Online evaluation method of non-cooperative target communication interference based on long short-term memory network

Abstract

This disclosure relates to a method and system for online evaluation of non-cooperative target communication interference based on a long-short-term memory network. The method includes: determining anti-interference behavior parameter indicators during communication confrontation; collecting sample data from the anti-interference behavior parameter indicators, labeling and normalizing the sample data to obtain normalized data; constructing a long-short-term memory network evaluation model, and using the normalized data to train and validate the long-short-term memory network evaluation model to obtain a non-cooperative target interference effect evaluation model; and using the non-cooperative target interference effect evaluation model to evaluate the anti-interference behavior parameter indicators to be evaluated. This method can improve the ability to evaluate online interference during communication confrontation.

Description

Technical Field

[0001] The present disclosure relates to the technical field of communication countermeasure interference evaluation, and in particular to a method and system for online evaluation of non-cooperative target communication interference based on a long short-term memory network. Background Art

[0002] Interference assessment in communication countermeasures is crucial for ensuring the effectiveness of interference. A rational, quantitative assessment of interference effects forms a feedback mechanism that directly impacts the communication countermeasure process. Traditional communication countermeasure assessment methods primarily focus on the signal-to-interference ratio (SIR), estimating the SIR by establishing SIR-related evaluation parameters and metrics to determine the effectiveness of the interference assessment. However, traditional interference assessment methods struggle to effectively analyze the relationship between interference behavior and its effectiveness. Furthermore, in actual combat, the SIR-related calculation parameter values ​​are difficult to obtain and often exhibit a certain lag, making them incapable of meeting the requirements of real-time online assessment. Therefore, it is necessary to propose a solution that addresses one or more of the issues identified in the aforementioned related technical solutions.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute prior art known to ordinary technicians in the field. Summary of the Invention

[0004] A first aspect of an embodiment of the present disclosure provides an online evaluation method for non-cooperative target communication interference based on a long short-term memory network, comprising the following steps:

[0005] Determine the anti-interference behavior parameter indicators during communication confrontation;

[0006] Collecting sample data of the anti-interference behavior parameter index, and performing label processing and normalization processing on the sample data to obtain normalized data;

[0007] Constructing a long short-term memory network evaluation model, and using the normalized data to train and verify the long short-term memory network evaluation model to obtain a non-cooperative target interference effect evaluation model;

[0008] The non-cooperative target interference effect evaluation model is used to evaluate the anti-interference behavior parameter index to be evaluated.

[0009] In an exemplary embodiment of the present disclosure, the anti-interference behavior parameter indicators include: communication power, communication channel, communication mode, signal pattern and communication distance; wherein,

[0010] The effectiveness of the jamming behavior is determined by monitoring the increase or sudden change to zero of the communication power before and after the jamming;

[0011] Determining the effectiveness of the jamming behavior by monitoring changes to the communication channel to avoid interference or enhance the anti-interference capability of the communication process;

[0012] Determining the effectiveness of the jamming behavior by monitoring the switching of different communication modes to escape the jamming;

[0013] Determining the effectiveness of the jamming behavior by monitoring different signal patterns;

[0014] The effectiveness of the jamming behavior is determined by monitoring the change in the communication distance.

[0015] In an exemplary embodiment of the present disclosure, the steps of collecting sample data from the anti-interference behavior parameter index and performing label processing and normalization processing on the sample data to obtain normalized data include:

[0016] The sample data is established by using the sliding window method, and the 10 groups of anti-interference behavior parameter indicators collected within 1s are used as a sample data; wherein,

[0017] The sampling rate is 10 / second;

[0018] The moving step of the sliding window is 1;

[0019] Establishing a label value for each sample data, wherein the label value is an evaluation category of the interference effect of the sample data during the time of collecting the sample data;

[0020] All the sample data with the label value are normalized to obtain the normalized data.

[0021] In an exemplary embodiment of the present disclosure, the normalized data includes at least training set data and validation set data.

