A signal management system based on dual-frequency signals

Abstract

The present invention relates to the technical field of signal management, and discloses a signal management system based on dual-frequency signals, comprising a data acquisition module, a signal matching module, a signal transmitting module, a signal receiving module, a signal adjustment module and an intelligent control module; by providing a signal adjustment module, it is beneficial to analyze corresponding data based on the signal quality conditions of different frequency bands, so as to obtain the optimal signal adjustment strategy and adjust the signal, which can be generally applied to dual-frequency signals to improve the signal quality, and combine channel prediction with a neural network model, and can automatically select the most suitable modulation and coding scheme according to the real-time characteristics of the channel, while integrating the trained neural network model into the fitness calculation of the improved nature-inspired algorithm, which can give full play to the nonlinear and multimodal data modeling capabilities of the neural network and effectively capture complex data relationships.

Description

Technical Field

[0001] The present invention relates to the technical field of signal management, and more specifically to a signal management system based on dual-frequency signals. Background Art

[0002] Dual-band signals refer to signals that can support two different frequency bands at the same time. Dual-band signal management usually refers to the management of 2.4GHz and 5GHz wireless signals emitted by dual-band routers. Different devices need to connect to signals of different frequency bands based on the distance, needs and performance of the devices to provide the best user experience. Dual-band signals provide more choices and flexibility for wireless smart devices.

[0003] However, in the existing technology for signal management of dual-frequency signals, users are required to weigh and select signal frequency bands based on the actual device performance, network requirements and network environment of smart devices. However, most users often lack the corresponding professional knowledge and are unable to select the best frequency band signal. At the same time, during the signal transmission process, the channel state is not static. Therefore, it is necessary to adaptively adjust the coding and modulation methods according to the channel state in a timely manner to enhance signal quality and improve user experience.

[0004] In view of this, the present application proposes a signal management system based on dual-frequency signals, which can intelligently select the signal frequency band of smart devices and intelligently optimize and adjust the signals. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a signal management system based on dual-frequency signals to solve the problems existing in the above-mentioned background technology.

[0006] The present invention provides the following technical solutions: a signal management system based on dual-frequency signals, comprising a data acquisition module, a signal matching module, a signal transmitting module, a signal receiving module, a signal adjustment module and an intelligent management and control module;

[0007] The data acquisition module is used to collect target data of different smart devices and classify the smart devices based on the signal connection frequency band;

[0008] The signal matching module is used to collect device data of the target object, perform signal matching on the target object, use the successfully matched signal as the connection signal of the target object, and send a transmission instruction to the signal transmission module;

[0009] The signal transmitting module is used to generate a signal of a corresponding frequency band after receiving a transmitting instruction, and transmit the signal to the signal receiving module, and is composed of a signal source, a modulator, a power amplifier and an antenna. The signal transmitting module includes a first transmitting unit and a second transmitting unit;

[0010] The signal receiving module is used to receive the signal from the signal transmitting module, and is composed of an antenna, a low noise amplifier, a filter and a demodulator; the signal receiving module includes a first receiving unit and a second receiving unit;

[0011] The signal adjustment module is used to collect signal transmission data from the signal transmission module to the signal receiving module and analyze the signal quality, predict the channel state based on the channel prediction algorithm, and obtain the optimal signal adjustment strategy in combination with the improved natural inspiration algorithm;

[0012] The intelligent management and control module is used to intelligently control all modules and execute the optimal signal adjustment strategy to intelligently manage the signals.

[0013] Preferably, the target data is the signal connection requirement data and signal connection frequency band of the smart device; the transmission instruction includes the frequency band information of the transmitted signal, that is, the successfully matched signal; the target object is the smart device for signal connection, and the device data is the signal connection requirement data of the target object;

[0014] The signal source is used to generate signals of two different frequency bands; the modulator is used to modulate the baseband signal to two different carrier frequencies; the power amplifier is used to amplify the modulated signal; the antenna is used to transmit the modulated signal; the first transmitting unit is used to transmit the signal of one frequency band, and the second transmitting unit is used to transmit the signal of the other frequency band;

[0015] The first receiving unit is used to receive signals in one frequency band, and the second receiving unit is used to receive signals in another frequency band; the antenna is used to receive signals transmitted by the signal transmitting module; the low-noise amplifier is used to amplify the received signal; the filter is used to filter out clutter in the received signal; and the demodulator is used to demodulate the modulated signal back to a baseband signal.

[0016] Preferably, the specific manner in which the signal matching module performs signal matching on the target object is:

[0017] Step S11: converting the device data of the target object into a corresponding word vector through a word vector conversion model, and recording it as a target point;

[0018] Step S12: record the target point as M, calculate the distance from the target point to the cluster center point of each cluster, and sort them in ascending order from small to large, and assign the target point to the cluster corresponding to the cluster center point closest to it, that is, the cluster corresponding to the cluster center point with the smallest distance value;

[0019] The distance is calculated as follows: , where D Mcis the distance between the target point and the cluster center of the cth cluster, M u is the coordinate of the target point in the uth dimension, z´ cu is the cluster center point z´ of the cth cluster c At the coordinate of the u-th dimension, R is the dimension, u=1, 2, 3, ..., R;

[0020] Step S13: Outputting the connection signal frequency band corresponding to the smart device category of the cluster where the target point is located in step S12, that is, the signal of successful matching.

