Anti-interference method and system for wireless communication data extraction

Abstract

The invention discloses an anti-interference method and system for wireless communication data extraction, and relates to the technical field of wireless communication, and the method comprises the steps: collecting interference data in a wireless communication environment, and determining the type of an interference source, the method comprises the steps of collecting real-time data and historical data, collecting interference source types including man-made interference, natural interference and inter-equipment interference, preprocessing the collected real-time data and historical data, extracting interference features, identifying main interference sources and interference modes, obtaining an interference feature analysis list, and establishing an interference prediction evaluation model based on the interference feature analysis list and the historical interference data. According to the method, interference sources in a wireless communication environment and types of the interference sources are analyzed, including man-made interference, natural interference and mutual interference between devices, interference factors are accurately identified and classified, potential interference scenes are predicted in advance, and corresponding anti-interference measures are taken, so that the accuracy and integrity of data transmission are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wireless communication, and in particular to an anti-interference method and system for extracting wireless communication data. Background Art

[0002] Wireless communication data extraction usually involves capturing, decoding and analyzing data from wireless signals. These data may include text information, voice information, image information or other types of digital information. During wireless communication, data is transmitted in free space through electromagnetic wave signals. Therefore, the data extraction process needs to take into account factors such as signal transmission characteristics, noise interference and the performance of the receiving device. Communication interference can be classified according to its source and nature. The impact of these interferences on wireless communication systems is mainly reflected in the following aspects.

[0003] In the prior art, due to the complex and changeable wireless communication environment, interference sources and their types, such as human interference, natural interference, and mutual interference between devices, are constantly changing. This dynamic nature poses a great challenge to the prediction and evaluation of anti-interference methods, because it is extremely difficult to accurately simulate and predict all potential interference scenarios. This uncertainty often leads to a decrease in the quality of the received signal, which in turn affects the accuracy and completeness of data extraction and analysis. Therefore, how to effectively predict and evaluate interference scenarios to improve the accuracy and completeness of data transmission has become a problem that needs to be solved urgently. Summary of the invention

[0004] The present invention aims to provide an anti-interference method and system for extracting wireless communication data to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] In a first aspect, an anti-interference method for extracting wireless communication data comprises the following steps:

[0007] Step 1: collect interference data in the wireless communication environment and determine the type of interference source, wherein the collected interference data includes historical data and real-time data, so as to facilitate comprehensive analysis and prediction of interference scenarios. The types of interference sources include human interference, natural interference, and interference between devices. Human interference includes electromagnetic interference generated by human activities, such as the operation of electronic equipment, radio communication, etc. Natural interference includes electromagnetic interference generated by natural phenomena, such as lightning, cosmic rays, etc. Interference between devices includes interference caused by similar frequencies or mutual interference, such as co-channel interference and adjacent frequency interference;

[0008] Step 2: Preprocess the collected real-time data and historical data, and extract interference features, such as the waveform, spectrum characteristics, and duration of the interference signal, identify the main interference sources and interference modes, and obtain an interference feature analysis list; an interference recognition algorithm based on convolutional neural networks combined with multi-domain feature extraction can be used to extract interference features from time-frequency images and frequency domain sequences to improve interference recognition performance;

[0009] Step 3: Based on the interference feature analysis list and historical interference data, establish an interference prediction and evaluation model, obtain the man-made interference index, natural interference index and inter-device interference index, locate the interference source, analyze the characteristics of the interference source and its impact on the wireless communication system, determine the type of interference, and adjust the anti-interference strategy in time;

[0010] Step 4: Based on the human interference index, natural interference index and inter-device interference index, obtain the interference factor evaluation coefficient, evaluate the influence of different interference scenarios on wireless communication data extraction, evaluate the interference impact, and output the evaluation result;

[0011] Step 5: Use the interference prediction and evaluation model and the interference factor coefficient to predict abnormal conditions of wireless communication data extraction, implement anti-interference avoidance schemes based on the evaluation results, and optimize the anti-interference avoidance schemes. The anti-interference avoidance schemes can adopt wireless communication interference avoidance strategies based on fast reinforcement learning, such as learning fast strategy hill climbing learning methods, to quickly respond to interference changes and significantly improve the reliability of system transmission under fast time-varying malicious interference. Optimizing anti-interference avoidance schemes includes adjusting the transmission power, changing the communication frequency, or using other anti-interference technologies to ensure the reliability and efficiency of communications.

[0012] A further improvement of the technical solution of the present invention is that in step 1, the process of determining the interference source type is:

[0013] Step 101, determine the scope and target of interference data in the wireless communication environment, including the type of interference data to be collected, the type of interference source, and the frequency and accuracy of interference data; such as monitoring once every hour, day, or week

[0014] Step 102: Deploy monitoring equipment according to monitoring requirements to form a monitoring network, and use the deployed monitoring equipment to monitor the interference in the wireless communication environment in real time, and transmit it to the data center for analysis in real time; monitoring equipment such as spectrum analyzers, radio monitoring stations, etc., and ensure that the monitoring equipment has sufficient accuracy and sensitivity to accurately capture and record interference signals.

