Wireless communication interference automatic identification and adaptive optimization system and method

Abstract

The invention provides a wireless communication interference automatic identification and adaptive optimization system and method, and the method comprises the steps: a signal data collection module is used for carrying out the collection of original signal data; the signal analysis and identification module is used for preprocessing the collected original signal data to obtain preprocessed signal data; the deep learning algorithm module is used for carrying out model training through the neural network model building module based on the preprocessed signal data, carrying out feature extraction through the interference feature extraction module, and carrying out feature extraction according to the trained model and the extracted features; self-adaptive adjustment processing is carried out through the self-adaptive adjustment module, and signal optimization processing is carried out through the self-adaptive optimization module. According to the invention, wireless communication interference automatic identification and adaptive optimization functions can be realized.

Description

Technical Field

[0001] The present application relates to the field of wireless communication technology, and in particular to a system and method for automatic identification and adaptive optimization of wireless communication interference. Background Art

[0002] Wireless communication system is one of the indispensable infrastructures in modern society. With the popularization of mobile Internet and the rapid development of wireless communication technology, people have an increasingly higher demand for wireless communication systems. However, in practical applications, interference problems in wireless communication systems have always been one of the main challenges limiting system performance, resulting in problems such as unstable wireless network signals, limited coverage, and decreased signal quality.

[0003] At present, the types of wireless communication interference mainly include: co-channel interference (CCI), adjacent channel interference (ACI), intermodulation interference (IMI), narrowband interference (NBI), wideband interference (Wideband Interference), etc. The main causes of interference include: hardware problems, improper network planning, environmental factors, human factors, etc.

[0004] Therefore, how to reduce the impact of interference factors on wireless communications has become a problem that needs to be solved. Summary of the invention

[0005] The technical problem to be solved by the present application is to provide a wireless communication interference automatic identification and adaptive optimization system and method in view of the above-mentioned deficiencies in the prior art, so as to solve the problems existing in the prior art.

[0006] In a first aspect, the present application provides a wireless communication interference automatic identification and adaptive optimization system, the system comprising: a signal data acquisition module, a signal analysis and identification module, a neural network model construction module, a deep learning algorithm module, an interference feature extraction module, an adaptive adjustment module, and an adaptive optimization module;

[0007] The signal data acquisition module is used to collect original signal data;

[0008] The signal analysis and identification module is used to preprocess the collected original signal data to obtain preprocessed signal data;

[0009] The deep learning algorithm module is used to perform model training through the neural network model construction module based on the preprocessed signal data, perform feature extraction through the interference feature extraction module, and, according to the trained model and the extracted features, perform adaptive adjustment processing through the adaptive adjustment module and perform signal optimization processing through the adaptive optimization module.

[0010] In some embodiments, the deep learning algorithm module includes at least one of a decision tree algorithm unit, a logistic regression algorithm unit, a support vector machine algorithm unit, and a neural network algorithm unit.

[0011] In some embodiments, the interference feature extraction module is used to extract at least one of interference time domain features, interference frequency features, interference space features, and internal and external interference features.

[0012] In some embodiments, the adaptive adjustment module performs adaptive adjustment processing, including at least one of adjusting wireless signal transmission power, changing channel allocation mode, and adjusting the direction of the receiving antenna.

[0013] In some embodiments, the adaptive optimization module performs signal optimization processing, including at least one of interference prediction, interference suppression, and filter control.

[0014] In a second aspect, the present application provides a method for automatic identification and adaptive optimization of wireless communication interference, the method comprising:

[0015] Carry out raw signal data acquisition;

[0016] Preprocessing the collected original signal data to obtain preprocessed signal data;

[0017] Based on the preprocessed signal data, model training and feature extraction are performed through a deep learning algorithm, and adaptive adjustment processing and signal optimization processing are performed according to the trained model and the extracted features.

[0018] In some embodiments, the deep learning algorithm includes at least one of a decision tree algorithm, a logistic regression algorithm, a support vector machine algorithm, and a neural network algorithm.