[0021] Preferably, the calculation formula for analyzing the signal quality by the signal adjustment module is expressed as: , where XZ is the signal quality, βx is the signal-to-noise ratio, βw is the bit error rate, βd is the packet loss rate; λ1, λ2 and λ3 are the corresponding proportional factors respectively;

[0022] , where SP is the signal power and NP is the noise power; , where s(t) is the signal amplitude at time t, when the signal is a periodic signal, T is the signal period, and when the signal is a non-periodic signal, T is the time taken for the signal to be transmitted and received; , where f(t) is the noise amplitude at time t;

[0023] , where B1 is the number of erroneous bits, B z is the total number of bits transmitted;

[0024] , where q1 is the number of data packets received by the signal receiving module, and q2 is the number of data packets sent by the signal transmitting module.

[0025] Preferably, the channel prediction algorithm predicts the channel state by estimating the channel state through a Kalman filter algorithm, obtaining an estimated value of the channel state, obtaining corresponding predicted signal transmission data, and obtaining an estimated signal quality. If the estimated signal quality decreases relative to the signal quality XZ, the optimal signal adjustment strategy is obtained through an improved natural inspiration algorithm, otherwise the current transmission mode, channel coding and modulation mode are used as the optimal signal adjustment strategy;

[0026] The method for obtaining the corresponding predicted signal transmission data is: pre-collecting a variety of different channel states and corresponding feature data, constructing a knowledge graph, matching the estimated value of the acquired channel state with the knowledge graph, obtaining the matched channel state and the corresponding feature data, wherein the feature data includes signal transmission data, and calculating the estimated signal quality based on this.

[0027] Preferably, the step of obtaining the optimal signal adjustment strategy comprises the following steps:

[0028] Step S21: setting different digital labels for different signal adjustment strategies and marking them as strategy labels;

[0029] Step S22: presetting the population size Z and the number threshold T;

[0030] Step S23: Initialize the population, the positions of the lizards in the initialized population are defined in a one-dimensional search space, the positions of the lizards correspond to the strategy labels one by one, and the number of iterations t of the initialized population is 0;

[0031] Step S24: determining a fitness function;

[0032] Step S25: defining the temperature and food intake of each lizard's location;

[0033] Step S26: defining the location of the cave and determining whether the lizard has entered the cave or entered the foraging stage;

[0034] Step S27: Update the position of the lizard;

[0035] Step S28: Determine whether the iteration is completed. If not, return to step S25 and set the number of iterations t=t+1; if completed, proceed to step S29;

[0036] Step S29: Calculate the fitness corresponding to the position of each lizard, obtain the position of the lizard corresponding to the fitness with the largest value, and obtain the signal adjustment strategy corresponding to the corresponding strategy label according to the lizard position as the optimal signal adjustment strategy.

[0037] Preferably, the initialized population is expressed as: , where Ω is the initialized population, Z is the number of lizards in the population, i.e., the number of signal adjustment strategies, μ Z Adjust the strategy for the Zth signal;

[0038] The expression for the position of each lizard is: , where μ e 0 is the initial position of the e-th lizard, E e is a random number between [0, 1], e=1, 2, 3, …, M, where M is the total number of strategy tags;

[0039] The fitness function in step S24 is expressed as: , where SY is the fitness of the e-th lizard, θ e is the signal quality gain of the signal adjustment strategy corresponding to the e-th lizard;

[0040] The signal quality gain is obtained by taking the signal adjustment strategy and the corresponding signal transmission data corresponding to the lizard and the current signal strategy and the corresponding signal transmission data as research data, inputting the research data into a trained signal quality gain prediction model, and predicting the corresponding signal quality gain; the current signal strategy is the current signal transmission method, channel coding and modulation method.

[0041] Preferably, the training process of the signal quality gain prediction model is specifically as follows:

[0042] A current signal strategy and corresponding signal transmission data and a signal adjustment strategy and corresponding signal transmission data are taken as a set of analysis data, d sets of analysis data are collected in advance, d is an integer greater than 1, and the analysis data and the corresponding signal quality gain are converted into a corresponding set of feature vectors; the signal quality gain can be obtained by subtracting the signal quality corresponding to the signal transmission data before adjustment from the signal quality corresponding to the adjusted signal transmission data; the adjusted signal transmission data can be obtained according to the actual signal transmission data after adjustment; d sets of analysis data are collected, and under the condition of each set of analysis data, the quality gain of each signal adjustment strategy is comprehensively analyzed;

[0043] Each group of feature vectors is used as the input of the signal quality gain prediction model. The signal quality gain prediction model uses a group of predicted signal quality gains corresponding to each group of analysis data as output, and uses the actual signal quality gain corresponding to each group of analysis data as the prediction target. The actual signal quality gain is the pre-collected signal quality gain corresponding to the analysis data. Minimizing the sum of the prediction errors of all analysis data is used as the training target. The formula of the prediction error is expressed as follows: , where ε p is the prediction error, p is the group number of the eigenvector corresponding to the analyzed data, δ p is the predicted signal quality gain corresponding to the pth group of analysis data, ρ p The actual signal quality gain corresponding to the p-th group of analysis data is trained on the signal quality gain prediction model until the sum of the prediction errors reaches convergence and the training is stopped.

