Electronic target simulation equipment anti-interference decision-making method based on hierarchical strategy library

Abstract

The invention relates to the technical field of electronic countermeasure simulation, in particular to an electronic target simulation equipment anti-interference decision-making method based on a hierarchical strategy library, and the method comprises the steps: constructing a hierarchical strategy library; wherein the hierarchical strategy library comprises a base layer strategy library, a scene layer strategy library and a dynamic strategy library; generating an interference situation map based on the received interference signal; establishing a multi-level strategy screening mechanism, and obtaining anti-interference candidate strategies from the hierarchical strategy library based on the interference situation map; wherein the strategy libraries of different levels are matched with different methods; constructing a comprehensive efficiency evaluation model, and obtaining an optimal anti-interference strategy from the anti-interference candidate strategies through the comprehensive efficiency evaluation model; and executing the optimal anti-interference strategy, issuing the optimal anti-interference strategy to a signal processing unit through a standard interface, monitoring an execution state and recording execution effect data. According to the method, the technical problems of response lag and poor adaptability in the anti-interference decision of the traditional electronic target simulation equipment can be solved.

Description

Technical Field

[0001] The embodiments of this application relate to the field of electronic countermeasures simulation technology, and in particular to an anti-jamming decision-making method for electronic target simulation equipment based on a hierarchical strategy library. Background Technology

[0002] In the context of current demands for realistic electronic warfare testing and training, electronic target simulators, acting as the "blue force," simulate playing the role of a formidable adversary. They need to flexibly change signal parameters according to the characteristics of electronic warfare equipment to generate threat target information for the "red force," achieving a dynamic game-like effect. However, due to their cost and scalability, electronic simulators cannot perceive interference and autonomously resist it like real equipment.

[0003] Existing electronic target anti-jamming decisions are mostly made through static strategy libraries, which cannot cope with dynamic load interference. Furthermore, the decisions are lagging, and the strategy libraries need to be updated periodically, so the timeliness, adaptability, and effectiveness cannot be guaranteed. Summary of the Invention

[0004] In view of this, embodiments of this application propose an anti-interference decision-making method for electronic target simulation equipment based on a hierarchical strategy library, which aims to solve the technical problems of slow response and poor adaptability in the anti-interference decision-making of traditional electronic target simulation equipment. Through hierarchical collaborative decision-making and closed-loop optimization mechanism, the intelligent level and real-time performance of anti-interference decision-making of electronic target simulation equipment are significantly improved.

[0005] To achieve the above objectives, embodiments of this application propose an anti-interference decision-making method for electronic target simulation devices based on a hierarchical policy library, the method comprising: Construct a layered strategy library; the layered strategy library includes: a basic strategy library, a scenario-level strategy library, and a dynamic strategy library; Based on the received interference signals, an interference situation map is generated; the interference situation map includes feature vectors and situation level assessment. A multi-level strategy screening mechanism is established, and based on the interference situation map, anti-interference candidate strategies are obtained from the hierarchical strategy library through the multi-level strategy screening mechanism; the matching methods are different for different levels of strategy library. A comprehensive performance evaluation model is constructed, and the optimal anti-interference strategy is obtained from each anti-interference candidate strategy through the comprehensive performance evaluation model; The optimal anti-interference strategy is executed and sent to the signal processing unit through a standard interface. At the same time, the execution status is monitored and the execution effect data is recorded.

[0006] To achieve the above objectives, embodiments of this application also propose an anti-interference decision-making device for electronic target simulation equipment based on a hierarchical policy library, the device comprising: The building module is used to build a layered strategy library; the layered strategy library includes: a base layer strategy library, a scenario layer strategy library, and a dynamic strategy library. The generation module is used to generate an interference situation map based on the received interference signals; the interference situation map includes feature vectors and situation level assessment. The acquisition module is used to establish a multi-level strategy filtering mechanism, and through this mechanism, anti-interference candidate strategies are obtained from the hierarchical strategy library based on the interference situation map; the matching methods are different for different levels of the strategy library. The determination module is used to construct a comprehensive performance evaluation model and obtain the optimal anti-interference strategy from each anti-interference candidate strategy through the comprehensive performance evaluation model; The execution module is used to execute the optimal anti-interference strategy and send it to the signal processing unit through a standard interface. At the same time, it monitors the execution status and records the execution effect data.

[0007] To achieve the above objectives, embodiments of this application also propose an electronic device, including a processor and a memory, wherein the memory stores instructions executable by the processor, and the processor is configured to execute the instructions such that the electronic device can implement the anti-interference decision method for electronic target simulation devices based on a hierarchical policy library as described above.

[0008] To achieve the above objectives, embodiments of this application also propose a computer-readable storage medium storing a computer program that, when executed by a processor, enables the implementation of an anti-interference decision-making method for electronic target simulation equipment based on a hierarchical policy library as described above.