[0022] In an exemplary embodiment of the present disclosure, the long short-term memory network evaluation model includes an input gate, a forget gate, and an output gate; wherein,

[0023] The calculation formula of the input gate includes:

[0024] I t =σ(X t W xi +H t-1 W hi +b i ) (1)

[0025] The calculation formula of the forget gate includes:

[0026] F t =σ(X t W xf +Ht-1 W hf +b f ) (2)

[0027] The calculation formula of the output gate includes:

[0028] O t =σ(X t W xo +H t-1 W ho +b o ) (3)

[0029] Among them, I t represents the input gate at time t; F t represents the forget gate at time t; O t represents the output gate at time t; X t represents the input at time t; W xi Represents the weight value of the input gate at time t; W xf Represents the weight value of the forget gate at time t; W xo Represents the weight value of the output gate at time t; H t-1 represents the input at time t-1; W hi Represents the weight value of the input gate at time t-1; W hf Represents the weight value of the forget gate at time t-1; W ho represents the weight value of the output gate at time t-1; b i represents the threshold of the input gate; b f represents the threshold of the forget gate; b o Represents the threshold of the output gate.

[0030] In an exemplary embodiment of the present disclosure, the long short-term memory network evaluation model is a multi-input single-output network; the input sample data includes five categories, each of which contains 10 groups of sample data, namely: A i represents the communication power; B i represents the communication channel; C i Indicates the communication mode; D i Indicates the signal pattern; E i represents the communication distance; wherein, i represents the i-th group of sample data, i=1,…,10.

[0031] In an exemplary embodiment of the present disclosure, in the step of constructing a long short-term memory network evaluation model and using the normalized data to train and verify the long short-term memory network evaluation model to obtain a non-cooperative target interference effect evaluation model,

[0032] The long short-term memory network evaluation model is trained using the training set data, comprising:

[0033] Inputting the training set data into the long short-term memory network evaluation model, and training the long short-term memory network evaluation model using a gradient back propagation method and a loss function;

[0034] When the value of the loss function is less than 10 -4 When , the training is stopped; and the weights of the long short-term memory network evaluation model are generated.

[0035] In an exemplary embodiment of the present disclosure, in the step of constructing a long short-term memory network evaluation model and using the normalized data to train and verify the long short-term memory network evaluation model to obtain a non-cooperative target interference effect evaluation model,

[0036] Utilizing the validation set data to validate the trained long short-term memory network evaluation model includes:

[0037] When the training of the long short-term memory network evaluation model is stopped,

[0038] If the accuracy of the verification result is greater than 90%, the non-cooperative target interference effect evaluation model is obtained;

[0039] If the accuracy of the verification result is less than or equal to 90%, the hyperparameters of the long short-term memory network evaluation model are adjusted.

[0040] In an exemplary embodiment of the present disclosure, the step of evaluating the anti-interference behavior parameter index to be evaluated using the non-cooperative target interference effect evaluation model includes:

[0041] The generated evaluation weight and the anti-interference behavior parameter to be evaluated are input into the non-cooperative target interference effect evaluation model to obtain an interference evaluation result; wherein,

[0042] The interference assessment result includes an interference assessment score and an interference state, and the mapping relationship between the interference assessment score and the interference state is:

[0043] When the evaluation score is [0, 0.25), the interference state is invalid interference;

[0044] When the evaluation score is [0.25, 0.5), the interference state is mild interference;

[0045] When the evaluation score is [0.5, 0.75), the interference state is moderate interference;

[0046] When the evaluation score is [0.75, 1], the interference state is severe interference.

[0047] A second aspect of the embodiments of the present disclosure provides an online evaluation system for non-cooperative target communication interference based on a long short-term memory network, the system comprising: a parameter indicator module, a data processing module, a long short-term memory network module and an evaluation module connected in sequence; wherein,

[0048] The parameter indicator module is used to provide anti-interference behavior parameter indicators during the communication confrontation process;

[0049] The data processing module is used to collect sample data from the anti-interference behavior parameter index, and perform label processing and normalization processing on the sample data to obtain normalized data;

[0050] The long short-term memory network module is trained and verified using the normalized data to obtain a non-cooperative target interference effect evaluation model;

[0051] An evaluation module uses the non-cooperative target interference effect evaluation model to evaluate the anti-interference behavior parameter index to be evaluated.