[0044] Technical effects and advantages of the present invention:

[0045] The present invention is provided with a signal adjustment module, which is conducive to analyzing corresponding data based on the signal quality conditions of different frequency bands, so as to obtain the optimal signal adjustment strategy and adjust the signal. It can be generally applied to dual-frequency signals to improve signal quality, and combines channel prediction with a neural network model. It can automatically select the most suitable modulation and coding scheme according to the real-time characteristics of the channel, and integrate the trained neural network model into the fitness calculation of the improved nature-inspired algorithm, so as to give full play to the nonlinear and multimodal data modeling capabilities of the neural network and effectively capture complex data relationships; based on the parallel computing processing mechanism, the computing efficiency is improved, and the effect of the signal adjustment strategy is evaluated through deep learning technology, so as to improve the pertinence and effectiveness of the signal adjustment; the results of the channel prediction algorithm are fully utilized, and the complex data relationships are captured through deep learning technology, so that the influence of different signal adjustment strategies on the signal quality can be fully and accurately understood, and the signal can be further optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a structural diagram of the signal management system based on dual-frequency signals of the present invention. DETAILED DESCRIPTION

[0047] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative. The signal management system based on dual-frequency signals involved in the present invention is not limited to the various structures recorded in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0048] like Figure 1 As shown, the present invention provides a signal management system based on dual-frequency signals, including a data acquisition module, a signal matching module, a signal transmitting module, a signal receiving module, a signal adjustment module and an intelligent management and control module;

[0049] The data acquisition module is used to collect target data of different smart devices and classify the smart devices based on the signal connection frequency band; the target data is the signal connection requirement data and signal connection frequency band of the smart device, which can be specifically data describing the data transmission mode and the signal connection mode, such as high-speed data transmission, long-distance connection, short-distance connection, through-wall connection, etc., which are textual description data describing the data transmission and signal connection mode of the smart device; its purpose is to obtain the characteristics of smart devices connected to the same frequency band signal by classifying the signals of different smart devices. The frequency band signals required to be connected to different smart devices are inconsistent. For example, devices requiring high-speed data transmission and low latency, such as game consoles and smart TVs, need to connect to the 5GHz frequency band signal; devices requiring long-distance connection or through-wall connection, such as smart phones and tablets, need to connect to the 2.4GHz frequency band signal; by classifying the signals of different smart devices, the characteristics of smart devices connected to the same frequency band signal can be obtained, thereby laying the foundation for subsequent signal matching, and can perform signal matching for smart devices that need to be connected to signals, and obtain accurate frequency band signals for connection;

[0050] The signal matching module is used to collect device data of the target object, perform signal matching on the target object, use the successfully matched signal as the connection signal of the target object, and send a transmission instruction to the signal transmission module; the transmission instruction includes the frequency band information of the transmitted signal, that is, the successfully matched signal; the target object is a smart device for signal connection, and the device data is the signal connection requirement data of the target object;

[0051] The signal transmitting module is used to generate signals of corresponding different frequency bands after receiving a transmitting instruction, and transmit the signals to the signal receiving module, and is composed of a signal source, a modulator, a power amplifier and an antenna; the signal source is used to generate signals of two different frequency bands; the modulator is used to modulate the baseband signal to two different carrier frequencies; the power amplifier is used to amplify the modulated signal to ensure the stability and effectiveness of signal transmission; the antenna is used to transmit the modulated signal; the signal transmitting module includes a first transmitting unit and a second transmitting unit, the first transmitting unit is used to transmit a signal of one frequency band, and the second transmitting unit is used to transmit a signal of another frequency band;

[0052] The signal receiving module is used to receive signals from the signal transmitting module, and is composed of an antenna, a low-noise amplifier, a filter and a demodulator; the signal receiving module includes a first receiving unit and a second receiving unit, the first receiving unit is used to receive signals in one frequency band, and the second receiving unit is used to receive signals in another frequency band; the antenna is used to receive signals transmitted by the signal transmitting module; the low-noise amplifier is used to amplify the received signal and reduce signal noise; the filter is used to filter out clutter in the received signal to improve signal quality; the demodulator is used to demodulate the modulated signal back to the baseband signal;

[0053] The signal adjustment module is used to collect signal transmission data from the signal transmission module to the signal receiving module and analyze the signal quality, predict the channel state based on the channel prediction algorithm, and obtain the optimal signal adjustment strategy in combination with the improved nature-inspired algorithm; the signal transmission data includes but is not limited to the signal period, the data packet sent by the signal, the data packet received by the signal, the background noise of the signal, the bits in the signal transmission process and the corresponding channel data; the channel data includes but is not limited to the coding, modulation method and channel state; its purpose is to accurately predict the change of the channel through the channel prediction algorithm, adjust the modulation and coding scheme in real time to adapt to the current state of the channel, and at the same time combine the improved nature-inspired algorithm to introduce a neural network model to better adjust the transmission signal, improve the data transmission rate, and reduce the channel changes. The transmission delay caused by , since the channel prediction algorithm can support adaptive modulation and coding technology, it can automatically select the most appropriate modulation and coding scheme according to the real-time characteristics of the channel. At the same time, combined with the improved nature-inspired algorithm, the trained neural network model is integrated into the fitness calculation of the improved nature-inspired algorithm, which can give full play to the nonlinear and multimodal data modeling capabilities of the neural network and effectively capture complex data relationships; based on the parallel computing processing mechanism, the computing efficiency is improved, and the signal adjustment strategy effect is evaluated through deep learning technology, thereby improving the pertinence and effectiveness of signal adjustment; making full use of the results of the channel prediction algorithm, and capturing complex data relationships through deep learning technology, it can fully and accurately understand the impact of different signal adjustment strategies on signal quality, and further optimize the signal;

[0054] The intelligent management and control module is used to intelligently control all modules and execute the optimal signal adjustment strategy to intelligently manage the signals.

