A method and system for adaptive detection of RNTI in an NR network environment

Abstract

The application relates to the technical field of communication, and discloses an RNTI adaptive detection method and system in an NR network environment, which comprises a processor, a data acquisition module, a preprocessing module, a feature extraction module, an adaptive adjustment module, a detection module and a verification module. The data acquisition module acquires network data, and the preprocessing module processes the data to obtain a preprocessing data set. The feature extraction module extracts a multi-dimensional feature vector, and the adaptive adjustment module dynamically adjusts RNTI detection parameters accordingly. The detection module combines a blind detection algorithm and a neural network model to identify RNTI, outputs a candidate RNTI set, and the verification module filters out an effective RNTI list and sends the effective RNTI list to a network scheduling end. The application acquires network data in real time and adaptively adjusts detection parameters, improves the accuracy of RNTI detection and the system adaptability, optimizes network resource scheduling, reduces detection cost, and improves the performance of the NR network and the user experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication technology, in particular to an RNTI adaptive detection method and system in NR network environment. BACKGROUND

[0002] With the wide application of 5G technology, NR network brings users a new communication experience with its high speed, low latency and large capacity. However, in the actual NR network environment, there are many complex factors that bring great challenges to the detection of RNTI.

[0003] The channel state of NR network is complex and changeable. The channel is affected by multiple factors such as multipath fading, shadowing effect and interference. In the environment of high-rise buildings in the city, the signal is easily reflected multiple times between buildings, causing multipath fading, making the channel state parameters such as channel quality indicator (CQI) and reference signal received power (RSRP) fluctuate sharply. This makes it difficult for traditional fixed parameter RNTI detection methods to adapt to the dynamic changes of the channel, and it is difficult to accurately detect RNTI, which further affects the accuracy of network scheduling and communication quality.

[0004] The signal strength of user equipment is quite different. Different user equipment has different location, transmission power and hardware performance, resulting in uneven signal strength. In areas with weak signal strength, the signal of user equipment is easily overwhelmed by noise, and if the signal detection threshold of traditional detection methods is not properly set, it may miss detecting RNTI; while in areas with strong signal strength, if the threshold is too high, it may also cause false detection, increase the invalid detection overhead and reduce the network detection efficiency.

[0005] Network load presents dynamic changes. During the network usage peak period, such as large-scale activity site or office area working hours, a large number of users access the network at the same time, and the physical layer resource block occupation rate rises sharply, and the network load increases. At this time, if the fixed resource block allocation weight and detection window length are still used, the detection accuracy will decrease, and it will not be able to accurately detect all user equipment RNTI in time, affecting the reasonable allocation of network resources and the communication experience of users.

[0006] Traditional RNTI detection methods mostly use fixed detection parameters, and lack the ability to adapt to changes in network environment. These methods cannot dynamically adjust the detection strategy according to real-time channel state, signal strength and network load parameters, and are difficult to meet the demand of NR network for efficient and accurate detection of RNTI, limiting the further improvement of network performance. SUMMARY

[0007] The purpose of the present application is to provide an RNTI adaptive detection method and system in NR network environment to solve the problems raised in the background.

[0008] To achieve the above object, the present application provides the following technical solutions: an RNTI adaptive detection system in an NR network environment, comprising a processor, a data acquisition module, a preprocessing module, a feature extraction module, an adaptive adjustment module, a detection module and a verification module;

[0009] The data acquisition module acquires channel state parameters, user equipment signal strength and network load data in real time under the NR network environment, and sends the acquired data to the preprocessing module;

[0010] The preprocessing module performs noise reduction processing on the channel state parameters, normalization processing on the user equipment signal strength, and time sequence alignment processing on the network load data, to obtain a preprocessed data set;

[0011] The feature extraction module extracts a multi-dimensional feature vector from the preprocessed data set, including time domain features, frequency domain features and spatial domain features, and inputs the multi-dimensional feature vector into the adaptive adjustment module;

[0012] The adaptive adjustment module dynamically adjusts RNTI detection parameters based on the multi-dimensional feature vector, including detection window length, signal detection threshold and resource block allocation weight, to generate an adaptive parameter configuration instruction;

[0013] The detection module executes a blind detection algorithm according to the adaptive parameter configuration instruction, identifies the RNTI of the user equipment in combination with a pre-trained neural network model, and outputs a candidate RNTI set;

[0014] The verification module performs redundancy checking and conflict detection on the candidate RNTI set, filters out an effective RNTI list, and sends the effective RNTI list to the network scheduling end through the processor.