[0019] In some embodiments, the extracted features include at least one of interference time domain features, interference frequency features, interference space features, and internal and external interference features.

[0020] In some embodiments, the adaptive adjustment process includes at least one of adjusting the wireless signal transmission power, changing the channel allocation method, and adjusting the direction of the receiving antenna.

[0021] In some embodiments, the signal optimization processing includes at least one of interference prediction, interference suppression, and filter control.

[0022] The present application provides a wireless communication interference automatic identification and adaptive optimization system and method, the system includes: a signal data acquisition module, a signal analysis and identification module, a neural network model construction module, a deep learning algorithm module, an interference feature extraction module,

[0023] Adaptive adjustment module, adaptive optimization module; the signal data acquisition module is used to collect original signal data; the signal analysis and identification module is used to preprocess the collected original signal data to obtain preprocessed signal data; the deep learning algorithm module is used to perform model training based on the preprocessed signal data through the neural network model construction module, perform feature extraction through the interference feature extraction module, and, according to the trained model and the extracted features, perform adaptive adjustment processing through the adaptive adjustment module and perform signal optimization processing through the adaptive optimization module. The present application obtains a large amount of signal data through the signal data acquisition module, the signal analysis and identification module analyzes, identifies and preprocesses the signal, the deep learning algorithm module learns and understands the features in the data through the neural network model construction module, and performs adaptive adjustment and optimization, extracts interference time domain features, interference frequency features, interference space features, internal and external interference features through the interference feature extraction module, and performs adaptive adjustment and signal optimization based on these features through the adaptive adjustment module and the adaptive optimization module, the adaptive adjustment includes dynamically adjusting the transmission power of the wireless signal, changing the channel allocation method, and adjusting the direction of the receiving antenna, and the adaptive optimization includes interference prediction, interference suppression, and filter control, thereby realizing the automatic identification and adaptive optimization functions of wireless communication interference. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0025] Figure 1 A schematic diagram of a wireless communication interference automatic identification and adaptive optimization system provided in an embodiment of the present application;

[0026] Figure 2 Another schematic diagram of the wireless communication interference automatic identification and adaptive optimization system provided in an embodiment of the present application;

[0027] Figure 3 A schematic diagram of a method for automatic identification and adaptive optimization of wireless communication interference provided in an embodiment of the present application.

[0028] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the technical solution of the present application, the implementation mode of the present application will be further described in detail below with reference to the accompanying drawings.

[0030] It should be understood that the specific embodiments and drawings described herein are only used to explain the present application, rather than to limit the present application.

[0031] It can be understood that, in the absence of conflict, the various embodiments in the present application and the various features in the embodiments can be combined with each other.

[0032] It can be understood that, for the convenience of description, the drawings of the present application only show the parts related to the present application, while the parts unrelated to the present application are not shown in the drawings.

[0033] It can be understood that each unit and module involved in the embodiments of the present application may correspond to only one physical structure, or may be composed of multiple physical structures, or multiple units and modules may be integrated into one physical structure.

[0034] It can be understood that the terms "first", "second", etc. in the embodiments of the present application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0035] It is understandable that, in the absence of conflict, the functions and steps marked in the flowcharts and block diagrams of the present application may occur in an order different from that marked in the drawings.

[0036] It is understood that the flowcharts and block diagrams of the present application illustrate the possible architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present application. Among them, each box in the flowchart or block diagram may represent a unit, module, program segment, code, which contains executable instructions for implementing the specified functions. Moreover, each box or combination of boxes in the block diagram and flowchart may be implemented by a hardware-based system that implements the specified functions, or by a combination of hardware and computer instructions.

[0037] It can be understood that the units and modules involved in the embodiments of the present application can be implemented by software or hardware, for example, the units and modules can be located in a processor.

[0038] Interference in wireless communication systems is an important factor affecting communication quality. The types and causes of wireless communication interference mainly include the following:

[0039] 1. Types of interference

[0040] 1.1 Co-Channel Interference (CCI), when two or more signals are transmitted on the same frequency, they interfere with each other. This situation is common in environments with limited frequency resources.

