solved and optimized in intelligent network wireless routing control systems. Summary of the invention

[0005] The present invention provides an intelligent network wireless routing control system, which solves the technical problem of how to improve the accuracy and stability of spectrum signals in related technologies.

[0006] In order to solve the above technical problems, the present invention provides an intelligent network wireless routing control system, and the specific technical solution is as follows:

[0007] In a first aspect, an intelligent network wireless routing control system comprises the following steps:

[0008] Spectrum identification module, bandwidth allocation module, intelligent monitoring module, security management module and user terminal to intelligently control wireless network signal transmission;

[0009] The spectrum identification module scans and collects a plurality of data to obtain a data set;

[0010] Wherein, the spectrum data set is acquired based on the data set, and the spectrum data set includes a plurality of spectrum signal data;

[0011] Acquire the spectrum signal feature data set based on the spectrum signal data; acquire the interference signal feature data set based on the spectrum signal feature data set to construct a training set to acquire a signal analysis model, and verify the interference state of the input new spectrum data set, and process the interference signal data to obtain an interference-free spectrum data set;

[0012] Acquire the channel information set based on the data set, where the channel information set includes a plurality of channel data;

[0013] A channel state is determined based on the signal strength of the channel data in the channel information set, and an available channel is selected according to the channel state to transmit the processed spectrum data set.

[0014] As a further optimization solution of the present invention, the spectrum identification module, the bandwidth allocation module, the intelligent monitoring module, the security management module and the user terminal include:

[0015] Based on obtaining the data set, obtaining an interference signal characteristic data set and identifying an available signal channel, and processing the interference signal so that the available signal channel transmits an interference-free spectrum data set;

[0016] Based on the non-interference spectrum data set, sending the non-interference spectrum data set to the bandwidth allocation module, supporting the transmission of the non-interference spectrum data set through the bandwidth allocation module, and dynamically allocating bandwidth data;

[0017] Based on the spectrum identification module and the bandwidth allocation module, the intelligent monitoring module monitors the spectrum data set transmission and the bandwidth allocation of the bandwidth allocation module in real time, so that the wireless network data can be accessed to the router device in an orderly manner;

[0018] The security management module integrates advanced security management functions to cooperate with the intelligent monitoring module to monitor network security risks that exist when performing spectrum identification and bandwidth allocation;

[0019] The user terminal views the display data of the intelligent monitoring module and the security management module in real time through the mobile application and the Web interface to dynamically adjust the settings of the router device.

[0020] As a further optimization solution of the present invention, the spectrum identification module further includes:

[0021] Spectrum scanning unit, channel identification unit, signal analysis unit and signal processing unit;

[0022] Scanning and collecting spectrum signal data in multiple frequency bands in the spectrum data set by the spectrum scanning unit;

[0023] Sending the spectrum data set to the channel identification unit;

[0024] Receiving the spectrum data set through the channel identification unit;

[0025] Determining the channel status based on the channel identification unit to obtain an available channel, so as to transmit the spectrum data set to the signal analysis unit;

[0026] Performing interference analysis on the spectrum data set based on the signal analysis unit to obtain an interference state analysis result of the spectrum data set;

[0027] Based on the interference status analysis result of the spectrum data set, the interference data of the spectrum data set is processed by the signal processing unit to obtain an interference-free spectrum data set.

[0028] As a further optimization solution of the present invention, a method for obtaining an available channel based on the channel identification unit judging the channel state includes:

[0029] The channel identification unit identifies the plurality of channel data in the channel information set one by one, and sets the single channel data as a time series X[n] of length N;

[0030] The sequence length N is equal to 2 by zero padding k , and input the sequence length N as 2 k The time series X[n] is sent to the channel identification unit;

[0031] The channel identification unit converts the input sequence length N into 2 k The time series X[n] is divided into two sequences according to even index and odd index, and the DFT of the two sequences is obtained by recursive calculation, that is, two small-block DFTs are obtained, wherein the DFT is a discrete Fourier transform, so that the time series X[n] is converted into a frequency domain signal; the two small-block DFT results are combined into a DFT sequence set to obtain the frequency domain representation of the time series X[n] as X[k];

[0032] Based on the frequency domain X[k], a spectrum analysis is performed on the frequency domain X[k] to obtain a frequency domain power spectrum of each spectrum component, and the signal strength data of each channel is obtained through the change amplitude of the frequency domain power spectrum; the channel signal strength data is compared with a preset noise threshold to determine the channel state; and an available channel is obtained based on the determination result of the channel state.

[0033] As a further optimization solution of the present invention, a method for performing interference analysis on a spectrum data set based on the signal analysis unit to obtain an interference state analysis result of the spectrum data set includes:

[0034] Inputting the spectrum data set into the signal analysis unit, and extracting the signal frequency, intensity and modulation information of a plurality of the spectrum signal data in the spectrum data set;

[0035] Based on acquiring the signal frequency, intensity and modulation information of the plurality of spectrum signal data, a spectrum signal feature data set is obtained;

[0036] Based on the spectrum signal feature data set, the spectrum signal feature data set is divided into a plurality of spectrum signal feature subsets; interference features in the spectrum signal feature subsets are stripped to output interference signal feature data; the interference signal feature data is identified to obtain reproduced interference signal feature data and overlapping interference signal feature data;

[0037] Among them, the recurring interference signal characteristic data means the same or similar spectrum signal data that appear repeatedly in different frequency bands; the overlapping interference signal characteristic data means that when the previous spectrum signal data is transmitted, the next spectrum signal data is output without gaps, and the spectrum signal data overlaps before and after;

[0038] A training set is constructed based on the reproduced interference signal characteristic data, the overlapping interference signal characteristic data and the available channel data to train and obtain a signal analysis model.