[0009] This application proposes an anti-interference decision-making method for electronic target simulation equipment based on a hierarchical strategy library. First, a hierarchical strategy library is constructed, and an interference situation map is generated based on the received interference signals. Then, a multi-level strategy screening mechanism is established, and anti-interference candidate strategies are obtained from the hierarchical strategy library based on the interference situation map. Next, a comprehensive performance evaluation model is constructed, and the optimal anti-interference strategy is obtained from each candidate strategy through this model. Finally, the optimal anti-interference strategy is executed and sent to the signal processing unit via a standard interface, while simultaneously monitoring the execution status and recording the execution effect data. The method provided in this application solves the technical problems of slow response and poor adaptability in traditional electronic target simulation equipment anti-interference decision-making through hierarchical collaborative decision-making and closed-loop optimization mechanisms. These mechanisms significantly improve the intelligence level and real-time performance of anti-interference decision-making in electronic target simulation equipment.

[0010] Optionally, a hierarchical strategy library is constructed, including: a basic layer strategy library built using a relational database; wherein the basic layer strategy library stores single-parameter anti-interference strategies based on signal dimension features, each strategy including strategy ID, applicable conditions, parameter adjustment range, and expected effect evaluation indicators, and a rule engine is used to achieve fast matching; a scenario layer strategy library built using a distance-based classification algorithm; wherein the scenario layer strategy library stores multi-dimensional combination strategies for typical interference scenarios, and extracts multi-dimensional feature vectors based on historical interference data, establishes a mapping relationship between scenario features and anti-interference strategy combinations, and classifies scenarios through feature similarity; and a dynamic strategy library built using a time-series database to store historical interference events and the execution results of the strategies corresponding to those historical interference events; wherein the dynamic layer strategy library uses a time-series database to store historical interference event data, each record including a timestamp, interference feature vector, adopted strategy, execution result, and performance evaluation, and supports strategy retrieval based on similarity matching.

[0011] Optionally, based on the received interference signal, an interference situation map is generated, including: extracting features from the multidimensional features of the interference signal to obtain feature parameters of the interference signal; the feature parameters include intensity feature parameters, pattern feature parameters, time-frequency domain feature parameters, and spatial feature parameters; normalizing and fusing the feature parameters of the interference signal to convert each feature parameter into a standard dimension to form a unified feature vector; and calculating the interference situation level assessment using a fuzzy comprehensive evaluation algorithm based on the unified feature vector to generate the interference situation map.

[0012] Optionally, the normalization process uses the Min-Max standardization algorithm to map each feature parameter to the [0,1] interval, and the calculation formula is as follows: ; in, Represents the normalized eigenvalues. Represents characteristic parameters, This represents the minimum value of a parameter characteristic, that is, the lower limit of the possible value of this characteristic parameter within the current system definition or calibration range. This indicates the maximum value of the parameter characteristic, that is, the upper limit of the possible value of the characteristic parameter within the current system definition or calibration range; Feature fusion employs a weighted fusion algorithm, calculated using the following formula: ; in, This represents the weight of each feature parameter. Represents the normalized eigenvalues; The interference situation score is calculated using a fuzzy comprehensive evaluation algorithm. It can be expressed by the following formula: ; in, This represents the feature membership degree of the feature parameter.

[0013] Optionally, a multi-level strategy filtering mechanism includes: The probability distribution of each feature parameter is calculated to obtain the comprehensive interference entropy value, and the optimal strategy library level is determined based on the level selection formula; whereby the comprehensive interference entropy value represents the complexity of the overall interference environment. In the basic layer strategy library, a rule matching algorithm is used to quickly match single-dimensional interference features and output a candidate set of basic anti-interference strategies. In the scene-level policy library, multi-dimensional feature similarity matching is achieved by calculating Euclidean distance, scene classification is performed by applying the K nearest neighbor algorithm, and a scene-based combination policy candidate set is output. In the dynamic layer strategy library, successful response strategies are retrieved based on historical data similarity, and a composite similarity measurement method is used to set similarity thresholds to filter effective cases; among them, the composite similarity measurement method includes feature space similarity, interference intensity similarity, and scene context similarity.

[0014] Optionally, the overall interference entropy value The calculation formula is as follows: ; in, This represents the dimension of each feature parameter. This indicates the statistical probability percentage of each feature parameter in the total interference features; Optimal strategy library hierarchy The calculation formula is as follows: ; in, The maximum interference entropy value preset for the system; The effective cases selected in the dynamic layer strategy library based on successful historical data similarity retrieval strategies, using a composite similarity measurement method to set similarity thresholds for filtering, include: Feature space similarity is achieved using cosine similarity. The calculation formula is as follows: ; in, Represents the current set of interference feature vectors. Represents the set of historical interference feature vectors; Interference intensity similarity The calculation formula is as follows: ; in, Indicates intensity similarity; This represents the normalized value of the current interference intensity. This represents the normalized value of the historical scene interference intensity; Scene context similarity The calculation formula is as follows: ; in, Indicates the task type matching weight. Indicates the degree of task type matching. Indicates the device status matching weight. Indicates the device status matching degree, and .