[0015] Step 103, extracting interference events that occurred in the past from the historical records of the data center, including time, location, interference source type, intensity, and frequency, and obtaining long-term interference data to analyze interference patterns and trends;

[0016] Step 104, organize and analyze the collected real-time data and historical data to extract key information, including using an interference recognition algorithm based on a convolutional neural network combined with multi-domain feature extraction, and extracting interference features from both the time-frequency image and the frequency domain sequence through CNN to improve interference recognition performance.

[0017] A further improvement of the technical solution of the present invention is that in step 2, the process of obtaining the interference feature analysis list is as follows:

[0018] Step 201, data cleaning and preprocessing are performed on the collected real-time data and historical data to remove noise, outliers and redundant information;

[0019] Step 202, extracting interference features from the pre-processed real-time data and historical data, wherein the interference features include human interference factors, natural interference factors and interference factors between devices, and clustering the extracted features;

[0020] Step 203, according to the pre-processed historical data, obtain the correlation data of the man-made interference factor, the natural interference factor and the interference factor between devices, wherein the man-made interference factor includes time domain data and frequency domain data, the natural interference factor includes meteorological data and wireless communication environment data, and the interference factor between devices includes device data, network monitoring data and spectrum data; wherein the time domain characteristics include envelope fluctuation, pulse width and pulse repetition frequency, the frequency domain characteristics include carrier frequency, spectrum width and spectrum flatness, and the spectrum data includes waveform, spectrum characteristics, duration, etc. of the interference signal;

[0021] Step 204, classify and identify the clustered interference data based on factors including human interference, natural interference, and interference between devices, and obtain identification results; this can be achieved by comparing data from different monitoring points, analyzing the propagation path of the interference signal, etc.;

[0022] Step 205 , sorting and summarizing the extracted interference features, the identified interference sources and interference modes, and the interference feature analysis list to create an interference feature analysis list.

[0023] A further improvement of the technical solution of the present invention is that in step 3, the process of obtaining the artificial interference index, the natural interference index and the inter-device interference index is as follows:

[0024] Step 301, integrating the correlation data of human interference factors, natural interference factors and inter-device interference factors in the pre-processed historical data to form a unified data set;

[0025] Step 302, feature encoding is performed on the associated data of the man-made interference factors, natural interference factors and inter-device interference factors in the data set to construct an interference prediction and evaluation model;

[0026] Step 303, dividing the integrated data set into a training set, a validation set and a test set, using the training set data to train the interference prediction and evaluation model, and using the validation set and the test set data to verify the trained interference prediction and evaluation model, and evaluating the performance of the interference prediction and evaluation model;

[0027] Step 304, using the trained model and combining the pre-processed historical data, calculate the man-made interference index, natural interference index and inter-device interference index, predict the type of interference source, analyze the activity mode of the interference source, and predict the change trend of the interference mode;

[0028] Step 305, based on the identification results of the interference data after clustering and the characteristics of the wireless communication environment, the interference source is located. The channel difference and decision fusion method can be used to identify deceptive interference and then locate the interference source. At the same time, the impact of the interference on the performance of the wireless communication system is analyzed according to the activity mode of the interference source, such as signal quality degradation, communication interruption, network performance deterioration, etc., to evaluate the impact of the interference on the stability and reliability of the wireless communication system.

[0029] A further improvement of the technical solution of the present invention is that the calculation formula of the human interference index is:

[0030]

[0031] Among them, HI is the artificial interference index, A is the intensity coefficient of the artificial interference source, B is the frequency change rate of the artificial interference source, C is the environmental noise background value, D is the sensitivity of the system to artificial interference, E is the distribution unevenness of the interference source, F is the time scale factor, G is the duration of the interference source, H is the attenuation rate of the interference source, I is the system's own noise, J is the anti-interference ability, K is the spatial distribution factor of the interference source, and L is the energy density of the interference source;

[0032] The calculation formula of natural interference index is:

[0033]

[0034] Among them, NI is the natural interference index, M is the intensity of the natural interference source, ω is the frequency of the natural interference source, N is the natural component of the environmental background noise, P is the sensitivity of the system to natural interference, Q is the variance of the natural interference source, R is the mean of the natural interference source, S is the logarithmic base, T is the duration of the natural interference source, U is the volatility of the natural interference source, and V is the cumulative effect factor of the natural interference source;

[0035] The calculation formula of the interference index between devices is:

[0036]

[0037] Among them, DI is the interference index between devices, W is the strength of the interference source between devices, X is the frequency correlation coefficient of the interference between devices, Y is the phase difference of the interference between devices, Z is the initial value of the interference between devices, A1 is the reference value of the phase difference, C1 is the energy coefficient of the interference between devices, C2 is the static component of the interference between devices, C3 is the dynamic attenuation coefficient of the interference between devices, and D1 is the attenuation rate of the interference between devices.