[0055] In this embodiment, it should be specifically explained that the data acquisition module classifies the signals of the smart device including the following steps:

[0056] Step S01: Obtain target data of n smart devices, and convert the target data of the n smart devices into corresponding word vectors in sequence; the word vector conversion model is a BERT semantic model, which is a prior art means and will not be described in detail in this implementation;

[0057] Step S02: Take the converted n word vectors as sample points, randomly select k sample points as initial cluster centers, and mark them as z1, z2, z3, ..., z k ;

[0058] Step S03: record the sample points that are not used as cluster center points as calculation points and mark them as j1, j2, j3, ..., j n-k ; Calculate the distance D from each calculation point to each cluster center in turn ba , the calculation formula is expressed as: , where D ba is the bth calculation point j b To the a-th cluster center z a The distance, where b = 1, 2, 3, ..., nk; a = 1, 2, 3, ..., k; R is the dimension of the sample point, u = 1, 2, 3, ..., R; j bu is the bth calculation point j b The coordinates in the u-th dimension, z au is the a-th cluster center z a Coordinates in the u-th dimension;

[0059] Step S04: establishing corresponding N clusters based on k cluster centers, k=N;

[0060] Step S05: calculate point j b The distance to each cluster center is compared, and the calculated point is assigned to the cluster corresponding to the cluster center closest to it;

[0061] Step S06: set b=b+1, and jump back to step S05;

[0062] Step S07: Repeat steps S05 to S06 until b=nk, and the loop ends, and the nk calculation points are all assigned to the corresponding clusters;

[0063] Step S08: Recalculate the new cluster center coordinates of each cluster. The calculation formula is expressed as: , where z´ c is the new cluster center coordinate of the cth cluster, c=1, 2, 3, ..., N, y i is the coordinate of the i-th calculation point in the c-th cluster, i=1, 2, 3, …, I, I is the total number of calculation points in the c-th cluster, ;

[0064] Step S09: Repeat steps S03 to S08 until the new cluster center coordinates of each cluster are recalculated in step S08, and the loop ends when the new cluster center coordinates of each cluster calculated in the previous loop are consistent; obtain the cluster centers and corresponding sample points corresponding to the N clusters;

[0065] For dual-band signals, there are only two frequency bands, so the smart device can only select any one of the two frequency bands for connection. Therefore, in steps S01-S09, the value of k is 2, so N=2, and two clusters will eventually be formed, one cluster represents the category of smart devices connected to 5GHz frequency band signals, and the other cluster represents the category of smart devices connected to 2.4GHz frequency band signals; the sample points corresponding to each cluster are the smart devices connected to the corresponding frequency band signals.

[0066] In this embodiment, it should be specifically explained that the specific manner in which the signal matching module performs signal matching on the target object is:

[0067] Step S11: converting the device data of the target object into a corresponding word vector through a word vector conversion model, which is recorded as a target point; the word vector model is the same as that in step S01;

[0068] Step S12: record the target point as M, calculate the distance from the target point to the cluster center point of each cluster in step S09, and arrange them in ascending order from small to large, and assign the target point to the cluster corresponding to the cluster center point closest to it, that is, the cluster corresponding to the cluster center point with the smallest distance value;

[0069] The distance is calculated as follows: , where D Mc is the distance between the target point and the cluster center of the cth cluster, M u is the coordinate of the target point in the uth dimension, z´ cu is the cluster center point z´ of the cth cluster c At the coordinate of the u-th dimension, R is the dimension in step S03, u=1, 2, 3, ..., R;

[0070] Step S13: Outputting the connection signal frequency band corresponding to the smart device category of the cluster where the target point is located in step S12, that is, the signal of successful matching.

[0071] In this embodiment, it should be specifically explained that the calculation formula for analyzing the signal quality by the signal adjustment module is expressed as: , where XZ is the signal quality, βx is the signal-to-noise ratio, βw is the bit error rate, and βd is the packet loss rate; λ1, λ2, and λ3 are corresponding proportional factors, all of which are greater than 0 and less than 1; this embodiment does not specifically limit the specific values ​​of the proportional factors;

[0072] , where SP is the signal power and NP is the noise power; , where s(t) is the signal amplitude at time t, when the signal is a periodic signal, T is the signal period, and when the signal is a non-periodic signal, T is the time taken for the signal to be transmitted and received; , where f(t) is the noise amplitude at time t;

[0073] , where B1 is the number of erroneous bits, B z is the total number of bits transmitted;

[0074] , where q1 is the number of data packets received by the signal receiving module, and q2 is the number of data packets sent by the signal transmitting module.