[0052] The technical solution provided by the present disclosure may have the following beneficial effects: The present disclosure proposes an online evaluation method for non-cooperative target communication interference based on a long short-term memory network. This method normalizes the anti-interference behavior parameter indicators to obtain normalized data, and uses this normalized data to train and verify the introduced long short-term memory network evaluation model, thereby obtaining a non-cooperative target interference effect evaluation model. The trained non-cooperative target interference effect evaluation model can perform real-time evaluation of the anti-interference behavior parameter indicators to be evaluated without retraining. This improves the ability to evaluate online interference during communication countermeasures. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification, serve to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0054] Figure 1 A schematic diagram illustrating the steps of a method for online evaluation of non-cooperative target communication interference based on a long short-term memory network in an exemplary embodiment of the present disclosure is shown;

[0055] Figure 2 A flowchart illustrating an online evaluation method for non-cooperative target communication interference based on a long short-term memory network in an exemplary embodiment of the present disclosure is shown;

[0056] Figure 3A schematic diagram illustrating a framework of a long short-term memory network evaluation model in an exemplary embodiment of the present disclosure is shown;

[0057] Figure 4 A structural diagram of an online evaluation system for non-cooperative target communication interference based on a long short-term memory network in an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0058] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0059] In addition, the accompanying drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0060] The first aspect of this exemplary embodiment provides an online evaluation method for non-cooperative target interference effects based on a long short-term memory network, such as Figure 1 As shown, the following steps may be included:

[0061] Step S101: Determine anti-interference behavior parameter indicators during the communication confrontation process.

[0062] Step S102: collecting sample data of the anti-interference behavior parameter index, and performing label processing and normalization processing on the sample data to obtain normalized data.

[0063] Step S103: constructing a long short-term memory network evaluation model, and using normalized data to train and verify the long short-term memory network evaluation model to obtain a non-cooperative target interference effect evaluation model.

[0064] Step S104: using the non-cooperative target interference effect evaluation model to evaluate the anti-interference behavior parameter index to be evaluated.

[0065] The disclosed embodiments propose an online evaluation method for non-cooperative target communication interference based on a long short-term memory network. This method normalizes the interference behavior parameter indicators to obtain normalized data, and uses this normalized data to train and verify the introduced long short-term memory network evaluation model, thereby obtaining a non-cooperative target interference effect evaluation model. The trained non-cooperative target interference effect evaluation model can perform real-time evaluation of the anti-interference behavior parameter indicators to be evaluated without retraining. This improves the ability to evaluate online interference during communication countermeasures.

[0066] Below, each step of the above method in this exemplary embodiment will be described in more detail. Figure 2 As shown,

[0067] Online evaluation of jamming effects against non-cooperative targets plays a crucial role in improving electronic countermeasures (ECM) capabilities. In complex electromagnetic environments, traditional jamming assessment methods struggle to effectively analyze the relationship between jamming behavior and jamming effects. Deep learning methods, however, can fully exploit underlying dependencies between data when fitting complex nonlinear objective functions. Long Short-Term Memory (LSTM) networks, in particular, can capture long-range input dependencies. Compared to traditional assessment methods, they place greater emphasis on the impact of both the current state of the jammed target's anti-jamming behavior and state changes on the jamming assessment.

[0068] In step S101, the communication confrontation process is analyzed and anti-interference behavior parameter indicators are established during the communication confrontation process. During the establishment process, it is important to consider that each anti-interference behavior parameter indicator should be reasonably configured under the principles of observability, short time consumption and weak correlation.

[0069] Anti-interference behavior refers to the anti-interference measures taken by a target after being effectively interfered with. This behavior is reflected in certain parameters, namely anti-interference behavior parameter indicators. In actual combat, the friendly side cannot directly obtain the enemy's communication results. However, if anti-interference behavior parameters can be extracted from the information obtained by the friendly reconnaissance system, these parameters can be used to determine whether the enemy has taken anti-interference measures and thus understand the interference effect. Research has been conducted on using anti-interference behavior to evaluate the effectiveness of communication anti-interference. However, these studies focus solely on analyzing the interference effect based on the anti-interference behavior parameters at the current moment, ignoring the fact that interference effect evaluation depends on the state changes of the anti-interference behavior parameters. Therefore, they do not fully reflect the relationship between the anti-interference behavior parameters and interference effect evaluation.