[0015] Preferably, the specific operation process of the data acquisition module is as follows:

[0016] The channel quality indicator (CQI), reference signal received power (RSRP) and physical layer resource block occupation rate of the NR network are acquired;

[0017] The CQI is matched with a preset standard channel quality mapping table to obtain a channel state classification value;

[0018] The RSRP is differentially calculated with a dynamic signal strength baseline to obtain a signal strength offset value;

[0019] The resource block occupation rate is compared with historical same-period data to obtain a network load fluctuation value;

[0020] If the channel state classification value, the signal strength offset value or the network load fluctuation value exceeds the corresponding preset threshold, a network environment abnormality marker is generated.

[0021] Preferably, the preprocessing module comprises:

[0022] The channel state parameter is filtered by wavelet transform to remove high-frequency noise and generate a noise-reduced channel parameter;

[0023] The user equipment signal strength is dynamically compressed by range normalization algorithm to obtain a normalized signal strength sequence;

[0024] The network load data is segmented by time series using a sliding window mechanism, and is synchronized and aligned with the system clock to form time series aligned load data.

[0025] Preferably, the specific implementation of the feature extraction module comprises:

[0026] The signal periodicity is calculated by autocorrelation function for time domain features to generate time domain periodicity coefficients;

[0027] The energy ratio of main frequency components is extracted by fast Fourier transform for frequency domain features to generate a frequency energy distribution vector;

[0028] The spatial correlation of multi-antenna signals is analyzed by covariance matrix for spatial domain features to generate a spatial correlation matrix.

[0029] Preferably, the operation process of the adaptive adjustment module comprises:

[0030] The multi-dimensional feature vector is input into the reinforcement learning model, and the expected utility value of different detection parameter combinations is calculated by Q-learning algorithm;

[0031] According to the principle of maximizing the expected utility value, the optimal detection window length, signal detection threshold and resource block allocation weight are selected;

[0032] When the network load fluctuation value exceeds the preset threshold, the backup parameter configuration strategy is enabled, the detection window length is dynamically expanded, and the signal detection threshold is reduced.

[0033] Preferably, the detection module executes the blind detection algorithm as follows:

[0034] The energy detection method is used in the frequency domain to preliminarily screen potential RNTI frequency points;

[0035] The symbol level alignment of candidate frequency points is performed in the time domain by using a matched filter to generate a time domain synchronization signal;

[0036] The time domain synchronization signal is input into a convolutional neural network (CNN) model to identify the RNTI encoding mode and output a candidate RNTI set.

[0037] Preferably, the verification module comprises:

[0038] Looping redundancy check is performed on each RNTI in the candidate RNTI set, and items failing the check are removed;

[0039] The allocated RNTIs are recorded by a hash table, the collision between the candidate RNTIs and the allocated RNTIs is detected, and the colliding items are removed;

[0040] The remaining RNTIs are arranged in descending order of signal strength, and the first N RNTIs are selected as the effective RNTI list.

[0041] Preferably, the application further comprises a historical data analysis module, and the operation process is as follows:

[0042] The historical effective RNTI list and the corresponding network environment parameters are stored;

[0043] The RNTI distribution mode in the historical data is analyzed by a clustering algorithm, and a typical scene template is generated;

[0044] When the similarity between the current network environment parameters and any typical scene template exceeds a preset threshold, the detection parameter configuration corresponding to the template is directly called.

[0045] Preferably, the application further comprises a dynamic threshold setting module, and the operation process is as follows:

[0046] The sensitivity coefficient of the signal detection threshold is adjusted according to the real-time network load fluctuation value, and the calculation formula is:

[0047]

[0048] Wherein, L current is the current signal strength offset value, L base is the baseline signal strength, V load is the network load fluctuation value, V max is the maximum allowed fluctuation value, and α and β are weight factors;

[0049] The signal detection threshold is dynamically updated according to the sensitivity coefficient K.