[0039] As a further optimization scheme of the present invention, a method for constructing a training set based on the reproduced interference signal characteristic data, the overlapping interference signal characteristic data and the available channel data to train and obtain a signal analysis model includes:

[0040] The training set is set as an observation vector S, and the observation vector S is input into the signal analysis model;

[0041] The observation vector S is encoded into sequence data, which includes j sequence units. The jth sequence unit represents the observation vector S at the current moment, and the jmth sequence unit represents the observation vector S at the mth moment before the current moment.

[0042] The sequence data is input into the hidden layer of the signal analysis model, and the intermediate state is output; the intermediate state is the identification result representing the signal interference source, which is as follows:

[0043] u (t) =σ(W u x (t) +W u H (t-1) +b u )

[0044] r (t) =σ(W r x (t) +W r H(t-1) +b r )

[0045] c (t) =tanh(W c x (t) +W c r (t) ·H (t-1) +b c )

[0046] H (t) =(1-u (t) )·c (t) +u (t) ·H (t-1)

[0047] Among them, W u , W r , W c represents the weight parameter, b u , b r , b c represents the bias parameter, represents the dot product, and u (t) 、r (t) and c (t) Represent the intermediate states of the first, second, and third hidden layers respectively, S is the observation vector, X (t) represents the tth data item in the training set, H (t) and H (t-1) They represent the t-th and t-1-th intermediate representation data, respectively, n≥t≥1, n represents the total number of input training set data items, and when t=1, H (t-1) =X (t) , tanh is the hyperbolic tangent function, and σ represents the sigmoid function.

[0048] As a further optimization solution of the present invention, the signal analysis model includes:

[0049] Based on the signal analysis model, the new spectrum data set sequence data is input into the signal analysis model to obtain and output the interference state of the new spectrum data set, as follows:

[0050] y t =σ(W y +h t +b y )

[0051] Among them, y t represents the output vector of the t-th intermediate period, where the components of the output vector represent the input data item belonging to the i-th state, and h t represents the tth intermediate representation data, W y is the weight parameter, b yis the bias parameter, and σ represents the sigmoid function.

[0052] As a further optimization scheme of the present invention, based on the interference state analysis result of the spectrum data set, the method of processing the interference data of the spectrum data set by the signal processing unit to obtain the interference-free spectrum data set includes:

[0053] Based on obtaining the recurring interference signal characteristic data and the overlapping interference signal characteristic data, marking the recurring interference signal characteristic data and the overlapping interference signal characteristic data to obtain first marking data and second marking data;

[0054] Performing recurrence interference processing on the first marked data to obtain a spectrum data set without recurrence interference;

[0055] Perform overlapping interference processing on the second labeled data to obtain a spectrum data set without overlapping interference;

[0056] The non-recurring interference spectrum data set and the non-overlapping interference spectrum data set are fused to obtain a non-interference spectrum data set.

[0057] As a further optimization solution of the present invention, a method for performing recurrence interference processing on the first marked data to obtain a spectrum data set without recurrence interference includes:

[0058] pass: The first labeled data S is divided into a plurality of first labeled data subsets S1, S2, ..., S n , where ∪ represents the partition function, S i represents the first label data of the i-th subset, and n is the number of spectrum signal feature subsets;

[0059] Based on the first labeled data subset, obtaining similarities between feature vectors of a plurality of the first labeled data subsets to identify recurring interference signal data;

[0060] pass: So that the identified recurring interference signal data is suppressed and removed, where H(z) represents the interference signal suppression removal function, Z represents the interference signal, and a1, b1 and b2 represent the suppression removal coefficients;

[0061] The plurality of first labeled data subsets after suppressing and removing interference are fused to obtain a spectrum data set without recurring interference.

[0062] As a further optimization solution of the present invention, a method for performing overlapping interference processing on the second labeled data to obtain a spectrum data set without overlapping interference includes:

[0063] The second labeled data K is divided into a plurality of second labeled data subsets K1, K2, ..., K n and inserting the plurality of second labeled data subsets into the time series data respectively to obtain a plurality of time series subsets;

[0064] detecting a plurality of said second labeled data subsets by time windows to identify overlapping interference signal data, and scanning a plurality of said time series subsets to find overlapping regions;

[0065] pass: Where, J(W) is the separation interference signal function; E is the separation interference matrix; m is the number of the second labeled data subset; W is the separation coefficient; J t is the second labeled data subset J at the tth moment, X is the time series subset observation signal matrix;

[0066] Based on the plurality of second labeled data subsets after the overlapping interference signals are separated, the plurality of second labeled data subsets are reconstructed through inverse transformation and fused to obtain a spectrum data set without overlapping interference.

[0067] The present invention has at least the following beneficial effects: the present invention intelligently controls spectrum signal data transmission through a spectrum identification module, a bandwidth allocation module, an intelligent monitoring module, a security management module and a user terminal, and further obtains available channels by using the channel status through the spectrum identification module, thereby improving the spectrum signal data transmission rate and reducing interference factors to which the spectrum signal is subjected during transmission;

[0068] At the same time, the spectrum identification module identifies the spectrum signal data and processes the interfered spectrum signal data to obtain interference-free spectrum signal data, and uses available channels to transmit the interference-free spectrum signal data, so that the system aims to optimize network stability performance and improve system control efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 The present invention provides a flow chart of an intelligent network wireless routing control system. DETAILED DESCRIPTION

[0070] The present application is further described in detail below in conjunction with the accompanying drawings. It is necessary to point out here that the following specific implementation methods are only used to further illustrate the present application and cannot be understood as limiting the scope of protection of the present application. Technical personnel in this field can make some non-essential improvements and adjustments to the present application based on the above application content.

