Real-time simulation method, device and equipment based on multi-domain situation awareness and storage medium

Abstract

The invention provides a real-time simulation method, device and equipment based on multi-domain situation awareness and a storage medium, and the method comprises the steps: firstly obtaining data sources of a plurality of combat domains, and carrying out the preprocessing of the data source of each combat domain; wherein the data source comprises land domain data, sea area data, airspace data, sky domain data and network domain data; fusing the preprocessed data sources of the combat domains to generate unified multi-domain data, and constructing a simulation model based on the unified multi-domain data; experimental factors are obtained, the experimental factors are used for constructing multiple experimental schemes through an orthogonal test, the multiple experimental schemes are input into the simulation model to generate key indexes, and the key indexes comprise combat target achievement conditions, military strength consumption, combat time and resource consumption; and dynamically optimizing the key indexes, and outputting a combat decision scheme which can be used for reference of a command and control system. The problem that the decision of a command and control system is affected due to insufficient simulation precision is solved.

Description

Technical Field

[0001] The present invention relates to the field of simulation, and in particular to a real-time simulation method, device, equipment and storage medium based on multi-domain situational awareness. Background Art

[0002] As the combat space gradually expands from the traditional land, sea, and air to multi-dimensional fields such as space and network, the information transmission and data interaction between various combat domains are becoming increasingly complex, making it difficult for simulation systems built based on single-domain data to accurately reflect the real-time situation of the battlefield. Existing technologies mostly use independent data acquisition and processing methods, and pre-process and simply fuse radar, image, sonar, and network data separately. As a result, when facing heterogeneous and dynamic data from multiple combat domains such as land, sea, air, space, and network, the simulation system has problems such as slow response, insufficient data fusion, insufficient simulation accuracy, and difficulty in generating reliable decision-making plans in a timely manner, thus affecting the decision-making support capabilities of the command and control system in a rapidly changing battlefield environment.

[0003] In view of this, this application is filed. Summary of the invention

[0004] The present invention discloses a real-time simulation method, device, equipment and storage medium based on multi-domain situational awareness, aiming to solve the problem of inadequate simulation accuracy affecting the decision-making of command and control systems.

[0005] The first embodiment of the present invention provides a real-time simulation method based on multi-domain situational awareness, comprising: Acquire data sources of multiple combat domains, and pre-process the data sources of each combat domain respectively; wherein the data sources include land domain data, sea domain data, air domain data, space domain data, and network domain data; fusing the pre-processed data sources of each combat domain to generate unified multi-domain data, and constructing a simulation model based on the unified multi-domain data; Acquire experimental factors, construct multiple experimental schemes using orthogonal experiments for the experimental factors, and input the multiple experimental schemes into the simulation model to generate key indicators, wherein the key indicators include the achievement of combat objectives, manpower consumption, combat time, and resource consumption; The key indicators are dynamically optimized and the output is used to generate combat decision plans that can be used as reference for the command and control system.

[0006] Preferably, the land area data includes troop deployment and topography collected by ground reconnaissance radar and unmanned aerial vehicle reconnaissance equipment; preprocessing the land area data includes using sliding window statistics to calculate the local mean and standard deviation to identify and eliminate Gaussian noise and impulse noise; The sea area data includes sea target information obtained through shipborne sonar and maritime reconnaissance satellites; preprocessing the sea area data includes calculating the first and third quartiles and interquartile ranges using a box plot method to determine the range of outliers and perform median replacement; The airspace data includes an aerial target image obtained by using an aerial reconnaissance aircraft-borne optoelectronic sensor and a synthetic aperture radar; preprocessing the airspace data includes performing image smoothing processing on the airspace data using wavelet threshold denoising and Gaussian filtering, and implementing geometric correction; The sky data includes cloud and surface feature information collected by satellite images; preprocessing the sky data includes using a convolutional neural network to detect and remove clouds, and combining multi-temporal data to perform time series compensation; The network domain data includes network communication and network attack data obtained through network monitoring equipment; pre-processing the network domain data includes using SHA-256 or MD5 hash algorithm to remove duplications and uniformly converting them into a standard TCP / IP format.