[0050] Preferably, the application further comprises an RNTI adaptive detection method in an NR network environment, comprising the following steps:

[0051] Step 1: Real-time acquisition of channel state parameters, user equipment signal strength and network load data in the NR network environment by the data acquisition module, and sending the acquired data to the preprocessing module;

[0052] Step 2: The channel state parameters are denoised, the user equipment signal strength is normalized, and the network load data is time-aligned by the preprocessing module, and a preprocessed data set is obtained;

[0053] Step three: extract a multi-dimensional feature vector from the pre-processed data set by means of a feature extraction module, the multi-dimensional feature vector including time domain features, frequency domain features and spatial domain features, and input the multi-dimensional feature vector into an adaptive adjustment module;

[0054] Step four: dynamically adjust the RNTI detection parameters based on the multi-dimensional feature vector by the adaptive adjustment module, the detection parameters including detection window length, signal detection threshold and resource block allocation weight, generate adaptive parameter configuration instructions;

[0055] Step five: according to the adaptive parameter configuration instructions, a blind detection algorithm is executed by using the detection module, and the RNTI of the user equipment is identified in combination with the pre-trained neural network model, and a candidate RNTI set is output;

[0056] Step six: use the verification module to perform redundancy check and conflict detection on the candidate RNTI set, filter out an effective RNTI list, and send the effective RNTI list to the network scheduling end through the processor.

[0057] Compared with the prior art, the beneficial effects of the present application are:

[0058] The present application can effectively remove noise and interference in the data and improve data quality by real-time acquisition of channel state parameters, user equipment signal strength and network load data through the data acquisition module, and denoising, normalization and time sequence alignment processing of the data by the preprocessing module, providing accurate data basis for subsequent feature extraction and detection. The feature extraction module extracts a multi-dimensional feature vector from the pre-processed data set, including time domain, frequency domain and spatial domain features, which comprehensively reflects the characteristics of the signal. The adaptive adjustment module dynamically adjusts the RNTI detection parameters based on these feature vectors, such as detection window length, signal detection threshold and resource block allocation weight, so that the detection parameters can adapt to different network environments. In the case of serious channel fading, the adaptive adjustment module can appropriately increase the detection window length to improve the signal capture ability; in the case of weak signal strength, the signal detection threshold is reduced to avoid missing RNTI, thereby significantly improving the accuracy of RNTI detection.

[0059] The adaptive adjustment module adopts a reinforcement learning model and a Q-learning algorithm to select optimal parameters according to expected utility values of different detection parameter combinations. When the network load fluctuation value exceeds a preset threshold, a backup parameter configuration strategy is enabled to dynamically expand the detection window length and reduce the signal detection threshold, thereby ensuring that the RNTI can be stably detected in the case of network load changes. The historical data analysis module stores a list of historical valid RNTIs and network environment parameters, and generates a typical scene template by analyzing the RNTI distribution pattern through a clustering algorithm. When the current network environment matches the typical scene, the corresponding detection parameter configuration is directly called, which greatly improves the adaptation speed of the system to different network scenes and reduces the time overhead of parameter adjustment.

[0060] Accurate detection of RNTI is the basis for reasonable scheduling of network resources. The verification module of the present application performs redundancy check and conflict detection on the candidate RNTI set, filters out the valid RNTI list and sends it to the network scheduling end, ensuring that the RNTI information obtained by the network scheduling end is accurate and reliable, avoiding resource allocation errors caused by RNTI errors, and improving the utilization efficiency of network resources. The adaptive adjustment module dynamically adjusts the resource block allocation weight, so that the network resources can be reasonably allocated according to the actual needs of the user equipment. In the case of good signal strength and high channel quality of user equipment, more resource blocks are allocated to improve the communication rate of users; when the signal is weak or the network load is high, the resource allocation is reasonably adjusted to ensure the overall performance of the network, optimize the network resource scheduling, and improve the communication experience of users.