[0041] 1.2 Adjacent Channel Interference (ACI) occurs when the signal leaks into an adjacent channel. This is usually caused by inadequate filter design or nonlinear devices.

[0042] 1.3 Intermodulation Interference (IMI), which is caused by nonlinear circuits or devices. When two or more signals are transmitted simultaneously, their frequencies mix to produce new frequencies, which may fall within the useful signal band of the system.

[0043] 1.4 Narrowband Interference (NBI) This interference is usually caused by signals of a single frequency or narrow bandwidth, such as radio broadcasts or radar signals.

[0044] 1.5 Wideband Interference: This type of interference covers a wider frequency range and may be a mixture of multiple signals.

[0045] 2. Causes of interference

[0046] 2.1 Hardware problems, such as nonlinear characteristics of the device, insufficient antenna directivity or gain mismatch, poor filter performance, etc.

[0047] 2.2 Improper network planning, such as unreasonable channel allocation, excessive overlapping areas of base station coverage, and poor radio frequency management.

[0048] 2.3 Environmental factors, such as multipath propagation caused by physical obstacles (such as buildings) and meteorological conditions (such as fog and rain) affecting signal propagation.

[0049] 2.4 Human factors, such as illegal or unauthorized use of wireless devices, intentional interference (such as signal jammers), etc.

[0050] In order to improve the quality of wireless communications, the present application proposes a system and method for automatic identification and adaptive optimization of wireless communication interference, which realizes automatic identification and adaptive optimization of wireless communication interference by collecting signal data and performing data analysis and processing.

[0051] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0052] Figure 1 A schematic diagram of a wireless communication interference automatic identification and adaptive optimization system provided in an embodiment of the present application, Figure 2 Another schematic diagram of the wireless communication interference automatic identification and adaptive optimization system provided in the embodiment of the present application is as follows Figure 1 as well as Figure 2 As shown, the present application provides a wireless communication interference automatic identification and adaptive optimization system, the system comprising: a signal data acquisition module 1, a signal analysis and identification module 2, a neural network model construction module 3, a deep learning algorithm module 4, an interference feature extraction module 5, an adaptive adjustment module 6, and an adaptive optimization module 7;

[0053] Among them, the signal data acquisition module 1 is signal-connected with the signal analysis and identification module 2, and the deep learning algorithm module 4 is signal-connected with the signal analysis and identification module 2, the neural network model construction module 3, the interference feature extraction module 5, the adaptive adjustment module 6, and the adaptive optimization module 7 respectively.

[0054] The signal data acquisition module 1 includes electronic components for signal data acquisition, and is used for acquiring original signal data.

[0055] For example, common electronic components used for wireless communication signal data collection mainly include the following:

[0056] (1) Antenna: The antenna is used to receive or transmit wireless signals. During the data collection process, the antenna is responsible for capturing wireless signals in the air.

[0057] (2) RF front end: The RF front end usually includes RF amplifiers, RF filters, and RF switches, which are used to amplify the received signal, filter out unnecessary frequency components, and pass the signal to the next level of processing.

[0058] (3) Downconverter: The downconverter converts the RF signal into a lower frequency signal, usually an intermediate frequency (IF) or baseband signal, for subsequent processing.

[0059] (4) Analog-to-Digital Converters (ADCs). ADCs convert analog signals into digital signals, which is a key step in wireless communication signal data acquisition.

[0060] (5) Digital Signal Processor (DSP): DSP is used to process the digital signal converted by ADC and perform operations such as filtering, demodulation, and decoding.

[0061] The signal analysis and identification module 2 is used to pre-process the collected original signal data to obtain pre-processed signal data;

[0062] Specifically, preprocessing of raw wireless communication signals is an important step in signal processing, the purpose of which is to improve signal quality and make it more suitable for subsequent processing and analysis. The following are some common methods for preprocessing raw wireless communication signals:

[0063] (1) Signal amplification: increasing the power of the signal to facilitate subsequent processing, especially when the signal is weak.

[0064] (2) Filtering: Use various filters (such as low-pass, high-pass, band-pass, and band-stop filters) to remove noise and unnecessary frequency components from the signal.