[0038] A further improvement of the technical solution of the present invention is that in step 4, the process of obtaining the interference factor evaluation coefficient is:

[0039] Step 401, traversing the pre-processed historical data, combining the human interference index, the natural interference index and the inter-device interference index with the historical data, and analyzing the correlation between the interference source and the human interference index, the natural interference index and the inter-device interference index;

[0040] Step 402, defining application scenarios of the wireless communication system, such as urban environment, suburban environment, thunderstorm weather, electromagnetic radiation area, etc., assigning corresponding weights to the interference index, natural interference index, and inter-device interference index according to the characteristics and application scenarios of the wireless communication system. For example, in an urban environment, the human interference index and the inter-device interference index may have higher weights because of dense buildings and frequent human activities; and in thunderstorm weather, the weight of the natural interference index may be higher. The three indexes are weighted and calculated to obtain the interference factor evaluation coefficient;

[0041] Step 403, comparing the interference factor evaluations of different scenarios, analyzing the influence of the interference factor evaluation coefficient on the wireless communication data extraction, the higher the interference factor evaluation coefficient value, the more serious the interference, and the greater the influence on the wireless communication data extraction, according to the pre-processed historical data matching, determining different influence levels, namely, the first level influence level, the second level influence level and the third level influence level, wherein the influence level increases step by step from the first level influence level to the third level influence level;

[0042] Step 404, matching the determined different impact levels with the results of the interference factor evaluation coefficient, and setting corresponding impact thresholds for the different impact levels;

[0043] Step 405, arrange all interference factor evaluation coefficient values ​​in descending order, assign a corresponding impact level to each value, and make an impact evaluation sequence table for subsequent analysis and reference, listing the corresponding relationship between interference factor evaluation coefficients and impact levels.

[0044] A further improvement of the technical solution of the present invention is that the calculation formula of the interference factor evaluation coefficient is:

[0045]

[0046] Among them, IFC is the interference factor evaluation coefficient, HI is the human interference index, and HI std is the standard value of the human interference index, NI is the natural interference index, and NI std is the standard value of the natural interference index, DI is the interference index between devices, and DI std is the standard value of the inter-device interference index, and f(env) is a function related to environmental factors, which is used to adjust the weight of the natural interference index in the evaluation.

[0047] A further improvement of the technical solution of the present invention is that: multiple impact levels correspond to multiple impact thresholds, wherein the impact threshold includes an upper threshold and a lower threshold;

[0048] Multiple impact levels and multiple impact thresholds satisfy the following relationship:

[0049] Level 1 Impact Level 0 <IFC≤S1;

[0050] Secondary impact level S1 <IFC<S2;

[0051] Level 3 Impact Level S2 <IFC≤1;

[0052] Among them, IFC is the interference factor assessment coefficient, S1 is the upper threshold corresponding to the first-level impact level and the lower threshold corresponding to the second-level impact level, and S2 is the upper threshold corresponding to the second-level impact level and the lower threshold corresponding to the third-level impact level.

[0053] A further improvement of the technical solution of the present invention is that in step 5, the process of implementing the anti-interference avoidance solution is:

[0054] Step 501, inputting the human interference factor, natural interference factor and inter-device interference factor in the real-time data into the trained interference prediction and evaluation model, calculating the human interference index, natural interference index and inter-device interference index respectively, and predicting the interference source type and interference mode;

[0055] Step 502, combining the calculated artificial interference index, natural interference index and inter-device interference index to obtain an interference factor evaluation coefficient, and determining a current impact level according to a preset impact threshold;

[0056] Step 503, formulate corresponding anti-interference avoidance plans according to different impact levels;

[0057] Level 3 impact level: Take immediate measures, such as shutting down potential interference sources, adjusting communication equipment parameters, and enabling backup communication links;

[0058] Level 2 impact: Strengthen monitoring, pay close attention to changes in communication quality, and adjust anti-interference strategies in a timely manner;

[0059] Impact level 1: Maintain the status quo, continue to monitor communication quality, and prepare for possible changes;

[0060] Step 504, after implementing the anti-interference avoidance scheme, collect and analyze communication quality data, evaluate the effectiveness of the scheme, and continuously improve the anti-interference avoidance scheme according to actual needs to improve the stability and reliability of the communication system.

