Multi-index unification and time sequence aggregation method and device for drone swarm jamming effectiveness

Abstract

The application provides a method and device for multi-index normalization and time sequence aggregation of unmanned aerial vehicle swarm interference effectiveness, which comprises the following steps: dividing the to-be-evaluated indexes according to index types; performing normalization processing on the time sequence indexes in the case that the index type of the to-be-evaluated indexes is a time sequence index; and respectively processing different types of indexes in the normalized time sequence indexes by using different event-driven aggregation operators to obtain corresponding strategy-level scalar utilities, wherein the strategy-level scalar utility is valued in [0, 1], and the greater the value of the strategy-level scalar utility, the better. According to the category difference normalization processing and aggregation, the scalarized entropy indexes and time sequence indexes are consistent in the same framework, and then the multiple indexes with different physical meanings, dimensions and time scales are unified into comparable strategy-level scalars reflecting dynamic adaptability. In addition, the indexes can be compared and fused on the same scale after processing, and the direction and dimension conflicts are eliminated.

Description

Technical Field

[0001] This application relates to the field of UAV swarm cooperative electronic countermeasures and effectiveness evaluation, specifically to a method and apparatus for unifying and temporally aggregating multiple indicators of UAV swarm jamming effectiveness. Background Technology

[0002] In the process of drone swarms dynamically jamming radar, the evaluation indicators differ significantly in physical meaning, dimension, direction, and time scale: electromagnetic suppression indicators use power ratio or probability as the dimension, with higher values ​​being better; swarm state indicators (such as collision risk) have lower values ​​being better; and swarm intelligence emergence indicators use information entropy as the dimension, with direction requiring semantic judgment. Furthermore, some indicators are time-series outputs at each time step, while others are scalars quantized at the policy level. However, existing methods lack a mechanism for directional consistency. Summary of the Invention

[0003] In view of this, the purpose of this application is to provide a method and apparatus for unifying and time-series aggregation of multiple indicators of UAV swarm interference effectiveness, which can unify multiple indicators with different physical meanings, dimensions and time scales into comparable, dynamic adaptive strategy-level scalars.

[0004] In a first aspect, embodiments of this application provide a method for unmanned aerial vehicle (UAV) swarm interference effectiveness multi-index consistency and temporal aggregation, comprising: classifying the indicators to be evaluated into index types; when the index type of the indicators to be evaluated is a temporal index, performing consistency processing on the temporal index; and processing different categories of the consistent temporal indexes using different event-driven aggregation operators to obtain their respective corresponding policy-level scalar utilities; wherein the policy-level scalar utility takes values ​​in the range [0,1] and the larger the value of the policy-level scalar utility, the better.

[0005] In the above implementation process, normalization and aggregation based on category differences can avoid redundant normalization and unreasonable biases, ensuring that scalarized entropy indicators and time-series indicators have consistent definitions within the same framework. This unifies multiple types of indicators with vastly different physical meanings, dimensions, and time scales into comparable, dynamically adaptive strategy-level scalars. Furthermore, after uniform mapping, all indicators satisfy the principle of "the larger the better," allowing for comparison and fusion on the same scale and eliminating conflicts in direction and dimension.

[0006] In one embodiment, the time-series indicators include: interference effectiveness indicators and cluster status indicators.

[0007] In one embodiment, the step of processing different categories of time-series indicators after unification using different event-driven aggregation operators to obtain their respective policy-level scalar utilities includes: when the indicator is an interference performance indicator, constructing an evaluation time set; wherein the evaluation time set includes the union of the event window of external events and the steady-state sampling time; and taking the average of the utility sequence of the interference performance indicator on the evaluation time set to obtain the policy-level scalar utility of the interference performance indicator.

[0008] In the above implementation process, when the indicator is a disturbance performance indicator, the constructed evaluation time set includes both event windows and steady-state sampling points. This can avoid the dilution of the full-time domain average by the silent period and also avoid the loss of steady-state information by a single-moment snapshot, thus taking into account both event response and steady state.

[0009] In one embodiment, the step of processing different categories of time-series indicators after consistency processing using different event-driven aggregation operators to obtain their respective corresponding policy-level scalar utilities includes: when the indicator is a cluster state indicator, introducing an event weighting function and performing weighted mean aggregation on the utility sequence of the cluster state indicator in the full time domain to obtain its policy-level scalar utility; wherein, the weighting coefficient of the event weighting function within the event window of the external event is greater than the weighting coefficient outside the event window.