[0015] Optionally, a comprehensive performance evaluation model is constructed, and the optimal anti-interference strategy is obtained from each anti-interference candidate strategy through the comprehensive performance evaluation model, including: Obtain the evaluation indicator system; the evaluation indicator system includes strategy execution time, system resource utilization, historical success rate and scenario matching degree; Based on the evaluation index system, the weighted summation method is used to calculate the comprehensive effectiveness score, which is expressed by the following formula: ; in, Indicates anti-interference candidate strategies The overall performance score; These represent the indicator weight coefficients; Indicates anti-interference candidate strategies Normalized execution time score Indicates anti-interference candidate strategies Normalized resource usage score, Indicates anti-interference candidate strategies Normalized historical success rate score Indicates anti-interference candidate strategies Normalized scene matching score; Based on the comprehensive performance score, the optimal anti-interference strategy is obtained from all anti-interference candidate strategies.

[0016] Optionally, the method proposed in this application embodiment further includes: continuously optimizing the hierarchical strategy library based on execution effect data using an intelligent learning algorithm; wherein the optimization timing includes periodic optimization, event-driven optimization, and performance warning optimization. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies of this application will be briefly introduced below. Obviously, the following drawings are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. The drawings described herein are only used to explain this application and are not intended to limit this application.

[0018] Figure 1 This is a flowchart of an anti-interference decision-making method for electronic target simulation equipment based on a hierarchical policy library provided in one embodiment of this application; Figure 2 This is another detailed flowchart of an anti-interference decision-making method for electronic target simulation devices based on a hierarchical policy library provided in one embodiment of this application; Figure 3 This is an architecture diagram of an anti-interference decision system for electronic target simulation devices based on a hierarchical policy library, provided in another embodiment of this application; Figure 4 This is a schematic diagram of the structure of an anti-interference decision device for an electronic target simulation device based on a hierarchical strategy library, provided in another embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in another embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the various embodiments of this application will be described in detail below with reference to the accompanying drawings. Those skilled in the art will understand that many technical details have been presented in the embodiments of this application to facilitate better understanding. However, the technical solutions claimed in this application can be implemented even without these technical details and various variations and modifications based on the following embodiments. The division of the following embodiments is for ease of description and should not constitute any limitation on the specific implementation of this application. The following embodiments can be combined with and referenced by each other without contradiction.

[0020] One embodiment of this application proposes an anti-interference decision-making method for electronic target simulation devices based on a hierarchical policy library, applied to electronic devices, wherein the electronic device can be a terminal or a server. This embodiment and the following embodiments will use a server as an example for description. The implementation details of the anti-interference decision-making method for electronic target simulation devices based on a hierarchical policy library proposed in this embodiment will be described in detail below. The following implementation details are provided for ease of understanding and are not necessary for implementing this solution.

[0021] The specific process of the anti-interference decision-making method for electronic target simulation equipment based on a hierarchical policy library proposed in this embodiment can be described as follows: Figure 1 As shown, it includes: Step 101: Build a layered strategy library.

[0022] The layered strategy library includes: the basic strategy library, the scenario strategy library, and the dynamic strategy library.

[0023] In one possible embodiment, a hierarchical strategy library is constructed, including: A relational database is used to build a basic layer strategy library. The basic layer strategy library stores single-parameter anti-interference strategies based on signal dimension features. Each strategy includes a strategy ID, applicable conditions, parameter adjustment range, and expected effect evaluation index. A rule engine is used to achieve fast matching.

[0024] For example, a single-parameter anti-interference strategy library based on signal dimension features can be created to store basic anti-interference methods such as frequency modulation anti-interference, spread spectrum anti-interference, power adaptive adjustment, and intelligent switching of adjustment style. Each basic strategy includes strategy ID, applicable conditions, parameter adjustment range, and expected effect evaluation index.

[0025] For example, a basic strategy table is created using a relational database, with pre-defined basic anti-interference rules. The strategy data structure of the basic layer strategy library is designed as follows: [Strategy ID, Strategy Name, Applicable Conditions, Parameter Adjustment Range, Expected Effect].

[0026] A distance-based classification algorithm is used to construct a scene-level policy library. The scene-level policy library stores multi-dimensional combination policies for typical interference scenarios, extracts multi-dimensional feature vectors based on historical interference data, establishes a mapping relationship between scene features and anti-interference policy combinations, and classifies scenes through feature similarity.

[0027] For example, a multi-dimensional rule base for typical interference scenarios can be created. Multi-dimensional feature vectors are constructed by extracting factors such as interference type, intensity level, time-frequency domain features, and duration from historical interference data. This allows for automatic classification and pattern recognition of typical interference scenarios, establishing a mapping relationship between scenario features and anti-interference strategy combinations.

[0028] For example, a scene-level policy library can be built using a distance-based classification algorithm. This involves extracting historical data, with each scene represented by a multi-dimensional feature vector, associated with one or more combined policies. The feature vector representation is as follows: .

[0029] Furthermore, the following policy data structure for the scenario-layer policy library is designed: [Scene ID, Feature Vector, Policy 1 ID, Policy 2 ID, ..., Policy n ID].

[0030] A time-series database is used to store historical interference events and the execution results of the corresponding strategies for those events, in order to construct a dynamic strategy library. The dynamic strategy library uses a time-series database to store historical interference event data. Each record includes a timestamp, interference feature vector, adopted strategy, execution result, and performance evaluation, and supports strategy retrieval based on similarity matching.