[0007] Preferably, the pre-processed data sources of each combat domain are fused to generate unified multi-domain data, specifically: The Bayesian fusion algorithm is used to calculate the prior probability and likelihood probability of the data from different sensors to obtain the fused posterior probability distribution; The Kalman filter algorithm is used to predict and update the data of the posterior probability distribution, and the state of the target is continuously estimated. For some static or slowly changing data, weights are assigned according to the reliability of each data source and a weighted average algorithm is used for fusion.

[0008] Preferably, it also includes: Selecting the same target data from the unified multi-domain data, using a convolutional neural network to automatically extract features of the same target data and preliminarily identify target information, and using a recurrent neural network to process the time series information of the target to predict its motion trajectory; Generate target candidate areas based on the initially identified target information, and further extract features and classify and identify each candidate area to obtain accurate positioning of the target; The precise positioning is fed back to the convolutional neural network and the recurrent neural network to optimize the prediction of the target's motion trajectory so as to continuously update the target state in real time.

[0009] Preferably, it also includes: Selecting target data from the unified multi-domain data, performing principal component analysis and dimensionality reduction processing on the target data, and optimizing the input weights and thresholds of the extreme learning machine using an improved particle swarm optimization algorithm to obtain a preliminary threat assessment value; A graph convolutional network is used to perform convolution operations on the spatial topological relationship and attribute information between targets, the preliminary threat assessment value is combined with the mutual influence between targets, and the target threat value is corrected and sorted according to the combined result.

[0010] A second embodiment of the present invention provides a real-time simulation device based on multi-domain situational awareness, comprising: A preprocessing unit, used to obtain data sources of multiple combat domains, and preprocess the data sources of each combat domain respectively; wherein the data sources include land domain data, sea domain data, air domain data, space domain data, and network domain data; A simulation model building unit: used for fusing the pre-processed data sources of each combat domain to generate unified multi-domain data, and building a simulation model based on the unified multi-domain data; A key indicator generating unit is used to obtain experimental factors, construct multiple experimental schemes using the experimental factors by orthogonal experiments, and input the multiple experimental schemes into the simulation model to generate key indicators, wherein the key indicators include the achievement of combat objectives, manpower consumption, combat time and resource consumption; The optimization unit is used to dynamically optimize the key indicators and output a combat decision plan for reference by the command and control system.

[0011] The third embodiment of the present invention provides a real-time simulation device based on multi-domain situational awareness, including a memory and a processor, wherein a computer program is stored in the memory, and the computer program can be executed by the processor to implement a real-time simulation method based on multi-domain situational awareness as described in any one of the above items.

[0012] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored therein, and the computer program can be executed by a processor of a device where the computer-readable storage medium is located to implement a real-time simulation method based on multi-domain situational awareness as described in any one of the above items.

[0013] Based on the first embodiment of the present invention, a real-time simulation method, device, equipment and storage medium based on multi-domain situational awareness are provided, by first obtaining data sources of multiple combat domains, and preprocessing the data sources of each combat domain respectively; wherein the data sources include land data, sea data, air data, sky data, and network data; then, the preprocessed data sources of each combat domain are integrated to generate unified multi-domain data, and a simulation model is constructed based on the unified multi-domain data; then, experimental factors are obtained, and multiple experimental schemes are constructed using orthogonal experiments for the experimental factors, and the multiple experimental schemes are input into the simulation model to generate key indicators, wherein the key indicators include the achievement of combat objectives, force consumption, combat time and resource consumption; finally, the key indicators are dynamically optimized, and output for generating combat decision-making schemes for reference by the command and control system. The problem of insufficient simulation accuracy affecting the decision-making of the command and control system is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a flowchart of a real-time simulation method based on multi-domain situational awareness provided by the first embodiment of the present invention; Figure 2 It is a module schematic diagram of a real-time simulation device based on multi-domain situational awareness provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0015] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0017] It should be clear that the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0019] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0020] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0021] The "first\second" mentioned in the embodiments is only to distinguish similar objects, and does not represent a specific order for the objects. It is understandable that the "first\second" can be interchanged with the specific order or sequence where permitted. It should be understood that the objects distinguished by "first\second" can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than those illustrated or described herein.