[0010] In the above implementation process, when the metric is a cluster state metric, introducing an event weighting function can make the aggregation result more sensitive to the disturbance response within the event window, distinguishing between high-adaptive and low-adaptive policies. For example, at the frequency jump event t=60, the fixed policy continues to mismatch after the event, while the adaptive policy recovers quickly, effectively amplifying the difference and highlighting the dynamic adaptive differences driven by the event.

[0011] In one embodiment, the event weighting function is a step function or a continuous kernel function that decays with time distance.

[0012] In one embodiment, the time-series index is uniformized using a directional and uniformity mapping function, a linear range normalization function, a piecewise linear mapping function, or tanh. In one embodiment, after classifying the indicator to be evaluated into indicator types, the method further includes: if the indicator type of the indicator to be evaluated is a strategy-level scalar indicator, directly using the self-defined value of the strategy-level scalar indicator as the strategy-level scalar utility.

[0013] In the above implementation process, for policy-level scalar indicators, directly using them as policy-level scalar utilities can avoid redundant normalization and improve processing efficiency.

[0014] Secondly, embodiments of this application also provide a device for unmanned aerial vehicle (UAV) swarm interference effectiveness multi-index consistency and temporal aggregation, comprising: a type classification module for classifying the index to be evaluated into index types; a consistency processing module for performing consistency processing on the temporal index when the index type of the index to be evaluated is a temporal index; and a processing module for processing different categories of the temporal index after consistency processing using different event-driven aggregation operators to obtain their respective corresponding policy-level scalar utility.

[0015] Thirdly, embodiments of this application also provide an electronic device, including: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the machine-readable instructions are executed by the processor to perform the steps of the method described in the first aspect or any possible implementation of the first aspect.

[0016] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the method for unmanned aerial vehicle swarm interference effectiveness multi-index consistency and timing aggregation in the first aspect or any possible implementation of the first aspect.

[0017] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, specific embodiments are described below in conjunction with the accompanying drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a block diagram of an electronic device provided in an embodiment of this application.

[0020] Figure 2 The flowchart illustrates the method for unmanned aerial vehicle (UAV) swarm interference effectiveness multi-index consistency and temporal aggregation provided in this application embodiment.

[0021] Figure 3 This is a schematic diagram of the functional modules of the device for unmanned aerial vehicle swarm interference effectiveness multi-index consistency and time-series aggregation provided in the embodiments of this application. Detailed Implementation

[0022] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0023] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] During the process of drone swarms dynamically jamming radar, the evaluation indicators differ significantly in physical meaning, dimension, direction, and time scale: electromagnetic suppression indicators use power ratio or probability as the dimension and the larger the value, the better; swarm state indicators (such as collision risk) use smaller values, the better; and swarm intelligence emergence indicators use information entropy as the dimension and the direction needs to be combined with semantic judgment. At the same time, some indicators are time-series outputs at each time step, while others are scalars that have been scalarized at the policy level.

[0025] Existing techniques for evaluating indicators involved in the dynamic jamming of radar by drone swarms include: the first category is indicator normalization methods, which use range normalization, Z-score standardization, etc. to map indicators of different dimensions to a unified range; the second category is time series aggregation methods, which often use simple averaging across the entire time domain or single-time snapshots to obtain policy-level scalars before comparison.

[0026] The aforementioned existing technologies have the following objective drawbacks when evaluating the effectiveness of dynamic bee colony defense: (1) Lack of a directional consistency mechanism. The advantages and disadvantages of different indicators are inconsistent (the higher the benefit, the better; the lower the cost, the better). Simply normalizing and directly adding or ranking them will cause directional conflicts, leading to distorted evaluation.

[0027] (2) Static or snapshot-based aggregation cannot reflect dynamics. A simple average across the entire time domain will be diluted by a large number of silent periods without events, making it difficult to reflect the adaptive differences of the strategy under event-driven conditions; while a single-moment snapshot will lose steady-state information.

[0028] (3) Use the same aggregation operator for different categories of indicators. The generation methods and time granularity of performance, state and quantified entropy indicators are different. Unified processing will introduce unreasonable bias or duplicate normalization.