[0061] The dynamic threshold setting module adjusts the sensitivity coefficient of the signal detection threshold according to the real-time network load fluctuation value, and dynamically updates the signal detection threshold. This avoids the problem of excessive detection or missed detection caused by fixed threshold in different network environments, reduces invalid detection operations, reduces detection overhead, and improves detection efficiency. The detection module adopts a blind detection algorithm combining energy detection method and matching filter, which can quickly exclude invalid signals in the preliminary screening and symbol level alignment process, reduce the data amount processed by the subsequent convolutional neural network (CNN) model, and further reduce the computational complexity and time overhead of detection. BRIEF DESCRIPTION OF DRAWINGS

[0062] Fig. 1 The working principle diagram of the system described in the present application;

[0063] Fig. 2 The working flowchart of the data acquisition module;

[0064] Fig. 3 The working flowchart of the adaptive adjustment module. DETAILED DESCRIPTION

[0065] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0066] Please refer to Figs. 1-3 The present application provides a technical solution: an RNTI adaptive detection system in an NR network environment, which comprises:

[0067] The system is mainly composed of a processor, a data acquisition module, a preprocessing module, a feature extraction module, an adaptive adjustment module, a detection module and a verification module. The data acquisition module collects channel state parameters, user equipment signal strength and network load data in real time under the NR network environment, and transmits these data to the preprocessing module. The preprocessing module performs noise reduction processing on the channel state parameters, normalizes the user equipment signal strength, and simultaneously performs time sequence alignment processing on the network load data, thereby obtaining a preprocessed data set. The feature extraction module extracts a multi-dimensional feature vector including time domain features, frequency domain features and spatial domain features from the preprocessed data set, and inputs it into the adaptive adjustment module. The adaptive adjustment module dynamically adjusts RNTI detection parameters, including detection window length, signal detection threshold and resource block allocation weight, according to the multi-dimensional feature vector, and then generates an adaptive parameter configuration instruction. The detection module executes a blind detection algorithm according to the instruction, identifies the RNTI of the user equipment in combination with a pre-trained neural network model, and outputs a candidate RNTI set. The verification module performs redundancy check and conflict detection on the candidate RNTI set, screens out an effective RNTI list, and finally the processor sends the effective RNTI list to the network scheduling end.

[0068] The present application will be further described below in combination with Examples 1 to 5:

[0069] Example 1:

[0070] When the data acquisition module is running, it acquires the channel quality indicator CQI, reference signal received power RSRP and physical layer resource block occupation rate of the NR network. After acquiring the CQI, it matches it with a preset standard channel quality mapping table, thereby obtaining a channel state classification value. In this process, the preset standard channel quality mapping table is established in advance, which corresponds different ranges of CQI values to corresponding channel state classifications, such as mapping CQI values within a certain interval to different classifications such as “good”, “general” and “poor”, facilitating subsequent evaluation of the channel state.

[0071] For RSRP, the data collection module calculates the difference between it and the dynamic signal strength baseline to obtain the signal strength offset value. The dynamic signal strength baseline is not a fixed value, but is dynamically adjusted according to historical data and real-time changes of the network. For example, the system adjusts the baseline according to the average RSRP value over a period of time, combined with factors such as the current network load and user distribution, to more accurately reflect the changes in signal strength.

[0072] In processing the physical layer resource block occupancy rate, the data collection module compares it with historical data at the same period to obtain the network load fluctuation value. Historical data at the same period is the resource block occupancy rate data collected and stored by the system in the past same time period, and through comparison, the fluctuation degree of the current network load compared with the historical situation can be directly observed.

[0073] If the channel state classification value, signal strength offset value or network load fluctuation value exceeds the corresponding preset threshold value, the data collection module will generate a network environment abnormality marker. These preset threshold values are determined through a large amount of experimental data and actual network operation experience. For example, through analysis of a large amount of network environment data, it is determined that when the channel state classification value reaches a certain specific level, or the signal strength offset value exceeds a certain numerical range, or the network load fluctuation value exceeds a certain proportion, the network environment is considered to be abnormal, and the network environment abnormality marker generated at this time will be an important basis for subsequent processing, reminding the system that special detection parameter adjustment or other measures may need to be taken.