[0061] In a second aspect, an anti-interference system for wireless communication data extraction includes a data center, wherein the data center is communicatively connected with a signal receiving module, a signal processing module, an interference detection and identification module, an anti-interference strategy selection module, a data output module, and an adaptive and learning module, wherein electrical signals are connected between the modules;

[0062] Signal receiving module: used to receive signals from wireless channels, including useful data signals and potential interference signals;

[0063] Signal processing module: used to enhance, filter, decode and process the received signal to extract useful data, improve signal quality, and enhance the accuracy and reliability of data extraction;

[0064] Interference detection and identification module: used to analyze the received signals, identify and distinguish useful signals from interference signals, and identify the types of interference signals, providing a basis for subsequent anti-interference strategies;

[0065] Anti-interference strategy selection module: used to select appropriate anti-interference strategy according to the information provided by the interference detection and identification module to improve the reliability and anti-interference ability of communication;

[0066] Data output module: used to output processed useful data to subsequent processing systems or users to ensure data integrity and availability;

[0067] The adaptive and learning module is used to adaptively adjust the anti-interference strategy according to environmental changes and changes in interference types to adapt to different communication environments and interference scenarios.

[0068] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:

[0069] 1. The present invention provides an anti-interference method and system for extracting wireless communication data. By analyzing the interference sources and their types in the wireless communication environment, including human interference, natural interference, and mutual interference between devices, these interference factors are accurately identified and classified, potential interference scenarios are predicted in advance, and corresponding anti-interference measures are taken, which significantly improves the accuracy and integrity of data transmission. Even in a complex electromagnetic environment, the stable transmission of data signals can be ensured, avoiding signal distortion and data loss caused by interference, thereby improving the overall performance of the communication system.

[0070] 2. The present invention provides an anti-interference method and system for wireless communication data extraction. Through real-time monitoring and adaptive adjustment, it can quickly respond to environmental changes and adjust communication parameters and strategies to adapt to new interference scenarios. This adaptive capability not only improves the anti-interference performance of the communication system, but also enhances its stability in complex environments. Even under extreme conditions, such as areas with enhanced electromagnetic interference or severe signal attenuation, the communication system can maintain stable communication quality and ensure reliable data transmission.

[0071] 3. The present invention provides an anti-interference method and system for extracting wireless communication data, which improves the reliability and performance of the network by identifying and locating interference sources. By detecting wireless signals, the system can monitor network quality, identify interference sources, and ensure system security. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0073] Figure 1 is a flow chart of the method of the present invention;

[0074] Figure 2 A flowchart for obtaining an interference feature analysis list of the present invention;

[0075] Figure 3 A flowchart for obtaining the interference factor evaluation coefficient of the present invention;

[0076] Figure 4 It is a module structure diagram of the present invention. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0078] Embodiment 1, as Figure 1-3 As shown, the present invention provides an anti-interference method for extracting wireless communication data, comprising the following steps:

[0079] Step 1, collect interference data in the wireless communication environment and determine the type of interference source, wherein the collected interference data includes historical data and real-time data, so as to facilitate comprehensive analysis and prediction of interference scenarios, and the types of interference sources include human interference, natural interference and interference between devices, human interference includes electromagnetic interference generated by human activities, such as the operation of electronic equipment, radio communication, etc., natural interference includes electromagnetic interference generated by natural phenomena, such as lightning, cosmic rays, etc., and interference between devices includes interference caused by similar frequencies or mutual interference, such as co-channel interference and adjacent frequency interference; the process of determining the type of interference source is: determining the scope and target of interference data in the wireless communication environment, including the type of interference data to be collected, the type of interference source, and the frequency and accuracy of interference data; such as monitoring once every hour, every day or every week , deploy monitoring equipment according to monitoring needs, form a monitoring network, and use the deployed monitoring equipment to monitor the interference situation in the wireless communication environment in real time, and transmit it to the data center for analysis in real time; monitoring equipment such as spectrum analyzers, radio monitoring stations, etc., and ensure that the monitoring equipment has sufficient accuracy and sensitivity to accurately capture and record interference signals, extract past interference events from the historical records of the data center, including time, location, type of interference source, intensity and frequency, obtain long-term interference data to analyze interference patterns and trends, organize and analyze the collected real-time data and historical data, and extract key information, including using an interference identification algorithm based on convolutional neural network combined with multi-domain feature extraction, and extract interference features from time-frequency images and frequency domain sequences through CNN to improve interference identification performance;