[0022] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0023] The present invention discloses a real-time simulation method, device, equipment and storage medium based on multi-domain situational awareness, aiming to solve the problem of inadequate simulation accuracy affecting the decision-making of command and control systems.

[0024] See also Figure 1 The first embodiment of the present invention provides a real-time simulation method based on multi-domain situational awareness, which can be executed by a real-time simulation device based on multi-domain situational awareness (hereinafter referred to as a simulation device), and in particular, executed by one or more processors in the simulation device to at least implement the following steps: S101, obtaining data sources of multiple combat domains, and preprocessing the data sources of each combat domain respectively; wherein the data sources include land domain data, sea domain data, air domain data, space domain data, and network domain data; In this embodiment, the simulation device can be a terminal with data processing capabilities such as a desktop computer, a laptop computer, a workstation, etc., which can establish communication connections with sensor components in multiple combat domains. The simulation device can be installed with a corresponding operating system and application software, and the functions required by this embodiment are realized through the combination of the operating system and the application software.

[0025] It should be noted that the land data is collected by ground reconnaissance radar and UAV reconnaissance equipment, and its content covers troop deployment and terrain information. When preprocessing the land data, the system conducts time series analysis on the troop deployment and terrain information collected by ground reconnaissance radar and UAV reconnaissance equipment, and establishes a mathematical model to decompose the radar signal into effective signal and noise signal, where the noise mainly includes Gaussian noise and impulse noise; then, the signal is locally statistically analyzed by the sliding window method, the mean and standard deviation within the window are calculated, and the signal that deviates from the mean by more than a certain multiple is marked as noise data according to the preset abnormal judgment threshold, thereby realizing noise removal, and at the same time, the missing values ​​in the effective signal are filled by linear interpolation to ensure the continuity of the signal; in addition, in order to ensure the accuracy of time series analysis, the timestamps of all radar signals are uniformly parsed as ISO 8601 standard format, and dynamically correct the random errors caused by the inherent errors of the equipment and the environmental influence through Kalman filtering, and convert the geographic coordinates into the WGS84 coordinate system. The processed data is finally packaged in XML format containing fields such as timestamp, coordinate information and signal strength, and stored as HDF5 files; For sea area data, the information of sea targets is collected through shipborne sonar and maritime reconnaissance satellites. The preprocessing is mainly for the sea target information collected by shipborne sonar and maritime reconnaissance satellites. The box plot method is used to calculate the first quartile, third quartile and interquartile range of the data, and then the normal range and abnormal value range of the data are determined. For abnormal values ​​beyond the range, the median or mean is replaced according to the data distribution characteristics to achieve effective correction of the abnormal values; at the same time, the depth data of the sonar signal is converted to a standard numerical format (such as unified into meters or feet), and an error model is established to correct the delay and frequency parameters of the signal to ensure data accuracy. In this process, the timestamp of the sonar data is also converted to a standard format of seconds, and its geographic coordinates are also converted to the WGS84 coordinate system. Finally, the preprocessed sea area data is encapsulated in XML format and stored as an HDF5 file; The airspace data is collected by the photoelectric sensors and synthetic aperture radars carried by aerial reconnaissance aircraft. The preprocessing process uses the wavelet threshold method to denoise the image data collected by the photoelectric sensors and synthetic aperture radars carried by aerial reconnaissance aircraft. The image is decomposed into wavelet coefficients of different frequencies and thresholded to effectively remove random noise. The image is then smoothed with the Gaussian filter algorithm to prevent excessive blurring of the image edge information. On this basis, in order to improve the processing efficiency and compatibility of the data, the image data is converted into the NumPy array format, and the geometric correction technology is introduced to calculate the correction parameters according to the sensor error and shooting angle to ensure that the image data can accurately reflect the real position and shape of the target. At the same time, the timestamp of the image data is uniformly converted to the second-level standard format, and its geographic coordinates are converted to the WGS84 coordinate system. The processed image data is also encapsulated in XML format and stored as an HDF5 file. Tianyu Data collects cloud and surface feature information through satellite images. In the preprocessing process, in order to solve the cloud occlusion problem in satellite images, a convolutional neural network model is first built to train a large amount of labeled data, so as to automatically identify and remove cloud areas, and combine multi-phase satellite images for time series compensation to supplement the areas blocked by clouds. In addition, dark current, gain and atmospheric correction steps are used for radiation calibration, and a polynomial model is used to correct geometric distortion in combination with ground control points and satellite orbit parameters to ensure that the image data has consistent radiation and geometric accuracy at different times and between sensors. Finally, the timestamp and geographic coordinates of the satellite image are converted into the ISO 8601 standard format and the WGS84 coordinate system respectively, and the processed data is encapsulated in XML format and stored as an HDF5 file. The network domain data is collected by network monitoring equipment for network communication and network attack data. The preprocessing process uses SHA-256 or MD5 hash algorithm to perform hash calculations on key fields in the data (such as IP address, port number and timestamp) to address the duplication and format diversity problems of network monitoring data, thereby efficiently removing duplicate records and converting data packets from different sources into the standard TCP / IP protocol format. For non-standard protocol data, it is mapped to standard fields through the protocol conversion module. At the same time, the timestamp of the data packet is dynamically corrected based on the clock synchronization error model to ensure the time accuracy of network event records, and the geographic location information in the network data (if any) is converted into the WGS84 coordinate system. Finally, all preprocessed network domain data is encapsulated in XML format containing fields such as timestamp, coordinates, protocol type, source address and destination address, and stored as HDF5 files after integrity verification.

