A Virtual Simulation Confrontation Dynamic Demonstration System and Method Based on Electronic Sand Table

By employing multi-dimensional situational awareness switching, weapon behavior simulation, and user intent prediction, the system addresses the issues of limited situational awareness and insufficient interactive intelligence in electronic sand table systems, enabling flexible battlefield simulations and forward-looking decision support.

CN123071601APending Publication Date: 2026-11-10HANGZHOU DIANZI UNIV +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611267526.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-20
Publication Date
2026-11-10

AI Technical Summary

Technical Problem

Existing electronic sand table systems suffer from limited battlefield situation dimensions, rigid simulation of physical behavior, and insufficient human-computer interaction intelligence, making it difficult to conduct flexible, realistic, and forward-looking battlefield simulations.

Method used

It employs a multi-dimensional complex situation switching module, a weapon behavior dynamic simulation module, and a user behavior dynamic control module. By collecting sensor data, it constructs a multi-dimensional battlefield situation model, calculates weapon and equipment behavior in real time, and predicts user operational intentions, thereby achieving dynamic adjustment and intelligent prediction of the battlefield situation.

Benefits of technology

It enables multi-dimensional battlefield situation display and weapon user intent analysis, provides forward-looking decision support, and enhances the intelligence and flexibility of battlefield simulation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123071601A_ABST
    Figure CN123071601A_ABST
Patent Text Reader

Abstract

This invention relates to the field of virtual simulation electronic warfare, providing a virtual simulation combat dynamic demonstration system and method based on an electronic sand table. In this embodiment, a multi-dimensional complex situation switching module can construct several situation models of different dimensions using multi-source data from different dimensions within the combat environment, adjusting the combat situation models and data when a dimension switch is triggered. A weapon behavior dynamic simulation module can calculate the behavior of weapon equipment models in real time based on collected real-time data and constructed behavior rule models, simulating the execution of the predicted behavior to obtain the predicted execution result. A user behavior dynamic control module can determine the user's intention based on the user's operation signals, predict the user's next operation probabilistically based on historical operations, and provide intelligent prediction for virtual simulations based on the prediction results. This solves the problems of a single situation dimension in combat scenarios and insufficient intelligence in the simulation process, making it difficult for commanders to obtain forward-looking decision support.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of military simulation electronic warfare, and in particular to a virtual simulation combat dynamic demonstration system and method based on an electronic sand table. Background Technology

[0002] In modern military exercises and operational simulations, electronic sand table systems have become important decision-making support tools. However, traditional electronic sand table systems often focus on static or pre-programmed situational displays, resulting in a single-dimensional battlefield model that struggles to flexibly and seamlessly switch between different levels of abstraction (such as strategic panorama and tactical details). This prevents commanders from dynamically adjusting the granularity of their observations based on battlefield focus. Furthermore, the behaviors of various entities within the system often rely on fixed scripts, lacking the ability to simulate and extrapolate autonomous behaviors based on real-time data and rule-based models. This leads to a rigid simulation process that fails to realistically reflect the complex and ever-changing battlefield dynamics. In addition, the human-computer interaction methods of existing systems are relatively passive, unable to effectively identify and predict user intentions, resulting in insufficient intelligence in the simulation process and hindering commanders from obtaining forward-looking decision support. Summary of the Invention

[0003] In view of this, this application provides a virtual simulation confrontation dynamic demonstration system and method based on electronic sand table to solve the problems of existing electronic sand table systems, such as single battlefield situation dimension, rigid entity behavior simulation and insufficient human-computer interaction intelligence, making it difficult to conduct flexible, realistic and forward-looking battlefield simulations.

[0004] The first aspect of this application provides a battlefield simulation and confrontation dynamic demonstration system based on an electronic sand table. The system includes a multi-dimensional complex situation switching module, a weapon behavior dynamic simulation module, and a user behavior dynamic control module. The multi-dimensional complex situation switching module is used to collect data through sensors to obtain multi-source data of different dimensions, then determine several battlefield situation models of different dimensions based on the multi-source data, and adjust the battlefield situation models and data when the battlefield triggers a dimension switch. The weapon behavior dynamic simulation module is used to set initial state parameters for the weapon equipment model according to the actual scenario or needs, and then calculate the next predicted behavior of the weapon equipment model in real time based on the collected real-time data and the trained weapon behavior rule model, and simulate the execution of the predicted behavior to obtain the predicted execution result. The weapon behavior rule model defines the behavior patterns of each weapon equipment under various conditions. The user behavior dynamic control module is used to acquire multi-source operation signals input by the user, determine the user's operation intention in real time, and then make probability predictions on the user's next operation through historical operation data to obtain the estimated user operation result. The estimated user operation result is then used to provide intelligent prediction for battlefield simulation.