[0031] For example, a time-series database can be used to store historical interference events and the execution effects of their response strategies. Each record includes complete data such as interference feature vectors, adopted strategies, execution results, and performance evaluations. It supports strategy retrieval based on similarity matching and has an automatic data cleaning and archiving mechanism.

[0032] For example, the time-series database stores historical interference event data. Each record includes a timestamp, interference feature vector, policy ID, execution result, environmental description, and performance evaluation. The data employs an automatic cleaning mechanism, retaining only the most recently valid records.

[0033] Step 102: Generate an interference situation map based on the received interference signals.

[0034] The interference situation map includes feature vectors and situation level assessment.

[0035] For example, a multi-dimensional interference situation awareness model, i.e., an interference situation map, can be constructed based on the characteristic parameters of the interference signal.

[0036] In one possible embodiment, based on the received interference signal, an interference situation map is generated, including: Feature extraction is performed on the multidimensional features of the interference signal to obtain the feature parameters of the interference signal. The feature parameters include intensity feature parameters, pattern feature parameters, time-frequency domain feature parameters, and spatial feature parameters. By normalizing and fusing the feature parameters of the interference signal, each feature parameter is transformed into a standard dimension to form a unified feature vector. Based on the unified feature vector, the interference situation level assessment is calculated by a fuzzy comprehensive evaluation algorithm to generate an interference situation map.

[0037] For example, multiple interference features of the interference signal can be extracted in parallel. These extracted interference features include: First, interference intensity features (e.g., signal-to-interference ratio, interference power spectral density, etc.). Second, interference pattern features (e.g., identification of types such as frequency sweep interference, pulse interference, and noise interference). Third, time-frequency domain features (e.g., interference duration, bandwidth coverage, modulation period, etc.). Fourth, spatial features (e.g., spatial parameters such as interference source location and beam pointing).

[0038] For example, feature fusion technology is used to integrate multi-dimensional interference features. Through normalization, each feature parameter is transformed into a standard dimension to form a unified feature vector. Then, based on the normalization result, an interference situation level assessment with visual expression is generated, which intuitively reflects the interference intensity and distribution characteristics. Finally, a standardized situation description file is output to provide structured input for subsequent strategy matching and decision analysis.

[0039] In one possible implementation, the normalization process uses the Min-Max standardization algorithm to map each feature parameter to the [0,1] interval, and the calculation formula is as follows: ; in, Represents the normalized eigenvalues. Represents characteristic parameters, This represents the minimum value of a parameter characteristic, that is, the lower limit of the possible value of this characteristic parameter within the current system definition or calibration range. This indicates the maximum value of the parameter characteristic, that is, the upper limit of the possible value of the characteristic parameter within the current system definition or calibration range; Feature fusion employs a weighted fusion algorithm, calculated using the following formula: ; in, This represents the weight of each feature parameter. Represents the normalized eigenvalues; The interference situation score is calculated using a fuzzy comprehensive evaluation algorithm. It can be expressed by the following formula: ; in, This represents the feature membership degree of the feature parameter.

[0040] For example, the interference situation is divided into four levels—mild, moderate, severe, and extreme—based on the scoring range. For instance, if the interference situation score is in [0, 0.3), the interference situation is mild; if it is in [0.3, 0.6), the interference situation is moderate; if it is in [0.6, 0.8), the interference situation is severe; and if it is in [0.8, 1), the interference situation is extreme. Finally, a standardized situation description file is generated for the interference situation, encapsulating all feature parameters, fusion results, and situation levels in a structured data format, outputting a visually expressible interference situation map.

[0041] Step 103: Establish a multi-level strategy screening mechanism, and obtain anti-interference candidate strategies from the hierarchical strategy library based on the interference situation map through the multi-level strategy screening mechanism.

[0042] Different strategy libraries at different levels use different matching methods.

[0043] For example, based on the interference entropy value, the strategy library hierarchy is selected by real-time acquisition of the time domain, frequency domain, spatial domain, and polarization domain features of the interference signal, calculating the probability distribution of each feature dimension, and then calculating the comprehensive interference entropy value. The optimal strategy library hierarchy is determined according to the hierarchy selection formula, and then anti-interference strategies are matched in the corresponding hierarchy strategy library, finally outputting the anti-interference candidate strategies corresponding to each hierarchy.

[0044] Understandably, by establishing a multi-level strategy screening mechanism, the comprehensiveness and accuracy of strategy matching methods can be ensured.

[0045] In one possible embodiment, the multi-level strategy selection mechanism includes: calculating the probability distribution of each feature parameter to obtain a comprehensive interference entropy value and determining the optimal strategy library level; wherein, the comprehensive interference entropy value represents the complexity of the overall interference environment; in the basic layer strategy library, a rule matching algorithm is used to quickly match single-dimensional interference features and output basic anti-interference candidate strategies; in the scene layer strategy library, multi-dimensional feature similarity matching is achieved by calculating Euclidean distance, and the K-nearest neighbor algorithm is applied for scene classification to output scene-based combined candidate strategies; in the dynamic layer strategy library, candidate strategies that have successfully responded are retrieved based on historical data similarity, and effective cases are selected by setting a similarity threshold using a composite similarity measurement method; wherein, the composite similarity measurement method includes feature space similarity, interference intensity similarity, and scene context similarity.