[0026] S102, fusing the pre-processed data sources of each combat domain to generate unified multi-domain data, and constructing a simulation model based on the unified multi-domain data; In this embodiment, the simulation device first integrates the pre-processed data from the land, sea, air, space, and network combat domains, calculates the prior probability of the data collected by different sensors and the likelihood probability of the measured value, and uses the Bayesian fusion algorithm to obtain the fused posterior probability distribution, which realizes the statistical integration of the data in each domain, so that the heterogeneity between the data is effectively bridged. Then, the simulation device uses the Kalman filter algorithm to continuously predict and update the data in the posterior probability distribution, so as to make real-time and dynamic estimates of the target state (such as position, speed, etc.), and continuously corrects the prediction results on this basis to ensure continuous tracking of the target state in a dynamic environment. At the same time, for some static or slowly changing data, the simulation device assigns corresponding weights based on the historical performance and reliability of each data source, and uses the weighted average algorithm to fuse the data again to further improve the accuracy of the data. The above multi-level fusion processing generates unified and accurate multi-domain data; In this embodiment, the simulation device extracts key state variables and environmental parameters based on these data, and establishes a mathematical model that reflects the interaction between various combat domains. Subsequently, by adopting discrete event simulation and hybrid simulation technology, a simulation framework that can dynamically reflect target movement, environmental changes and tactical interactions is constructed. The framework uses the fused real-time data as the initial condition and dynamic input, and realizes real-time tracking of the target state through continuous state updates. Among them, multiple sub-models are set inside the model to describe the target position, speed, sensor detection capability and the synergy effect of each domain. These sub-models are interconnected through predefined interfaces to ensure that the overall simulation system can be updated synchronously when receiving external data input. In addition, the simulation device also uses historical data and previous combat drill results to calibrate and verify the model parameters during the model construction process to ensure that the simulation results are consistent with the actual battlefield situation. The entire process always maintains the time synchronization and spatial consistency of the data, so that the simulation model can not only reflect the dynamic changes of various elements in a complex battlefield environment in real time, but also has strong prediction capabilities and decision support functions.