[0029] In view of this, this application proposes a method for unifying and time-series aggregation of multiple indicators of UAV swarm interference effectiveness. By processing and aggregating indicators according to category differences, it avoids redundant normalization and unreasonable biases, ensuring that scalarized entropy-based indicators and time-series indicators are consistent within the same framework. This unifies multiple types of indicators with vastly different physical meanings, dimensions, and time scales into comparable, policy-level scalars that reflect dynamic adaptability. Furthermore, all indicators, after unification mapping, satisfy the principle of "the larger the better," allowing for comparison and fusion on the same scale and eliminating conflicts in direction and dimension.

[0030] To facilitate understanding of this embodiment, the electronic device that performs the method for unmanned aerial vehicle swarm interference effectiveness multi-index consistency and time-series aggregation disclosed in this application embodiment will first be described in detail.

[0031] like Figure 1 The diagram shown is a block illustration of an electronic device. The electronic device 100 may include a memory 111 and a processor 113. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device 100. For example, the electronic device 100 may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0032] The aforementioned memory 111 and processor 113 are electrically connected to each other directly or indirectly to enable data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses or signal lines. The aforementioned processor 113 is used to execute executable modules stored in the memory.

[0033] The memory 111 can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory 111 stores programs, and the processor 113 executes these programs upon receiving execution instructions. The methods executed by the electronic device 100 as defined in any embodiment of this application can be applied to the processor 113, or implemented by the processor 113.

[0034] The aforementioned processor 113 may be an integrated circuit chip with signal processing capabilities. The processor 113 may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a digital signal processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor.

[0035] The electronic device 100 in this embodiment can be used to execute various steps in the various methods provided in the embodiments of this application. The implementation process of the method for unmanned aerial vehicle (UAV) swarm interference effectiveness multi-index consistency and temporal aggregation is described in detail below through several embodiments.

[0036] Please see Figure 2 This is a flowchart of the method for unmanned aerial vehicle (UAV) swarm interference effectiveness multi-index consistency and temporal aggregation provided in the embodiments of this application. The following will describe... Figure 2 The specific process shown will be explained in detail.

[0037] Step 201: Classify the indicators to be evaluated into different types.

[0038] The types of metrics here can include time-series metrics and policy-level scalar metrics. Time-series metrics include those related to interference effectiveness and cluster status. These time-series metrics can be derived from the simulation output of the original time-series sequence and / or intermediate time-series sequence.

[0039] The strategy-level scalar metrics include the swarm intelligence emergence entropy metric, which has been scalarized at the strategy level.

[0040] The above-mentioned policy-level scalar utility takes values ​​in the range [0,1], and the larger the value of the policy-level scalar utility, the better.

[0041] Step 202: If the indicator to be evaluated is a time-series indicator, perform consistency processing on the time-series indicator.

[0042] The time-series indicators here can be mapped using a directional consistency mapping function, which maps the original sequence to a utility sequence in the interval [0,1]. This directional consistency mapping function can be used to eliminate differences in the dimensions and directions of advantage and disadvantage between different indicators, so that both benefit-type indicators (the larger the better) and cost-type indicators (the smaller the better) satisfy the unified semantics of "the larger the better" after mapping.

[0043] In one embodiment, the standardization of this time-series metric can be expressed by the following formula: ; in, For the unified interval, For directional uniformity mapping functions, It is a time-series indicator.

[0044] In one embodiment, for cost-type indicators that are naturally in the [0,1] interval, the directional consistency mapping function can degenerate into a complementary mapping, i.e., the output value is 1 minus the original value.

[0045] Step 203: For different categories of time-series metrics after the consistency processing, different event-driven aggregation operators are used to process them to obtain their respective policy-level scalar utilities.

[0046] In the above implementation process, normalization and aggregation based on category differences can avoid redundant normalization and unreasonable biases, ensuring that scalarized entropy indicators and time-series indicators have consistent definitions within the same framework. This unifies multiple types of indicators with vastly different physical meanings, dimensions, and time scales into comparable, dynamically adaptive strategy-level scalars. Furthermore, after uniform mapping, all indicators satisfy the principle of "the larger the better," allowing for comparison and fusion on the same scale and eliminating conflicts in direction and dimension.

[0047] In one possible implementation, the time-series metrics include: interference effectiveness metrics and cluster status metrics.

[0048] The jamming effectiveness metrics here are used to directly measure the jamming effect of drone swarms on enemy radar. These metrics are measured in units of power ratio (signal strength ratio) or probability (such as detection probability, interception probability), and are benefit-oriented metrics; that is, the higher the value, the better. For example, a higher suppression ratio indicates a better jamming effect.