[0005] Optionally, the sensors include optical sensors, two-dimensional phased array LD sensors, and laser LD sensors, and the battlefield situation models of different dimensions include two-dimensional battlefield situation models and three-dimensional battlefield situation models.

[0006] Optionally, adjusting the battlefield situation model and data when the battlefield triggers a high-low dimension switch includes: Pre-set the dimension switching trigger method and perform real-time detection; When a switch from low dimension to high dimension is detected, the low-dimensional battlefield situation model is switched to a high-dimensional battlefield situation model, and the missing high-dimensional information is supplemented by an interpolation algorithm. When a switch from high-dimensional to low-dimensional is detected, the high-dimensional battlefield situation model is projected, transformed, and simplified. Then, the graphics rendering engine is used to render the low-dimensional battlefield situation model in real time according to its format and parameters.

[0007] Optionally, the initial state parameters in the weapon behavior dynamic simulation module include initial position, initial velocity, initial attitude, and initial weapon equipment state.

[0008] Optionally, the weapon behavior dynamic simulation module also includes a dynamic visualization display unit, which is used to transmit the calculated weapon equipment model behavior data to the electronic sand table in real time, and dynamically display the process of simulating the execution of the predicted behavior in the virtual scene through three-dimensional rendering technology.

[0009] Optionally, the weapon behavior dynamic simulation module further includes a dynamic adjustment unit, which compares the predicted behavior of the weapon equipment model with the actual behavior to obtain the corresponding deviation value, and updates the weapon behavior rule model when the deviation value is greater than a preset deviation threshold.

[0010] Optionally, the user behavior dynamic control module includes a sand table situation dynamic rendering unit; The sand table dynamic rendering unit includes a parameter generator and a scene discriminator. The parameter generator is used to generate rendering parameters based on the real-time state of the sand table. The scene discriminator is used to compare the scene generated based on the rendering parameters with a pre-stored scene to determine the corresponding difference information, and then adjust the rendering parameters based on the difference information.

[0011] Optionally, the system further includes a digital twin driving module for constructing digital twins for each object in the electronic sandbox, the digital twins being used to map the physical state and behavior of the objects in real time.

[0012] A second aspect of this application provides a method for dynamically demonstrating adversarial simulation cases based on an electronic sand table, the method comprising: Collect multi-source data of different dimensions on the battlefield, determine several battlefield situation models of different dimensions based on the multi-source data, and adjust the battlefield situation models and data when the battlefield triggers a dimension switch. Based on the actual scenario or requirements, initial state parameters are set for the weapon equipment model. Then, based on the collected real-time data and the trained weapon behavior rule model, the predicted behavior of the weapon equipment model is calculated in real time, and the predicted behavior is simulated to obtain the predicted execution result. The system acquires multi-source operation signals from user input, determines the user's operation intention in real time, and then uses historical operation data to predict the probability of the user's next operation to obtain the estimated user operation result. Finally, the estimated user operation result is used to provide intelligent prediction for battlefield simulation.

[0013] In the embodiments provided in this application, the multi-dimensional complex situation switching module can construct several battlefield situation models of different dimensions using multi-source data of different dimensions on the battlefield, and adjust the battlefield situation models and data when a dimension switch is triggered on the battlefield; the weapon behavior dynamic simulation module can calculate the behavior of weapon equipment models in real time based on the collected real-time data and the constructed behavior rule model, and simulate the execution of the predicted behavior to obtain the predicted execution result; the user behavior dynamic control module can determine the user's intention based on the user's operation signal, and make probability predictions of the user's next operation based on historical operations, and provide intelligent predictions for battlefield simulation based on the prediction results. This solves the problem of a single battlefield situation dimension and enables battlefield simulation based on real-time battlefield data. It also addresses the problem that the human-computer interaction method of existing systems is relatively passive, unable to effectively identify and predict the user's operation intention, resulting in insufficient intelligence in the simulation process and difficulty for commanders to obtain forward-looking decision support. Attached Figure Description