[0075] In this embodiment, it should be specifically explained that the channel prediction algorithm predicts the channel state by estimating the channel state through the Kalman filter algorithm, obtaining the estimated value of the channel state, obtaining the corresponding predicted signal transmission data, and obtaining the estimated signal quality. If the estimated signal quality is reduced relative to the signal quality XZ, the optimal signal adjustment strategy is obtained through the improved natural inspiration algorithm, otherwise the current transmission mode, channel coding and modulation mode are used as the optimal signal adjustment strategy;

[0076] The method for obtaining the corresponding predicted signal transmission data is: pre-collecting a variety of different channel states and corresponding feature data, constructing a knowledge graph, matching the estimated value of the acquired channel state with the knowledge graph, obtaining the matched channel state and the corresponding feature data, wherein the feature data includes signal transmission data, and calculating the estimated signal quality based on this.

[0077] In this embodiment, it should be specifically explained that the obtaining of the optimal signal adjustment strategy includes the following steps:

[0078] Step S21: different digital labels are set for different signal adjustment strategies, and marked as strategy labels; the signal adjustment strategy is specifically the transmission mode, channel coding and modulation mode after the signal adjustment; the signal adjustment strategy can be acquired by collecting historical signal transmission mode, channel coding and modulation mode, and modifying and acquiring in combination with the professional knowledge of professional technicians; the signal transmission mode includes but is not limited to frequency division multiplexing, time division multiplexing and orthogonal frequency division multiplexing; the channel coding includes but is not limited to convolutional code, block code and low-density parity code; the channel modulation mode includes but is not limited to amplitude modulation, frequency modulation and phase modulation;

[0079] Step S22: Preset the population size Z and the number threshold T; the number threshold T is determined by a technician in the field, who performs multiple lizard optimization algorithms under multiple different signal adjustment strategies during the optimization process of the historical signal adjustment strategy to obtain multiple strategy labels, wherein the number of iterations of the lizard optimization algorithm is different each time, and the population size is the same and is Z; the number of iterations that is closest to the strategy label and the actual strategy label is used as the number of iterations corresponding to the signal adjustment strategy; the average of multiple iterations is used as the number threshold T; the population size Z is determined by a technician in the field, who sets multiple different signal adjustment strategies during the optimization process of the historical signal adjustment strategy. The population size is determined, and the lizard optimization algorithm is performed multiple times. After the same number of iterations, the corresponding strategy label is obtained. The population size with the same strategy label and the actual strategy label is used as the population size corresponding to the test data set. The actual strategy label is the signal adjustment strategy digital label that best matches the signal adjustment strategy. The actual strategy label is obtained by a person skilled in the art through experiments based on actual experience. Similarly, the mean of multiple population sizes is used as the preset population size Z. The population size Z determines the breadth of the search. A larger population size can explore more solution spaces, and the number threshold T determines the termination condition of the algorithm and can control the speed at which the algorithm converges.

[0080] Step S23: Initialize the population, the positions of the lizards in the initialized population are defined in a one-dimensional search space, the positions of the lizards correspond to the strategy labels one by one, and the number of iterations t of the initialized population is 0;

[0081] Step S24: determining a fitness function;

[0082] Step S25: defining the temperature and food intake of each lizard's location;

[0083] Step S26: defining the location of the cave and determining whether the lizard has entered the cave or entered the foraging stage;

[0084] Step S27: Update the position of the lizard;

[0085] Step S28: Determine whether the iteration is completed. If not, return to step S25 and set the number of iterations t=t+1; if completed, proceed to step S29;

[0086] Step S29: Calculate the fitness corresponding to the position of each lizard, obtain the position of the lizard corresponding to the fitness with the largest value, and obtain the signal adjustment strategy corresponding to the corresponding strategy label according to the lizard position as the optimal signal adjustment strategy.

[0087] In this embodiment, it should be specifically explained that the initialized population is expressed as: , where Ω is the initialized population, Z is the number of lizards in the population, i.e., the number of signal adjustment strategies, μZ Adjust the strategy for the Zth signal;

[0088] The expression for the position of each lizard is: , where μ e 0 is the initial position of the e-th lizard, E e is a random number between [0, 1], e=1, 2, 3, …, M, where M is the total number of strategy tags;

[0089] The fitness function in step S24 is expressed as: , where SY is the fitness of the e-th lizard, θ e is the signal quality gain of the signal adjustment strategy corresponding to the e-th lizard; the signal quality gain is obtained by taking the signal adjustment strategy corresponding to the lizard and the corresponding signal transmission data and the current signal strategy and the corresponding signal transmission data as research data, inputting the research data into the trained signal quality gain prediction model, and predicting the corresponding signal quality gain; the current signal strategy is the current signal transmission mode, channel coding and modulation mode.