[0049] The aforementioned swarm status indicators are used to evaluate flight safety and collaborative stability within the swarm during adversarial processes. These swarm status indicators typically include metrics such as collision risk, reflecting the spatial safety margin among drones within the swarm. They are cost-based indicators, meaning that the lower the value, the better (lower collision risk is better).

[0050] In one possible implementation, step 203 includes: when the indicator is a disturbance effectiveness indicator, constructing an evaluation time set; taking the average of the utility sequence of the disturbance effectiveness indicator on the evaluation time set to obtain the policy-level scalar utility of the disturbance effectiveness indicator.

[0051] The evaluation time set includes the union of the event windows of external events and the steady-state sampling times.

[0052] In one embodiment, the event window can be represented by the following formula: ; The steady-state sampling time can be expressed by the following formula: ; The set of evaluation times can be represented as: ; in, For window length, The sampling interval is... The moment when the external event occurs. This represents the total number of simulation steps. For the sampling point index, For steady-state sampling time, For the event window, It is a collection of external event moments.

[0053] The sampling interval here is a pre-configured fixed interval, which can be configured according to the scenario.

[0054] Optionally, external events can be sudden changes in parameters such as radar operating frequency, transmit power, or beam pointing angle; in extended scenarios, they can also include jamming command issuance, jamming mode switching, swarm topology changes, or sudden threat alarms, and these external events can be set according to actual conditions.

[0055] The mean of the above-mentioned utility series of interference effectiveness indicators can be expressed by the following formula: ; Optionally, the strategy-level scalar utility of the interference effectiveness index can be obtained by taking the median of the utility sequence of the interference effectiveness index over the evaluation time set. Alternatively, the strategy-level scalar utility of the interference effectiveness index can be obtained by taking the quantile of the utility sequence of the interference effectiveness index over the evaluation time set. The method for obtaining the strategy-level scalar utility of the interference effectiveness index can be selected according to the actual situation.

[0056] In the above implementation process, when the indicator is a disturbance performance indicator, the constructed evaluation time set includes both event windows and steady-state sampling points. This can avoid the dilution of the full-time average by the silent period and the loss of steady-state information by a single snapshot, thus taking into account both event response and steady state.

[0057] In one possible implementation, step 203 includes: when the metric is a cluster state metric, introducing an event weighting function and performing weighted mean aggregation on the utility sequence of the cluster state metric over the entire time domain to obtain its policy-level scalar utility.

[0058] Among them, cluster status indicators can be calculated in the entire time domain.

[0059] In one embodiment, to highlight the perturbation effect of event-driven events on the cluster state while preserving steady-state constraints, an event weighting function is introduced. The event-weighted average aggregation can be expressed by the following formula: ,otherwise ; .

[0060] in, The length of the event window. These are the weighting coefficients.

[0061] The length of the event window and / or the weighting coefficients mentioned here are configurable parameters.

[0062] The weighting coefficients of the event weighting function described above are greater inside the event window than outside the event window. (For example, the weighting coefficient β>1 inside the event window and 1 outside the window).

[0063] In the above implementation process, when the metric is a cluster state metric, introducing an event weighting function can make the aggregation result more sensitive to the disturbance response within the event window, distinguishing between high-adaptive and low-adaptive policies. For example, at the frequency jump event t=60, the fixed policy continues to mismatch after the event, while the adaptive policy recovers quickly, effectively amplifying the difference and highlighting the dynamic adaptive differences driven by the event.

[0064] In one possible implementation, the event weighting function is either a step function or a continuous kernel function that decays over time.

[0065] The step function here is a piecewise constant function. Within the defined event window, the weights abruptly change to a constant greater than 1 (β>1); outside the event window, the weights remain at their base value (1). The weights undergo discontinuous abrupt changes (steps) at the boundaries of the event window. All moments within the window are assigned the same fixed weight, regardless of their proximity to the event occurrence. The step function allows for a simple, hard-truncation of the indicator weights within the event window, directly amplifying the event-driven perturbation effect on the cluster state.

[0066] The aforementioned continuous kernel function that decays over time is a smooth, continuous mathematical function (such as a Gaussian kernel or an exponentially decaying function). Its weights gradually decrease as the time distance between the current evaluation moment and the event's occurrence moment increases. The weight changes of this continuous kernel function are continuous and smooth, without abrupt boundary changes. The closer to the event's center moment, the greater the weight; the farther away, the weight gradually decays and approaches the base value. Using a continuous kernel function that decays over time allows for a more refined reflection of the dynamic evolution of the event's impact. It can demonstrate the objective law that the event disturbance has the greatest impact at its occurrence and then gradually weakens, avoiding the unreasonable bias that might result from the hard truncation at the window edge of a step function.