[0071] The present invention provides an intelligent network wireless routing control system, the specific implementation of which is as follows:

[0072] like Figure 1As shown, an intelligent network wireless routing control system includes:

[0073] Spectrum identification module, bandwidth allocation module, intelligent monitoring module, security management module and user terminal to intelligently control wireless network signal transmission;

[0074] The spectrum identification module scans and collects a plurality of data to obtain a data set;

[0075] Wherein, the spectrum data set is acquired based on the data set, and the spectrum data set includes a plurality of spectrum signal data;

[0076] Acquire the spectrum signal feature data set based on the spectrum signal data; acquire the interference signal feature data set based on the spectrum signal feature data set to construct a training set to acquire a signal analysis model, and verify the interference state of the input new spectrum data set, and process the interference signal data to obtain an interference-free spectrum data set;

[0077] Acquire the channel information set based on the data set, where the channel information set includes a plurality of channel data;

[0078] A channel state is determined based on the signal strength of the channel data in the channel information set, and an available channel is selected according to the channel state to transmit the processed spectrum data set.

[0079] In the embodiment of the present invention, the spectrum identification module is responsible for optimizing channel selection and reducing interference signals.

[0080] The bandwidth allocation module ensures that critical applications and devices receive sufficient bandwidth.

[0081] The intelligent monitoring module monitors the network in real time and automatically adjusts to maintain optimal performance.

[0082] The security management module provides comprehensive network security protection.

[0083] The user terminal provides a friendly interface and remote management functions, making it convenient for users to control and monitor the network.

[0084] In a preferred embodiment of the present invention, the above-mentioned intelligent network wireless routing control system further includes:

[0085] Based on obtaining the data set, obtaining an interference signal characteristic data set and identifying an available signal channel, and processing the interference signal so that the available signal channel transmits an interference-free spectrum data set;

[0086] Based on the non-interference spectrum data set, sending the non-interference spectrum data set to the bandwidth allocation module, supporting the transmission of the non-interference spectrum data set through the bandwidth allocation module, and dynamically allocating bandwidth data;

[0087] Based on the spectrum identification module and the bandwidth allocation module, the intelligent monitoring module monitors the spectrum data set transmission and the bandwidth allocation of the bandwidth allocation module in real time, so that the wireless network data can be accessed to the router device in an orderly manner;

[0088] The security management module integrates advanced security management functions to cooperate with the intelligent monitoring module to monitor network security risks that exist when performing spectrum identification and bandwidth allocation;

[0089] The user terminal views the display data of the intelligent monitoring module and the security management module in real time through the mobile application and the Web interface to dynamically adjust the settings of the router device.

[0090] In an embodiment of the present invention, the spectrum identification module collects multiple data on the radio spectrum by scanning, generates a data set, and performs spectrum scanning to measure the strength of the signal in each frequency band; based on the scanned data, a spectrum data set is formed, which includes multiple spectrum signal data, and the data features of each signal, such as amplitude, frequency, power, etc., are extracted to generate a spectrum signal feature data set.

[0091] Interference detection and processing: Based on the spectrum signal feature data set, the interference signal features are extracted, a training set is constructed, and a signal analysis model is trained using a machine learning algorithm. The new spectrum data is then input into the model to identify the interference state, suppress or remove the identified interference signal, and generate an interference-free spectrum data set.

[0092] Obtain channel information set: Use the spectrum information in the data set to obtain channel information, such as signal strength and occupancy status, and judge the channel status: idle channel: no signal transmission; occupied channel: there is a communication signal; interference channel: there is an obvious interference signal or congestion occurs, affecting the communication quality.

[0093] The availability of each channel is evaluated based on the signal strength and interference conditions to select a channel with a high signal-to-noise ratio and less interference for transmission.

[0094] The bandwidth allocation module intelligently allocates bandwidth based on the evaluation results of available channels, dynamically controls bandwidth, and gives priority to allocating it to the transmission path with the best channel conditions, making wireless transmission efficient and stable.

[0095] The intelligent monitoring module monitors the status and performance of the wireless network in real time, collects network status data, including throughput, latency, and bit error rate, and promptly identifies network anomalies and makes adjustments through data analysis.

[0096] The security management module cooperates with the intelligent monitoring module to protect the security of the wireless network by implementing encryption and authentication strategies to prevent unauthorized access, detect potential network threats, and automatically take defensive measures.

[0097] User terminals use user interfaces to access and utilize wireless network resources, provide users with network usage status information, and simplify user operations through friendly interfaces and interactive mechanisms;

[0098] This enables the intelligent wireless network routing control system to reduce the impact of interference through effective interference identification and channel selection, optimize the use of spectrum resources, dynamically allocate bandwidth and intelligent monitoring, improve the stability and reliability of data transmission, ensure high performance and low latency of the network, and provide users with a high-quality connection experience. Through the role of the security management module, the network is protected from attacks and unauthorized use, and the functions of each module are integrated to form an efficient and adaptive wireless network management system.