[0090] In this embodiment, it should be specifically explained that the training process of the signal quality gain prediction model is specifically as follows:

[0091] A currently implemented signal strategy and corresponding signal transmission data and a signal adjustment strategy and corresponding signal transmission data are taken as a set of analysis data, d sets of analysis data are collected in advance, d is an integer greater than 1, and the analysis data and the corresponding signal quality gain are converted into a corresponding set of feature vectors; the signal quality gain can be obtained by subtracting the signal quality corresponding to the signal transmission data before adjustment from the signal quality corresponding to the adjusted signal transmission data; the adjusted signal transmission data can be obtained according to the actual signal transmission data after adjustment; d sets of analysis data are collected, and under the condition of each set of analysis data, the quality gain of each signal adjustment strategy is comprehensively analyzed;

[0092] Each group of feature vectors is used as the input of the signal quality gain prediction model. The signal quality gain prediction model uses a group of predicted signal quality gains corresponding to each group of analysis data as output, and uses the actual signal quality gain corresponding to each group of analysis data as the prediction target. The actual signal quality gain is the pre-collected signal quality gain corresponding to the analysis data. Minimizing the sum of the prediction errors of all analysis data is used as the training target. The formula of the prediction error is expressed as follows: , where ε p is the prediction error, p is the group number of the eigenvector corresponding to the analyzed data, δ p is the predicted signal quality gain corresponding to the pth group of analysis data, ρ pis the actual signal quality gain corresponding to the p-th group of analysis data, the signal quality gain prediction model is trained until the sum of the prediction errors reaches convergence and the training is stopped;

[0093] The signal quality gain prediction model is specifically a deep neural network model; it includes an input layer, a hidden layer and an output layer; each hidden layer includes multiple neurons, each neuron is connected to the neurons in the next layer, and the connection contains weights, which determine the importance and influence of data transmission in the neural network; an activation function is applied to each neuron between the hidden layer and the output layer, and the activation function is mapped into nonlinearity, allowing the network to learn more complex patterns and features.

[0094] In this embodiment, it should be specifically explained that in step S25, the temperature at the lizard position is expressed as: ,in, represents the temperature at the position of the e-th lizard, R1 and R2 are both constants, R1 satisfies 10≤R1≤15, and R2 satisfies 15≤R1≤20;

[0095] The food intake is expressed as: , where P e is the food intake of the e-th lizard, G is the normalization constant used to adjust the lizard food intake model to ensure that the sum of the probabilities of all values ​​is 1, σ is the standard deviation of food intake, ZJ is the optimal temperature, and the optimal temperature is the temperature corresponding to the maximum food intake of the lizard. The standard deviation of food intake and the optimal temperature are obtained from the lizard food intake model;

[0096] The lizard food intake model is a normal distribution model. The lizard food intake model is pre-built to predict the food intake of lizards at different temperatures. The lizard food intake model is pre-built by a technician in the field by collecting food intake data of multiple lizards at different temperatures.

[0097] In step S26, the specific method for determining whether the lizard has entered a cave or a foraging stage is:

[0098] like , indicating that the temperature where the lizard is located is too high, so the lizard enters the cave to escape the heat;

[0099] like , indicating that the temperature at the location of the lizard is suitable for the lizard to eat, and the lizard enters the foraging stage;

[0100] The CS is a threshold temperature, satisfying 25≤CS≤30;

[0101] The location of the cave can be expressed as: , where μ o is the cave location, μ max is the position of the lizard with the highest fitness during multiple iterations of the population, μmax ´ It is the position of the lizard with the highest fitness in the last population iteration;

[0102] In step S27, the specific method of updating the position of the lizard is:

[0103] Each lizard that enters the cave is given a random number SJ between 0 and 1 e ´ ;

[0104] If the random number is less than 0.5, it means that there is no other lizard competing for the corresponding cave, and the position of the lizard is updated to: ,in, is the position of the e-th lizard entering the cave, μ e t is the position of the e-th lizard at the t-th iteration, Qd is the decreasing curve;

[0105] If the random number is greater than or equal to 0.5, it means that the cave that the corresponding lizard enters has other lizards competing, so the position of the lizard in the cave is updated as follows: , where μ h t is the position of a random lizard in the population after the tth iteration;

[0106] The specific method for updating the position of the lizard entering the foraging phase is:

[0107] When eating, the lizard will choose whether to tear the food into pieces according to the size of the food. If the food is of the right size, the lizard will eat it directly; if the food is too big, the lizard will tear the food into pieces before eating it; Food position F = μ max ´ , the expression of food size is: , where Q is the food size, η is the food factor, which is 3, SJ * is a random number between 0 and 1, SY e is the fitness corresponding to the position of the e-th lizard, SY F is the fitness corresponding to the food position, that is, the maximum fitness value during the last population iteration;

[0108] like , indicating that the food is too big and the lizard needs to tear it into pieces. The position of the torn food is expressed as: , where F' is the position of the food after it is torn into pieces. The calculation formula for the position of the lizard during the foraging phase is: ,in, is the position of the e-th lizard after the foraging phase, and ω is a random number between 0 and 1;

[0109] like , then the lizard moves directly to the food and eats it. The calculation formula for the position of the lizard entering the foraging stage is expressed as: ,in, is the position of the e-th lizard after the foraging phase, and θ is a random number between 0 and 1;

[0110] The method for determining whether the iteration is successful in step S08 is:

[0111] If the number of iterations t is less than T, the iteration is not completed, and the iteration is performed again after the number of iterations t=t+1; if the number of iterations t is greater than or equal to T, the iteration is completed.

