A Data Acquisition and Analysis Method for an RFID Reading Distance Intelligent Terminal

Abstract

The present invention relates to the field of electronic information technology, in particular to a data acquisition and analysis method for an RFID reading distance intelligent terminal. By introducing the variational mode decomposition technology, the radio frequency signal is decomposed into high-order IMF components containing the carrier fundamental frequency and low-frequency residual components reflecting the multipath effect, which can better separate the signal characteristics; combined with segmented windowing, Hilbert transform, and phase gradient analysis, the time-frequency characteristics of the phase mutation signal segment can be accurately extracted; finally, by constructing an evaluation model for the multipath interference suppression effect, a quantitative basis is provided for system optimization. The present invention analyzes the anti-interference ability of the RFID reading distance intelligent terminal, thereby providing technical support for the deployment and performance evaluation of RFID systems in complex environments.

Description

Technical Field

[0001] The present invention relates to the field of electronic information technology, and in particular to a method for data acquisition and analysis of an RFID reading distance intelligent terminal. Background Art

[0002] With the rapid development of Internet of Things technology, RFID (Radio Frequency Identification) technology, as a non-contact automatic identification technology, has been widely used in fields such as logistics management, intelligent warehousing, and asset tracking. As the core device of the RFID system, the performance of the RFID reading distance intelligent terminal directly affects the recognition accuracy and stability of the system. However, in practical applications, due to factors such as multipath effects, environmental noise, and device hardware limitations, the acquisition and analysis of RFID signals often face many challenges. The multipath effect refers to the phenomenon that radio frequency signals generate multiple paths of propagation after being reflected by obstacles during propagation, which will cause signal superposition, phase distortion, and power attenuation, seriously reducing the reading distance accuracy and recognition reliability of the RFID system. Traditional signal processing methods, such as Fourier transform and wavelet transform, although they can separate signal features to a certain extent, have limited effects on non-linear and non-stationary RFID signals, and it is difficult to accurately extract the phase mutation features under multipath interference. In addition, the existing technology mainly analyzes phase mutation signals in a single dimension in the time domain or frequency domain, lacking the ability of time-frequency joint analysis and unable to comprehensively reflect the non-linear dynamic characteristics of the signal. Therefore, developing a method for data acquisition and analysis of an RFID reading distance intelligent terminal that can effectively suppress multipath interference, accurately extract phase mutation features, and evaluate system performance has become the key to improving the overall performance of the RFID system. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a method for data acquisition and analysis of an RFID reading distance intelligent terminal.

[0004] The technical solution adopted by the present invention to achieve the above purpose is as follows:

[0005] The first aspect of the present invention discloses a method for data acquisition and analysis of an RFID reading distance intelligent terminal, including the following steps:

[0006] Obtain the radio frequency signal of the RFID reading distance intelligent terminal, perform variational mode decomposition processing on the radio frequency signal, and obtain high-order IMF components containing the carrier fundamental frequency and low-frequency residual components reflecting the multipath effect;

[0007] Perform segmented windowing and Hilbert transform analysis processing on each high-order IMF component to obtain the phase mutation signal segment of the radio frequency signal;

[0008] Perform a first-order difference calculation on the instantaneous phase sequence of the phase mutation signal segment to obtain the phase gradient sequence of the phase mutation signal segment, and construct a phase gradient change curve based on the phase gradient sequence combined with weighted moving average;

[0009] Perform feature analysis on the phase gradient change curve to obtain the mutation feature parameters of the phase mutation signal segment. The mutation feature parameters include the mutation starting point, the effective peak point, and the mutation duration;

[0010] Evaluate the multi-path interference suppression effect level of the RFID reading distance intelligent terminal according to the mutation feature parameters of the phase mutation signal segment.

[0011] Preferably, obtain the radio frequency signal of the RFID reading distance intelligent terminal, perform variational mode decomposition processing on the radio frequency signal to obtain the high-order IMF components containing the carrier fundamental frequency and the low-frequency residual components reflecting the multi-path effect, specifically:

[0012] Set the mode number K and the penalty factor α, initialize the variational mode decomposition framework based on the mode number K and the penalty factor α, and import the radio frequency signal into the variational mode decomposition framework for iterative decomposition;

[0013] In each iterative decomposition process, impose instantaneous frequency smoothness constraints and energy density gradient constraints on each mode component simultaneously;

[0014] Detect the center frequency interval between adjacent modes after each iterative decomposition. When the center frequency interval between any two adjacent modes is less than the preset minimum allowable interval, activate the bandwidth parameter linkage adjustment mechanism, preferentially compress the bandwidth upper limit of the high-frequency mode and recalculate the energy constraint conditions;

[0015] Set an adaptive stop threshold based on the energy attenuation rate of the decomposition residual. When the three consecutive iterative change amplitudes of the residual energy are all lower than the threshold, determine that the decomposition process ends and output each mode component;

[0016] According to the coincidence degree between the center frequency of each mode component and the theoretical interval of the carrier fundamental frequency and the satisfaction of the double constraint conditions, eliminate the pseudo modes generated by multi-path interference, and retain the effective carrier components that meet the instantaneous frequency stability and spectral energy focusing;

[0017] Perform Hilbert marginal spectrum analysis on each effective carrier component to obtain the instantaneous frequency peak and fluctuation variance of each effective carrier component;

[0018] If the instantaneous frequency peak of a certain effective carrier component is within the theoretical fluctuation interval of the carrier fundamental frequency and its fluctuation variance is less than half of that of the adjacent component, then determine the effective carrier component as a high-order IMF component; otherwise, determine the effective carrier component as a low-frequency residual component.

[0019] Preferably, Hilbert marginal spectrum analysis is performed on each effective carrier component to obtain the instantaneous frequency peak and fluctuation variance of each effective carrier component, specifically as follows:

[0020] Perform segmented windowing preprocessing on the effective carrier component, adopt an adaptive window length adjustment strategy, dynamically set the window function length according to the center frequency of the effective carrier component, so that the signal within the window covers at least three fundamental frequency periods to suppress spectral leakage;

[0021] Perform complex analytic processing on the windowed component signal segment, generate the corresponding analytic signal through Hilbert transform, extract the real part and imaginary part of the analytic signal, and perform cross permutation and combination on the real part and imaginary part of the analytic signal to form a complex number sequence;

[0022] Based on the phase difference algorithm, calculate the instantaneous frequency of the complex number sequence point by point, fit the instantaneous frequency of the complex number sequence into a continuous phase sequence curve according to the cubic spline interpolation method, and obtain the second derivative of the phase sequence curve as the instantaneous frequency sequence;

[0023] Perform probability density estimation on the instantaneous frequency sequence to obtain the probability density function of the instantaneous frequency, map each frequency value and its corresponding probability density in the probability density function of the instantaneous frequency, use the frequency value as the horizontal axis and the probability density as the vertical axis, and use the method of plotting points and connecting lines to construct the probability density curve of the instantaneous frequency;

[0024] Take the peak position of the probability density curve as the instantaneous frequency peak, and take the distribution variance of the probability density curve as the fluctuation variance.