[0046] In one possible embodiment, the combined interference entropy value The calculation formula is as follows: ; in, This represents the dimension of each feature parameter. This indicates the statistical probability percentage of each feature parameter in the total interference features; Optimal strategy library hierarchy The calculation formula is as follows: ; in, The maximum interference entropy value preset for the system; For example, The values ​​can be 1, 2, or 3; the output mapping relationship is: 1 is the base layer, 2 is the scene layer, and 3 is the dynamic layer.

[0047] As an example, in the basic policy library, a rule matching algorithm is used to quickly match basic policies to single salient features in the interference situation using a rule engine, outputting a candidate set List_basic. The specific execution steps are as follows: First, the interference features extracted in real time (such as sir=-15dB, type="NOISE") are inserted into Drools' working memory as fact objects.

[0048] Second, the Drools engine automatically triggers all rules that meet the criteria.

[0049] Third, the action part of the rule is executed, generating the corresponding anti-interference strategy object and outputting it.

[0050] Fourth, the system collects all the policies generated by the triggered rules to form a candidate set of basic layer policies.

[0051] As another example, in the scene-level policy library, the similarity between the current interference features and scenes in the scene library is first calculated. The nearest neighbor algorithm is then used for classification, and a suitable combined policy for the current scene is output. The specific execution steps are as follows: First, Euclidean distance is used to calculate the distance between the current interference situation feature vector and the feature vector of each scene in the scene database. .

[0052] .

[0053] Where X=( , , ,…, Y represents the feature vector of the current real-time interference signal. , , ,…, ) represents the feature vector of a typical scene pre-stored in the scene library.

[0054] Second, the most similar scene is selected using the K-nearest neighbor algorithm. All pre-stored scenes are sorted in ascending order of distance d, and the K scenes with the smallest distance (e.g., K=5) are selected as the "most similar scene set" for the current disturbance.

[0055] Third, the generation of the policy candidate set. From the K most similar scenarios, all policies associated with them are extracted to form an initial policy candidate set, which is then output in order. The sorting principle is as follows: (1) The more similar the template is to the current scenario, the higher the recommendation weight of its strategy; (2) If a strategy appears in multiple similar scenarios, its weights are accumulated.

[0056] As another example, in the dynamic layer policy library, the dynamic layer matching mechanism corresponds to the scene layer matching mechanism. By calculating the similarity between the current interference scene and the scenes in the policy library, a similarity threshold is set, and the policies corresponding to the scenes within the threshold are output to form a policy candidate set. A composite similarity measurement method is used to evaluate the similarity between the current interference and historical cases from multiple perspectives.

[0057] The effective cases selected in the dynamic layer strategy library based on successful historical data similarity retrieval strategies, using a composite similarity measurement method to set similarity thresholds for filtering, include: Feature space similarity is achieved using cosine similarity. The calculation formula is as follows: ; in, Represents the current set of interference feature vectors. Represents the set of historical interference feature vectors; Interference intensity similarity The calculation formula is as follows: ; in, Indicates intensity similarity; This represents the normalized value of the current interference intensity. This represents the normalized value of the historical scene interference intensity; Scene context similarity The calculation formula is as follows: ; in, Indicates the task type matching weight. Indicates the degree of task type matching. Indicates the device status matching weight. Indicates the device status matching degree, and .

[0058] For example, in similarity threshold filtering, a comprehensive similarity threshold is set. (e.g., 0.7), filter out Historical cases were included in the candidate set.

[0059] in, This represents the overall similarity score, which is a weighted average of feature, intensity, and context similarity. The calculation formula is: = ; in, α + β + γ =1.

[0060] For example, in the effect-weighted scoring, for each similar case, its overall weight is calculated. .

[0061] ; in, Indicates the success rate. As a time decay factor, recent cases have a higher weight.

[0062] For example, in policy derivation and generation, if... And the effect is excellent ( For cases with high similarity, we will directly recommend their historical strategies. For cases with moderate similarity, we will analyze their strategy combination patterns and generate new strategy combinations.

[0063] Step 104: Construct a comprehensive performance evaluation model and obtain the optimal anti-interference strategy from each anti-interference candidate strategy through the comprehensive performance evaluation model.

[0064] In one possible embodiment, a comprehensive performance evaluation model is constructed, and the optimal anti-interference strategy is obtained from each anti-interference candidate strategy through the comprehensive performance evaluation model, including: Obtain the evaluation indicator system; the evaluation indicator system includes strategy execution time, system resource utilization, historical success rate and scenario matching degree; For example, strategy execution time can represent the estimated time required for strategy execution, with a weight of 0.2; system resource utilization can include the utilization of computing resources, storage resources, and communication resources, with a weight of 0.25; historical success rate can represent a statistical evaluation based on historical execution records, with a weight of 0.3; and scenario matching degree can represent the degree of matching between the current scenario and the applicable scenario of the strategy, with a weight of 0.25.