[0065] (3) Downconversion: converting the radio frequency (RF) signal to a lower frequency, usually an intermediate frequency (IF) or baseband, for digital processing.

[0066] (4) Gain Control: Automatically or manually adjust the signal gain to keep the signal within an appropriate level range to avoid the signal being too strong or too weak.

[0067] (5) Synchronization, including symbol synchronization, frame synchronization, and time synchronization, ensures that the receiver correctly interprets the transmitted signal.

[0068] (6) Signal Shaping: using matched filters or other techniques to improve the waveform of the signal so that it is closer to the ideal signal shape.

[0069] (7) Equalization, which is used to compensate for the frequency selective fading of the transmission channel so that the signal has the same gain and phase at all frequencies.

[0070] (8) Denoising: using various algorithms (such as Wiener filtering, wavelet transform, Kalman filtering, etc.) to reduce the noise in the signal.

[0071] (9) Signal Separation: In a multiplexing or frequency division multiplexing system, multiple signals are separated from each other.

[0072] (10) Signal demodulation: extracting the original information, such as amplitude, frequency or phase, from the modulated signal.

[0073] By performing the preprocessing step, the performance of subsequent signal processing can be guaranteed.

[0074] The deep learning algorithm module 4 is used to perform model training based on the preprocessed signal data through the neural network model construction module 3, perform feature extraction through the interference feature extraction module 5, and, according to the trained model and the extracted features, perform adaptive adjustment processing through the adaptive adjustment module 6 and perform signal optimization processing through the adaptive optimization module 7.

[0075] In some embodiments, the deep learning algorithm module 4 includes at least one of a decision tree algorithm unit, a logistic regression algorithm unit, a support vector machine algorithm unit, and a neural network algorithm unit.

[0076] Among them, the decision tree algorithm is a simple but powerful classification and regression algorithm. Its working principle is to segment the data through a series of questions, each node represents a feature, each branch represents a decision rule, and finally reaches the leaf node to get the prediction result.

[0077] Logistic Regression Algorithm is a generalized linear regression model for binary classification problems. Although the name contains "regression", it is actually used for classification problems. The core idea is to use a logistic function (such as the Sigmoid function) to map the output of linear regression to between 0 and 1 to represent probability.

[0078] Support Vector Machine (SVM) is a machine learning algorithm used for classification and regression analysis. It separates data points of different categories by finding the best hyperplane. The core idea is to maximize the margin of the data set, that is, the distance between the separating hyperplane and the nearest data point.

[0079] Neural Network Algorithm is a computational model that imitates the way neurons in the human brain are connected. It is particularly suitable for complex nonlinear problems. Its structure consists of a large number of simple units (neurons) connected to each other, divided into input layer, hidden layer and output layer.

[0080] In some embodiments, the interference feature extraction module 5 is used to extract at least one of interference time domain features, interference frequency features, interference space features, and internal and external interference features.

[0081] Among them, the interference time domain characteristics refer to the analysis of the characteristics of the interference signal on the time axis, mainly involving the characteristics of the interference signal changing with time. The main characteristics include amplitude, duration, waveform, burstiness, and periodicity.

[0082] Interference frequency characteristics refer to the characteristics of interference signals in the frequency domain, which are usually obtained from time domain signals through methods such as Fourier transform. Interference frequency characteristics describe the frequency components and distribution of interference signals. The main characteristics include frequency components, spectrum width, center frequency, and spectrum shape.

[0083] Interference spatial characteristics refer to the characteristics of interference signals in spatial distribution. Interference spatial characteristics involve the propagation and distribution of interference signals in space. The main characteristics include directivity, spatial distribution, interference and diffraction, multipath effect, etc.

[0084] Internal and external interference characteristics include interference generated inside the system, such as thermal noise and nonlinear distortion of the equipment, as well as interference introduced by the external environment of the system, such as electromagnetic interference and radiation from other equipment.