[0099] In a preferred embodiment of the present invention, the spectrum identification module further includes:

[0100] Spectrum scanning unit, channel identification unit, signal analysis unit and signal processing unit;

[0101] Scanning and collecting spectrum signal data in multiple frequency bands in the spectrum data set by the spectrum scanning unit;

[0102] Sending the spectrum data set to the channel identification unit;

[0103] Receiving the spectrum data set through the channel identification unit;

[0104] Determining the channel status based on the channel identification unit to obtain an available channel, so as to transmit the spectrum data set to the signal analysis unit;

[0105] Performing interference analysis on the spectrum data set based on the signal analysis unit to obtain an interference state analysis result of the spectrum data set;

[0106] Based on the interference status analysis result of the spectrum data set, the interference data of the spectrum data set is processed by the signal processing unit to obtain an interference-free spectrum data set.

[0107] In this embodiment, the spectrum scanning unit obtains signal data in various frequency bands by scanning the wireless spectrum to form a spectrum data set covering multiple spectrum signals;

[0108] The channel identification unit identifies and evaluates the channel status, and analyzes the usage and signal strength of each channel based on the spectrum data set, determines whether the channel is available, selects the best channel for data transmission, and passes the information of the available channels to the signal analysis unit;

[0109] The signal analysis unit performs interference analysis by receiving data from the channel identification unit, analyzes interference characteristics in the spectrum data set, identifies possible interference sources and types, generates interference status analysis results, and provides data basis for the signal processing unit;

[0110] Based on the interference status analysis results, the signal processing unit applies filtering or other signal processing techniques to remove or suppress interference signals, optimize spectrum data, and output an interference-free spectrum data set for subsequent data transmission.

[0111] As a result, the spectrum identification module can effectively identify and eliminate interference through the cooperation of the spectrum scanning unit, channel identification unit, signal analysis unit and signal processing unit, ensure that spectrum resources are maximized, improve the stability and reliability of signal transmission through precise channel identification and interference processing, select the best channel to transmit interference-free data, reduce data loss and bit errors, improve network performance, provide clearer and more reliable signal transmission, improve user access experience, integrate modular processing, and improve the intelligent management and scheduling capabilities of spectrum resources.

[0112] In a preferred embodiment of the present invention, the channel identification unit further comprises:

[0113] The channel identification unit identifies the plurality of channel data in the channel information set one by one, and sets the single channel data as a time series X[n] of length N;

[0114] The sequence length N is equal to 2 by zero padding k , and input the sequence length N as 2 k The time series X[n] is sent to the channel identification unit;

[0115] The channel identification unit converts the input sequence length N into 2 k The time series X[n] is divided into two sequences according to even index and odd index, and the DFT of the two sequences is obtained by recursive calculation, that is, two small-block DFTs are obtained, wherein the DFT is a discrete Fourier transform, so that the time series X[n] is converted into a frequency domain signal; the two small-block DFT results are combined into a DFT sequence set to obtain the frequency domain representation of the time series X[n] as X[k];

[0116] Based on the frequency domain X[k], a spectrum analysis is performed on the frequency domain X[k] to obtain a frequency domain power spectrum of each spectrum component, and the signal strength data of each channel is obtained through the change amplitude of the frequency domain power spectrum; the channel signal strength data is compared with a preset noise threshold to determine the channel state; and an available channel is obtained based on the determination result of the channel state.

[0117] In this embodiment, for each channel data in the channel information set, the length is set to

[0118] N time series X[n], expand the time series to 2 k The length is filled with zeros to meet the FFT requirements. This processing helps to optimize the computational efficiency of the discrete Fourier transform (DFT), especially to meet the requirements of the fast Fourier transform (FFT) algorithm.

[0119] Then change the length 2 k The sequence X[n] is divided into two subsequences according to even and odd indexes, and the discrete Fourier transform (DFT) is recursively calculated for the two subsequences to obtain DFT results of two small blocks.

[0120] pass: Combine the two small DFT results to get the complete frequency domain representation X[n], where X[k] is the DFT combination result, X[k+N / 2] is the single DFT result, G[k] and H[k] are the DFTs of the subsequences, and W N k is the rotation factor, and N is the number of DFT results.

[0121] Based on the combined frequency domain X[k], the power spectrum is obtained, the amplitude change of the power spectrum is analyzed, the signal strength of each spectral component is evaluated, and the important spectral components are identified by the power spectrum amplitude, where P[k]>|X[k]| 2 , usually represents a strong signal, and determines the part where the signal strength is higher than the background noise, where P[k]≤|X[k]| 2 Usually represents a normal signal, determining the portion where the signal strength is lower than the background noise.

[0122] Set noise threshold: Wi-Fi noise threshold is set at -85dBm to -90dBm; 4G / 5G noise threshold is around -100dBm; LoRa / NB-IoT low-power IoT devices may use noise thresholds as low as -120dBm;

[0123] The signal strength of the channel is compared with the preset noise threshold: when the channel signal strength is greater than the noise threshold, the channel is considered to be occupied; when the channel signal strength is less than or equal to the noise threshold, the channel is considered to be idle; thereby determining whether each channel is available, and based on the channel status, selecting channels that can be used for data transmission.

[0124] Furthermore, among the available channels, the channel with the least signal interference and the best signal quality is selected for data transmission: the channel quality index is represented by the signal-to-noise ratio, which is the ratio of signal strength to background noise, specifically expressed as: SNR = -(signal strength) -[-(preset noise threshold)]; the higher the signal-to-noise ratio, the better the transmission quality of the channel. The SNR of each channel is obtained, and channels with higher SNR are selected first. When the signal-to-noise ratio of each channel is evaluated to be low, that is, there are a lot of spectrum signal data being transmitted on the current channel. If there is already a lot of signal data transmission on a certain channel, the utilization rate of the channel is high, which may lead to data transmission delays and increased packet loss rate.