[0112] In this embodiment, it should be specifically explained that the purpose of using the lizard optimization algorithm is to simulate the behaviors of lizards such as foraging, summer heat avoidance and competition in different environments through the lizard algorithm, so as to perform global search in a complex multi-dimensional search space; by simulating the foraging and burrowing behaviors of lizards, the algorithm can effectively avoid falling into the local optimum, thereby increasing the probability of finding the global optimal solution; and the lizard algorithm can adapt to different adjustment strategies by adjusting the population size Z and the number threshold T; the optimization process can dynamically adjust the population size and the number of iterations according to historical data to ensure the applicability and efficiency of the algorithm; at the same time, by reasonably setting the fitness function and the burrowing update mechanism, the lizard optimization algorithm can accelerate convergence and shorten the optimization time, which means that the optimal signal adjustment strategy can be found quickly to ensure signal quality; in addition, the lizard optimization algorithm can dynamically adjust the behavior of lizards in the foraging stage, such as directly eating or tearing up food, so as to achieve refined processing of local search; this search strategy that takes both local and global into consideration improves the performance of the algorithm in optimizing signal quality issues.

[0113] In this embodiment, it should be specifically explained that the difference between this embodiment and the prior art lies in that this embodiment has a signal adjustment module, which analyzes the corresponding data based on the signal quality of different frequency bands to obtain the optimal signal adjustment strategy and adjust the signal. It can be applied to dual-frequency signals to improve signal quality, and combines channel prediction with the neural network model. It can automatically select the most suitable modulation and coding scheme according to the real-time characteristics of the channel, and integrate the trained neural network model into the fitness calculation of the improved nature-inspired algorithm. It can give full play to the nonlinear and multimodal data modeling capabilities of the neural network and effectively capture complex data relationships; based on the parallel computing processing mechanism, it improves computing efficiency, and evaluates the effect of the signal adjustment strategy through deep learning technology, thereby improving the pertinence and effectiveness of the signal adjustment; makes full use of the results of the channel prediction algorithm, captures complex data relationships through deep learning technology, and can fully and accurately understand the impact of different signal adjustment strategies on signal quality, and further optimize the signal.

[0114] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0115] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A signal management system based on dual-frequency signals, characterized in that: It includes a data acquisition module, a signal matching module, a signal transmission module, a signal receiving module, a signal adjustment module and an intelligent control module; The data acquisition module is used to collect target data of different smart devices and classify the smart devices based on the signal connection frequency band; The signal matching module is used to collect device data of the target object, perform signal matching on the target object, use the successfully matched signal as the connection signal of the target object, and send a transmission instruction to the signal transmission module; The signal transmitting module is used to generate a signal of a corresponding frequency band after receiving a transmitting instruction, and transmit the signal to the signal receiving module, and is composed of a signal source, a modulator, a power amplifier and an antenna; the signal transmitting module includes a first transmitting unit and a second transmitting unit; The signal receiving module is used to receive the signal from the signal transmitting module, and is composed of an antenna, a low noise amplifier, a filter and a demodulator; the signal receiving module includes a first receiving unit and a second receiving unit; The signal adjustment module is used to collect signal transmission data from the signal transmission module to the signal receiving module and analyze the signal quality, predict the channel state based on the channel prediction algorithm, and obtain the optimal signal adjustment strategy in combination with the improved natural inspiration algorithm; The intelligent control module is used to intelligently control all modules and execute the optimal signal adjustment strategy to intelligently manage the signal; The target data is the signal connection requirement data and signal connection frequency band of the smart device; the transmission instruction includes the frequency band information of the transmitted signal, that is, the successfully matched signal; the target object is the smart device for signal connection, and the device data is the signal connection requirement data of the target object; The obtaining of the optimal signal adjustment strategy comprises the following steps: Step S21: setting different digital labels for different signal adjustment strategies and marking them as strategy labels; Step S22: presetting the population size Z and the number threshold T; Step S23: Initialize the population, the positions of the lizards in the initialized population are defined in a one-dimensional search space, the positions of the lizards correspond to the strategy labels one by one, and the number of iterations t of the initialized population is 0; Step S24: determining a fitness function; Step S25: defining the temperature and food intake of each lizard's location; Step S26: defining the location of the cave and determining whether the lizard has entered the cave or entered the foraging stage; Step S27: Update the position of the lizard; Step S28: Determine whether the iteration is completed. If not, return to step S25 and set the number of iterations t=t+1; if completed, proceed to step S29; Step S29: Calculate the fitness corresponding to the position of each lizard, obtain the position of the lizard corresponding to the fitness with the largest value, and obtain the signal adjustment strategy corresponding to the corresponding strategy label according to the lizard position as the optimal signal adjustment strategy.

2. The signal management system based on dual-frequency signals according to claim 1, characterized in that: The signal source is used to generate signals of two different frequency bands; the modulator is used to modulate the baseband signal to two different carrier frequencies; the power amplifier is used to amplify the modulated signal; the antenna of the signal transmission module is used to transmit the modulated signal; the first transmitting unit is used to transmit the signal of one frequency band, and the second transmitting unit is used to transmit the signal of the other frequency band; The first receiving unit is used to receive signals in one frequency band, and the second receiving unit is used to receive signals in another frequency band; the antenna of the signal receiving module is used to receive signals transmitted by the signal transmitting module; the low noise amplifier is used to amplify the received signal; and the filter is used to filter out clutter in the received signal; The demodulator is used to demodulate the modulated signal back to a baseband signal.