[0085] In some embodiments, the adaptive adjustment module 6 performs adaptive adjustment processing, including at least one of adjusting the wireless signal transmission power, changing the channel allocation method, and adjusting the direction of the receiving antenna.

[0086] Among them, adjusting the wireless signal transmission power refers to changing the energy level when the wireless transmitting device sends the signal. The transmission power is dynamically adjusted through the algorithm to adapt to changes in the communication environment and needs. By increasing the signal power, the transmission distance of the signal can be increased, allowing the signal to cover a wider range. By reducing the signal power, interference with other wireless devices can be reduced, especially in a dense wireless network environment. In addition, while ensuring the quality of communication, appropriately reducing the signal power can reduce the energy consumption of the device and extend the battery life.

[0087] Changing the channel allocation method refers to reallocating the frequency channels used in wireless communication systems to optimize signal transmission. Methods include static channel allocation, dynamic channel allocation, spectrum sensing, etc. By changing the channel allocation method, different wireless devices or networks can avoid using the same channel and reduce mutual interference. Through reasonable channel allocation, spectrum resources can be used more effectively. Channel allocation is dynamically adjusted according to the interference situation in the environment and user needs.

[0088] Adjusting the receiving antenna direction means changing the direction of the antenna to optimize the strength and quality of the received signal. For example, the method uses a phased array antenna and other technologies to electronically change the direction of the antenna beam. By adjusting the antenna direction, the received signal can be enhanced in a directional manner. By optimizing the antenna direction, signal distortion caused by multipath propagation can be reduced. Adjusting the antenna direction can reduce the reception of interfering signals from a specific direction.

[0089] In some embodiments, the adaptive optimization module 7 performs signal optimization processing, including at least one of interference prediction, interference suppression, and filter control.

[0090] Interference prediction refers to predicting possible interference in the future by analyzing signal characteristics and other relevant information in the wireless environment. By predicting potential interference sources, measures can be taken in advance to avoid or mitigate the impact of interference on communications. This provides a basis for spectrum resource allocation and scheduling, and avoids sending signals to frequencies where interference may exist.

[0091] Interference suppression refers to the use of various technical means to reduce or eliminate the impact of interference signals on useful signals. Methods include frequency domain filtering, spatial domain filtering, coding technology, etc. By suppressing interference, the ratio of the power of the received useful signal to the power of interference and noise can be increased. Reducing interference can reduce the bit error rate and improve the reliability of data transmission.

[0092] Filter control refers to dynamically adjusting the filter parameters according to the wireless communication environment and signal characteristics. The filter selectively receives or suppresses the signal to reduce interference and noise. The filter parameters are adjusted to optimize the spectrum characteristics of the signal to make it more suitable for the transmission medium.

[0093] In the present application, the neural network model construction module 3 includes a deep neural network model unit and a deep learning model unit. The deep learning algorithm module 4 can train and learn a large amount of wireless signal data through the deep neural network model unit and the deep learning model unit. Through training, the neural network can learn the representation and extraction methods of signal features from the data. Once the training is completed, the neural network can automatically analyze and extract signal features based on the input wireless signal data, and perform adaptive adjustment and signal optimization.

[0094] In addition, the deep learning algorithm module 4 can analyze and model the signal data, and extract the interference time domain characteristics, interference frequency characteristics, interference space characteristics, internal and external interference characteristics through the interference feature extraction module 5, and perform adaptive adjustment and signal optimization based on these characteristics through the adaptive adjustment module 6 and the adaptive optimization module 7.

[0095] The present application provides a wireless communication interference automatic identification and adaptive optimization system, which acquires a large amount of signal data through a signal data acquisition module 1, and analyzes, identifies and preprocesses the signal through a signal analysis and identification module 2. A deep learning algorithm module 4 learns and understands the features in the data through a neural network model construction module 3, and performs adaptive adjustment and optimization. An interference feature extraction module 5 extracts interference time domain features, interference frequency features, interference space features, and internal and external interference features, and based on these features, adaptive adjustment and signal optimization are performed through an adaptive adjustment module 6 and an adaptive optimization module 7. The adaptive adjustment includes dynamically adjusting the transmission power of the wireless signal, changing the channel allocation method, and adjusting the direction of the receiving antenna. The adaptive optimization includes interference prediction, interference suppression, and filter control, thereby realizing the automatic identification and adaptive optimization functions of wireless communication interference.