[0125] The signal-to-noise ratio can be used to exclude channels occupied by other strong signals first, and then select the channel with the lowest noise level and the highest SNR among the remaining channels; when in the 2.4GHz band, there is a certain spectrum overlap between the channels used by Wi-Fi. For example, channels 1, 6, and 11 are completely non-overlapping in the 2.4GHz band, so devices usually give priority to these channels to avoid overlapping interference.

[0126] In some cases, environmental interference and channel quality change dynamically. Modern wireless devices may support automatic channel switching, regularly scanning the quality of the current channel and automatically switching to a better channel when severe interference is detected. This dynamic switching is usually performed without the user's awareness to minimize the impact on the network connection. Once the device selects the best channel, it locks the channel and starts data transmission. Unless it detects that the channel quality has dropped significantly or a better channel is available, the device usually does not easily change the channel to ensure the stability of the connection.

[0127] The signal recognition unit uses FFT to quickly analyze the spectrum, accurately extract signal strength, improve algorithm efficiency, effectively identify and select the optimal channel, reduce interference, improve communication quality, quickly judge channel status, support real-time dynamic spectrum management, reduce channel congestion, improve spectrum utilization and transmission reliability, enhance user experience, automate channel identification, simplify network operation and maintenance, and improve management efficiency.

[0128] In a preferred embodiment of the present invention, the signal analysis unit may further include:

[0129] Inputting the spectrum data set into the signal analysis unit, and extracting the signal frequency, intensity and modulation information of a plurality of the spectrum signal data in the spectrum data set;

[0130] Based on acquiring the signal frequency, intensity and modulation information of the plurality of spectrum signal data, a spectrum signal feature data set is obtained;

[0131] Based on the spectrum signal feature data set, the spectrum signal feature data set is divided into a plurality of spectrum signal feature subsets; interference features in the spectrum signal feature subsets are stripped to output interference signal feature data; the interference signal feature data is identified to obtain reproduced interference signal feature data and overlapping interference signal feature data;

[0132] Among them, the recurring interference signal characteristic data means the same or similar spectrum signal data that appear repeatedly in different frequency bands; the overlapping interference signal characteristic data means that when the previous spectrum signal data is transmitted, the next spectrum signal data is output without gaps, and the spectrum signal data overlaps before and after;

[0133] A training set is constructed based on the reproduced interference signal characteristic data, the overlapping interference signal characteristic data and the available channel data to train and obtain a signal analysis model.

[0134] In this embodiment, the signal analysis unit is used to improve signal resolution and accuracy through detailed feature extraction and interference identification, identify and remove interference signals, reduce the impact on normal signal transmission, and improve communication quality. By combining spectrum data and channel information, the trained model can more accurately evaluate and predict channel status, optimize spectrum resource utilization, improve network efficiency, dynamically identify and process interference, improve spectrum signal quality and transmission stability, and improve user experience.

[0135] In another preferred embodiment of the present invention, the signal analysis model includes:

[0136] The training set is set as an observation vector S, and the observation vector S is input into the signal analysis model;

[0137] The observation vector S is encoded into sequence data, which includes j sequence units. The jth sequence unit represents the observation vector S at the current moment, and the jmth sequence unit represents the observation vector S at the mth moment before the current moment.

[0138] The sequence data is input into the hidden layer of the signal analysis model, and the intermediate state is output; the intermediate state is the identification result representing the signal interference source, which is as follows:

[0139] u (t) =σ(W u x (t) +W u H (t-1) +b u )

[0140] r (t) =σ(W r x (t) +W r H(t-1) +b r )

[0141] c (t) =tanh(W c x (t) +W c r (t) ·H (t-1) +b c )

[0142] H (t) =(1-u (t) )·c (t) +u (t) ·H (t-1)

[0143] Among them, W u , W r , W c represents the weight parameter, b u , b r , b c represents the bias parameter, represents the dot product, and u (t) 、r (t) and c (t) Represent the intermediate states of the first, second, and third hidden layers respectively, S is the observation vector, X (t) represents the tth data item in the training set, H (t) and H (t-1) They represent the t-th and t-1-th intermediate representation data, respectively, n≥t≥1, n represents the total number of input training set data items, and when t=1, H (t-1) =X (t) , tanh is the hyperbolic tangent function, and σ represents the sigmoid function.

[0144] In this embodiment, the signal analysis model is constructed by using the acquired spectrum signal data (including reproducing interference signals, overlapping interference signals and available channel data), which can significantly improve the interference identification capability, channel selection efficiency and overall network performance of wireless networks in complex environments. This data-driven signal analysis model can achieve more intelligent channel management, improve the generalization ability of the model, reduce manual intervention and network maintenance costs, and thus better adapt to complex and changing wireless environments.

[0145] In a preferred embodiment of the present invention, the above signal analysis model further includes:

[0146] Based on the signal analysis model, the new spectrum data set sequence data is input into the signal analysis model to obtain and output the interference state of the new spectrum data set, as follows:

[0147] y t =σ(Wy +h t +b y )

[0148] Among them, y t represents the output vector of the t-th intermediate period, where the components of the output vector represent the input data item belonging to the i-th state, and h t represents the tth intermediate representation data, W y is the weight parameter, b y is the bias parameter, and σ represents the sigmoid function.