[0080] Step 2, preprocess the collected real-time data and historical data, and extract interference features, such as the waveform, spectrum characteristics, duration, etc. of the interference signal, identify the main interference source and interference mode, and obtain an interference feature analysis list; an interference identification algorithm based on a convolutional neural network combined with multi-domain feature extraction can be used to extract interference features from time-frequency images and frequency domain sequences to improve interference identification performance; the process of obtaining the interference feature analysis list is as follows: data cleaning and preprocessing are performed on the collected real-time data and historical data to remove noise, outliers and redundant information, and interference features are extracted from the preprocessed real-time data and historical data, where the interference features include human interference factors, natural interference factors and interference factors between devices, and the extracted features are clustered, and human interference factors, natural interference factors and interference factors between devices are obtained based on the preprocessed historical data. Correlation data of interference factors between devices, where man-made interference factors include time domain data and frequency domain data, natural interference factors include meteorological data and wireless communication environment data, and interference factors between devices include device data, network monitoring data, and spectrum data; where time domain feature envelope fluctuation, pulse width, and pulse repetition frequency, frequency domain features include carrier frequency, spectrum width, and spectrum flatness, and spectrum data include waveform, spectrum characteristics, and duration of interference signals. Based on man-made interference factors, natural interference factors, and interference factors between devices, clustered interference data are classified and identified to obtain identification results; this can be achieved by comparing data from different monitoring points, analyzing the propagation path of interference signals, and organizing and summarizing the extracted interference features, identified interference sources and interference modes, and interference feature analysis lists to establish interference feature analysis lists;

[0081] Step 3, based on the interference feature analysis list and historical interference data, establish an interference prediction and evaluation model, obtain the artificial interference index, natural interference index and inter-device interference index, locate the interference source, analyze the characteristics of the interference source and its impact on the wireless communication system, and judge the type of interference, and adjust the anti-interference strategy in time; the process of obtaining the artificial interference index, natural interference index and inter-device interference index is as follows: integrate the associated data of artificial interference factors, natural interference factors and inter-device interference factors in the pre-processed historical data to form a unified data set, feature encode the associated data of artificial interference factors, natural interference factors and inter-device interference factors in the data set, build an interference prediction and evaluation model, divide the integrated data set into a training set, a validation set and a test set, and use the training set data to test the interference prediction The interference prediction and evaluation model is trained, and the trained interference prediction and evaluation model is verified using the data of the validation set and the test set to evaluate the performance of the interference prediction and evaluation model; the trained model is used in combination with the pre-processed historical data to calculate the artificial interference index, natural interference index and inter-device interference index, predict the type of interference source, analyze the activity mode of the interference source, and predict the change trend of the interference mode. According to the identification results of the interference data after clustering and the characteristics of the wireless communication environment, the interference source is located. The channel difference and decision fusion methods can be used to identify deceptive interference and then locate the interference source. At the same time, according to the activity mode of the interference source, the impact of interference on the performance of the wireless communication system is analyzed, such as signal quality degradation, communication interruption, network performance deterioration, etc., and the impact of interference on the stability and reliability of the wireless communication system is evaluated;

[0082] Furthermore, the calculation formula of the human interference index is:

[0083]

[0084] Among them, HI is the artificial interference index, A is the intensity coefficient of the artificial interference source, B is the frequency change rate of the artificial interference source, C is the environmental noise background value, D is the system's sensitivity to artificial interference, E is the distribution unevenness of the interference source, F is the time scale factor, G is the duration of the interference source, H is the attenuation rate of the interference source, I is the system's own noise, J is the system's anti-interference ability, K is the spatial distribution factor of the interference source, and L is the energy density of the interference source;

[0085] The calculation formula of natural interference index is:

[0086]

[0087] Among them, NI is the natural interference index, M is the intensity of the natural interference source, ω is the frequency of the natural interference source, N is the natural component of the environmental background noise, P is the sensitivity of the system to natural interference, Q is the variance of the natural interference source, R is the mean of the natural interference source, S is the logarithmic base, T is the duration of the natural interference source, U is the volatility of the natural interference source, and V is the cumulative effect factor of the natural interference source;

[0088] The calculation formula of the interference index between devices is:

[0089]

[0090] Wherein, DI is the interference index between devices, W is the strength of the interference source between devices, X is the frequency correlation coefficient of the interference between devices, Y is the phase difference of the interference between devices, Z is the initial value of the interference between devices, A1 is the reference value of the phase difference, C1 is the energy coefficient of the interference between devices, C2 is the static component of the interference between devices, C3 is the dynamic attenuation coefficient of the interference between devices, and D1 is the attenuation speed of the interference between devices;