[0027] S103, obtaining experimental factors, constructing multiple experimental schemes using the experimental factors by using orthogonal experiments, and inputting the multiple experimental schemes into the simulation model to generate key indicators, wherein the key indicators include the achievement of combat objectives, manpower consumption, combat time, and resource consumption; In this embodiment, the simulation device determines the various experimental factors that affect the combat effect through in-depth analysis of multi-domain data and historical combat exercise data according to combat needs and actual battlefield conditions. The experimental factors may include but are not limited to force deployment, weapon equipment configuration, tactical selection, environmental factors, and logistics resource allocation, and on this basis, the orthogonal experimental design method is used to construct multiple experimental schemes. The simulation device uses the balance and statistical efficiency of orthogonal experiments in factor combinations to generate experimental groups covering different parameter levels and combinations, so as to fully explore the impact of each factor on the combat effect under the premise of minimizing the number of experiments. Then, these experimental schemes are input into the pre-constructed simulation model, which is based on unified multi-domain data, and through real-time dynamic simulation of the interaction and changes of various elements of the battlefield, continuously calculates and generates a series of key indicators, including but not limited to the achievement of combat objectives, force consumption, combat time, and resource consumption. As a result, the simulation device can intuitively evaluate the combat effectiveness under different experimental schemes, provide data support and optimization basis for command decision-making, and realize scientific planning of combat strategies and resource allocation.

[0028] S104, dynamically optimizing the key indicators and outputting an operational decision plan for reference by the command and control system.

[0029] In this embodiment, the simulation device first dynamically evaluates each experimental scheme based on the key indicator data generated by the previous simulation experiment, and uses the pre-set benefit function to weight the sum of indicators such as the achievement of combat objectives, force consumption, combat time and resource consumption, so as to obtain the comprehensive performance score of each scheme. Subsequently, the simulation device automatically selects the scheme with relatively excellent performance, and on this basis, combines the real-time simulation results with the opinions of military experts to make subtle adjustments to the force deployment, combat strategy and weapon use in the advantageous scheme, such as optimizing the offensive route of the land force or improving the blockade strategy of the naval fleet to better adapt to the current battlefield environment. The adjusted scheme is input into the simulation model again for verification. The simulation device dynamically updates the benefit function parameters by comparing the simulation results before and after optimization, ensuring that the improvement effect of the final optimization scheme is significant and the key indicators are effectively improved. Finally, after multiple rounds of iterative optimization, the simulation device outputs a verified and optimized combat decision plan.

[0030] In a possible implementation of the present invention, the following may also be included: The simulation device first selects the same target data from the unified multi-domain data. The data may come from the reconnaissance radar in the land domain, the reconnaissance image in the air domain, or other sensors. After data fusion, it has a unified time and space reference. Then, the simulation device uses the pre-trained convolutional neural network to automatically extract the key features in the target image data in the computer, thereby realizing preliminary target recognition, and uses the recurrent neural network to analyze the time series information of the target data, predict its motion trajectory, and realize dynamic estimation of the initial state of the target. Based on the preliminary recognition results, the simulation device generates a candidate target area, and further extracts features and classifies and recognizes them in the candidate area through a series of area generation algorithms (such as the improved R-CNN method), so as to obtain the precise positioning information of the target. It is worth noting that the precise positioning information will be fed back to the convolutional neural network and recurrent neural network modules to update and optimize the feature extraction parameters and time series prediction model of the target, so as to realize the continuous real-time update and tracking of the target state.

[0031] In a possible implementation of the present invention, the following may also be included: The simulation device first selects target data from the unified multi-domain data, and performs principal component analysis and dimensionality reduction processing on the indicators that affect the threat level in the target data to eliminate the redundancy and correlation between the indicators, and then extract the most representative features. Subsequently, the simulation device uses an improved particle swarm optimization algorithm to adaptively adjust the input weights and thresholds of the extreme learning machine (ELM). By continuously iteratively searching for the optimal solution during the optimization process, the ELM can more accurately reflect the actual threat value of the target when performing threat assessment based on dimensionality reduction features, thereby obtaining preliminary threat assessment results. Next, the simulation device uses a graph convolutional network (GCN) to perform convolution operations on the spatial topological relationships between the selected targets and their attribute information. This process can capture the complex relationships between the targets in terms of spatial layout and mutual influence, and combine these relationships with the preliminary threat assessment values ​​to achieve dynamic correction and sorting of the threat values ​​of each target.