[0149] In this embodiment, by inputting new spectrum signal data into the signal analysis model to verify and extract interference signal features, efficient real-time interference detection can be achieved, identification accuracy can be improved, manual intervention can be reduced, model adaptability can be enhanced, and the anti-interference performance of the wireless network can be improved. This automated signal feature extraction and verification process can help wireless communication systems maintain stability and high performance in complex and changing environments.

[0150] In another preferred embodiment of the present invention, the signal processing unit comprises the following steps:

[0151] Step 1, based on obtaining the reproduced interference signal characteristic data and the overlapped interference signal characteristic data, marking the reproduced interference signal characteristic data and the overlapped interference signal characteristic data to obtain first marking data and second marking data;

[0152] Step 2, performing recurrence interference processing on the first marked data to obtain a spectrum data set without recurrence interference;

[0153] Step 3, performing overlapping interference processing on the second marked data to obtain a spectrum data set without overlapping interference;

[0154] Step 4: merge the non-recurring interference spectrum data set and the non-overlapping interference spectrum data set to obtain a non-interference spectrum data set.

[0155] In this embodiment, step 1 is used to collect the characteristic data of the reproduced interference signal and the overlapping interference signal from the spectrum analysis, and the reproduced interference signal is marked to form the first marking data, and the overlapping interference signal is marked to form the second marking data. Through marking, the type and position of the interference signal are clarified, providing a clear target for the processing of subsequent steps.

[0156] Based on step 1, step 2 is used to analyze the recurring signals in the frequency band of the first marked data, thereby obtaining a spectrum data set without recurrence interference, effectively eliminating repeated signals, improving the purity of the spectrum data, and enhancing the reliability and accuracy of the spectrum data.

[0157] Based on step 1, step 3 analyzes the part of adjacent signals in the second labeled data where there is no gap overlap, applies signal separation and reconstruction technology, processes the overlapping area, and generates a spectrum data set without overlapping interference, ensuring accurate separation of overlapping signals, reducing confusion, and enhancing data integrity: maintaining signal continuity and integrity.

[0158] Based on step 2 and step 3, step 4 uses the Kalman filter state estimation recursive algorithm to fuse the spectrum data set without recurring interference and overlapping interference, ensuring the integrity and continuity of the spectrum data, and obtaining an interference-free spectrum data set, providing interference-free and clear spectrum data, which is suitable for subsequent analysis and transmission, and improving the transmission efficiency and quality of the network by effectively utilizing the spectrum.

[0159] In a preferred embodiment of the present invention, the above step 2 includes:

[0160] Step 21, by: The first labeled data S is divided into a plurality of first labeled data subsets S1, S2, ..., S n , where ∪ represents the partition function, S i represents the first label data of the i-th subset, and n is the number of spectrum signal feature subsets;

[0161] Step 22, based on the first marked data subset, obtaining similarities between feature vectors of a plurality of the first marked data subsets to identify recurring interference signal data;

[0162] Step 23, by: So that the identified recurring interference signal data is suppressed and removed, where H(z) represents the interference signal suppression removal function, Z represents the interference signal, and a1, b1 and b2 represent the suppression removal coefficients;

[0163] Step 24: fuse the plurality of first labeled data subsets after suppressing and removing interference to obtain a spectrum data set without recurring interference.

[0164] In this embodiment, the first marked data is divided into a plurality of subsets through step 21, and the number and range of the subsets are determined by using a partitioning function, and the data is divided based on different features (such as frequency, time period, etc.). The partitioning of the data facilitates subsequent refined processing and analysis, and the block processing improves the processing efficiency and accuracy; based on step 21, a feature vector (such as frequency, intensity, etc.) is extracted from each subset through step 22, and the repeated interference signal is identified by calculating the similarity of the feature vectors between the subsets;

[0165] Commonly used methods: cosine similarity, Euclidean distance, etc.

[0166] Similarity analysis is used to help identify interference signals that appear multiple times, and the accuracy of repeated signal identification is improved through detailed comparison.

[0167] Based on step 22, step 23 effectively suppresses and removes the recurring interference, thereby purifying the signal.

[0168] Improve signal quality: improve the quality and integrity of spectrum data, and then use step 24 to integrate the subset after suppressing and removing interference through the recursive algorithm of Kalman filter state estimation to form a complete spectrum data set without recurring interference.

[0169] By merging all subsets, the integrity of the original data is restored, optimizing subsequent analysis: providing more accurate and interference-free data to support subsequent signal processing and analysis.

[0170] In a preferred embodiment of the present invention, the above step 3 includes:

[0171] Step 31: divide the second labeled data K into a plurality of second labeled data subsets K1, K2, ..., K n , and insert multiple second labeled data subsets into the time series data respectively: L window =t∈[t m -w,t m +w] to obtain multiple time series subsets; where L window represents the insertion window, t represents the time point, and t m represents the time series of labeled data, then in [t m -w,t m +w] All labeled data within the range will be assigned the same time series;

[0172] Step 32, detecting a plurality of the second labeled data subsets through a time window to identify overlapping interference signal data, and scanning a plurality of the time series subsets to find overlapping areas;

[0173] Step 33, by: Where, J(W) is the separation interference signal function; E is the separation interference matrix; m is the number of the second labeled data subset; W is the separation coefficient; J t is the second labeled data subset J at the tth moment, X is the time series subset observation signal matrix;

[0174] Step 34: Based on the plurality of second labeled data subsets after the overlapping interference signals are separated, the plurality of second labeled data subsets are reconstructed through inverse transformation, and are fused to obtain a spectrum data set without overlapping interference.