[0067] In one possible implementation, the time-series index is uniformized using a directional and uniformity mapping function, a linear range normalization function, a piecewise linear mapping function, or tanh. The directional and uniform mapping function here is used to map original time-series index sequences with different physical meanings and dimensions to the [0,1] interval. Its core characteristic is "directional uniformity," that is, regardless of whether the original index is benefit-oriented (the larger the better) or cost-oriented (the smaller the better), after processing by this function, it is uniformly transformed into the semantics of "the larger the better." For indices that are already naturally in the [0,1] interval, this function degenerates into an identity mapping (benefit-oriented) or a complementary mapping $1-x$ (cost-oriented).

[0068] Linear range normalization functions typically refer to Min-Max normalization. It uses linear scaling based on the maximum and minimum values ​​of the data. For benefit-related indicators, it uses $(x - \min) / (\max - \min)$; for cost-related indicators, it uses $(\max - x) / (\max - \min)$. It achieves dimensionless calculation and directional consistency through a simple linear transformation, and its calculation is intuitive, but it is sensitive to extreme outliers in the data.

[0069] Piecewise linear mapping functions divide the range of an indicator into multiple sub-intervals, and map each sub-interval using a linear function with different slopes and intercepts, resulting in a piecewise linear pattern. Its advantage lies in its flexibility; it can assign higher mapping sensitivity to critical threshold intervals (such as safety thresholds) and lower sensitivity to flat intervals, based on the actual physical meaning of the indicator, thus more accurately reflecting the actual effectiveness of the indicator.

[0070] The tanh function exhibits a smooth S-shaped curve with a range of (-1, 1). In practical applications, it is often mapped to the [0,1] interval through translation and scaling (e.g., $(tanh(x)+1) / 2$). Its central region is approximately linear, and it tends to saturate at both ends. The main function of this nonlinear compression is to suppress the influence of extreme outliers, smoothly compressing excessively large or small original index values ​​to the vicinity of the [0,1] boundary, thereby improving the robustness of the evaluation.

[0071] In one possible implementation, after step 201, the method further includes: if the indicator type of the indicator to be evaluated is a strategy-level scalar indicator, directly using the self-defined value of the strategy-level scalar indicator as the strategy-level scalar utility.

[0072] Understandably, strategy-level scalar metrics have already been scalarized according to their respective definitions, taking values ​​in the range [0,1] with larger values ​​being better. Therefore, once the metric to be evaluated is determined to be a strategy-level scalar metric, secondary time-series normalization or aggregation is no longer performed; it is directly used as the strategy-level scalar utility, avoiding redundant normalization.

[0073] Through the method in this embodiment, all types of indicators are unified into a strategy-level scalar utility with values ​​in the range [0,1] and "the larger the better", which then serves as a stable input for subsequent comprehensive scoring.

[0074] In the above implementation process, for policy-level scalar indicators, directly using them as policy-level scalar utilities can avoid redundant normalization and improve processing efficiency.

[0075] Based on the same application concept, this application also provides a device for unmanned aerial vehicle (UAV) swarm interference effectiveness multi-index consistency and time-series aggregation corresponding to the UAV swarm interference effectiveness multi-index consistency and time-series aggregation method. Since the principle of the device in this application is similar to that of the aforementioned UAV swarm interference effectiveness multi-index consistency and time-series aggregation method embodiment, the implementation of the device in this embodiment can refer to the description in the above method embodiment, and the repeated parts will not be repeated.

[0076] Please see Figure 3This is a functional module diagram of the UAV swarm interference effectiveness multi-index consistency and timing aggregation device provided in this application embodiment. Each module in the UAV swarm interference effectiveness multi-index consistency and timing aggregation device in this embodiment is used to execute the steps in the above method embodiments. The UAV swarm interference effectiveness multi-index consistency and timing aggregation device includes a type classification module, a consistency processing module, and a processing module; wherein, The type classification module is used to classify the indicators to be evaluated into different types.

[0077] The consistency processing module is used to perform consistency processing on time-series indicators when the indicator to be evaluated is a time-series indicator.

[0078] The processing module is used to process different categories of time-series metrics after the consistency processing using different event-driven aggregation operators to obtain their respective policy-level scalar utilities.