[0096] Based on the above-mentioned wireless communication interference automatic identification and adaptive optimization system, the present application provides a wireless communication interference automatic identification and adaptive optimization method.

[0097] Figure 3 A schematic diagram of a method for automatic identification and adaptive optimization of wireless communication interference provided in an embodiment of the present application, such as Figure 3 As shown, the present application provides a method for automatic identification and adaptive optimization of wireless communication interference, the method comprising:

[0098] S1, collect original signal data;

[0099] S2, preprocessing the collected original signal data to obtain preprocessed signal data;

[0100] S3. Based on the preprocessed signal data, model training and feature extraction are performed through a deep learning algorithm, and adaptive adjustment processing and signal optimization processing are performed according to the trained model and the extracted features.

[0101] In some embodiments, the deep learning algorithm includes at least one of a decision tree algorithm, a logistic regression algorithm, a support vector machine algorithm, and a neural network algorithm.

[0102] In some embodiments, the extracted features include at least one of interference time domain features, interference frequency features, interference space features, and internal and external interference features.

[0103] In some embodiments, the adaptive adjustment process includes at least one of adjusting the wireless signal transmission power, changing the channel allocation method, and adjusting the direction of the receiving antenna.

[0104] In some embodiments, the signal optimization processing includes at least one of interference prediction, interference suppression, and filter control.

[0105] Specifically, first, the signal data acquisition module acquires a large amount of original signal data, the signal analysis and identification module analyzes and identifies the original signal data and performs preprocessing, and the deep learning algorithm module learns and understands the features in the data through the deep neural network model unit and the deep learning model unit of the neural network model construction module, and performs adaptive adjustment and optimization. Specifically, the deep learning algorithm module can train and learn a large amount of wireless signal data through the deep neural network model unit and the deep learning model unit. Through training, the neural network can learn the representation and extraction method of signal features from the data. Once the training is completed, the neural network can automatically analyze and extract signal features based on the input wireless signal data, and perform adaptive adjustment and signal optimization. In addition, the deep learning algorithm module can analyze and model the signal data, and extract the interference time domain features, interference frequency features, interference space features, and internal and external interference features through the interference feature extraction module, and based on these features, perform adaptive adjustment and signal optimization through the adaptive adjustment module and the adaptive optimization module.

[0106] For example, in terms of signal interference, the deep learning model unit can automatically identify and analyze the interference sources in the wireless network by learning the patterns and rules of signal interference, and propose corresponding interference elimination strategies. These strategies can include dynamically adjusting the transmission power of the wireless signal, changing the channel allocation method, and adjusting the direction of the receiving antenna (azimuth angle, elevation angle, polarization angle); in terms of coverage, deep learning technology can model and predict signal attenuation in different environments and at different distances by learning and analyzing a large amount of signal strength data. Based on such a model, the system can adaptively adjust the signal transmission power and transmission method according to the current signal strength and distance information to achieve better signal coverage. Then, in the wireless communication system, the deep learning algorithm module can be used to The interference can be suppressed to improve the system performance. The adaptive optimization module can establish a model to predict the occurrence and amplitude of interference by analyzing historical data. The receiver can be optimized and adjusted according to the predicted results to improve the communication quality. When the interference signal is transmitted to the receiver, the deep neural network model unit can analyze the characteristics of the signal and automatically identify the interference signal. The system can suppress the interference signal according to the output of the model to minimize the impact of interference on the main signal. In addition, the self-interference technology based on deep learning can also realize adaptive filtering. Traditional filters need to be designed in advance, but in actual applications, the nature of interference signals may change continuously. Through deep learning algorithms, the system can dynamically adjust the filter according to real-time signal characteristics to adapt to the processing requirements under different interference scenarios.