[0175] In this embodiment, the second labeled data K is divided into multiple subsets through step 31, divided according to the time segment rule, and each subset is inserted into the corresponding time series to form multiple time series subsets. The data is integrated into the time series, which is conducive to time domain analysis. The block insertion makes subsequent detection and processing more efficient.

[0176] Based on step 31, each time series subset is scanned through step 32 to identify the overlapping interference signal area, accurately locate the time area where the overlapping signal is located, and detect the overlapping interference area that can be accurately located to improve the recognition accuracy of the overlapping signal. Then, through step 33, the overlapping interference signal separation function J(W) is used to separate the overlapping interference signals, extract and separate the overlapping signals, eliminate mutual interference, and then use methods such as independent component analysis to reduce the interference between overlapping signals and enhance the independence and clarity of the signals; finally, through step 34, the separated signals are inversely transformed and restored to the time domain, and the processed subsets are reintegrated to form a spectrum data set without overlapping interference, ensuring that all processed signals are restored and fused in the time domain, generating interference-free spectrum data, and providing high-quality data support for further analysis and application.

[0177] The purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0178] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation mode. The above-mentioned specific implementation mode is merely illustrative and not restrictive. Under the guidance of this embodiment, ordinary technicians in this field can also make more forms of equivalent embodiments, all of which are within the protection of this embodiment.

[0179] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. An intelligent network wireless routing control system, characterized in that: include: Spectrum identification module, bandwidth allocation module, intelligent monitoring module, security management module and user terminal to intelligently control wireless network signal transmission; The spectrum identification module scans and collects a plurality of data to obtain a data set; Wherein, the spectrum data set is acquired based on the data set, and the spectrum data set includes a plurality of spectrum signal data; Acquire the spectrum signal feature data set based on the spectrum signal data; acquire the interference signal feature data set based on the spectrum signal feature data set to construct a training set to acquire a signal analysis model, and verify the interference state of the input new spectrum data set, and process the interference signal data to obtain an interference-free spectrum data set; Acquire the channel information set based on the data set, where the channel information set includes a plurality of channel data; A channel state is determined based on the signal strength of the channel data in the channel information set, and an available channel is selected according to the channel state to transmit the processed spectrum data set.

2. The intelligent network wireless routing control system according to claim 1, characterized in that: Spectrum identification module, bandwidth allocation module, intelligent monitoring module, security management module and user terminal, including: Based on obtaining the data set, obtaining an interference signal characteristic data set and identifying an available signal channel, and processing the interference signal so that the available signal channel transmits an interference-free spectrum data set; Based on the non-interference spectrum data set, sending the non-interference spectrum data set to the bandwidth allocation module, supporting the transmission of the non-interference spectrum data set through the bandwidth allocation module, and dynamically allocating bandwidth data; Based on the spectrum identification module and the bandwidth allocation module, the intelligent monitoring module monitors the spectrum data set transmission and the bandwidth allocation of the bandwidth allocation module in real time, so that the wireless network data can be accessed to the router device in an orderly manner; The security management module integrates advanced security management functions to cooperate with the intelligent monitoring module to monitor network security risks that exist when performing spectrum identification and bandwidth allocation; The user terminal views the display data of the intelligent monitoring module and the security management module in real time through the mobile application and the Web interface to dynamically adjust the settings of the router device.

3. An intelligent network wireless routing control system according to claim 2, characterized in that: The spectrum identification module further includes: Spectrum scanning unit, channel identification unit, signal analysis unit and signal processing unit; Scanning and collecting spectrum signal data in multiple frequency bands in the spectrum data set by the spectrum scanning unit; Sending the spectrum data set to the channel identification unit; Receiving the spectrum data set through the channel identification unit; Determining the channel status based on the channel identification unit to obtain an available channel, so as to transmit the spectrum data set to the signal analysis unit; Performing interference analysis on the spectrum data set based on the signal analysis unit to obtain an interference state analysis result of the spectrum data set; Based on the interference status analysis result of the spectrum data set, the interference data of the spectrum data set is processed by the signal processing unit to obtain an interference-free spectrum data set.

4. The intelligent network wireless routing control system according to claim 1, characterized in that: The method for obtaining available channels based on the channel identification unit judging the channel state comprises: The channel identification unit identifies the plurality of channel data in the channel information set one by one, and sets the single channel data as a time series X[n] of length N; The sequence length N is equal to 2 by zero padding k , and input the sequence length N as 2 k The time series X[n] is sent to the channel identification unit; The channel identification unit sets the input sequence length N to 2 k The time series X[n] is divided into two sequences according to even index and odd index, and the DFT of the two sequences is obtained by recursive calculation, that is, two small-block DFTs are obtained, wherein the DFT is a discrete Fourier transform, so that the time series X[n] is converted into a frequency domain signal; the two small-block DFT results are combined into a DFT sequence set to obtain the frequency domain representation of the time series X[n] as X[k]; Based on the frequency domain X[k], a spectrum analysis is performed on the frequency domain X[k] to obtain a frequency domain power spectrum of each spectrum component, and the signal strength data of each channel is obtained through the change amplitude of the frequency domain power spectrum; the channel signal strength data is compared with a preset noise threshold to determine the channel state; and an available channel is obtained based on the determination result of the channel state.