[0065] Based on the evaluation index system, the weighted summation method is used to calculate the comprehensive effectiveness score, which is expressed by the following formula: ; in, Indicates anti-interference candidate strategies The overall performance score; These represent the indicator weight coefficients; Indicates anti-interference candidate strategies Normalized execution time score Indicates anti-interference candidate strategies Normalized resource usage score, Indicates anti-interference candidate strategies Normalized historical success rate score Indicates anti-interference candidate strategies Normalized scene matching score; Based on the comprehensive performance score, the optimal anti-interference strategy is obtained from all anti-interference candidate strategies.

[0066] For example, in a comprehensive performance evaluation model, some indicators (such as historical success rate) are subject to uncertainty; for instance, evaluations based on limited statistical data may not be accurate enough. To address this uncertainty, fuzzy logic methods can be employed, using membership functions to transform fuzzy qualitative descriptions into quantifiable numerical values, thereby enabling more reasonable calculation of indicator weights in the evaluation model. The core of membership function design is to map fuzzy concepts such as "high success rate," "medium success rate," and "low success rate" to specific mathematical representations, ensuring the objectivity and adaptability of the evaluation results.

[0067] Step 105: Execute the optimal anti-interference strategy and send it to the signal processing unit through the standard interface, while monitoring the execution status and recording the execution effect data.

[0068] For example, the highest priority anti-interference strategy after evaluation can be executed, strategy parameters can be loaded, and the signal processing unit can be sent through a standard interface to monitor the execution status and system response in real time. Then, the entire process data of the anti-interference strategy execution is recorded, including execution time, actual effect, system state changes, etc., and the execution effect data is evaluated and stored in the dynamic layer database.

[0069] For example, the standard interface could be a UDP protocol interface. Real-time monitoring is performed during the execution of the optimal anti-interference strategy, and the timeout mechanism can be set to 100 milliseconds.

[0070] For example, performance data may include execution timestamps, actual improvement in signal-to-interference ratio (SIR), and resource usage. Quantitative methods, such as the percentage improvement in SIR, are used to evaluate performance, and the data is stored in a dynamic layer database.

[0071] In one possible embodiment, the method provided in this application further includes: continuously optimizing the hierarchical strategy library using an intelligent learning algorithm based on execution effect data.

[0072] The timing of optimization includes regular optimization, event-driven optimization, and performance alert optimization.

[0073] For example, periodic optimization can refer to performing global optimization once every 24 hours; event-driven optimization can refer to triggering incremental learning when 100 new records are accumulated; and performance alert optimization can refer to starting optimization when the success rate of strategy execution is lower than a threshold.

[0074] For example, intelligent learning algorithms may include deep learning algorithms, applied genetic algorithms, and collaborative filtering algorithms. Specifically, deep learning algorithms can be used to optimize policy weights, applied genetic algorithms can be used to fine-tune policy parameters, and collaborative filtering algorithms can be used to discover potential policy associations, thereby ensuring the stability and consistency of the policy library during the optimization process.

[0075] like Figure 2 As shown, Figure 2 This is another detailed flowchart of an anti-interference decision-making method for electronic target simulation equipment based on a hierarchical strategy library, provided in one embodiment of this application. After system initialization, a hierarchical strategy library is constructed, interference signals are extracted, and then an interference situation map is generated. The strategy library level is selected, and then anti-interference strategies are screened to generate a candidate set. The strategies in the candidate set are evaluated to determine the optimal anti-interference strategy. Then, the optimal anti-interference strategy is executed, and the execution effect data is recorded. Finally, the strategy library is updated and optimized based on the execution effect data.

[0076] This application proposes an anti-interference decision-making method for electronic target simulation equipment based on a hierarchical strategy library. First, a hierarchical strategy library is constructed, and an interference situation map is generated based on the received interference signals. Then, a multi-level strategy screening mechanism is established, and anti-interference candidate strategies are obtained from the hierarchical strategy library based on the interference situation map. Next, a comprehensive performance evaluation model is constructed, and the optimal anti-interference strategy is obtained from each candidate strategy through this model. Finally, the optimal anti-interference strategy is executed and sent to the signal processing unit via a standard interface, while simultaneously monitoring the execution status and recording the execution effect data. The method provided in this application solves the technical problems of slow response and poor adaptability in traditional electronic target simulation equipment anti-interference decision-making through hierarchical collaborative decision-making and closed-loop optimization mechanisms. These mechanisms significantly improve the intelligence level and real-time performance of anti-interference decision-making in electronic target simulation equipment.

[0077] like Figure 3 As shown, Figure 3 This is another embodiment of the present application, providing an architecture diagram of an anti-interference decision-making system for electronic target simulation equipment based on a hierarchical policy library. The system includes: a perception and analysis layer, a policy construction layer, a decision execution layer, and a data storage layer; the perception and analysis layer includes a hierarchical policy library, a policy generation module, and a policy optimization module; the policy construction layer includes a signal receiving module, a feature extraction module, and a situation assessment module; the decision execution layer includes a policy selection module, an execution control module, a signal processing interface module, and an effect monitoring module; the data storage layer includes a real-time database, a historical database, and a knowledge database.