[0091] Step 4, based on the human interference index, natural interference index and inter-device interference index, obtain the interference factor evaluation coefficient, evaluate the influence of different interference scenarios on the extraction of wireless communication data, evaluate the interference impact, and output the evaluation result; the process of obtaining the interference factor evaluation coefficient is: traverse the pre-processed historical data, combine the human interference index, natural interference index and inter-device interference index with the historical data, analyze the correlation between the interference source and the human interference index, natural interference index and inter-device interference index, define the application scenarios of the wireless communication system, such as urban environment, suburban environment, lightning weather, electromagnetic radiation area, etc., according to the characteristics and application scenarios of the wireless communication system, assign corresponding weights to the interference index, natural interference index and inter-device interference index. For example, in an urban environment, the human interference index and the inter-device interference index may have higher weights because of the dense buildings and frequent human activities; while in lightning weather , the weight of the natural interference index may be higher, and the three indexes are weighted to obtain the interference factor evaluation coefficient. The interference factor evaluation of different scenarios is compared, and the influence of the interference factor evaluation coefficient on the extraction of wireless communication data is analyzed. The higher the value of the interference factor evaluation coefficient, the more serious the interference, and the greater the influence on the extraction of wireless communication data. According to the pre-processed historical data matching, different impact levels are determined, which are the first-level impact level, the second-level impact level and the third-level impact level, wherein the impact level increases step by step from the first-level impact level to the third-level impact level;, the determined different impact levels are matched with the results of the interference factor evaluation coefficient, and the corresponding impact thresholds are set for different impact levels, and all the interference factor evaluation coefficient values ​​are arranged in order from high to low, and the corresponding impact level is assigned to each value, and an impact evaluation sequence table is made for subsequent analysis and reference, and the corresponding relationship between the interference factor evaluation coefficient and the impact level is listed;

[0092] Furthermore, the calculation formula of the interference factor evaluation coefficient is:

[0093]

[0094] Among them, IFC is the interference factor evaluation coefficient, HI is the human interference index, and HI std is the standard value of the human interference index, NI is the natural interference index, and NI std is the standard value of the natural interference index, DI is the interference index between devices, and DI std is the standard value of the inter-device interference index, f(env) is a function related to environmental factors, which is used to adjust the weight of the natural interference index in the evaluation;

[0095] Step 5: Use the interference prediction and evaluation model and combine it with the interference factor coefficient to predict abnormal conditions of wireless communication data extraction, implement anti-interference avoidance schemes based on the evaluation results, and optimize the anti-interference avoidance schemes. The anti-interference avoidance scheme can adopt a wireless communication interference avoidance strategy based on fast reinforcement learning, such as learning a fast strategy hill climbing learning method, to quickly respond to interference changes and significantly improve the reliability of system transmission under fast time-varying malicious interference. The optimization of the anti-interference avoidance scheme includes adjusting the transmission power, changing the communication frequency or adopting other anti-interference technologies to ensure the reliability and efficiency of communication. The process of implementing the anti-interference avoidance scheme is as follows: inputting the human interference factor, natural interference factor and inter-device interference factor in the real-time data into the trained interference prediction and evaluation model, calculating the human interference index, natural interference index and inter-device interference index respectively, and predicting the interference source type and interference mode, combining the calculated human interference index, natural interference index and inter-device interference index to obtain the interference factor evaluation coefficient, and determining the current impact level according to the preset impact threshold, formulating corresponding anti-interference avoidance schemes for different impact levels, collecting and analyzing communication quality data after implementing the anti-interference avoidance scheme, evaluating the effectiveness of the scheme, and continuously improving the anti-interference avoidance scheme according to actual needs to improve the stability and reliability of the communication system.

[0096] Furthermore, the corresponding levels and anti-interference avoidance plans are as follows: Level 3 impact level: take immediate measures, such as shutting down potential interference sources, adjusting communication equipment parameters, and enabling backup communication links;

[0097] Level 2 impact: Strengthen monitoring, pay close attention to changes in communication quality, and adjust anti-interference strategies in a timely manner;

[0098] Impact Level 1: Maintain the current status, continue to monitor communication quality, and prepare for possible changes.

[0099] Embodiment 2, as Figure 4 As shown, on the basis of Example 1, the present invention provides an anti-interference system for wireless communication data extraction, including a data center, the data center is communicatively connected with a signal receiving module, a signal processing module, an interference detection and identification module, an anti-interference strategy selection module, a data output module and an adaptive and learning module, wherein the modules are electrically connected with each other;

[0100] Signal receiving module: used to receive signals from wireless channels, including useful data signals and potential interference signals;

[0101] Signal processing module: used to enhance, filter, decode and process the received signal to extract useful data, improve signal quality, and enhance the accuracy and reliability of data extraction;

[0102] Interference detection and identification module: used to analyze the received signals, identify and distinguish useful signals from interference signals, and identify the types of interference signals, providing a basis for subsequent anti-interference strategies;

[0103] Anti-interference strategy selection module: used to select appropriate anti-interference strategy according to the information provided by the interference detection and identification module to improve the reliability and anti-interference ability of communication;

[0104] Data output module: used to output processed useful data to subsequent processing systems or users to ensure data integrity and availability;

[0105] The adaptive and learning module is used to adaptively adjust the anti-interference strategy according to environmental changes and changes in interference types to adapt to different communication environments and interference scenarios.