[0014] Figure 1 A system block diagram provided for embodiments of this application; Figure 2 A flowchart illustrating the method provided in this application embodiment; Figure 3 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0015] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0016] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0017] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0018] This application provides a virtual simulation combat dynamic demonstration system and method based on an electronic sand table to provide a multi-dimensional battlefield situation display and analyze and predict weapon and user intentions, thereby realizing battlefield simulation and enabling commanders to obtain forward-looking decision support.

[0019] The technical solutions of this application will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0020] like Figure 1 The diagram shown is a system module diagram of a battlefield simulation and confrontation dynamic demonstration system based on an electronic sand table provided in this application. The system includes a multi-dimensional complex situation switching module, a weapon behavior dynamic simulation module, and a user behavior dynamic control module.

[0021] The functions and implementation process of each module are explained below: Module 1, Multi-Dimensional Complex Situation Switching Module. This module is used to collect data through sensors to obtain multi-source data of different dimensions, then determine several battlefield situation models of different dimensions based on the multi-source data, and adjust the battlefield situation models and data when a dimension switch is triggered on the battlefield.

[0022] This module requires data collection on the terrain and equipment of various areas on the electronic sand table. The collected data is then used to construct battlefield situation models of different dimensions, including terrain and military equipment models. For example, two-dimensional and three-dimensional models are used: The construction process of the two-dimensional battlefield situation model is as follows: First, data acquisition can be performed using high-resolution optical sensors, such as visible light cameras, infrared thermal imaging cameras, and two-dimensional phased array (LD) sensors. The UAV can be equipped with sensors to scan the terrain, landforms, and various military facilities in the target area from different heights and angles. Static data can be collected for fixed military facilities, and dynamic data can be collected for moving targets. Multi-source data such as target position, speed, acceleration, attitude angles (pitch angle, yaw angle, roll angle), engine condition, ammunition reserves, characteristics, and thermal radiation can be obtained.

[0023] Then, a model was constructed. For terrain models, the traditional approach of relying solely on GIS software was abandoned, and a Generative Adversarial Network (GAN) from deep learning was used to build a terrain generation model. A large amount of military area data with different landforms and terrain features was collected as a training set to train the generator and discriminator. The generator generates a two-dimensional terrain model based on input terrain-related parameters (such as altitude range, slope distribution, etc.), while the discriminator judges the similarity between the generated model and the real terrain data. After multiple rounds of adversarial training, the generated two-dimensional terrain model closely approximates the real terrain. Compared to models built with traditional GIS software, it can more accurately represent complex terrain details, such as the folds of mountains and the contours of canyons.

[0024] For military equipment models, 3D models are retrieved from the military equipment model library and projected onto a 2D plane for adaptation. For unknown or special targets, reverse engineering technology is used to construct 2D contour and feature models through point cloud data or images. Optical, LD and other auxiliary data are integrated in a unified coordinate system using data fusion algorithms, and machine learning-based optimization algorithms are used to train the model with a large amount of labeled military target data to optimize model details.

[0025] The construction process of the three-dimensional battlefield situation model is as follows: The first step is data acquisition. Unlike the two-dimensional model, in addition to the data collected by the optical and LD sensors mentioned above, a laser LD sensor is added to acquire three-dimensional point cloud data of the target area. The acquired optical images, LD data, and laser LD point cloud data are then preprocessed, including data cleaning, format conversion, and geographic coordinate calibration, to remove noise and standardize the data format and coordinate system.

[0026] Then, the model is constructed. For the terrain model, a point cloud-based meshing algorithm is used to construct a three-dimensional terrain model from the preprocessed laser LD point cloud data.

[0027] For military equipment models, a method combining model library matching and local detail reconstruction is used to construct 3D military equipment models with realistic textures and accurate geometric structures by combining texture information from optical images and geometric information from point cloud data. The 3D terrain model and the 3D military equipment model are then fused to form a complete 3D battlefield situation model.

[0028] After determining the battlefield situation models in different dimensions, users can set the models currently displayed on the electronic sand table according to different needs, and can adjust the current models manually or automatically.