[0025] Preferably, perform segmented windowing and Hilbert transform analysis processing on each high-order IMF component to obtain the phase mutation signal segment of the radio frequency signal, specifically as follows:

[0026] Perform time-varying adaptive segmented windowing on each high-order IMF component, and dynamically adjust the window function length according to the instantaneous frequency peak of the high-order IMF component to ensure that the signal within the window contains at least two complete phase fluctuation periods to balance the time-frequency resolution;

[0027] Convert each windowed high-order IMF component signal segment into a complex analytic signal through Hilbert transform, and then calculate the phase angle of the complex analytic signal point by point through the arctangent operation to obtain the instantaneous phase sequence of each high-order IMF component signal segment;

[0028] Calculate the phase difference value of adjacent instantaneous phase sequences frame by frame, perform weighted processing on the calculated phase difference values of adjacent instantaneous phase sequences, and use each weighted result as the phase fluctuation intensity index of the corresponding high-order IMF component signal segment;

[0029] Compare the phase fluctuation intensity index of each high - order IMF component signal segment with a preset index threshold, and mark the high - order IMF component signal segment whose phase fluctuation intensity index is greater than the preset index threshold as a phase mutation signal segment.

[0030] Preferably, perform a first - order difference calculation on the instantaneous phase sequence of the phase mutation signal segment to obtain the phase gradient sequence of the phase mutation signal segment, and construct a phase gradient change curve based on the phase gradient sequence combined with weighted moving average, specifically as follows:

[0031] Based on the sampling clock of the phase mutation signal segment, perform an isochronous segmentation process on the phase mutation signal segment to generate an equally - spaced phase sequence aligned based on timestamps;

[0032] Perform forward difference and backward difference on each equally - spaced phase sequence simultaneously, calculate the arithmetic mean of the forward difference and the backward difference as the initial value of the instantaneous phase gradient; and perform symmetric weighting on the initial value of the instantaneous phase gradient to obtain a weighted phase gradient sequence;

[0033] Perform a three - level progressive moving average process on the weighted phase gradient sequence: the first level performs linear weighted accumulation within the window and outputs a roughly smoothed gradient; the second level detects residual pulse noise based on the roughly smoothed result and replaces abnormal points using median filtering; the third level applies exponential decay weighting to the filtered data to strengthen the contribution of recent - time data;

[0034] Remap the phase gradient values after multi - level processing according to timestamps to construct a complete phase gradient change curve; and synchronously record the window length, weight, and filter status parameters at each time point to form a metadata chain for gradient calculation.

[0035] Preferably, perform feature analysis on the phase gradient change curve to obtain the mutation feature parameters of the phase mutation signal segment, specifically as follows:

[0036] Calculate the global gradient mean of the phase gradient change curve, and use the global gradient mean as the baseline mean for mutation detection;

[0037] Perform a forward search on the phase gradient change curve, and obtain the time points in the phase gradient change curve where the gradient exceeds the baseline mean as the initial judgment positions of the starting points;

[0038] Perform a first - order derivative sign consistency detection on the data in the neighborhood of the initial judgment position of the starting point. If the derivatives of several consecutive sampling points are all positive and the gradient increment is monotonically increasing, it is confirmed as the mutation starting point; otherwise, expand the search range until the condition is met;

[0039] Within the mutation section, the parabolic interpolation method is used to optimize the subsampling accuracy of discrete gradient extreme points, locate the peak gradient point, and calculate the gradient variance between the peak gradient point and its front and rear sampling points.

[0040] If the gradient variance is less than the preset tolerance and the slope of the gradient descent edge is greater than 70% of the slope of the rising edge, it is determined as a valid peak point; otherwise, resampling correction is triggered.

[0041] The time when the gradient descends from the valid peak point to the baseline mean is used as the mutation end point, and the absolute time difference from the start point to the end point is calculated as the mutation duration.

[0042] Preferably, the multipath interference suppression effect level of the RFID reading distance intelligent terminal is evaluated according to the mutation characteristic parameters of the phase mutation signal section, specifically:

[0043] Based on the RFID signal propagation theoretical model in an ideal interference-free environment, combined with the carrier wavelength and the spatial geometric parameters of the reading distance terminal, a benchmark model of phase mutation parameters is established.

[0044] The mutation characteristic parameters of the phase mutation signal section are imported into the benchmark model: the density at the mutation start point is compared with the benchmark model to generate a density deviation coefficient; the percentage over-limit of the peak gradient relative to the theoretical upper limit is calculated; the proportion of abnormal mutations where the mutation duration exceeds the theoretical range is statistically analyzed.

[0045] The weights of the characteristic parameters are determined by the entropy weight method, the density deviation coefficient, the percentage over-limit, and the proportion of abnormal mutations are standardized, and then weighted summation is performed to obtain the multipath interference suppression index.

[0046] The multipath interference suppression index is input into a pre-trained three-branch convolutional neural network, and the multipath interference suppression effect level is output through the feature fusion layer.

[0047] The second aspect of the present invention discloses a data acquisition and analysis system for an RFID reading distance intelligent terminal. The data acquisition and analysis system for an RFID reading distance intelligent terminal includes a memory and a processor. An RFID reading distance intelligent terminal data acquisition and analysis method program is stored in the memory. When the RFID reading distance intelligent terminal data acquisition and analysis method program is executed by the processor, the steps of any of the RFID reading distance intelligent terminal data acquisition and analysis methods are implemented.

[0048] The third aspect of the present invention discloses a computer-readable storage medium, which includes a program for the data acquisition and analysis method of the RFID reading distance intelligent terminal. When the program for the data acquisition and analysis method of the RFID reading distance intelligent terminal is executed by a processor, the steps of any of the data acquisition and analysis methods of the RFID reading distance intelligent terminal are implemented.

[0049] The present invention solves the technical defects existing in the background art and has the following beneficial effects: By introducing the variational mode decomposition technology, the radio frequency signal is decomposed into high-order IMF components containing the carrier fundamental frequency and low-frequency residual components reflecting the multipath effect, which can better separate the signal characteristics; Combining segmented windowing, Hilbert transform, and phase gradient analysis, the time-frequency characteristics of the phase mutation signal segment can be accurately extracted; Finally, by constructing an evaluation model for the multipath interference suppression effect, a quantitative basis is provided for system optimization. The present invention analyzes the anti-interference ability of the RFID reading distance intelligent terminal, thereby providing technical support for the deployment and performance evaluation of the RFID system in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0051] Figure 1 It is the overall method flow chart of a data acquisition and analysis method for an RFID reading distance intelligent terminal;

[0052] Figure 2 It is a partial method flow chart of a data acquisition and analysis method for an RFID reading distance intelligent terminal;

[0053] Figure 3 It is the system block diagram of a data acquisition and analysis system for an RFID reading distance intelligent terminal. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In order to be able to more clearly understand the above-mentioned objects, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0055] Many specific details are set forth in the following description in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0056] As Figure 1 shown, the first aspect of the present invention discloses a method for data collection and analysis of an RFID reading distance intelligent terminal, including the following steps:

[0057] S102: Obtain the radio frequency signal of the RFID reading distance intelligent terminal, perform variational mode decomposition processing on the radio frequency signal to obtain high-order IMF components including the carrier fundamental frequency and low-frequency residual components reflecting multipath effects;

[0058] S104: Perform segmented windowing and Hilbert transform analysis on each high-order IMF component to obtain the phase mutation signal segment of the radio frequency signal;

[0059] S106: Perform first-order difference calculation on the instantaneous phase sequence of the phase mutation signal segment to obtain the phase gradient sequence of the phase mutation signal segment, and construct a phase gradient change curve based on the phase gradient sequence combined with weighted moving average;

[0060] S108: Perform feature analysis on the phase gradient change curve to obtain the mutation feature parameters of the phase mutation signal segment, and the mutation feature parameters include the mutation starting point, effective peak point, and mutation duration;

[0061] S110: Evaluate the multipath interference suppression effect level of the RFID reading distance intelligent terminal according to the mutation feature parameters of the phase mutation signal segment.