[0106] The above are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. An anti-interference method for extracting wireless communication data, characterized in that: The following steps are involved: Step 1, collecting interference data in a wireless communication environment and determining the type of interference source, wherein the collected interference data includes historical data and real-time data, and the interference source type includes human interference, natural interference, and interference between devices; Step 2: pre-process the collected real-time data and historical data, extract interference features, identify the main interference sources and interference modes, and obtain an interference feature analysis list; Step 3: Based on the interference feature analysis list and historical interference data, an interference prediction and evaluation model is established to obtain the man-made interference index, natural interference index, and inter-device interference index, locate the interference source, analyze the characteristics of the interference source and its impact on the wireless communication system, and determine the type of interference; Step 4: Based on the human interference index, natural interference index and inter-device interference index, obtain the interference factor evaluation coefficient, evaluate the influence of different interference scenarios on wireless communication data extraction, evaluate the interference impact, and output the evaluation result; Step 5: Use the interference prediction and evaluation model and combine it with the interference factor coefficient to predict abnormal conditions of wireless communication data extraction, implement anti-interference avoidance schemes based on the evaluation results, and optimize the anti-interference avoidance schemes.

2. The anti-interference method for extracting wireless communication data according to claim 1, characterized in that: In step 1, the process of determining the interference source type is as follows: Step 101, determining the scope and target of interference data in a wireless communication environment, including the type of interference data to be collected, the type of interference source, and the frequency and accuracy of the interference data; Step 102, deploy monitoring equipment according to monitoring requirements to form a monitoring network, and use the deployed monitoring equipment to monitor interference in the wireless communication environment in real time, and transmit it to the data center for analysis in real time; Step 103, extracting interference events that occurred in the past from the historical records of the data center, including time, location, interference source type, intensity, and frequency, and obtaining long-term interference data to analyze interference patterns and trends; Step 104, sorting and analyzing the collected real-time data and historical data to extract key information.

3. The anti-interference method for extracting wireless communication data according to claim 2, characterized in that: In step 2, the process of obtaining the interference feature analysis list is as follows: Step 201, data cleaning and preprocessing are performed on the collected real-time data and historical data to remove noise, outliers and redundant information; Step 202, extracting interference features from the pre-processed real-time data and historical data, wherein the interference features include human interference factors, natural interference factors and interference factors between devices, and clustering the extracted features; Step 203, obtaining correlation data of man-made interference factors, natural interference factors and inter-device interference factors according to the pre-processed historical data, wherein the man-made interference factors include time domain data and frequency domain data, the natural interference factors include meteorological data and wireless communication environment data, and the inter-device interference factors include device data, network monitoring data and spectrum data; Step 204, classifying and identifying the clustered interference data based on human interference factors, natural interference factors, and interference factors between devices to obtain an identification result; Step 205: sort and summarize the extracted interference features, identified interference sources and interference patterns, and the interference feature analysis list to create an interference feature analysis list.

4. The anti-interference method for extracting wireless communication data according to claim 3, characterized in that: In step 3, the process of obtaining the human interference index, the natural interference index and the inter-device interference index is as follows: Step 301, integrating the correlation data of human interference factors, natural interference factors and inter-device interference factors in the pre-processed historical data to form a unified data set; Step 302, feature encoding is performed on the associated data of the man-made interference factors, natural interference factors and inter-device interference factors in the data set to construct an interference prediction and evaluation model; Step 303, dividing the integrated data set into a training set, a validation set and a test set, using the training set data to train the interference prediction and evaluation model, and using the validation set and the test set data to verify the trained interference prediction and evaluation model, and evaluating the performance of the interference prediction and evaluation model; Step 304, using the trained model and combining the pre-processed historical data, calculate the man-made interference index, natural interference index and inter-device interference index, predict the type of interference source, analyze the activity mode of the interference source, and predict the change trend of the interference mode; Step 305, locate the interference source based on the identification result of the clustered interference data and the characteristics of the wireless communication environment, analyze the impact of the interference on the performance of the wireless communication system based on the activity pattern of the interference source, and evaluate the impact of the interference on the stability and reliability of the wireless communication system.

5. The anti-interference method for extracting wireless communication data according to claim 4, characterized in that: The calculation formula of the human interference index is: Among them, HI is the artificial interference index, A is the intensity coefficient of the artificial interference source, B is the frequency change rate of the artificial interference source, C is the environmental noise background value, D is the sensitivity of the system to artificial interference, E is the distribution unevenness of the interference source, F is the time scale factor, G is the duration of the interference source, H is the attenuation rate of the interference source, I is the system's own noise, J is the anti-interference ability, K is the spatial distribution factor of the interference source, and L is the energy density of the interference source; The calculation formula of the natural interference index is: Among them, NI is the natural interference index, M is the intensity of the natural interference source, ω is the frequency of the natural interference source, N is the natural component of the environmental background noise, P is the sensitivity of the system to natural interference, Q is the variance of the natural interference source, R is the mean of the natural interference source, S is the logarithmic base, T is the duration of the natural interference source, U is the volatility of the natural interference source, and V is the cumulative effect factor of the natural interference source; The calculation formula of the inter-device interference index is: Among them, DI is the interference index between devices, W is the strength of the interference source between devices, X is the frequency correlation coefficient of the interference between devices, Y is the phase difference of the interference between devices, Z is the initial value of the interference between devices, A1 is the reference value of the phase difference, C1 is the energy coefficient of the interference between devices, C2 is the static component of the interference between devices, C3 is the dynamic attenuation coefficient of the interference between devices, and D1 is the attenuation rate of the interference between devices.