[0029] When manually triggered, a model switching button can be set on the operation page, allowing users to switch the currently displayed model using this button.

[0030] When automatically triggered, switching conditions and corresponding results can be preset, such as switching from low-dimensional to high-dimensional when a target enters a specific area, or switching from high-dimensional to low-dimensional during a transition in combat phases. When the trigger condition is met, the corresponding model switch is performed, and data adjustments are made after the switch. For example, when switching from low-dimensional to high-dimensional, data adjustments mainly include: calling and loading high-precision terrain data and detailed models, calculating and displaying more detailed attributes of entities, such as specific damage status and ammunition reserves, and initiating high-refresh-rate sensor data streams. When switching from high-dimensional to low-dimensional, the reverse adjustment is performed: aggregating or simplifying entity units into icon-based symbols, filtering out detailed attributes and displaying only key summary information, such as overall combat effectiveness and mission status, and adopting a low-refresh-rate data-driven strategy to improve the rendering and response efficiency of the macro-situation.

[0031] In another embodiment, adjusting the battlefield situation model and data when the battlefield triggers a high-low dimension switch includes: Pre-set the dimension switching trigger method and perform real-time detection; When a switch from low dimension to high dimension is detected, the low-dimensional battlefield situation model is switched to a high-dimensional battlefield situation model, and the missing high-dimensional information is supplemented by an interpolation algorithm. When a switch from high-dimensional to low-dimensional is detected, the high-dimensional battlefield situation model is projected, transformed, and simplified. Then, the graphics rendering engine is used to render the low-dimensional battlefield situation model in real time according to its format and parameters.

[0032] In this embodiment, when converting from low-dimensional to high-dimensional, such as from two-dimensional to three-dimensional, the first step is to identify two-dimensional pixels or regions lacking elevation information. Then, neighboring points with known three-dimensional coordinates are extracted as sampling points. Based on the elevation values ​​of these sampling points, a suitable interpolation algorithm, such as Kriging interpolation or inverse distance weighted (IDW) interpolation, is used for spatial estimation. This algorithm calculates a weighted average elevation value based on the spatial distance and distribution patterns between neighboring points and the point to be interpolated, thereby assigning reasonable elevation information to the two-dimensional point and ultimately generating a continuous, smooth, and realistic three-dimensional model surface.

[0033] When converting from high-dimensional to low-dimensional space, such as from 3D to 2D, the 3D model data is first transformed by projection, such as orthographic projection, mapping it from 3D spatial coordinates to a 2D plane. Simultaneously, the model is simplified, for example, by removing unnecessary details, simplifying textures, and converting the 3D model into 2D icons. Then, using a graphics rendering engine, such as Unity or Unreal Engine, the processed 2D scene is rendered in real-time according to predefined 2D model formats and display parameters, such as icon styles, colors, and wireframes, thus efficiently and clearly displaying the macroscopic battlefield situation after the switch.

[0034] Module Two, Weapon Behavior Dynamic Simulation Module. This module is used to set initial state parameters for weapon equipment models according to actual scenarios or requirements, and then calculate the predicted behavior of the weapon equipment model in real time based on the collected real-time data and the trained weapon behavior rule model, and simulate the execution of the predicted behavior to obtain the predicted execution result. The weapon behavior rule model defines the behavior patterns of each weapon equipment under various conditions.

[0035] This module analyzes the behavioral logic and operational procedures of weapons and equipment under different combat scenarios, and pre-constructs a weapon behavior rule model by combining military expert knowledge and historical combat data. This model defines the behavioral patterns of weapons and equipment under various conditions, such as attack triggering conditions, defense strategy selection rules, and maneuver evasion path planning principles, providing a decision-making basis for weapon and equipment behavior simulation.

[0036] During simulated combat, initial state parameters, such as initial ammunition reserves and initial engine operating conditions, are first set for the weapon and equipment model based on the actual combat scenario or simulation requirements. Then, the behavior of the weapon and equipment model is calculated in real time based on the collected real-time data and the aforementioned weapon behavior rule model. The specific process is as follows: First, the collected data is filtered and normalized, including dynamic environmental information such as terrain and weather, as well as the equipment's own status fed back by sensors, such as location, ammunition reserves, and fuel levels.