[0074] Embodiment 2:

[0075] The preprocessing module includes different processing methods for channel state parameters, user equipment signal strength and network load data. For channel state parameters, wavelet transform is used to filter out high-frequency noise to generate denoised channel parameters. Wavelet transform is a time-frequency analysis method that can effectively separate different frequency components in a signal. In the NR network environment, channel state parameters may be disturbed by various high-frequency noise, which will affect the accurate judgment of channel state in the subsequent. Through wavelet transform, high-frequency noise can be extracted and removed from channel state parameters, and useful signal components can be retained, so that more accurate denoised channel parameters can be obtained. For example, in actual application, the multi-resolution analysis characteristic of wavelet transform is used to decompose the channel state parameters into different frequency subbands, then the noise in the high-frequency subband is threshold processed, and finally the denoised channel parameters are reconstructed through inverse wavelet transform.

[0076] For user equipment signal strength, the preprocessing module performs dynamic range compression through range difference normalization algorithm to obtain a normalized signal strength sequence. The formula of range difference normalization algorithm is: where X is the original user equipment signal strength value, X minand X max respectively are the minimum and maximum values in the collected signal strength data. Through this algorithm, the signal strengths of different user equipment are uniformly mapped into the interval [0, 1], eliminating the dimensional differences caused by factors such as hardware differences, making subsequent analysis and comparison of signal strengths more reasonable and accurate.

[0077] For network load data, the preprocessing module uses a sliding window mechanism to segment time series and align with the system clock, forming time series aligned load data. The size of the sliding window is set according to the characteristics and needs of actual network data. For example, set a sliding window of length n, the window slides on the time series one time unit at a time, and the data in the window is processed as a segment. Then, by synchronizing with the system clock, the load data of different time periods is aligned in time, ensuring the consistency of the time dimension in subsequent analysis, facilitating feature extraction and analysis based on time series.

[0078] Embodiment 3:

[0079] In the implementation process, the feature extraction module uses autocorrelation function to calculate the periodicity of the signal in the time domain, generating time domain periodicity coefficients. The calculation formula of the autocorrelation function is: Where x(t) is the signal in the time domain, T is the observation time length of the signal, and τ is the time delay. By calculating the autocorrelation function, the similarity of the signal at different time points can be measured, and thus the periodicity of the signal can be obtained. For example, in the NR network, the signal of the user equipment may have a certain periodicity, and by calculating the autocorrelation function, this periodicity feature can be accurately extracted, generating time domain periodicity coefficients, which provide a basis for subsequent detection parameter adjustment.

[0080] For frequency domain features, the feature extraction module uses fast Fourier transform to extract the energy ratio of the main frequency component, generating a frequency energy distribution vector. Fast Fourier transform (FFT) is an efficient algorithm for calculating discrete Fourier transform (DFT), which can quickly convert time domain signals to frequency domain. In the frequency domain, the proportion of the energy of the main frequency component to the total energy is calculated, and thus the frequency energy distribution vector is obtained. This vector reflects the energy distribution of the signal at different frequencies, which is of great significance for analyzing the frequency characteristics and interference of the signal.

[0081] In terms of spatial domain features, the feature extraction module uses the covariance matrix to analyze the spatial correlation of multi-antenna signals and generates a spatial correlation matrix. The covariance matrix can measure the degree of linear correlation between multiple variables. In a multi-antenna system, there is a certain correlation between the signals received by different antennas. By calculating the covariance matrix, the spatial correlation information between these signals can be obtained, and a spatial correlation matrix can be generated. This matrix plays an important role in optimizing detection parameters such as resource block allocation weights.

[0082] The adaptive adjustment module inputs the multi-dimensional feature vector into the reinforcement learning model after receiving it, and calculates the expected utility value of different detection parameter combinations through the Q-learning algorithm. Q-learning algorithm is a model-free reinforcement learning algorithm that finds the optimal strategy through continuous trial and learning. In this invention, the expected utility value under different combinations of detection window length, signal detection threshold, and resource block allocation weight is calculated through the Q-learning algorithm. According to the principle of maximizing expected utility value, the optimal detection parameter combination is selected. When the network load fluctuation value exceeds the preset threshold, the backup parameter configuration strategy is enabled, and the detection window length is dynamically expanded and the signal detection threshold is reduced. This is because when the network load is high, the possibility of signal interference and conflict increases, and expanding the detection window length can increase the time range of detection and improve the probability of detecting RNTI. Reducing the signal detection threshold can make the detection more sensitive and avoid missing some weak but effective signals.