[0062] Preferably, obtaining the radio frequency signal of the RFID reading distance intelligent terminal, performing variational mode decomposition processing on the radio frequency signal to obtain high-order IMF components including the carrier fundamental frequency and low-frequency residual components reflecting multipath effects, specifically:

[0063] Set the mode number K and the penalty factor α, initialize the variational mode decomposition framework based on the mode number K and the penalty factor α, and import the radio frequency signal into the variational mode decomposition framework for iterative decomposition;

[0064] It should be noted that the mode number K is initially estimated according to the spectral characteristics of the radio frequency signal and the theoretical range of the carrier fundamental frequency to ensure that the K value can cover the main frequency components of the signal; secondly, based on the energy distribution characteristics of the signal, the initial value of the penalty factor α is determined by the trial-and-error method or an optimization algorithm (such as grid search) to ensure that the α value can balance the bandwidth of the mode components and the separation degree of the center frequencies during the mode decomposition process; then, use K and α to initialize the variational mode decomposition framework and construct an objective function, including the bandwidth constraint and center frequency constraint of the mode components; finally, solve the objective function through an iterative optimization algorithm (such as ADMM), and update the frequencies and bandwidths of the mode components in each iteration until the convergence condition is met.

[0065] In each iterative decomposition process, instantaneous frequency smoothness constraints and energy density gradient constraints are simultaneously applied to each modal component;

[0066] Among them, the instantaneous frequency smoothness constraint calculates the rate of change of the instantaneous frequency in adjacent time windows (such as 1μs window) in real time, dynamically sets the frequency trajectory fluctuation threshold (such as 10MHz / μs), and triggers the local smoothing processing based on secondary frequency domain regularization when a sudden change exceeding the threshold is detected, forcing the correction of the frequency time-varying trajectory of the modal component to suppress the irrational frequency jump caused by multipath reflection;

[0067] The energy density gradient constraint analyzes the energy ratio of the spectrum main lobe (carrier fundamental frequency) and side lobe (multipath interference) in real time. When the main lobe to side lobe energy ratio is lower than the critical value (such as 3dB), the weight of the gradient penalty term is adaptively enhanced (such as increasing the coefficient α to 1.5 times the initial value). The side lobe energy diffusion is suppressed through frequency domain gradient operation, forcing the spectrum energy to converge to the main lobe.

[0068] The synergistic effect of the two forms a dual optimization mechanism in the frequency domain - the former ensures the time-frequency continuity of the carrier signal, and the latter enhances the energy resolution of the spectral components, ultimately achieving improved physical isolation accuracy between the carrier baseband component and the multipath residual component.

[0069] After each iterative decomposition, the center frequency interval between adjacent modes is detected. When the center frequency interval between any two adjacent modes is less than the preset minimum allowable interval, the bandwidth parameter linkage adjustment mechanism is activated to give priority to compressing the bandwidth upper limit of the high-frequency mode and recalculate the energy constraint condition.

[0070] It should be noted that the bandwidth parameter linkage adjustment mechanism is a dynamic adjustment strategy designed to address the problem of frequency overlap of adjacent modes in variational mode decomposition. When it is detected that the center frequency interval of adjacent modes is less than a preset threshold (such as 10MHz), the mechanism reduces the bandwidth upper limit of the high-frequency mode (such as from the initial 50MHz to 40MHz), forcing its spectrum main lobe to shift to low frequency to expand the frequency interval; at the same time, the penalty factor in the energy constraint condition is updated in linkage, and the energy convergence boundary of the mode decomposition is recalculated to prevent signal energy truncation and distortion caused by bandwidth compression.

[0071] An adaptive stop threshold is set based on the energy decay rate of the decomposed residual. When the residual energy changes in three consecutive iterations are all lower than the threshold, the decomposition process is judged to be over and each modal component is output.

[0072] According to the overlap between the center frequency of each modal component and the theoretical interval of the carrier fundamental frequency and the satisfaction of the dual constraints, the pseudo-modes caused by multipath interference are eliminated, and the effective carrier components that meet the instantaneous frequency stability and spectrum energy focusing are retained;

[0073] It should be noted that based on the preset theoretical range of carrier fundamental frequency (such as 902 - 928 MHz), the coincidence degree of the center frequencies of each mode is calculated, and candidate modes with a deviation less than 15% from the theoretical range are screened out; subsequently, a quantitative evaluation with double constraint conditions is carried out on the candidate modes, and the proportion of the over-limit points of the instantaneous frequency change rate is counted not to exceed 5%, and at the same time, the main lobe energy ratio needs to reach more than 85% of the initial decomposition value; then a weighted scoring model including the interval coincidence degree (weight 60%), the frequency smoothing compliance rate (weight 20%), and the energy focusing degree (weight 20%) is constructed, and the modes with a comprehensive score higher than 0.8 enter the next stage; then through Hilbert time-frequency spectrum analysis, it is verified that the standard deviation of the instantaneous frequency fluctuation of the candidate mode is less than 2 MHz and the energy ratio within the 3 dB bandwidth of the main lobe exceeds 90%; finally, multi-dimensional cross-judgment is performed, and only the modes that simultaneously meet the triple criteria of the scoring threshold, time-frequency stability, and energy aggregation are retained as effective carrier components, and the rest are determined as multipath pseudo-modes and eliminated.

[0074] Perform Hilbert marginal spectrum analysis on each effective carrier component to obtain the instantaneous frequency peak and fluctuation variance of each effective carrier component;

[0075] If the instantaneous frequency peak of a certain effective carrier component is within the theoretical fluctuation range of the carrier fundamental frequency and its fluctuation variance is less than half of that of the adjacent component, then the said effective carrier component is determined as a high-order IMF component; otherwise, the said effective carrier component is determined as a low-frequency residual component.

[0076] It should be noted that, first of all, by setting the number of modes and the penalty factor, and introducing the constraints of instantaneous frequency smoothness and energy density gradient, it is ensured that the frequency trajectory of the mode components is smooth and the spectral energy is concentrated during the decomposition process, effectively suppressing the influence of multipath interference on the signal; secondly, by dynamically detecting the center frequency interval of adjacent modes and activating the bandwidth parameter linkage adjustment mechanism, the mode aliasing problem is avoided, and the decomposition accuracy and robustness are improved; thirdly, based on the energy attenuation rate of the decomposition residual, an adaptive stop threshold is set to optimize the convergence efficiency of the decomposition process and avoid over-decomposition or under-decomposition; finally, through Hilbert marginal spectrum analysis (Hilbert marginal spectrum analysis), the effective carrier components are screened to accurately separate the high-order IMF components containing the carrier fundamental frequency and the low-frequency residual components reflecting the multipath effect. The present invention not only improves the accuracy and stability of RFID signal decomposition, but also provides a high-quality signal basis for subsequent phase mutation analysis, multipath interference suppression, and system performance evaluation, thereby enhancing the anti-interference ability and recognition reliability of RFID reading distance intelligent terminals in complex environments as a whole.