5. The intelligent network wireless routing control system according to claim 4 is characterized in that: The method of performing interference analysis on a spectrum data set based on the signal analysis unit to obtain an interference state analysis result of the spectrum data set includes: Inputting the spectrum data set into the signal analysis unit, and extracting the signal frequency, intensity and modulation information of a plurality of the spectrum signal data in the spectrum data set; Based on acquiring the signal frequency, intensity and modulation information of the plurality of spectrum signal data, a spectrum signal feature data set is obtained; Based on the spectrum signal feature data set, the spectrum signal feature data set is divided into a plurality of spectrum signal feature subsets; interference features in the spectrum signal feature subsets are stripped to output interference signal feature data; the interference signal feature data is identified to obtain reproduced interference signal feature data and overlapping interference signal feature data; Among them, the recurring interference signal characteristic data means the same or similar spectrum signal data that appear repeatedly in different frequency bands; the overlapping interference signal characteristic data means that when the previous spectrum signal data is transmitted, the next spectrum signal data is output without gaps, and the spectrum signal data overlaps before and after; A training set is constructed based on the reproduced interference signal characteristic data, the overlapping interference signal characteristic data and the available channel data to train and obtain a signal analysis model.

6. The intelligent network wireless routing control system according to claim 5, characterized in that: The method of constructing a training set based on the reproduced interference signal characteristic data, the overlapping interference signal characteristic data and the available channel data to train and obtain a signal analysis model includes: The training set is set as an observation vector S, and the observation vector S is input into the signal analysis model; The observation vector S is encoded into sequence data, which includes j sequence units. The jth sequence unit represents the observation vector S at the current moment, and the jmth sequence unit represents the observation vector S at the mth moment before the current moment. The sequence data is input into the hidden layer of the signal analysis model, and the intermediate state is output; the intermediate state is the identification result representing the signal interference source, which is as follows: u (t) =σ(W u x (t) +W u H (t-1) +b u ) r (t) =σ(W r x (t) +W r H (t-1) +b r ) c (t) =tanh(W c x (t) +W c r (t) ·H (t-1) +b c ) H (t) =(1-u (t) )·c (t) +u (t) ·H (t-1) Among them, W u , W r , W c represents the weight parameter, b u , b r , b c represents the bias parameter, represents the dot product, and u (t) 、r (t) and c (t) Represent the intermediate states of the first, second, and third hidden layers respectively, S is the observation vector, X (t) represents the tth data item in the training set, H (t) and H (t-1) They represent the t-th and t-1-th intermediate representation data, respectively, n≥t≥1, n represents the total number of input training set data items, and when t=1, H (t-1) =X (t) , tanh is the hyperbolic tangent function, and σ represents the sigmoid function.

7. An intelligent network wireless routing control system according to claim 6, characterized in that: The signal analysis model comprises: Based on the signal analysis model, the new spectrum data set sequence data is input into the signal analysis model to obtain and output the interference state of the new spectrum data set, as follows: y t =σ(W y +h t +b y ) Among them, y t represents the output vector of the t-th intermediate period, where the components of the output vector represent the input data item belonging to the i-th state, and h t represents the tth intermediate representation data, W y is the weight parameter, b y is the bias parameter, and σ represents the sigmoid function.

8. The intelligent network wireless routing control system according to claim 7, characterized in that: The method of processing the interference data of the spectrum data set by the signal processing unit based on the interference state analysis result of the spectrum data set to obtain the interference-free spectrum data set includes: Based on obtaining the recurring interference signal characteristic data and the overlapping interference signal characteristic data, marking the recurring interference signal characteristic data and the overlapping interference signal characteristic data to obtain first marking data and second marking data; Performing recurrence interference processing on the first marked data to obtain a spectrum data set without recurrence interference; Perform overlapping interference processing on the second labeled data to obtain a spectrum data set without overlapping interference; The non-recurring interference spectrum data set and the non-overlapping interference spectrum data set are fused to obtain a non-interference spectrum data set.

9. The intelligent network wireless routing control system according to claim 8, characterized in that: The method of performing recurrence interference processing on the first marked data to obtain a spectrum data set without recurrence interference includes: pass: The first labeled data S is divided into a plurality of first labeled data subsets S1, S2, ..., S n , where ∪ represents the partition function, S i represents the first label data of the i-th subset, and n is the number of spectrum signal feature subsets; Based on the first labeled data subset, obtaining similarities between feature vectors of a plurality of the first labeled data subsets to identify recurring interference signal data; pass: So that the identified recurring interference signal data is suppressed and removed, where H(z) represents the interference signal suppression removal function, Z represents the interference signal, and a1, b1 and b2 represent the suppression removal coefficients; The plurality of first labeled data subsets after suppressing and removing interference are fused to obtain a spectrum data set without recurring interference.

10. An intelligent network wireless routing control system according to claim 9, characterized in that: The method of performing overlapping interference processing on the second marked data to obtain a spectrum data set without overlapping interference includes: The second labeled data K is divided into a plurality of second labeled data subsets K1, K2, ..., K n and inserting the plurality of second labeled data subsets into the time series data respectively to obtain a plurality of time series subsets; detecting a plurality of said second labeled data subsets by time windows to identify overlapping interference signal data, and scanning a plurality of said time series subsets to find overlapping regions; pass: Where, J(W) is the separation interference signal function; E is the separation interference matrix; m is the number of the second labeled data subset; W is the separation coefficient; J t is the second labeled data subset J at the tth moment, X is the time series subset observation signal matrix; Based on the plurality of second labeled data subsets after the overlapping interference signals are separated, the plurality of second labeled data subsets are reconstructed through inverse transformation and fused to obtain a spectrum data set without overlapping interference.

Images