[0078] The steps described above are for clarity only. In implementation, they can be combined into one step, or some steps can be broken down into multiple steps, as long as they involve the same logical relationship, they are all within the scope of protection of this application. Adding insignificant modifications or introducing insignificant designs to the algorithm or process, without changing the core design of the algorithm and process, are also within the scope of protection of this application.

[0079] Another embodiment of this application proposes an anti-jamming decision-making device for electronic target simulation equipment based on a hierarchical policy library. The details of this embodiment's anti-jamming decision-making device are described below. The following implementation details are provided for ease of understanding and are not essential for implementing this example. Figure 4 This is a schematic diagram of the anti-interference decision-making device for electronic target simulation equipment based on a hierarchical strategy library proposed in this embodiment, including: Module 410 is used to build a layered strategy library; the layered strategy library includes: a base layer strategy library, a scene layer strategy library, and a dynamic strategy library. The generation module 420 is used to generate an interference situation map based on the received interference signal; wherein the interference situation map includes feature vectors and situation level assessment. The acquisition module 430 is used to establish a multi-level strategy screening mechanism and obtain anti-interference candidate strategies from the hierarchical strategy library based on the interference situation map; the matching methods are different for different levels of strategy library. The module 440 is used to establish a multi-level strategy screening mechanism and, based on the interference situation map, obtain anti-interference candidate strategies from the hierarchical strategy library through the multi-level strategy screening mechanism. The execution module 450 is used to execute the optimal anti-interference strategy and send it to the signal processing unit through a standard interface. At the same time, it monitors the execution status and records the execution effect data.

[0080] It is not difficult to see that this embodiment is a system embodiment corresponding to the above method embodiments, and this embodiment can be implemented in conjunction with the above method embodiments. The relevant technical details and technical effects mentioned in the above method embodiments are still valid in this embodiment, and will not be repeated here to reduce repetition. Accordingly, the relevant technical details mentioned in this embodiment can also be applied to the above method embodiments.

[0081] It is worth mentioning that all modules and units involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this application, this embodiment does not introduce units that are not closely related to solving the technical problems proposed in this application; however, this does not mean that other units do not exist in this embodiment.

[0082] Another embodiment of this application provides an electronic device, such as Figure 5 As shown, it includes a processor 51 and a memory 52. ​​The memory 52 stores instructions that the processor 51 can execute. When the processor 51 is configured to execute the instructions, the electronic device can implement an anti-interference decision method for an electronic target simulation device based on a hierarchical policy library as described in the above method embodiment.

[0083] The memory and processor are connected via a bus, which includes any number of interconnecting buses and bridges, connecting various circuits of one or more processors and the memory. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and will not be described further herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be a single component or multiple components, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor is transmitted over the wireless medium via an antenna, which further receives data and transmits it to the processor.

[0084] The processor manages the bus and general processing, and also provides various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory is used to store data used by the processor during operation.

[0085] Another embodiment of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, can implement an anti-interference decision-making method for electronic target simulation equipment based on a hierarchical policy library as described in the above method embodiments.

[0086] That is, those skilled in the art will understand that all or part of the steps in the above method embodiments can be implemented by a program instructing related hardware. The program is stored in a storage medium and includes several instructions to cause a device (such as a microcontroller, chip, etc.) or processor to execute all or part of the steps of the method described in the method embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0087] Those skilled in the art will understand that the above embodiments are specific implementations of this application, and in practical applications, various changes can be made in form and detail without departing from the spirit and scope of this application. For those skilled in the art, several improvements and modifications can be made without departing from the principles of this application, and these improvements and modifications are also considered to be within the scope of protection of this application.

Claims

1. A method for anti-interference decision-making of electronic target simulation equipment based on a hierarchical strategy library, characterized in that, The method includes: Construct a layered strategy library; the layered strategy library includes: a basic strategy library, a scenario-level strategy library, and a dynamic strategy library; Based on the received interference signals, an interference situation map is generated; the interference situation map includes feature vectors and situation level assessment. A multi-level strategy screening mechanism is established, and based on the interference situation map, anti-interference candidate strategies are obtained from the hierarchical strategy library through the multi-level strategy screening mechanism; the matching methods are different for different levels of strategy library. A comprehensive performance evaluation model is constructed, and the optimal anti-interference strategy is obtained from each anti-interference candidate strategy through the comprehensive performance evaluation model; The optimal anti-interference strategy is executed and sent to the signal processing unit through a standard interface. At the same time, the execution status is monitored and the execution effect data is recorded.

2. The method according to claim 1, characterized in that, The construction of the layered strategy library includes: A relational database is used to build a basic layer strategy library. The basic layer strategy library stores single-parameter anti-interference strategies based on signal dimension features. Each strategy includes a strategy ID, applicable conditions, parameter adjustment range, and expected effect evaluation index. A rule engine is used to achieve fast matching. A distance-based classification algorithm is used to construct a scene-layer strategy library. The scene-layer strategy library stores multi-dimensional combination strategies for typical interference scenarios, extracts multi-dimensional feature vectors based on historical interference data, establishes a mapping relationship between scene features and anti-interference strategy combinations, and classifies scenes through feature similarity. A time-series database is used to store historical interference events and the execution results of the corresponding strategies for those events, in order to construct a dynamic strategy library. The dynamic strategy library uses a time-series database to store historical interference event data. Each record includes a timestamp, interference feature vector, adopted strategy, execution result, and performance evaluation, and supports strategy retrieval based on similarity matching.