[0077] Preferably, perform Hilbert marginal spectrum analysis on each effective carrier component to obtain the instantaneous frequency peak and fluctuation variance of each effective carrier component, such as Figure 2As shown below, specifically:

[0078] S202: Perform segmented windowing preprocessing on the effective carrier component. Adopt an adaptive window length adjustment strategy, dynamically set the window function length according to the center frequency of the effective carrier component, so that the signal within the window covers at least three fundamental frequency periods to suppress spectral leakage.

[0079] It should be noted that when performing segmented windowing preprocessing on the effective carrier component, first calculate the fundamental frequency period based on its center frequency, and dynamically set the window function length according to the signal sampling rate to ensure that at least three complete fundamental frequency periods are included within the window; subsequently, perform windowing processing using a Hanning window function to suppress spectral leakage through the edge attenuation characteristics of the window function; during the window length adjustment process, monitor the instantaneous frequency stability of the signal within the window in real time. If the frequency fluctuation exceeds the preset threshold, dynamically expand the window length to cover more periods to ensure the consistency of the frequency characteristics within the signal segment; finally, perform overlapping segmentation processing on the windowed signal segments, and combine the weighted average method to smooth the segmentation boundary to further reduce the spectral distortion introduced by window function switching, thereby providing high-quality signal segments for subsequent Hilbert transform and frequency analysis.

[0080] S204: Perform complex analytic transformation processing on the windowed component signal segments, generate the corresponding analytic signal through Hilbert transform, extract the real part and the imaginary part of the analytic signal, and perform cross-arrangement and combination on the real part and the imaginary part of the analytic signal to form a complex number sequence.

[0081] It should be noted that when performing complex analytic transformation processing on the windowed component signal segments, first convert the real signal into a complex signal through Hilbert transform to generate the corresponding analytic signal; subsequently, extract the real part (i.e., the original signal) and the imaginary part (i.e., the orthogonal component after Hilbert transform) of the analytic signal, and perform cross-arrangement and combination on the real part and the imaginary part in chronological order to form a complex number sequence; during the arrangement process, ensure that the real part and the imaginary part at each time point correspond one by one to form a complete complex number sequence; finally, perform normalization processing on the complex number sequence to eliminate the influence of amplitude fluctuations on subsequent analysis, thereby providing high-quality complex signal data for instantaneous frequency calculation.

[0082] S206: Calculate the instantaneous frequency of the complex number sequence point by point based on the phase difference algorithm, fit the instantaneous frequency of the complex number sequence into a continuous phase sequence curve according to the cubic spline interpolation method, and obtain the second derivative of the phase sequence curve as the instantaneous frequency sequence.

[0083] It should be noted that when calculating the instantaneous frequency of a complex sequence point by point based on the phase difference algorithm, first, the phase angle of the complex sequence is extracted through the arctangent function, and the difference value of adjacent phase angles is calculated to obtain the discrete sequence of instantaneous frequency; subsequently, the cubic spline interpolation method is used to perform curve fitting on the discrete instantaneous frequency to generate a continuous and smooth phase sequence curve, ensuring the continuity of frequency changes.

[0084] S208: Perform probability density estimation on the instantaneous frequency sequence to obtain the probability density function of the instantaneous frequency. Map each frequency value and its corresponding probability density in the probability density function of the instantaneous frequency. Use the frequency value as the horizontal axis and the probability density as the vertical axis, and construct the probability density curve of the instantaneous frequency by the method of plotting points and connecting lines;

[0085] S210: Take the peak position of the probability density curve as the instantaneous frequency peak, and take the distribution variance of the probability density curve as the fluctuation variance.

[0086] In summary, through the above steps, the present invention improves the accuracy and stability of instantaneous frequency analysis, and also provides key data support for subsequent signal feature extraction, multipath interference suppression, and system performance evaluation, thereby overall enhancing the signal processing ability and anti-interference performance of the RFID reading distance intelligent terminal in a complex environment.

[0087] Preferably, perform segmented windowing and Hilbert transform analysis processing on each high-order IMF component to obtain the phase mutation signal segment of the radio frequency signal, specifically:

[0088] Perform time-varying adaptive segmented windowing on each high-order IMF component, and dynamically adjust the window function length according to the instantaneous frequency peak of the high-order IMF component to ensure that the signal within the window contains at least two complete phase fluctuation cycles to balance the time-frequency resolution;

[0089] It should be noted that the instantaneous frequency sequence of the high-order IMF component is extracted through the Hilbert transform, and its peak frequency is calculated; the fundamental frequency period is dynamically calculated according to the peak frequency, and the window function length is determined based on the sampling rate to ensure that at least two complete phase fluctuation cycles are included within the window; during the window length adjustment process, the instantaneous frequency stability of the signal within the window is monitored in real time. If the frequency fluctuation exceeds the preset threshold, the window length is dynamically extended to cover more cycles to ensure the consistency of frequency characteristics within the signal segment; finally, the Hamming window function is used to window the signal segment, and the spectral leakage is suppressed through the edge attenuation characteristics of the window function, and the overlapping segmentation strategy is combined to smooth the segmentation boundary, thereby providing high-quality time-frequency localized signal segments for subsequent Hilbert transform and phase mutation analysis.

[0090] Each windowed high-order IMF component signal segment is transformed into a complex analytic signal through Hilbert transform. Subsequently, the phase angle of the complex analytic signal is calculated point by point through the arctangent operation to obtain the instantaneous phase sequence of each high-order IMF component signal segment;

[0091] It should be noted that the windowed signal segment is subjected to Hilbert transform to generate an orthogonal component, and it is combined with the original signal segment to form a complex analytic signal; subsequently, the real part (i.e., the original signal) and the imaginary part (i.e., the orthogonal component) of the complex analytic signal are extracted, and the ratio of the real part to the imaginary part is calculated point by point; then, the phase angle at each time point is calculated through the arctangent operation to obtain the instantaneous phase sequence; finally, the phase unwrapping process is performed on the instantaneous phase sequence to eliminate phase jumps and ensure the continuity and consistency of the phase sequence, thereby providing high-precision instantaneous phase data for subsequent phase mutation detection.

[0092] The phase difference values of adjacent instantaneous phase sequences are calculated frame by frame, the calculated phase difference values of adjacent instantaneous phase sequences are weighted, and each weighted result is used as the phase fluctuation intensity index of the corresponding high-order IMF component signal segment;

[0093] The phase fluctuation intensity index of each high-order IMF component signal segment is compared with a preset index threshold, and the high-order IMF component signal segment with a phase fluctuation intensity index greater than the preset index threshold is marked as a phase mutation signal segment.

[0094] In summary, the time-varying adaptive segmented windowing strategy is adopted, and the window function length is dynamically adjusted according to the instantaneous frequency peak of the high-order IMF component to ensure that the signal within the window contains at least two complete phase fluctuation cycles, effectively balancing the time-frequency resolution and avoiding the loss of frequency characteristics or insufficient time resolution caused by a fixed window length; secondly, the windowed signal segment is transformed into a complex analytic signal through Hilbert transform, and the instantaneous phase sequence is calculated point by point in combination with the arctangent operation, providing high-precision phase data for phase mutation detection; thirdly, by calculating the phase difference values of adjacent instantaneous phase sequences frame by frame and performing weighted processing, a phase fluctuation intensity index is generated, which can quantify the severity of phase changes, thereby accurately identifying the phase mutation region; finally, by comparing the phase fluctuation intensity index with a preset threshold, the phase mutation signal segment is marked, providing key data support for subsequent multipath interference analysis and system performance optimization.