3. The signal management system based on dual-frequency signals according to claim 2, characterized in that: The specific method in which the signal matching module performs signal matching on the target object is: Step S11: converting the device data of the target object into a corresponding word vector through a word vector conversion model, and recording it as a target point; Step S12: record the target point as M, calculate the distance from the target point to the cluster center point of each cluster, and sort them in ascending order from small to large, and assign the target point to the cluster corresponding to the cluster center point closest to it, that is, the cluster corresponding to the cluster center point with the smallest distance value; The distance is calculated as follows: Among them, D Mc is the distance between the target point and the cluster center of the cth cluster, M u is the coordinate of the target point in the uth dimension, z′ cu is the cluster center point z′ of the cth cluster c At the coordinate of the u-th dimension, R is the dimension, u = 1, 2, 3, ..., R; Step S13: Outputting the connection signal frequency band corresponding to the smart device category of the cluster where the target point is located in step S12, that is, the signal of successful matching.

4. The signal management system based on dual-frequency signals according to claim 3, characterized in that: The calculation formula for analyzing the signal quality of the signal adjustment module is expressed as: Where XZ is the signal quality, βx is the signal-to-noise ratio, βw is the bit error rate, βd is the packet loss rate; λ1, λ2 and λ3 are the corresponding proportional factors respectively; Among them, SP is the signal power and NP is the noise power; Where s(t) is the signal amplitude at time t. When the signal is a periodic signal, T is the signal period. When the signal is a non-periodic signal, T is the time taken for the signal to be transmitted and received. Where, f(t) is the noise amplitude at time t; Among them, B1 is the number of erroneous bits, B z is the total number of bits transmitted; Among them, q1 is the number of data packets received by the signal receiving module, and q2 is the number of data packets sent by the signal transmitting module.

5. The signal management system based on dual-frequency signals according to claim 4, characterized in that: The channel prediction algorithm predicts the channel state by estimating the channel state through the Kalman filter algorithm, obtaining the estimated value of the channel state, obtaining the corresponding predicted signal transmission data, and obtaining the estimated signal quality. If the estimated signal quality is reduced relative to the signal quality XZ, the optimal signal adjustment strategy is obtained through the improved natural inspiration algorithm, otherwise the current transmission mode, channel coding and modulation mode are used as the optimal signal adjustment strategy; The method for obtaining the corresponding predicted signal transmission data is: pre-collecting a variety of different channel states and corresponding feature data, constructing a knowledge graph, matching the estimated value of the acquired channel state with the knowledge graph, obtaining the matched channel state and the corresponding feature data, wherein the feature data includes signal transmission data, and calculating the estimated signal quality based on this.

6. The signal management system based on dual-frequency signals according to claim 1, characterized in that: The initialized population is expressed as: Ω = {μ1, μ2, μ3, ..., μ Z }, where Ω is the population after initialization, Z is the number of lizards in the population, i.e., the number of signal adjustment strategies, μ Z Adjust the strategy for the Zth signal; The expression for the position of each lizard is: Among them, μ e 0 is the initial position of the e-th lizard, E e is a random number between [0, 1], e = 1, 2, 3, ..., M, where M is the total number of policy tags; The fitness function in step S24 is expressed as: SY e =θ e , where SY e is the fitness of the e-th lizard, θ e is the signal quality gain of the signal adjustment strategy corresponding to the e-th lizard; The signal quality gain is obtained by taking the signal adjustment strategy and the corresponding signal transmission data corresponding to the lizard and the current signal strategy and the corresponding signal transmission data as research data, inputting the research data into a trained signal quality gain prediction model, and predicting the corresponding signal quality gain; the current signal strategy is the current signal transmission method, channel coding and modulation method.

7. The signal management system based on dual-frequency signals according to claim 6, characterized in that: The training process of the signal quality gain prediction model is specifically as follows: A current signal strategy and corresponding signal transmission data and a signal adjustment strategy and corresponding signal transmission data are taken as a set of analysis data, d sets of analysis data are collected in advance, d is an integer greater than 1, and the analysis data and the corresponding signal quality gain are converted into a corresponding set of feature vectors; the signal quality gain can be obtained by subtracting the signal quality corresponding to the signal transmission data before adjustment from the signal quality corresponding to the adjusted signal transmission data; the adjusted signal transmission data can be obtained according to the actual signal transmission data after adjustment; d sets of analysis data are collected, and under the condition of each set of analysis data, the quality gain of each signal adjustment strategy is comprehensively analyzed; Each group of feature vectors is used as the input of the signal quality gain prediction model. The signal quality gain prediction model uses a group of predicted signal quality gains corresponding to each group of analysis data as output, and uses the actual signal quality gain corresponding to each group of analysis data as the prediction target. The actual signal quality gain is the pre-collected signal quality gain corresponding to the analysis data; the training target is to minimize the sum of the prediction errors of all analysis data; the formula of the prediction error is expressed as: ε p =δ p -ρ p , where ε p is the prediction error, p is the group number of the eigenvector corresponding to the analyzed data, δ p is the predicted signal quality gain corresponding to the pth group of analysis data, ρ p The actual signal quality gain corresponding to the p-th group of analysis data is trained on the signal quality gain prediction model until the sum of the prediction errors reaches convergence and the training is stopped.

Images