[0070] In the embodiment of the present disclosure, the anti-interference behavior parameter indicators include communication power, communication channel, communication mode, signal pattern and communication distance. Specifically,

[0071] (1) Communication power

[0072] When encountering broadband jamming during communication, the communication power is typically increased to meet the required signal-to-interference ratio. Furthermore, when the interference intensity is excessive, communication may terminate, followed by a brief silence followed by re-establishment. Generally, both communicating parties have multiple power modes to meet communication requirements under varying interference conditions. Therefore, a friendly reconnaissance system can determine the effectiveness of jamming by monitoring changes in communication power before and after the jamming, such as increases or drops to zero.

[0073] (2) Communication channel

[0074] Changing the communication channel to avoid interference or enhance the anti-interference capability of the communication process is a common measure. The friendly party can determine the effectiveness of the jamming behavior by monitoring the change of the communication channel to avoid interference or enhance the anti-interference capability of the communication process.

[0075] (3) Communication mode

[0076] Typically, communication equipment features multiple communication modes, such as fixed frequency and frequency hopping. When subject to interference, it can switch to a different communication mode to overcome it. The jammer's reconnaissance receiver can use spectrum analysis to determine in real time whether the victim has switched communication modes. If a change in communication mode is detected, the jammer can be considered effective. Therefore, the jammer can determine the effectiveness of the jamming operation by observing the switch to a different communication mode to overcome the interference.

[0077] (4)Signal style

[0078] Signal patterns are generally analyzed based on information redundancy, message encapsulation structure, and encoding methods. Generally speaking, higher information redundancy, more complex encoding methods, and message encapsulation structures improve anti-interference capabilities. Therefore, the effectiveness of jamming can be determined by monitoring different signal patterns.

[0079] (5) Communication distance

[0080] For both communicating parties, the anti-interference capability can be improved by shortening the communication distance. The communication party can determine the effectiveness of the interference behavior by monitoring the change in communication distance.

[0081] In step S102, during the actual communication confrontation process, sample data is collected from the anti-interference behavior parameter index, including the following sub-steps:

[0082] Sub-step S1021: using the sliding window method to establish data, taking the 10 groups of anti-interference behavior parameter indicators collected within 1 second as a sample data, with a sampling rate of 10 per second; the moving step of the sliding window is 1;

[0083] Sub-step S1022: establishing a label value for each sample data, where the label value is an evaluation category of the interference effect of the sample data during the time of collecting the sample data;

[0084] Sub-step S1023: normalize all sample data with label values ​​to obtain normalized data.

[0085] Furthermore, the normalized data includes training set data, validation set data, and test set data.

[0086] In step S103, in this embodiment, the LSTM evaluation model is used to perform real-time evaluation of the interference effectiveness during the communication confrontation process; the LSTM evaluation model includes an input gate, a forget gate, and an output gate, wherein:

[0087] The calculation formula of the input gate includes:

[0088] I t =σ(X t W xi +H t-1 W hi +b i ) (1)

[0089] The calculation formula of the forget gate includes:

[0090] F t =σ(X t W xf +H t-1 W hf +b f ) (2)

[0091] The calculation formula of the output gate includes:

[0092] O t =σ(X t W xo +H t-1 W ho +b o ) (3)

[0093] Among them, I t represents the input gate at time t; F t represents the forget gate at time t; O t represents the output gate at time t; X t represents the input at time t; W xi Represents the weight value of the input gate at time t; Wxf Represents the weight value of the forget gate at time t; W xo Represents the weight value of the output gate at time t; H t-1 represents the input at time t-1; W hi Represents the weight value of the input gate at time t-1; W hf Represents the weight value of the forget gate at time t-1; W ho represents the weight value of the output gate at time t-1; b i represents the threshold of the input gate; b f represents the threshold of the forget gate; b o Represents the threshold of the output gate.

[0094] like Figure 3 As shown, the LSTM evaluation model is a multi-input single-output network; the input sample data includes five categories, each category contains 10 groups of sample data, namely: A i Indicates communication power; B i Represents the communication channel; C i Indicates the communication mode; D i Indicates signal style; E i Represents the communication distance; wherein, i represents the i-th group of sample data, i=1,…,10.