[0095] Preferably, a first-order difference calculation is performed on the instantaneous phase sequence of the phase mutation signal segment to obtain the phase gradient sequence of the phase mutation signal segment, and a phase gradient change curve is constructed based on the phase gradient sequence in combination with weighted moving average, specifically:

[0096] Based on the sampling clock of the phase mutation signal segment, the phase mutation signal segment is subjected to isochronous segmentation processing to generate an equally spaced phase sequence aligned based on timestamps;

[0097] It should be noted that the time interval is determined according to the sampling rate, and the signal segment is divided into isochronous segments at a fixed time interval; cubic spline interpolation is performed on the phase data within each isochronous segment to generate phase values aligned with equally spaced timestamps, ensuring the time consistency of the phase sequence; then, it is detected whether there are abnormal points in the interpolated phase sequence, and if an abnormality is found, it is replaced with the mean value of neighboring points to ensure the integrity of the data; finally, the equally spaced phase sequence is normalized to eliminate the influence of amplitude fluctuations on subsequent analysis, thereby providing high-quality equally spaced phase data for instantaneous phase gradient calculation.

[0098] Forward difference (the difference between the current point and the next phase point) and backward difference (the difference between the current point and the previous phase point) are simultaneously performed on each equally spaced phase sequence, and the arithmetic mean of the forward difference and the backward difference is calculated as the initial value of the instantaneous phase gradient; and the initial value of the instantaneous phase gradient is symmetrically weighted to obtain a weighted phase gradient sequence;

[0099] Three-level progressive moving average processing is performed on the weighted phase gradient sequence: in the first level, linear weighted accumulation is performed within the window to output a coarsely smoothed gradient; in the second level, residual pulse noise is detected based on the coarsely smoothed result, and median filtering is used to replace abnormal points; in the third level, exponential decay weighting is applied to the filtered data to strengthen the contribution of near-time data;

[0100] It should be noted that when performing three-level progressive moving average processing on the weighted phase gradient sequence, first, in the first-level processing, the Hanning window function is used to perform linear weighted accumulation on the gradient sequence to generate a coarsely smoothed gradient sequence; subsequently, in the second-level processing, residual pulse noise is detected based on the coarsely smoothed result, abnormal points are identified by calculating the local variance, and median filtering is used to replace abnormal points to ensure the smoothness of the gradient sequence; then, in the third-level processing, exponential decay weighting is applied to the filtered gradient sequence, with the current moment as the center, and higher weight coefficients are given to near-time data to strengthen the contribution of near-time data; finally, the gradient sequence after three-level processing is normalized to eliminate the amplitude deviation introduced by weighting, thereby providing high-quality data support for constructing the phase gradient change curve.

[0101] The phase gradient values after multi-level processing are remapped according to the timestamps to construct a complete phase gradient change curve; and the window length, weight, and filtering status parameters at each time point are synchronously recorded to form a metadata chain for gradient calculation.

[0102] In summary, through the present method, the accuracy and stability of phase gradient analysis are improved, providing a reliable technical guarantee for signal processing and performance optimization of RFID reading distance intelligent terminals in complex environments.

[0103] Preferably, perform feature analysis on the phase gradient change curve to obtain the mutation characteristic parameters of the phase mutation signal segment, specifically:

[0104] Calculate the global gradient mean of the phase gradient change curve, and use the global gradient mean as the baseline mean for mutation detection;

[0105] It should be noted that the phase gradient change curve is segmented, and the curve is divided into multiple equal-length intervals; subsequently, calculate the arithmetic mean of the gradient values within each interval as the local gradient mean; then, perform a weighted average on all local gradient means, where the weight coefficient is dynamically adjusted based on the gradient stability of each interval, and a higher weight is given to the interval with less gradient fluctuation; finally, use the weighted average result as the global gradient mean and as the baseline mean for mutation detection, providing a reliable reference benchmark for subsequent initial judgment of the starting point and positioning of the peak gradient point.

[0106] Perform a forward search on the phase gradient change curve, and obtain the time point where the gradient in the phase gradient change curve exceeds the baseline mean as the initial judgment position of the starting point;

[0107] It should be noted that when performing a forward search on the phase gradient change curve, first start from the starting point of the curve, compare the gradient value with the baseline mean point by point, and record the time point when the gradient first exceeds the baseline mean as the initial judgment position of the starting point; subsequently, perform secondary verification within the neighborhood of the initial judgment position, calculate the mean and variance of the gradient values within the neighborhood, if the mean is higher than the baseline mean and the variance is lower than the preset threshold, then confirm it as the initial judgment position of the starting point; finally, record the timestamp and gradient value of the initial judgment position, providing initial data support for subsequent first-order derivative sign consistency detection.

[0108] Perform a first-order derivative sign consistency detection on the data in the neighborhood of the initial judgment position of the starting point. If the derivatives of several consecutive (such as 5, 8, or 10) sampling points are all positive and the gradient increment is monotonically increasing, then confirm it as the mutation starting point, otherwise expand the search range until the condition is met;

[0109] It should be noted that first start from the initial judgment position, calculate the first-order derivative of the gradient value point by point backward, and detect the sign of the derivative; then, count the signs of several consecutive sampling points (preferably 8), if they are all positive and the gradient increment is monotonically increasing, then confirm it as the mutation starting point; if the condition is not met, expand the search range, move forward or backward by several sampling points, and repeat the above detection process until a mutation starting point that meets the condition is found; finally, record the timestamp and gradient value of the mutation starting point, providing accurate starting position information for subsequent positioning of the peak gradient point.

[0110] Within the mutation section, the parabolic interpolation method is used to optimize the subsampling accuracy of discrete gradient extreme points, locate the peak gradient point, and calculate the gradient variance between the peak gradient point and its adjacent sampling points before and after.

[0111] It should be noted that within the mutation section, first, the discrete extreme points in the gradient sequence are identified, and the gradient values and corresponding timestamps of the extreme points and their two adjacent sampling points before and after are extracted. Subsequently, a parabolic model is constructed based on these three points, and the vertex coordinates of the parabola are calculated as the peak gradient point after subsampling accuracy optimization. Then, the rationality of the parabola vertex is verified. If the vertex is within the neighborhood of the extreme point and the gradient value is higher than the surrounding points, it is confirmed as the peak gradient point. Finally, the timestamp and gradient value of the peak gradient point are recorded to provide accurate peak position information for subsequent gradient variance calculation and falling edge slope analysis.

[0112] If the gradient variance is less than the preset tolerance and the slope of the gradient falling edge is greater than 70% of the slope of the rising edge, it is determined as a valid peak point; otherwise, resampling correction is triggered.