[0032] See also Figure 2 The second embodiment of the present invention provides a real-time simulation device based on multi-domain situational awareness, comprising: The preprocessing unit 201 is used to obtain data sources of multiple combat domains and preprocess the data sources of each combat domain respectively; wherein the data sources include land domain data, sea domain data, air domain data, sky domain data, and network domain data; The simulation model building unit 202 is used to fuse the pre-processed data sources of each combat domain to generate unified multi-domain data, and build a simulation model based on the unified multi-domain data; The key indicator generating unit 203 is used to obtain experimental factors, construct multiple experimental schemes using the experimental factors by orthogonal experiments, and input the multiple experimental schemes into the simulation model to generate key indicators, wherein the key indicators include the achievement of combat objectives, manpower consumption, combat time and resource consumption; The optimization unit 204 is used to dynamically optimize the key indicators and output a combat decision plan for reference by the command and control system.

[0033] The third embodiment of the present invention provides a real-time simulation device based on multi-domain situational awareness, including a memory and a processor, wherein a computer program is stored in the memory, and the computer program can be executed by the processor to implement a real-time simulation method based on multi-domain situational awareness as described in any one of the above items.

[0034] The fourth embodiment of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored therein, and the computer program can be executed by a processor of a device where the computer-readable storage medium is located to implement a real-time simulation method based on multi-domain situational awareness as described in any one of the above items.

[0035] Based on the first embodiment of the present invention, a real-time simulation method, device, equipment and storage medium based on multi-domain situational awareness are provided, by first obtaining data sources of multiple combat domains, and preprocessing the data sources of each combat domain respectively; wherein the data sources include land data, sea data, air data, sky data, and network data; then, the preprocessed data sources of each combat domain are integrated to generate unified multi-domain data, and a simulation model is constructed based on the unified multi-domain data; then, experimental factors are obtained, and multiple experimental schemes are constructed using orthogonal experiments for the experimental factors, and the multiple experimental schemes are input into the simulation model to generate key indicators, wherein the key indicators include the achievement of combat objectives, force consumption, combat time and resource consumption; finally, the key indicators are dynamically optimized, and output for generating combat decision-making schemes for reference by the command and control system. The problem of insufficient simulation accuracy affecting the decision-making of the command and control system is solved.

[0036] Exemplarily, the computer program described in the third embodiment and the fourth embodiment of the present invention can be divided into one or more modules, and the one or more modules are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the real-time simulation device for implementing a multi-domain situational awareness. For example, the device described in the second embodiment of the present invention.

[0037] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the real-time simulation method based on multi-domain situational awareness, and uses various interfaces and lines to connect the various parts of the real-time simulation method based on multi-domain situational awareness.

[0038] The memory can be used to store the computer program and / or module, and the processor realizes various functions of a real-time simulation method based on multi-domain situational awareness by running or executing the computer program and / or module stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, a text conversion function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, text message data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0039] Wherein, if the implemented module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0040] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0041] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A real-time simulation method based on multi-domain situational awareness, characterized in that: include: Acquire data sources of multiple combat domains, and pre-process the data sources of each combat domain respectively; wherein the data sources include land domain data, sea domain data, air domain data, space domain data, and network domain data; fusing the pre-processed data sources of each combat domain to generate unified multi-domain data, and constructing a simulation model based on the unified multi-domain data; Acquire experimental factors, construct multiple experimental schemes using orthogonal experiments for the experimental factors, and input the multiple experimental schemes into the simulation model to generate key indicators, wherein the key indicators include the achievement of combat objectives, manpower consumption, combat time, and resource consumption; The key indicators are dynamically optimized and the output is used to generate combat decision plans that can be used as reference for the command and control system.