[0095] Furthermore, the steps of training and validating the LSTM evaluation model using normalized data to finally obtain the non-cooperative target interference effect evaluation model include the following steps:

[0096] Sub-step S1031: training the LSTM evaluation model using the training data;

[0097] Specifically, the training data is input into the LSTM evaluation model, and the LSTM evaluation model is trained using the gradient back propagation method and the loss function. Here, it is preferred to use the mean square error as the loss function. When the value of the loss function is less than 10 -4 When , stop training; and generate evaluation weights.

[0098] Sub-step S1032: using the validation set data to test the trained LSTM evaluation model;

[0099] Specifically, when the training of the LSTM evaluation model is stopped, if the accuracy of the verification result is greater than 90%, a non-cooperative target interference effect evaluation model is obtained; when the accuracy of the verification result is less than or equal to 90%, the hyperparameters in the LSTM evaluation model are adjusted.

[0100] In step S104, the generated evaluation weight and the anti-interference behavior parameter to be evaluated are input into the non-cooperative target interference effect evaluation model to obtain the interference evaluation result; wherein,

[0101] The interference assessment result includes an interference assessment score and an interference status. A mapping relationship between the interference assessment score and the interference status is established:

[0102] When the evaluation score is [0, 0.25), the interference state is invalid interference;

[0103] When the evaluation score is [0.25, 0.5), the interference state is mild interference;

[0104] When the evaluation score is [0.5, 0.75), the interference state is moderate interference;

[0105] When the evaluation score is [0.75, 1], the interference state is severe interference.

[0106] This establishes a connection between the interference state and the interference effect.

[0107] The second aspect of this exemplary embodiment provides an online evaluation system for non-cooperative target interference effects based on a long short-term memory network, such as Figure 4 As shown,

[0108] The system includes: a parameter indicator module, a data processing module, a long short-term memory network module and an evaluation module connected in sequence; wherein,

[0109] Parameter indicator module, used to provide anti-interference behavior parameter indicators during communication confrontation;

[0110] A data processing module is used to collect sample data from the anti-interference behavior parameter index, and perform label processing and normalization on the sample data to obtain normalized data;

[0111] The long short-term memory network module is trained and validated using normalized data to obtain a non-cooperative target interference effect evaluation model;

[0112] The evaluation module uses the non-cooperative target interference effect evaluation model to evaluate the anti-interference behavior parameter indicators to be evaluated.

[0113] It should be noted that although several units of the system for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the present disclosure, the features and functions of two or more units described above can be concretized in one unit. Conversely, the features and functions of a unit described above can be further divided into multiple units for concretization. Some or all of the units can be selected according to actual needs to achieve the purpose of the disclosed solution. Those of ordinary skill in the art can understand and implement it without paying creative work.

[0114] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the appended claims.

Claims

1. An online evaluation method for non-cooperative target communication interference based on long short-term memory network, characterized by: The following steps are involved: Determine the anti-interference behavior parameter indicators during communication confrontation; Collecting sample data of the anti-interference behavior parameter index, and performing label processing and normalization processing on the sample data to obtain normalized data; Constructing a long short-term memory network evaluation model, and using the normalized data to train and verify the long short-term memory network evaluation model to obtain a non-cooperative target interference effect evaluation model; Using the non-cooperative target interference effect evaluation model to evaluate the anti-interference behavior parameter index to be evaluated; The anti-interference behavior parameter indicators include: communication power, communication channel, communication mode, signal pattern and communication distance; The step of collecting sample data from the anti-interference behavior parameter index and performing label processing and normalization processing on the sample data to obtain normalized data includes: The sample data is established by using a sliding window method, and 10 groups of anti-interference behavior parameter indicators collected within a time period of 1 second are used as a sample data; wherein the sampling rate is 10 per second; and the moving step length of the sliding window is 1; Establishing a label value for each sample data, wherein the label value is an evaluation category of the interference effect of the sample data during the time of collecting the sample data; Performing the normalization process on all the sample data with the label value to obtain the normalized data; The long short-term memory network evaluation model is a multi-input single-output network; the input sample data includes five categories, each of which contains 10 groups of sample data, namely: A i represents the communication power; B i represents the communication channel; C i Indicates the communication mode; D i Indicates the signal pattern; E i represents the communication distance; wherein, i Indicates the i The sample data of group, i =1,…,10; The step of evaluating the anti-interference behavior parameter index to be evaluated by using the non-cooperative target interference effect evaluation model includes: The generated evaluation weight and the anti-interference behavior parameter to be evaluated are input into the non-cooperative target interference effect evaluation model to obtain the interference evaluation result; wherein, The interference assessment result includes an interference assessment score and an interference state, and the mapping relationship between the interference assessment score and the interference state is: When the evaluation score is When , the interference state is invalid interference; When the evaluation score is When , the interference state is mild interference; When the evaluation score is When , the interference state is moderate interference; When the evaluation score is , the interference state is severe interference.