[0113] It should be noted that when calculating the gradient variance between the peak gradient point and its adjacent sampling points before and after, first, the gradient values of the peak gradient point and its two adjacent sampling points before and after are extracted, and the gradient variance of these five points is calculated. Subsequently, the gradient variance is compared with the preset tolerance. If the variance is less than the tolerance, the slopes of the gradient sequences before and after the peak point are further calculated, namely the slope of the rising edge and the slope of the falling edge. Then, the ratio of the slope of the falling edge to the slope of the rising edge is compared. If the slope of the falling edge is greater than 70% of the slope of the rising edge, it is determined as a valid peak point; if the condition is not met, resampling correction is triggered, the sampling range is extended or the interpolation model is adjusted, and the gradient variance and slope are recalculated until a valid peak point that meets the conditions is found.

[0114] The time when the gradient drops from the valid peak point to the baseline mean is traced backward as the mutation end point, and the absolute time difference from the start point to the end point is calculated as the mutation duration.

[0115] In summary, by calculating the global gradient mean as the baseline for mutation detection, a reliable reference benchmark is provided for the initial judgment of the start point; by using forward search combined with the first derivative sign consistency detection, the mutation start point is accurately identified, ensuring the robustness and accuracy of the start point detection; by using the parabolic interpolation method to optimize the subsampling accuracy of discrete gradient extreme points, the peak gradient point is located, and its effectiveness is verified by combining the gradient variance and the falling edge slope, ensuring the accuracy and stability of the peak gradient point; by tracing the time when the gradient drops from the valid peak point to the baseline mean backward, the mutation duration is calculated, providing complete time dimension information for the feature description of the phase mutation signal segment.

[0116] Preferably, the multi-path interference suppression effect level of the RFID reading distance intelligent terminal is evaluated according to the mutation characteristic parameters of the phase mutation signal segment, specifically as follows:

[0117] Based on the RFID signal propagation theoretical model in an ideal interference-free environment, combined with the carrier wavelength and the spatial geometric parameters of the reading distance terminal, a reference model of phase mutation parameters is established;

[0118] It should be noted that according to the carrier wavelength, the spatial geometric parameters of the reading distance terminal, and the signal propagation path, the theoretical density of the phase mutation starting point, the upper limit of the peak gradient, and the mutation duration range are calculated; subsequently, a phase mutation signal in an ideal interference-free environment is generated through simulation, and its mutation characteristic parameters are extracted as reference values; then, combined with the multi-path effect and noise interference in the actual environment, the reference values are dynamically corrected to ensure that the reference model can reflect the signal characteristics in the real scenario; finally, the corrected reference values are stored as the reference model of the phase mutation parameters. Generally speaking, the reference model is a reference framework constructed based on the radio frequency identification signal propagation theory in an ideal interference-free environment, which includes the one-way theoretical ranges such as the density of the starting point, the upper limit of the peak gradient, and the mutation duration range. This reference model is obtained through prior training.

[0119] Import the mutation characteristic parameters of the phase mutation signal segment into the reference model: compare the density of the mutation starting point (the number of mutations per unit time) with the reference model to generate a density deviation coefficient; calculate the percentage over-limit of the peak gradient relative to the theoretical upper limit; count the proportion of abnormal mutations in the mutation duration that exceeds the theoretical range;

[0120] It should be noted that first, calculate the actual density of the mutation starting point per unit time, and compare it with the theoretical density in the reference model to generate a density deviation coefficient; then, extract the actual peak gradient value and calculate its percentage over-limit relative to the theoretical upper limit in the reference model; next, count the proportion of abnormal mutations in the phase mutation signal segment whose mutation duration exceeds the theoretical range of the reference model; finally, use the density deviation coefficient, the percentage over-limit, and the proportion of abnormal mutations as the key indicators for evaluating the multi-path interference suppression effect.

[0121] Determine the weights of the characteristic parameters by the entropy weight method, standardize the density deviation coefficient, the percentage over-limit, and the proportion of abnormal mutations, and then perform weighted summation to obtain the multi-path interference suppression index;

[0122] It should be noted that when determining the weights of feature parameters by the entropy weight method, first calculate the information entropy of the density deviation coefficient, the percentage over-limit amount, and the proportion of abnormal mutations. Determine the weight coefficients of each parameter according to the difference in information entropy; subsequently, perform standardization processing on the three feature parameters to convert them into dimensionless values to ensure comparison under the same dimension; then, multiply the standardized feature parameters by their corresponding weight coefficients and perform weighted summation to obtain the multipath interference suppression index; finally, perform normalization processing on the suppression index to make its value range between 0 and 1, providing a unified quantitative index for the subsequent classification of the suppression effect level.

[0123] Input the multipath interference suppression index into a pre-trained three-branch convolutional neural network, and output the multipath interference suppression effect level (including excellent / good / medium / poor) through the feature fusion layer.

[0124] It should be noted that when inputting the multipath interference suppression index into a pre-trained three-branch convolutional neural network, first map the suppression index to a feature vector through the input layer and input it into three parallel convolutional branches respectively; subsequently, each convolutional branch performs convolutional and pooling operations on the feature vector to extract feature information at different levels; then, splice and weighted fuse the output features of the three branches in the feature fusion layer to generate a comprehensive feature vector; finally, through the fully connected layer and the Softmax classifier, map the comprehensive feature vector to the multipath interference suppression effect level (excellent / good / medium / poor), providing intelligent decision-making support for the performance optimization of the RFID reading distance intelligent terminal.

[0125] It should be noted that the specific method steps for training the three-branch convolutional neural network are as follows: First, collect a large amount of RFID signal data containing different degrees of multipath interference and label their corresponding suppression effect levels (excellent / good / medium / poor); subsequently, perform preprocessing on the signal data, including normalization, segmentation, and feature extraction, to generate training samples; then, construct a three-branch convolutional neural network architecture, each branch containing a convolutional layer, a pooling layer, and a fully connected layer, respectively used to extract feature information at different levels; then, input the training samples into the network, optimize the network parameters through the backpropagation algorithm, and adopt cross-validation and early stopping strategies during the training process to prevent overfitting; finally, evaluate the network performance on an independent test set, adjust the network structure and hyperparameters until the predetermined classification accuracy and generalization ability are achieved, thus completing the pre-training of the network.

[0126] In this embodiment, the data acquisition and analysis method of the RFID reading distance intelligent terminal may further include the following steps:

[0127] Step 1: Based on the mutation starting point, peak gradient, and duration parameters in the phase gradient change curve, extract the instantaneous gradient slope at the mutation starting point, the peak rate of phase jump, and the length of the gradient saturation interval as the input parameters for gradient compensation;

[0128] Step 2: Construct a hyperbolic tangent type compensation function according to the input parameters: By adjusting the curvature parameter of the hyperbolic tangent function to match the peak rate of phase jump, make its derivative form a negative cancellation with the original gradient slope at the instantaneous gradient slope of the mutation starting point; At the same time, set the saturation threshold of the compensation function according to the length of the gradient saturation interval to ensure that the compensation effect only takes effect in the mutation active interval and avoid interfering with the stable segment signal;

[0129] Step 3: Apply the compensation function to the neighborhood of the mutation starting point of the original phase sequence to generate a corrected phase sequence; Synchronously calculate the phase difference residuals before and after compensation. If the moving window mean of the absolute value of the residuals exceeds the preset tolerance, reverse-adjust the curvature and saturation threshold of the hyperbolic tangent function according to the residual distribution characteristics until the residuals converge within the tolerance range;

[0130] Step 4: Define a stable segment interval after the mutation end point, extract the phase difference between the start and end of the stable segment of the corrected phase sequence, and correct the residual cumulative phase offset introduced by the compensation operation according to the phase difference;

[0131] Step 5: Compare the phase gradient change curves before and after correction, and statistically calculate the gradient peak attenuation rate in the mutation segment, the phase fluctuation variance in the stable segment, and the Hilbert spectral entropy value of the overall signal. If any index fails to reach the preset optimization goal, return to Step 2 to adjust the compensation function parameters to form a closed-loop optimization link, and finally achieve the suppression of phase jumps and the global elimination of system errors.