[0037] Subsequently, the aforementioned weapon behavior rule model calculates mass changes, such as the impact of factors like ammunition consumption, wind speed, and terrain slope on equipment motion parameters, such as position, speed, and attitude. Based on the current integrated battlefield situation, such as enemy and friendly positions and threat levels, it judges and generates behavioral instructions for the equipment according to preset rules or adaptive learning strategies, such as whether to attack, relocate, or defend.

[0038] Finally, the system predicts the execution of the aforementioned control commands, obtains the predicted execution results, and feeds these results back to update the battlefield. For example, during an assault, a Red team tank model's sensors detect a Blue team tank 2 kilometers directly ahead. The system's real-time behavior calculation module immediately activates. First, based on current ammunition reserves, terrain slope, and wind speed data, it uses a physics engine to calculate its own position and artillery firing angle. Then, the rules engine makes a decision: since the target is within effective range and the Red team has sufficient ammunition, the rules trigger an "attack" command. The tank model then fires, and the trajectory of the shell is deflected by the wind speed. Finally, the system calculates a "destroyed" result based on the hit algorithm and dynamically updates the Blue team tank's status in the battlefield environment to "destroyed."

[0039] In another embodiment, the weapon behavior dynamic simulation module also includes a dynamic visualization display unit, which is used to transmit the calculated weapon equipment model behavior data to the electronic sand table in real time, and dynamically display the process of simulating the execution of the predicted behavior in the virtual scene through three-dimensional rendering technology.

[0040] This unit transmits the calculated weapon and equipment model behavior data to the electronic sand table in real time. Through 3D rendering technology, it dynamically displays the behavior process of the weapon and equipment in the virtual scene, including the movement, turning, firing ammunition, activating defense devices, and other actions of the weapon and equipment, presenting the dynamic behavior of the weapon and equipment in the simulated scene in an intuitive way.

[0041] In another embodiment, the weapon behavior dynamic simulation module further includes a dynamic adjustment unit, which compares the predicted behavior of the weapon equipment model with the actual behavior to obtain the corresponding deviation value, and updates the weapon behavior rule model when the deviation value is greater than a preset deviation threshold.

[0042] This unit needs to establish a behavior simulation result evaluation system, comparing the estimated execution results with actual observation data or expected behavior data, and calculating the deviation value between the two. If the deviation value exceeds a preset deviation threshold, an adaptive adjustment mechanism is triggered, which uses machine learning algorithms to correct the weapon behavior rule model. Through continuous iterative training, the model can better adapt to different scenarios and conditions, improving the accuracy and realism of the behavior simulation. Simultaneously, the optimized model parameters and rules are saved for use in subsequent simulations.

[0043] Module 3, the User Behavior Dynamic Control Module, is used to acquire multi-source operation signals from user input, determine the user's operation intention in real time, and then make probability predictions for the user's next operation based on historical operation data to obtain the estimated user operation result. The estimated user operation result is then used to provide intelligent prediction for battlefield simulation.

[0044] This module is used to predict the user's intended action and determine the effect of executing that action. Specifically: It acquires multi-source input signals from users, such as mouse, keyboard, and gestures, and analyzes the user's operational intent in real time through an attention mechanism.

[0045] By leveraging historical operation data and current scenario information, a Long Short-Term Memory (LSTM) network is employed to predict the probability of the user's next action. First, time-series data of user actions, such as continuous sequences of command instructions, needs to be constructed, encoded, and normalized. Then, an LSTM model is designed and trained, utilizing its gating mechanism to learn long-term dependencies in the operation sequence, outputting the probability distribution of the user's possible next action given historical operation conditions. Finally, online prediction is performed based on the real-time operation flow; that is, based on the user's latest operation sequence in the current sandbox situation, the estimated probabilities of each feasible next action, such as "tank assault" or "drone reconnaissance," are dynamically calculated and output.

[0046] For example, in a tank company assault scenario, if the user's historical operation sequence is "Tank A advances → Tank B provides fire support", the LSTM model can predict that the next operation has the highest probability of "calling air support" (e.g., 0.7). After identifying the operation with the highest estimated probability, the model then predicts whether to execute the operation and obtains the corresponding operation result. This allows the commander to decide whether to execute the operation based on the result, thus providing the commander with forward-looking decision support.