6. The anti-interference method for extracting wireless communication data according to claim 5, characterized in that: In step 4, the process of obtaining the interference factor evaluation coefficient is as follows: Step 401, traversing the pre-processed historical data, combining the human interference index, the natural interference index and the inter-device interference index with the historical data, and analyzing the correlation between the interference source and the human interference index, the natural interference index and the inter-device interference index; Step 402, defining an application scenario of the wireless communication system, assigning corresponding weights to the interference index, the natural interference index, and the inter-device interference index according to the characteristics and application scenario of the wireless communication system, performing weighted calculation on the three indexes, and obtaining an interference factor evaluation coefficient; Step 403, comparing the interference factor evaluations of different scenarios, analyzing the influence of the interference factor evaluation coefficient on the wireless communication data extraction, and determining different influence levels according to the pre-processed historical data matching, namely, the first-level influence level, the second-level influence level, and the third-level influence level, wherein the influence level increases step by step from the first-level influence level to the third-level influence level; Step 404, matching the determined different impact levels with the results of the interference factor evaluation coefficient, and setting corresponding impact thresholds for the different impact levels; Step 405, arrange all interference factor evaluation coefficient values ​​in descending order, assign a corresponding impact level to each value, and make an impact evaluation sequence table to list the corresponding relationship between the interference factor evaluation coefficient and the impact level.

7. The anti-interference method for extracting wireless communication data according to claim 6, characterized in that: The calculation formula of the interference factor evaluation coefficient is: Among them, IFC is the interference factor evaluation coefficient, HI is the human interference index, and HI std is the standard value of the human interference index, NI is the natural interference index, and NI std is the standard value of the natural interference index, DI is the interference index between devices, and DI std is the standard value of the interference index between devices.

8. The anti-interference method for extracting wireless communication data according to claim 7, characterized in that: The multiple impact levels correspond to multiple impact thresholds, wherein the impact thresholds include an upper threshold and a lower threshold; The multiple impact levels and the multiple impact thresholds satisfy the following relationship: Level 1 Impact Level 0 <IFC≤S1; Secondary impact level S1 <IFC<S2; Level 3 Impact Level S2 <IFC≤1; Among them, IFC is the interference factor assessment coefficient, S1 is the upper threshold corresponding to the first-level impact level and the lower threshold corresponding to the second-level impact level, and S2 is the upper threshold corresponding to the second-level impact level and the lower threshold corresponding to the third-level impact level.

9. The anti-interference method for extracting wireless communication data according to claim 8, characterized in that: In step 5, the process of implementing the anti-interference avoidance solution is: Step 501, inputting the human interference factor, natural interference factor and inter-device interference factor in the real-time data into the trained interference prediction and evaluation model, calculating the human interference index, natural interference index and inter-device interference index respectively, and predicting the interference source type and interference mode; Step 502, combining the calculated artificial interference index, natural interference index and inter-device interference index to obtain an interference factor evaluation coefficient, and determining a current impact level according to a preset impact threshold; Step 503, formulate corresponding anti-interference avoidance plans according to different impact levels; Step 504, after implementing the anti-interference avoidance scheme, collect and analyze communication quality data, evaluate the effectiveness of the scheme, and continuously improve the anti-interference avoidance scheme according to actual needs to improve the stability and reliability of the communication system.

10. An anti-interference system for extracting wireless communication data, used to implement the anti-interference method for extracting wireless communication data according to any one of claims 1 to 9, comprising a data center, characterized in that: The data center communication connection includes a signal receiving module, a signal processing module, an interference detection and identification module, an anti-interference strategy selection module, a data output module and an adaptive and learning module, wherein the electrical signals between the modules are connected; The signal receiving module is used to receive signals from wireless channels, including useful data signals and potential interference signals; The signal processing module is used to enhance, filter and decode the received signal to extract useful data; The interference detection and identification module is used to analyze the received signal, identify and distinguish the useful signal from the interference signal, and identify the type of the interference signal; The anti-interference strategy selection module is used to select a suitable anti-interference strategy according to the information provided by the interference detection and identification module to improve the reliability and anti-interference capability of communication; The data output module is used to output the processed useful data to a subsequent processing system or user; The adaptive and learning module is used to adaptively adjust the anti-interference strategy according to environmental changes and changes in interference types to adapt to different communication environments and interference scenarios.

Images