3. The method according to claim 1, characterized in that, The generation of an interference situation map based on the received interference signal includes: Multidimensional features of the interference signal are extracted to obtain the feature parameters of the interference signal; the feature parameters include intensity feature parameters, pattern feature parameters, time-frequency domain feature parameters, and spatial feature parameters; By normalizing and fusing the characteristic parameters of the interference signal, each characteristic parameter is transformed into a standard dimension to form a unified feature vector. Based on a unified feature vector, a fuzzy comprehensive evaluation algorithm is used to calculate the interference situation level assessment in order to generate an interference situation map.

4. The method according to claim 3, characterized in that, The normalization process uses the Min-Max standardization algorithm to map each feature parameter to the [0,1] interval. The calculation formula is as follows: ； in, Represents the normalized eigenvalues. Represents characteristic parameters, This represents the minimum value of a parameter characteristic, that is, the lower limit of the possible value of this characteristic parameter within the range defined or calibrated in the current system. This indicates the maximum value of the parameter characteristic, that is, the upper limit of the possible value of the characteristic parameter within the current system definition or calibration range; Feature fusion employs a weighted fusion algorithm, calculated using the following formula: ； in, This represents the weight of each feature parameter. Represents the normalized eigenvalues; The interference situation score is calculated using a fuzzy comprehensive evaluation algorithm. It can be expressed by the following formula: ； in, This represents the feature membership degree of the feature parameter.

5. The method according to claim 1, characterized in that, A multi-level strategy filtering mechanism includes: The probability distribution of each feature parameter is calculated to obtain the comprehensive interference entropy value, and the optimal strategy library level is determined; whereby the comprehensive interference entropy value represents the complexity of the overall interference environment; In the basic layer strategy library, a rule matching algorithm is used to quickly match single-dimensional interference features and output basic anti-interference candidate strategies. In the scene-level policy library, multi-dimensional feature similarity matching is achieved by calculating Euclidean distance, scene classification is performed by applying the K nearest neighbor algorithm, and scene-based combination candidate policies are output. In the dynamic layer strategy library, candidate strategies that have been successfully responded to based on historical data similarity are retrieved, and effective cases are screened by setting a similarity threshold using a composite similarity measurement method. The composite similarity measurement method includes feature space similarity, interference intensity similarity, and scene context similarity.

6. The method according to claim 5, characterized in that, Comprehensive interference entropy value The calculation formula is as follows: ； in, This represents the dimension of each feature parameter. This indicates the statistical probability percentage of each feature parameter in the total interference features; Optimal strategy library hierarchy The calculation formula is as follows: ； in, The maximum interference entropy value preset for the system; The effective cases selected in the dynamic layer strategy library based on successful historical data similarity retrieval strategies, using a composite similarity measurement method to set similarity thresholds for filtering, include: Feature space similarity is achieved using cosine similarity. The calculation formula is as follows: ； in, Represents the current set of interference feature vectors. Represents the set of historical interference feature vectors; Interference intensity similarity The calculation formula is as follows: ； in, Indicates intensity similarity; This represents the normalized value of the current interference intensity. This represents the normalized value of the historical scene interference intensity; Scene context similarity The calculation formula is as follows: ； in, Indicates the task type matching weight. Indicates the degree of task type matching. Indicates the device status matching weight. Indicates the device status matching degree, and .

7. The method according to claim 1, characterized in that, The construction of a comprehensive performance evaluation model, and the obtaining of the optimal anti-interference strategy from various anti-interference candidate strategies through the comprehensive performance evaluation model, includes: Obtain the evaluation indicator system; the evaluation indicator system includes strategy execution time, system resource utilization, historical success rate, and scenario matching degree; Based on the evaluation index system, the weighted summation method is used to calculate the comprehensive effectiveness score, which is expressed by the following formula: ； in, Indicates anti-interference candidate strategies The overall performance score; These represent the indicator weight coefficients; Indicates anti-interference candidate strategies Normalized execution time score Indicates anti-interference candidate strategies Normalized resource usage score, Indicates anti-interference candidate strategies Normalized historical success rate score Indicates anti-interference candidate strategies Normalized scene matching score; Based on the comprehensive performance score, the optimal anti-interference strategy is obtained from all anti-interference candidate strategies.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Based on execution performance data, an intelligent learning algorithm is used to continuously optimize the hierarchical strategy library; the optimization timing includes periodic optimization, event-driven optimization, and performance alert optimization.

9. An electronic device, characterized in that, include: A processor and a memory, wherein the memory stores instructions executable by the processor, and the processor is configured to, when executing the instructions, enable the electronic device to implement the anti-interference decision method for electronic target simulation devices based on a hierarchical policy library as described in any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it can implement the anti-interference decision-making method for electronic target simulation equipment based on a hierarchical strategy library as described in any one of claims 1 to 8.

Images