[0132] It should be noted that extracting the instantaneous gradient slope, phase jump peak rate, and gradient saturation interval length of the mutation starting point based on the phase gradient change curve provides a scientific basis for the construction of the compensation function; by adjusting the curvature parameter and saturation threshold of the hyperbolic tangent function, the phase jump rate is dynamically matched and the compensation range is restricted to ensure the efficiency and locality of the compensation effect; by monitoring the phase difference residual before and after compensation in real time and inversely adjusting the compensation parameters, iterative optimization of the compensation accuracy is achieved; the phase difference is extracted in the stable section interval and the residual cumulative offset is corrected to eliminate the global error introduced by the compensation operation; finally, by comparing the phase gradient change curves before and after correction, the gradient peak attenuation rate in the mutation section, the phase fluctuation variance in the stable section, and the overall signal Hilbert spectral entropy value are statistically analyzed to form a closed-loop optimization link to ensure the global optimum of the phase jump suppression effect and system error elimination. This method constructs a closed-loop optimization link, dynamically adapts to the mutation characteristics caused by the environment of the RFID reading distance intelligent terminal, and realizes the effective suppression of phase jumps and the accurate correction of global errors in RFID reading distance data.

[0133] In this embodiment, the data acquisition and analysis method of the RFID reading distance intelligent terminal may further include the following steps:

[0134] After performing phase correction on the RFID reading distance intelligent terminal, the radio frequency signal of the RFID reading distance intelligent terminal is collected in real time, and the low-frequency residual component collected in real time is obtained based on variational mode decomposition of the radio frequency signal;

[0135] The residual component collected in real time is aligned frame by frame with the reference template, and the cross-correlation entropy value of the two in the time-frequency domain is calculated;

[0136] If the cross-correlation entropy value is lower than the preset threshold, it is determined that the multipath interference suppression is effective; if the cross-correlation entropy value exceeds the threshold, it is marked as an under-suppression area and its spatio-temporal distribution characteristics are recorded;

[0137] A parameter adjustment vector is generated according to the spatio-temporal distribution characteristics of the under-suppression area: for the high-frequency phase jump area, the curvature adjustment coefficient of the compensation function is increased proportionally to enhance the negative gradient compensation intensity; for the low-frequency residual accumulation area, the weight coefficient of the linear offset term is increased to strengthen the global error suppression;

[0138] The multipath effect is continuously suppressed in the above manner.

[0139] It should be noted that extracting the low-frequency residual component from real-time acquisition based on variational mode decomposition provides a high-precision signal basis for the quantitative evaluation of the multipath interference suppression effect; by calculating the cross-correlation entropy value in the time-frequency domain between the residual component and the reference template, the under-suppression area can be accurately identified and its spatio-temporal distribution characteristics can be recorded, providing a scientific basis for parameter adjustment; aiming at the different characteristics of the high-frequency phase jump area and the low-frequency residual accumulation area, the curvature adjustment coefficient and the linear offset term weight coefficient of the compensation function are dynamically adjusted to achieve precise suppression of multipath interference; finally, by continuously optimizing the parameters of the compensation function, a closed-loop feedback mechanism is formed to improve the real-time performance and robustness of multipath interference suppression, providing a reliable technical guarantee for the stable operation of the RFID reading distance intelligent terminal in a complex environment.

[0140] As Figure 3 shown, the second aspect of the present invention discloses a data acquisition and analysis system 6 for an RFID reading distance intelligent terminal. The data acquisition and analysis system for the RFID reading distance intelligent terminal includes a memory 41 and a processor 52. The data acquisition and analysis method program for the RFID reading distance intelligent terminal is stored in the memory 41. When the data acquisition and analysis method program for the RFID reading distance intelligent terminal is executed by the processor 52, the steps of any one of the data acquisition and analysis methods for the RFID reading distance intelligent terminal are implemented.

[0141] The third aspect of the present invention discloses a computer-readable storage medium. The computer-readable storage medium includes a data acquisition and analysis method program for the RFID reading distance intelligent terminal. When the data acquisition and analysis method program for the RFID reading distance intelligent terminal is executed by a processor, the steps of any one of the data acquisition and analysis methods for the RFID reading distance intelligent terminal are implemented.

[0142] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A data collection and analysis method for an RFID reading range intelligent terminal, characterized in that: The following steps are involved: Acquire the radio frequency signal of the RFID reading intelligent terminal, perform variational modal decomposition processing on the radio frequency signal, and obtain the high-order IMF component including the carrier fundamental frequency and the low-frequency residual component reflecting the multipath effect; Perform segmented windowing and Hilbert transform analysis on each high-order IMF component to obtain the phase mutation signal segment of the RF signal; Performing first-order difference calculation on the instantaneous phase sequence of the phase mutation signal segment to obtain the phase gradient sequence of the phase mutation signal segment, and constructing a phase gradient change curve according to the phase gradient sequence combined with weighted sliding average; Performing characteristic analysis on the phase gradient change curve to obtain mutation characteristic parameters of the phase mutation signal segment, wherein the mutation characteristic parameters include a mutation starting point, an effective peak point, and a mutation duration; Evaluate the multipath interference suppression effect level of the RFID reading intelligent terminal according to the mutation characteristic parameters of the phase mutation signal segment; The multipath interference suppression effect level of the RFID reading intelligent terminal is evaluated according to the mutation characteristic parameters of the phase mutation signal segment, specifically: Based on the theoretical model of RFID signal propagation in an ideal interference-free environment, combined with the carrier wavelength and the spatial geometric parameters of the range reader, a benchmark model of phase mutation parameters is established. Importing the mutation characteristic parameters of the phase mutation signal segment into the benchmark model: comparing the density of the mutation starting point with the benchmark model to generate a density deviation coefficient; calculating the percentage excess of the peak gradient relative to the theoretical upper limit; and calculating the proportion of abnormal mutations whose duration exceeds the theoretical range; The characteristic parameter weights are determined by the entropy weight method, and the density deviation coefficient, percentage over-limit and abnormal mutation ratio are standardized, and then weighted summation is performed to obtain the multipath interference suppression index. The multipath interference suppression index is input into a pre-trained three-branch convolutional neural network, and the multipath interference suppression effect level is output through a feature fusion layer.