[0107] The present application provides a method for automatic identification and adaptive optimization of wireless communication interference, which obtains a large amount of signal data through a signal data acquisition module, analyzes, identifies and preprocesses the signal through a signal analysis and identification module, and learns and understands the features in the data through a neural network model construction module, and performs adaptive adjustment and optimization, extracts interference time domain features, interference frequency features, interference space features, and internal and external interference features through an interference feature extraction module, and performs adaptive adjustment and signal optimization based on these features through an adaptive adjustment module and an adaptive optimization module, wherein the adaptive adjustment includes dynamically adjusting the transmission power of the wireless signal, changing the channel allocation method, and adjusting the direction of the receiving antenna, and the adaptive optimization includes interference prediction, interference suppression, and filter control, thereby realizing the functions of automatic identification and adaptive optimization of wireless communication interference.

[0108] It should be understood that, although the various steps in the flowcharts in the above-described embodiments are sequentially displayed according to the indications of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and they can be executed in other orders. Moreover, at least a portion of the steps in the figure may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily to be carried out sequentially, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0109] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present application, but the present application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of the present application, and these modifications and improvements are also considered to be within the scope of protection of the present application.

Claims

1. A wireless communication interference automatic identification and adaptive optimization system, characterized in that: The system includes: a signal data acquisition module, a signal analysis and recognition module, a neural network model construction module, a deep learning algorithm module, an interference feature extraction module, an adaptive adjustment module, and an adaptive optimization module; The signal data acquisition module is used to collect original signal data; The signal analysis and identification module is used to preprocess the collected original signal data to obtain preprocessed signal data; The deep learning algorithm module is used to perform model training through the neural network model construction module based on the preprocessed signal data, perform feature extraction through the interference feature extraction module, and, according to the trained model and the extracted features, perform adaptive adjustment processing through the adaptive adjustment module and perform signal optimization processing through the adaptive optimization module.

2. The wireless communication interference automatic identification and adaptive optimization system according to claim 1 is characterized in that: The deep learning algorithm module includes at least one of a decision tree algorithm unit, a logistic regression algorithm unit, a support vector machine algorithm unit, and a neural network algorithm unit.

3. The wireless communication interference automatic identification and adaptive optimization system according to claim 1 is characterized in that: The interference feature extraction module is used to extract at least one of interference time domain features, interference frequency features, interference space features, and internal and external interference features.

4. The wireless communication interference automatic identification and adaptive optimization system according to claim 1, characterized in that: The adaptive adjustment module performs adaptive adjustment processing, including at least one of adjusting the wireless signal transmission power, changing the channel allocation method, and adjusting the direction of the receiving antenna.

5. A wireless communication interference automatic identification and adaptive optimization system according to any one of claims 1 to 4, characterized in that: The adaptive optimization module performs signal optimization processing, including at least one of interference prediction, interference suppression, and filter control.

6. A method for automatic identification and adaptive optimization of wireless communication interference, characterized in that: The method comprises: Carry out raw signal data acquisition; Preprocessing the collected original signal data to obtain preprocessed signal data; Based on the preprocessed signal data, model training and feature extraction are performed through a deep learning algorithm, and adaptive adjustment processing and signal optimization processing are performed according to the trained model and the extracted features.

7. A wireless communication interference automatic identification and adaptive optimization method according to claim 6, characterized in that: The deep learning algorithm includes at least one of a decision tree algorithm, a logistic regression algorithm, a support vector machine algorithm, and a neural network algorithm.

8. The method for automatic identification and adaptive optimization of wireless communication interference according to claim 6, characterized in that: The extracted features include at least one of interference time domain features, interference frequency features, interference space features, and internal and external interference features.

9. The method for automatic identification and adaptive optimization of wireless communication interference according to claim 6, characterized in that: The adaptive adjustment process includes at least one of adjusting the wireless signal transmission power, changing the channel allocation method, and adjusting the direction of the receiving antenna.

10. A method for automatic identification and adaptive optimization of wireless communication interference according to any one of claims 6 to 9, characterized in that: The signal optimization processing includes at least one of interference prediction, interference suppression, and filter control.

Images