[0079] In one possible implementation, the processing module is specifically used to: construct an evaluation time set when the indicator is a disturbance effectiveness indicator; wherein the evaluation time set includes the union of the event window of the external event and the steady-state sampling time; and take the mean of the utility sequence of the disturbance effectiveness indicator on the evaluation time set to obtain the policy-level scalar utility of the disturbance effectiveness indicator.

[0080] In one possible implementation, the processing module is specifically used to: when the indicator is a cluster state indicator, introduce an event weighting function, and perform weighted mean aggregation on the utility sequence of the cluster state indicator in the full time domain to obtain its policy-level scalar utility; wherein, the weighting coefficient of the event weighting function within the event window of the external event is greater than the weighting coefficient outside the event window.

[0081] In one possible implementation, the processing module is further configured to: when the indicator type of the indicator to be evaluated is a strategy-level scalar indicator, directly use the self-defined value of the strategy-level scalar indicator as the strategy-level scalar utility.

[0082] Furthermore, this application embodiment also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the UAV swarm interference effectiveness multi-index consistency and timing aggregation method in the above method embodiment.

[0083] The computer program product of the method for unmanned aerial vehicle (UAV) swarm interference effectiveness multi-index consistency and timing aggregation provided in this application includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the steps of the method for unmanned aerial vehicle (UAV) swarm interference effectiveness multi-index consistency and timing aggregation in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0084] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0085] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0086] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various 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 (ROM), random access memory (RAM), magnetic disks, or optical disks. It should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0087] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for unifying and temporally aggregating multiple indicators of UAV swarm interference effectiveness, characterized in that, include: Classify the indicators to be evaluated into different types; When the indicator to be evaluated is a time-series indicator, the time-series indicator is subjected to a consistency process. Different event-driven aggregation operators are used to process the different categories of time-series metrics after the unification process to obtain their respective policy-level scalar utilities. The strategy-level scalar utility takes values ​​in the range [0,1], and the larger the value of the strategy-level scalar utility, the better.

2. The method according to claim 1, characterized in that, in, The time-series indicators include: interference effectiveness indicators and cluster status indicators.

3. The method according to claim 2, characterized in that, The different categories of time-series metrics after the standardization process are processed using different event-driven aggregation operators to obtain their respective policy-level scalar utilities, including: When the indicator is the interference effectiveness indicator, an evaluation time set is constructed; wherein, the evaluation time set includes the union of the event window of the external event and the steady-state sampling time; The strategy-level scalar utility of the interference effectiveness index is obtained by averaging the utility sequences of the interference effectiveness index over the set of evaluation times.

4. The method according to claim 2, characterized in that, The different categories of time-series metrics after the standardization process are processed using different event-driven aggregation operators to obtain their respective policy-level scalar utilities, including: When the indicator is the cluster state indicator, an event weighting function is introduced, and the utility sequence of the cluster state indicator is aggregated by weighted mean in the full time domain to obtain its policy-level scalar utility. The weighting coefficient of the event weighting function within the event window of the external event is greater than the weighting coefficient outside the event window.

5. The method according to claim 4, characterized in that, The event weighting function is either a step function or a continuous kernel function that decays with time distance.

6. The method according to claim 1, characterized in that, in, The time-series index is standardized using a directional and uniform mapping function, a linear range normalization function, a piecewise linear mapping function, or tanh.

7. The method according to claim 1, characterized in that, After classifying the indicators to be evaluated into different types, the method further includes: When the indicator to be evaluated is a strategy-level scalar indicator, the self-defined value of the strategy-level scalar indicator is directly used as the strategy-level scalar utility.

8. A device for unmanned aerial vehicle (UAV) swarm interference effectiveness multi-index consistency and temporal aggregation, characterized in that, include: The type classification module is used to classify the indicators to be evaluated into different types. A consistency processing module is used to perform consistency processing on the time-series indicator when the indicator type of the indicator to be evaluated is a time-series indicator. The processing module is used to process different categories of time-series indicators after the consistency processing using different event-driven aggregation operators to obtain their respective policy-level scalar utilities.

9. An electronic device, characterized in that, include: Processor, memory, the memory storing machine-readable data that the processor can execute. The read instruction, when the electronic device is running, performs the steps of the method as described in any one of claims 1 to 7 when the machine-readable instruction is executed by the processor.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method as described in any one of claims 1 to 7.

Images