[0083] Example 4:

[0084] This embodiment describes the working process of the detection module and the verification module in detail. Its role is to accurately identify the RNTI of user equipment and filter out the effective RNTI list through efficient detection algorithms and strict verification mechanisms, ensuring the accuracy and reliability of network scheduling.

[0085] The process of the detection module executing the blind detection algorithm is as follows: the energy detection method is used in the frequency domain to preliminarily screen potential RNTI frequency points. The energy detection method is a method of detecting based on the energy characteristics of a signal. In the frequency domain of the NR network, different RNTI signals will have different energy distributions at specific frequency points. By detecting the energy of the frequency domain signal, an energy threshold is set, and when the signal energy of a certain frequency point exceeds the threshold, it is preliminarily screened as a potential RNTI frequency point. This process can quickly screen out frequency points that may have RNTI signals from a large number of frequency points, reducing the workload of subsequent processing. In the time domain, a matched filter is used to align the candidate frequency points at the symbol level to generate a time domain synchronization signal. The matched filter is a filter used at the receiving end to improve the signal-to-noise ratio, and its characteristics match those of the transmitted signal. For the candidate frequency points preliminarily screened out, processing through the matched filter can make the received signal in the time domain synchronized with the symbol of the transmitted signal to generate a time domain synchronization signal. This step is crucial for accurately identifying RNTI, because only when the signal is synchronized, can the subsequent neural network model correctly identify the RNTI encoding mode.

[0086] The time domain synchronization signal is input into a convolutional neural network (CNN) model to identify the RNTI encoding mode and output a candidate RNTI set. The convolutional neural network (CNN) has strong feature extraction and pattern recognition capabilities. In the present application, the CNN model is pre-trained with a large number of RNTI sample data to learn the characteristics of different RNTI encoding modes. When the time domain synchronization signal is input into the CNN model, the model can identify the RNTI encoding mode in the signal according to the characteristics it has learned, thereby outputting a candidate RNTI set.

[0087] The verification module processes the candidate RNTI set, first performs a cyclic redundancy check on each RNTI and removes items that fail the check. Cyclic redundancy check (CRC) is a commonly used error detection method that generates a check code by performing a specific polynomial operation on the data. When sending RNTI, its CRC check code is also sent. At the receiving end, the received RNTI is recalculated for CRC check code and compared with the received check code. If the two are not consistent, it means that the RNTI may have errors during transmission and will be removed.

[0088] Next, the verification module records the allocated RNTI through a hash table and detects the conflict between the candidate RNTI and the allocated RNTI, and removes the conflicting items. The hash table is a high-efficiency data structure used for fast data lookup and insertion. In the present application, the hash table is used to record the RNTI that has been allocated in the network. For each RNTI in the candidate RNTI set, a search is performed in the hash table. If the RNTI is found to have been allocated, it means that there is a conflict and it will be removed from the candidate set.

[0089] Finally, the remaining RNTIs are arranged in descending order of signal strength, and the first N are selected as the effective RNTI list. The signal strength reflects the communication quality between the user equipment corresponding to the RNTI and the base station to some extent. Arranging the remaining RNTIs in descending order of signal strength and selecting the first N as the effective RNTI list can preferentially select user equipment with better communication quality, improving the efficiency and quality of network scheduling. The value of N is set according to the actual demand and performance requirements of the network, for example, when the network load is low, the value of N can be appropriately increased to access more user equipment; when the network load is high, the value of N can be reduced to ensure the communication quality of critical user equipment.

[0090] Embodiment 5:

[0091] The historical data analysis module stores the historical effective RNTI list and the corresponding network environment parameters when running. These historical data are accumulated by the system in the long-term running process, including the effective RNTI list at different time points and the channel state parameters, user equipment signal strength, network load data and other network environment parameters at that time. Through the storage of these historical data, a wealth of materials is provided for subsequent analysis.

[0092] Then, the historical data analysis module analyzes the RNTI distribution pattern in the historical data through a clustering algorithm to generate a typical scene template. The clustering algorithm is an unsupervised learning algorithm that can divide data into different categories according to similarity. In this invention, the clustering algorithm is used to analyze the RNTI distribution in the historical data, and network environment data with similar distribution patterns are classified into one category to form a typical scene template. For example, according to different network load conditions, channel quality and other factors, the historical data are divided into different typical scene templates such as "high load-good channel" and "low load-poor channel".