[0047] In another embodiment, the user behavior dynamic control module includes a sandbox situation dynamic rendering unit; The sand table dynamic rendering unit includes a parameter generator and a scene discriminator. The parameter generator is used to generate rendering parameters based on the real-time state of the sand table. The scene discriminator is used to compare the scene generated based on the rendering parameters with a pre-stored scene to determine the corresponding difference information, and then adjust the rendering parameters based on the difference information.

[0048] In this embodiment, the real-time state of the sandbox includes scene complexity, user operation frequency, etc. That is, the generator can dynamically generate optimal rendering parameters based on scene complexity, user operation frequency, etc., while the discriminator compares the rendered effect with the real scene, achieving a dynamic balance between rendering performance and image quality through adversarial training. For example, in a large-scale battlefield demonstration, the system automatically reduces the model precision of non-focused areas, prioritizing high-fidelity rendering of core areas.

[0049] This concludes the process. Figure 1 Explanation of the implementation process and functions of each module.

[0050] In the embodiments provided in this application, the multi-dimensional complex situation switching module can construct several battlefield situation models of different dimensions using multi-source data of different dimensions on the battlefield, and adjust the battlefield situation models and data when a dimension switch is triggered on the battlefield; the weapon behavior dynamic simulation module can calculate the behavior of weapon equipment models in real time based on the collected real-time data and the constructed behavior rule model, and simulate the execution of the predicted behavior to obtain the predicted execution result; the user behavior dynamic control module can determine the user's intention based on the user's operation signal, and make probability predictions of the user's next operation based on historical operations, and provide intelligent predictions for battlefield simulation based on the prediction results. This solves the problem of a single battlefield situation dimension and enables battlefield simulation based on real-time battlefield data. It also addresses the problem that the human-computer interaction method of existing systems is relatively passive, unable to effectively identify and predict the user's operation intention, resulting in insufficient intelligence in the simulation process and difficulty for commanders to obtain forward-looking decision support.

[0051] In another embodiment, the system further includes a digital twin driving module for constructing digital twins for each object in the electronic sandbox, the digital twins being used to map the physical state and behavior of the objects in real time.

[0052] In this module, the digital twin can map the physical state and behavior of the object in real time. For example, after the TK model receives the "forward" command, the digital twin synchronously calculates the impact of its movement trajectory on the surrounding terrain and friendly units, driving the sand table situation to be dynamically updated globally, ensuring the real-time nature and completeness of the situation information.

[0053] This application also provides a method for dynamically demonstrating adversarial simulation cases based on an electronic sand table, such as... Figure 2 As shown, the process of this method is as follows: Step S201: Collect multi-source data of different dimensions on the battlefield, determine several battlefield situation models of different dimensions based on the multi-source data, and adjust the battlefield situation models and data when the battlefield triggers a dimension switch.

[0054] Step S202: Based on the actual scenario or requirements, set initial state parameters for the weapon equipment model, then calculate the predicted behavior of the weapon equipment model in real time based on the collected real-time data and the trained weapon behavior rule model, and simulate the execution of the predicted behavior to obtain the predicted execution result.

[0055] Step S203: Acquire multi-source operation signals input by the user, determine the user's operation intention in real time, and then make probability predictions for the user's next operation based on historical operation data to obtain the estimated user operation result. Then, use the estimated user operation result to provide intelligent prediction for battlefield simulation.

[0056] This concludes the process. Figure 2 The process is shown below.

[0057] The above embodiments of the present invention provide a battlefield simulation and confrontation dynamic demonstration system based on an electronic sand table, and based on this system, a method for battlefield simulation and confrontation dynamic demonstration based on an electronic sand table. Through the above system and method, not only is the problem of a single dimension of battlefield situation addressed, but battlefield simulations can also be performed based on real-time battlefield data. This solves the problem that the human-computer interaction method of existing systems is relatively passive, unable to effectively identify and predict the user's operational intentions, resulting in insufficient intelligence in the simulation process and difficulty for commanders to obtain forward-looking decision support.

[0058] This embodiment also discloses a computer device, such as... Figure 3 As shown, the computer device includes a processor and a memory, the memory storing at least one instruction, which is loaded and executed by the processor to implement the method on the electronic sand table-based battlefield simulation and confrontation dynamic demonstration system described above.