2. The real-time simulation method based on multi-domain situational awareness according to claim 1, characterized in that: The land data includes troop deployment and topography collected by ground reconnaissance radar and unmanned aerial vehicle reconnaissance equipment; preprocessing the land data includes using sliding window statistics to calculate local mean and standard deviation to identify and eliminate Gaussian noise and impulse noise; The sea area data includes sea target information obtained through shipborne sonar and maritime reconnaissance satellites; preprocessing the sea area data includes calculating the first and third quartiles and interquartile ranges using a box plot method to determine the range of outliers and perform median replacement; The airspace data includes an aerial target image obtained by using an aerial reconnaissance aircraft-borne optoelectronic sensor and a synthetic aperture radar; preprocessing the airspace data includes performing image smoothing processing on the airspace data using wavelet threshold denoising and Gaussian filtering, and implementing geometric correction; The sky data includes cloud and surface feature information collected by satellite images; preprocessing the sky data includes using a convolutional neural network to detect and remove clouds, and combining multi-temporal data to perform time series compensation; The network domain data includes network communication and network attack data obtained through network monitoring equipment; pre-processing the network domain data includes using SHA-256 or MD5 hash algorithm to remove duplications and uniformly converting them into a standard TCP / IP format.

3. The real-time simulation method based on multi-domain situational awareness according to claim 1, characterized in that: The pre-processed data sources of each combat domain are integrated to generate unified multi-domain data, specifically: The Bayesian fusion algorithm is used to calculate the prior probability and likelihood probability of the data from different sensors to obtain the fused posterior probability distribution; The Kalman filter algorithm is used to predict and update the data of the posterior probability distribution, and the state of the target is continuously estimated. For some static or slowly changing data, weights are assigned according to the reliability of each data source and a weighted average algorithm is used for fusion.

4. The real-time simulation method based on multi-domain situational awareness according to claim 1, characterized in that: Also includes: Selecting the same target data from the unified multi-domain data, using a convolutional neural network to automatically extract features of the same target data and preliminarily identify target information, and using a recurrent neural network to process the time series information of the target to predict its motion trajectory; Generate target candidate areas based on the initially identified target information, and further extract features and classify and identify each candidate area to obtain accurate positioning of the target; The precise positioning is fed back to the convolutional neural network and the recurrent neural network to optimize the prediction of the target's motion trajectory so as to continuously update the target state in real time.

5. The real-time simulation method based on multi-domain situational awareness according to claim 1, characterized in that: Also includes: Selecting target data from the unified multi-domain data, performing principal component analysis and dimensionality reduction processing on the target data, and optimizing the input weights and thresholds of the extreme learning machine using an improved particle swarm optimization algorithm to obtain a preliminary threat assessment value; A graph convolutional network is used to perform convolution operations on the spatial topological relationship and attribute information between targets, the preliminary threat assessment value is combined with the mutual influence between targets, and the target threat value is corrected and sorted according to the combined result.

6. A real-time simulation device based on multi-domain situational awareness, characterized in that: include: A preprocessing unit, used to obtain data sources of multiple combat domains, and preprocess the data sources of each combat domain respectively; wherein the data sources include land domain data, sea domain data, air domain data, space domain data, and network domain data; A simulation model building unit: used for fusing the pre-processed data sources of each combat domain to generate unified multi-domain data, and building a simulation model based on the unified multi-domain data; A key indicator generating unit is used to obtain experimental factors, construct multiple experimental schemes using the experimental factors by orthogonal experiments, and input the multiple experimental schemes into the simulation model to generate key indicators, wherein the key indicators include the achievement of combat objectives, manpower consumption, combat time and resource consumption; The optimization unit is used to dynamically optimize the key indicators and output a combat decision plan for reference by the command and control system.

7. A real-time simulation device based on multi-domain situational awareness, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the computer program can be executed by the processor to implement a real-time simulation method based on multi-domain situational awareness as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: A computer program is stored, and the computer program can be executed by a processor of the device where the computer-readable storage medium is located to implement a real-time simulation method based on multi-domain situational awareness as described in any one of claims 1 to 5.

Images