2. The online evaluation method for non-cooperative target communication interference based on long short-term memory network according to claim 1 is characterized in that: in, The effectiveness of the jamming behavior is determined by monitoring the increase or sudden change to zero of the communication power before and after the jamming; Determining the effectiveness of the jamming behavior by monitoring changes to the communication channel to avoid interference or enhance the anti-interference capability of the communication process; Determining the effectiveness of the jamming behavior by monitoring the switching of different communication modes to escape the jamming; Determining the effectiveness of the jamming behavior by monitoring different signal patterns; The effectiveness of the jamming behavior is determined by monitoring the change in the communication distance.

3. The online evaluation method for non-cooperative target communication interference based on long short-term memory network according to claim 1 is characterized in that: The normalized data includes at least training set data and validation set data.

4. The online evaluation method for non-cooperative target communication interference based on long short-term memory network according to claim 3 is characterized in that: The long short-term memory network evaluation model includes an input gate, a forget gate and an output gate; wherein, The calculation formula of the input gate includes: The calculation formula of the forget gate includes: The calculation formula of the output gate includes: in, express The input gate at the moment; express The door of forgetfulness of moments; express Output gate at the moment; express Input at the moment; express Input the weight value of the gate at all times; express The weight value of the moment-forget gate; express The weight value of the output gate at each moment; express Input at the moment; express The weight value of the input gate at the moment; express The weight value of the forget gate at the moment; express The weight value of the output gate at the moment; Represents the threshold of the input gate; Represents the threshold of the forget gate; Represents the threshold of the output gate.

5. The online evaluation method for non-cooperative target communication interference based on long short-term memory network according to claim 4 is characterized in that: In the step of constructing a long short-term memory network evaluation model, and using the normalized data to train and verify the long short-term memory network evaluation model to obtain a non-cooperative target interference effect evaluation model, The long short-term memory network evaluation model is trained using the training set data, comprising: Inputting the training set data into the long short-term memory network evaluation model, and training the long short-term memory network evaluation model using a gradient back propagation method and a loss function; When the value of the loss function is less than When , the training is stopped; and the weights of the long short-term memory network evaluation model are generated.

6. The online evaluation method for non-cooperative target communication interference based on long short-term memory network according to claim 5 is characterized in that: In the step of constructing a long short-term memory network evaluation model, and using the normalized data to train and verify the long short-term memory network evaluation model to obtain a non-cooperative target interference effect evaluation model, Utilizing the validation set data to validate the trained long short-term memory network evaluation model includes: When the training of the long short-term memory network evaluation model is stopped, If the accuracy of the verification result is greater than 90%, the non-cooperative target interference effect evaluation model is obtained; If the accuracy of the verification result is less than or equal to 90%, the hyperparameters of the long short-term memory network evaluation model are adjusted.

7. A non-cooperative target communication interference online evaluation system based on a long short-term memory network applied to the non-cooperative target communication interference online evaluation method based on a long short-term memory network as claimed in claim 1, characterized in that: The system includes: a parameter indicator module, a data processing module, a long short-term memory network module and an evaluation module connected in sequence; wherein, The parameter indicator module is used to provide anti-interference behavior parameter indicators during the communication confrontation process; The data processing module is used to collect sample data from the anti-interference behavior parameter index, and perform label processing and normalization processing on the sample data to obtain normalized data; The long short-term memory network module is trained and verified using the normalized data to obtain a non-cooperative target interference effect evaluation model; An evaluation module uses the non-cooperative target interference effect evaluation model to evaluate the anti-interference behavior parameter index to be evaluated.

Images