[0059] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A virtual simulation combat dynamic demonstration system based on an electronic sand table, characterized in that, The system includes a multi-dimensional complex situation switching module, a weapon behavior dynamic simulation module, and a user behavior dynamic control module. The multi-dimensional complex situation switching module is used to collect data through sensors to obtain multi-source data of different dimensions, then determine several battlefield situation models of different dimensions based on the multi-source data, and adjust the battlefield situation models and data when the battlefield triggers a dimension switch. The weapon behavior dynamic simulation module is used to set initial state parameters for the weapon equipment model according to the actual scenario or needs, and then calculate the predicted behavior of the weapon equipment model in real time based on the collected real-time data and the trained weapon behavior rule model, and simulate the execution of the predicted behavior to obtain the predicted execution result. The weapon behavior rule model defines the behavior patterns of each weapon equipment under various conditions. The user behavior dynamic control module is used to acquire multi-source operation signals input by the user, determine the user's operation intention in real time, and then make probability predictions on the user's next operation through historical operation data to obtain the estimated user operation result. The estimated user operation result is then used to provide intelligent prediction for battlefield simulation.

2. The system according to claim 1, characterized in that, The sensors include optical sensors, two-dimensional phased array LD sensors, and laser LD sensors. The battlefield situation models of different dimensions include two-dimensional battlefield situation models and three-dimensional battlefield situation models.

3. The system according to claim 1, characterized in that, The adjustment of the battlefield situation model and data when the battlefield triggers a high-low dimension switch includes: Pre-set the dimension switching trigger method and perform real-time detection; When a switch from low dimension to high dimension is detected, the low-dimensional battlefield situation model is switched to a high-dimensional battlefield situation model, and the missing high-dimensional information is supplemented by an interpolation algorithm. When a switch from high-dimensional to low-dimensional is detected, the high-dimensional battlefield situation model is projected, transformed, and simplified. Then, the graphics rendering engine is used to render the low-dimensional battlefield situation model in real time according to its format and parameters.

4. The system according to claim 1, characterized in that, The initial state parameters in the weapon behavior dynamic simulation module include initial position, initial velocity, initial attitude, and initial weapon equipment state.

5. The system according to claim 1, characterized in that, The weapon behavior dynamic simulation module also includes a dynamic visualization display unit, which is used to transmit the calculated weapon and equipment model behavior data to the electronic sand table in real time, and dynamically display the process of simulating the execution of the predicted behavior in the virtual scene through three-dimensional rendering technology.

6. The system according to claim 1, characterized in that, The weapon behavior dynamic simulation module also includes a dynamic adjustment unit, which compares the predicted behavior of the weapon equipment model with the actual behavior to obtain the corresponding deviation value, and updates the weapon behavior rule model when the deviation value is greater than a preset deviation threshold.

7. The system according to claim 1, characterized in that, The user behavior dynamic control module includes a sandbox situation dynamic rendering unit; The sand table dynamic rendering unit includes a parameter generator and a scene discriminator. The parameter generator is used to generate rendering parameters based on the real-time state of the sand table. The scene discriminator is used to compare the scene generated based on the rendering parameters with a pre-stored scene to determine the corresponding difference information, and then adjust the rendering parameters based on the difference information.

8. The system according to claim 1, characterized in that, The system also includes a digital twin driving module, used to construct digital twins for each object in the electronic sandbox, the digital twins being used to map the physical state and behavior of the objects in real time.

9. A method for dynamic demonstration of adversarial simulation cases based on an electronic sand table, characterized in that, The method includes: Collect multi-source data of different dimensions on the battlefield, determine several battlefield situation models of different dimensions based on the multi-source data, and adjust the battlefield situation models and data when the battlefield triggers a dimension switch. Based on the actual scenario or requirements, initial state parameters are set for the weapon equipment model. Then, based on the collected real-time data and the trained weapon behavior rule model, the predicted behavior of the weapon equipment model is calculated in real time, and the predicted behavior is simulated to obtain the predicted execution result. The system acquires multi-source operation signals from user input, determines the user's operation intention in real time, and then uses historical operation data to predict the probability of the user's next operation to obtain the estimated user operation result. Finally, the estimated user operation result is used to provide intelligent prediction for battlefield simulation.