[0093] When the similarity between the current network environment parameters and any typical scene template exceeds a preset threshold, the historical data analysis module directly calls the detection parameter configuration corresponding to the template. The similarity can be calculated in various ways, such as Euclidean distance, cosine similarity, etc. The preset threshold is determined through experiments and experience. When the similarity between the current network environment parameters and a certain typical scene template exceeds the threshold, it means that the current network environment is similar to the typical scene, so the detection parameter configuration corresponding to the template can be directly called without the need for complex parameter adjustment, improving the response speed and efficiency of the detection system.

[0094] The dynamic threshold setting module adjusts the sensitivity coefficient of the signal detection threshold according to the real-time network load fluctuation value, and the calculation formula is: where L current is the current signal strength offset value, Lbase is the baseline signal intensity, V load is the network load fluctuation value, V max is the maximum allowed fluctuation value, and a and β are weight factors. The values of the weight factors a and β are adjusted according to the actual situation and performance requirements of the network. For example, in a scenario where the change in signal intensity has a greater impact on the detection result, the value of a can be appropriately increased; in a scenario where the network load fluctuation has a greater impact on the detection result, the value of β can be appropriately increased.

[0095] The dynamic threshold setting module dynamically updates the signal detection threshold according to the sensitivity coefficient K. When the network load fluctuation is large, the sensitivity coefficient K calculated by the above formula will change accordingly, and the signal detection threshold is adjusted according to the K value. For example, when the network load fluctuation value V load increases, the value of K may increase, at which time the signal detection threshold is correspondingly reduced, making the detection system more sensitive and able to detect weaker signals; conversely, when the network load fluctuation value is small, the signal detection threshold is appropriately increased, reducing the probability of false detection.

[0096] It should be noted that, in this document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0097] Although embodiments of the present application have been shown and described, it is to be understood that various modifications, substitutions, replacements and changes can be made to these embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. An RNTI adaptive detection system in an NR network environment, characterized in that, The application comprises a processor, a data acquisition module, a preprocessing module, a feature extraction module, an adaptive adjustment module, a detection module, and a verification module. The data acquisition module acquires channel state parameters, user equipment signal strength, and network load data in real time under an NR network environment, and sends the acquired data to the preprocessing module. The preprocessing module performs noise reduction processing on the channel state parameters, normalization processing on the user equipment signal strength, and time series alignment processing on the network load data, to obtain a preprocessed data set. The feature extraction module extracts a multi-dimensional feature vector from the preprocessed data set, including time domain features, frequency domain features, and spatial domain features, and inputs the multi-dimensional feature vector into the adaptive adjustment module. The adaptive adjustment module dynamically adjusts RNTI detection parameters based on the multi-dimensional feature vector, including a detection window length, a signal detection threshold, and a resource block allocation weight, to generate an adaptive parameter configuration instruction. The detection module executes a blind detection algorithm according to the adaptive parameter configuration instruction, identifies the RNTI of the user equipment in combination with a pre-trained neural network model, and outputs a candidate RNTI set. The verification module performs redundancy checking and conflict detection on the candidate RNTI set, filters out an effective RNTI list, and sends the effective RNTI list to a network scheduling end via the processor. 2.The RNTI adaptive detection system in a NR network environment of claim 1, wherein, The specific operation process of the data acquisition module is as follows: The channel quality indicator (CQI), reference signal received power (RSRP), and physical layer resource block occupation rate of the NR network are acquired. The CQI is matched with a preset standard channel quality mapping table to obtain a channel state classification value. The RSRP is subtracted from a dynamic signal strength baseline to obtain a signal strength offset value. The resource block occupation rate is compared with historical same-period data to obtain a network load fluctuation value. If the channel state classification value, the signal strength offset value, or the network load fluctuation value exceeds a corresponding preset threshold, a network environment abnormality marker is generated. 3.The RNTI adaptive detection system in a NR network environment of claim 1, wherein, The preprocessing module comprises: Wavelet transform is used to filter out high-frequency noise from the channel state parameters to generate noise-reduced channel parameters. A dynamic range compression algorithm is used to compress the user equipment signal strength to obtain a normalized signal strength sequence. A sliding window mechanism is used to segment the network load data in a time series, and the segmented data is synchronized and aligned with a system clock to form time series aligned load data.