2. The data collection and analysis method of the RFID reading intelligent terminal according to claim 1 is characterized in that: The radio frequency signal of the RFID reading intelligent terminal is obtained, and the radio frequency signal is subjected to variational mode decomposition processing to obtain a high-order IMF component including the carrier fundamental frequency and a low-frequency residual component reflecting the multipath effect, specifically: Setting a mode number K and a penalty factor α, initializing a variational mode decomposition framework based on the mode number K and the penalty factor α, and importing the radio frequency signal into the variational mode decomposition framework for iterative decomposition; In each iterative decomposition process, instantaneous frequency smoothness constraints and energy density gradient constraints are simultaneously imposed on each modal component; After each iterative decomposition, the center frequency interval between adjacent modes is detected. When the center frequency interval between any two adjacent modes is less than the preset minimum allowable interval, the bandwidth parameter linkage adjustment mechanism is activated to give priority to compressing the bandwidth upper limit of the high-frequency mode and recalculate the energy constraint condition. An adaptive stop threshold is set based on the energy decay rate of the decomposed residual. When the residual energy changes in three consecutive iterations are all lower than the threshold, the decomposition process is judged to be over and each modal component is output. According to the overlap between the center frequency of each modal component and the theoretical interval of the carrier fundamental frequency and the satisfaction of the dual constraints, the pseudo-modes caused by multipath interference are eliminated, and the effective carrier components that meet the instantaneous frequency stability and spectrum energy focusing are retained; Perform Hilbert marginal spectrum analysis on each effective carrier component to obtain the instantaneous frequency peak and fluctuation variance of each effective carrier component; If the instantaneous frequency peak of a certain effective carrier component is within the theoretical fluctuation range of the carrier fundamental frequency and its fluctuation variance is less than half of that of the adjacent component, the effective carrier component is determined to be a high-order IMF component; Otherwise, the effective carrier component is determined as a low-frequency residual component.

3. The data collection and analysis method of the RFID reading intelligent terminal according to claim 2 is characterized in that: Perform Hilbert marginal spectrum analysis on each effective carrier component to obtain the instantaneous frequency peak and fluctuation variance of each effective carrier component, specifically: The effective carrier component is preprocessed by segmented windowing, and an adaptive window length adjustment strategy is adopted to dynamically set the window function length according to the center frequency of the effective carrier component so that the signal in the window covers at least three base frequency cycles to suppress spectrum leakage; Performing complex analysis processing on the windowed component signal segment, generating a corresponding analytical signal through Hilbert transform, extracting the real part and the imaginary part of the analytical signal, and cross-arranging and combining the real part and the imaginary part of the analytical signal to form a complex sequence; The instantaneous frequency of the complex sequence is calculated point by point based on a phase difference algorithm, the instantaneous frequency of the complex sequence is fitted into a continuous phase sequence curve according to a cubic spline interpolation method, and the second-order derivative of the phase sequence curve is obtained as an instantaneous frequency sequence; Performing probability density estimation on the instantaneous frequency sequence to obtain a probability density function of the instantaneous frequency, mapping each frequency value and its corresponding probability density in the probability density function of the instantaneous frequency, and constructing a probability density curve of the instantaneous frequency by drawing points and connecting lines with the frequency value as the horizontal axis and the probability density as the vertical axis; The peak position of the probability density curve is taken as the instantaneous frequency peak, and the distribution variance of the probability density curve is taken as the fluctuation variance.

4. The data collection and analysis method of the RFID reading intelligent terminal according to claim 1 is characterized in that: Each high-order IMF component is subjected to segmented windowing and Hilbert transform analysis to obtain the phase mutation signal segment of the RF signal, specifically: Implement time-varying adaptive segmented windowing for each high-order IMF component, and dynamically adjust the window function length according to the instantaneous frequency peak of the high-order IMF component to ensure that the signal in the window contains at least two complete phase fluctuation cycles to balance the time-frequency resolution; Each windowed high-order IMF component signal segment is converted into a complex analytical signal by Hilbert transform, and then the phase angle of the complex analytical signal is calculated point by point by inverse tangent operation to obtain the instantaneous phase sequence of each high-order IMF component signal segment; The phase difference values ​​of adjacent instantaneous phase sequences are calculated frame by frame, the calculated phase difference values ​​of adjacent instantaneous phase sequences are weighted, and each weighted result is used as the phase fluctuation intensity index of the corresponding high-order IMF component signal segment; The phase fluctuation intensity index of each high-order IMF component signal segment is compared with a preset index threshold, and the high-order IMF component signal segment whose phase fluctuation intensity index is greater than the preset index threshold is marked as a phase mutation signal segment.

5. The data collection and analysis method of the RFID reading intelligent terminal according to claim 1 is characterized in that: The instantaneous phase sequence of the phase mutation signal segment is calculated by first-order difference to obtain the phase gradient sequence of the phase mutation signal segment, and a phase gradient change curve is constructed according to the phase gradient sequence combined with weighted sliding average, specifically: Based on the sampling clock of the phase mutation signal segment, the phase mutation signal segment is processed in an equal time manner to generate an equal interval phase sequence based on timestamp alignment; Performing forward difference and backward difference on each equally spaced phase sequence at the same time, calculating the arithmetic mean of the forward difference and the backward difference as the initial value of the instantaneous phase gradient; and symmetrically weighting the initial value of the instantaneous phase gradient to obtain a weighted phase gradient sequence; The weighted phase gradient sequence is subjected to three-level progressive sliding average processing: the first level performs linear weighted accumulation within the window and outputs a rough smoothed gradient; the second level detects residual pulse noise based on the rough smoothing result and uses median filtering to replace abnormal points; The third stage applies exponential decay weighting to the filtered data to enhance the contribution of recent data; The phase gradient values ​​after multi-level processing are remapped according to the timestamp to construct a complete phase gradient change curve; and the window length, weight and filter state parameters at each time point are synchronously recorded to form a metadata chain for gradient calculation.

6. The data collection and analysis method of the RFID reading intelligent terminal according to claim 1 is characterized in that: Performing feature analysis on the phase gradient change curve to obtain the mutation feature parameters of the phase mutation signal segment is specifically: Calculating a global gradient mean of the phase gradient change curve, and using the global gradient mean as a baseline mean for mutation detection; Performing a forward search on the phase gradient change curve, obtaining a time point in the phase gradient change curve when the gradient exceeds the baseline mean as a preliminary judgment position of the starting point; Perform a first-order derivative sign consistency check on the neighborhood data of the initial position of the starting point. If the derivatives of several consecutive sampling points are positive and the gradient increment increases monotonically, it is confirmed as the mutation starting point. Otherwise, the search range is expanded until the condition is met. In the mutation section, the parabolic interpolation method is used to optimize the sub-sampling accuracy of discrete gradient extreme points, locate the peak gradient point, and calculate the gradient variance between the peak gradient point and the sampling points before and after it. If the gradient variance is less than the preset tolerance and the gradient slope along the descending edge is greater than 70% of the slope along the ascending edge, it is determined to be a valid peak point, otherwise resampling correction is triggered; The time it takes for the gradient to drop from the effective peak point to the baseline mean is traced back as the end point of the mutation, and the absolute time difference from the starting point to the end point is calculated as the duration of the mutation.

7. A data collection and analysis system for an RFID reading range intelligent terminal, characterized in that: The data collection and analysis system of the RFID reading range intelligent terminal includes a memory and a processor, wherein the memory stores a data collection and analysis method program of the RFID reading range intelligent terminal. When the data collection and analysis method program of the RFID reading range intelligent terminal is executed by the processor, the steps of the data collection and analysis method of the RFID reading range intelligent terminal as claimed in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a data collection and analysis method program for an RFID range reading intelligent terminal. When the data collection and analysis method program for an RFID range reading intelligent terminal is executed by a processor, the steps of the data collection and analysis method for an RFID range reading intelligent terminal as described in any one of claims 1 to 6 are implemented.

Images