4. The RNTI adaptive detection system in a NR network environment of claim 1, wherein, The specific implementation of the feature extraction module comprises: An autocorrelation function is used to calculate the periodicity of the time domain features to generate time domain periodicity coefficients. Fast Fourier transform is used to extract the main frequency component energy ratio of the frequency domain features to generate a frequency energy distribution vector. A covariance matrix is used to analyze the spatial correlation of the multi-antenna signal to generate a spatial correlation matrix. 5.The RNTI adaptive detection system in a NR network environment of claim 1, wherein, The operation process of the adaptive adjustment module comprises: The multi-dimensional feature vector is input into a reinforcement learning model, and a Q-learning algorithm is used to calculate the expected utility value of different detection parameter combinations. According to the maximum expected utility value principle, the optimal detection window length, signal detection threshold, and resource block allocation weight are selected. When the network load fluctuation value exceeds the preset threshold value, a backup parameter configuration strategy is enabled, a detection window length is dynamically extended, and a signal detection threshold value is reduced.

6. The RNTI adaptive detection system in a NR network environment of claim 1, wherein, The detection module executes a blind detection algorithm in the following process: An energy detection method is used in the frequency domain to preliminarily screen potential RNTI frequency points; A matching filter is used in the time domain to perform symbol-level alignment on the candidate frequency points to generate a time-domain synchronization signal; The time-domain synchronization signal is input into a convolutional neural network (CNN) model to identify an RNTI encoding mode and output a candidate RNTI set.

7. The RNTI adaptive detection system in a NR network environment of claim 1, wherein, The verification module includes: Each RNTI in the candidate RNTI set is subjected to a cyclic redundancy check, and items that fail the check are removed; A hash table is used to record allocated RNTIs, and the candidate RNTIs are detected for conflict with the allocated RNTIs, and conflict items are removed; The remaining RNTIs are arranged in descending order of signal strength, and the first N RNTIs are selected as an effective RNTI list. 8.The RNTI adaptive detection system in a NR network environment of claim 1, wherein, The historical data analysis module also includes the following process: The historical effective RNTI list and corresponding network environment parameters are stored; A clustering algorithm is used to analyze the RNTI distribution mode in the historical data to generate a typical scenario template; When the similarity between the current network environment parameters and any typical scenario template exceeds a preset threshold value, the detection parameter configuration corresponding to the template is directly called. 9.The RNTI adaptive detection system in a NR network environment of claim 1, wherein, The dynamic threshold setting module also includes the following process: The sensitivity coefficient of the signal detection threshold value is adjusted according to the real-time network load fluctuation value, and the calculation formula is: where L current is the current signal strength offset value, L base is the baseline signal strength, V load is the network load fluctuation value, V max is the maximum allowed fluctuation value, and a and β are weight factors; The signal detection threshold value is dynamically updated according to the sensitivity coefficient K.

10. An adaptive detection method for RNTI in an NR network environment, characterized in that, The following steps are included: Step one: real-time acquisition of channel state parameters, user equipment signal strength, and network load data in an NR network environment by a data acquisition module, and sending the acquired data to a preprocessing module; Step two: noise reduction processing of the channel state parameters, normalization processing of the user equipment signal strength, and time sequence alignment processing of the network load data by the preprocessing module to obtain a preprocessed data set; Step three: extraction of a multi-dimensional feature vector from the preprocessed data set by a feature extraction module, the multi-dimensional feature vector including time domain features, frequency domain features, and spatial domain features, and input of the multi-dimensional feature vector into an adaptive adjustment module; Step four: dynamic adjustment of RNTI detection parameters by the adaptive adjustment module based on the multi-dimensional feature vector, the detection parameters including a detection window length, a signal detection threshold value, and a resource block allocation weight, and generation of an adaptive parameter configuration instruction; Step five: execution of a blind detection algorithm by the detection module according to the adaptive parameter configuration instruction, identification of the RNTI of a user equipment by combining a pre-trained neural network model, and output of a candidate RNTI set; Step six: redundancy check and conflict detection of the candidate RNTI set by the verification module to screen an effective RNTI list, and sending of the effective RNTI list to a network scheduling end by a processor.

Images