Target damage assessment and analysis system based on large model

Abstract

The present invention relates to the technical field of target damage assessment, and in particular to a target damage assessment analysis and compilation system based on a large model. The system includes a combat target data cleaning module, a combat target feature fusion module, a target damage assessment model establishment module, and a target damage visualization compilation module. The system can obtain corresponding combat target geographic situation images through satellite reconnaissance and integrate the combat intelligence reports and combat instructions corresponding to the target combat units to obtain combat target text data; perform data standardization cleaning on the combat target geographic situation images and combat target text data to obtain combat target situation standard images and combat target standard text data; construct a corresponding target feature analysis large model and perform combat target drive analysis, and simultaneously perform target damage assessment analysis and target damage visualization compilation to generate combat target damage visualization compilation results. The present invention can improve the accuracy of joint combat target damage assessment.

Description

Technical Field

[0001] The present invention relates to the technical field of target damage assessment, and in particular to a target damage assessment analysis and compilation system based on a large model. Background Art

[0002] Target Damage Assessment (TDA) is a key technology in the military, used to assess the extent of damage inflicted on enemy targets during combat. In recent years, new reconnaissance methods such as remote sensing, drone surveillance, and satellite imagery have been widely used for battlefield situational awareness, providing a wealth of real-time data for TDA. Currently, data-analysis-based TDA methods are gaining widespread application. Driven particularly by big data and artificial intelligence, related algorithms are gradually developing towards intelligent and automated approaches. Using techniques such as image recognition, machine learning, and deep learning, researchers are attempting to improve the efficiency and accuracy of TDA through automated means. However, existing technologies still have many limitations. Most rely on data from specific fields or types of targets, making it difficult to comprehensively assess different types of targets and damage. Furthermore, effective compilation methods are still lacking, making it difficult to rapidly process massive amounts of information and generate accurate TDA results. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a target damage assessment and analysis compilation system based on a large model to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a target damage assessment and analysis system based on a large model is proposed, which includes the following modules:

[0005] The combat target data cleaning module is used to obtain the corresponding combat target geographic situation image through satellite reconnaissance, and integrate the combat intelligence reports and combat instructions corresponding to the target combat unit to obtain combat target text data; the combat target geographic situation image and combat target text data are cleaned according to data standards to obtain the combat target situation standard image and combat target standard text data;

[0006] The combat target feature fusion module is used to build a corresponding target feature analysis model using convolutional neural networks and Transformer architecture. It then inputs the combat target situation standard image and combat target standard text data into the target feature analysis model to perform combat target driven analysis and output the corresponding combat target image features and text semantic damage features.

[0007] The target damage assessment model establishment module is used to take the target feature analysis large model as the input layer and build a joint combat target damage assessment model based on the large model based on the input layer, the preset feature enhancement layer, the fusion reasoning layer, and the output layer;

[0008] The target damage visualization compilation module is used to obtain the corresponding combat target data to be evaluated, including the corresponding combat target situation image and combat target intelligence text; input the corresponding combat target data to be evaluated into the joint combat target damage assessment model based on the large model to perform target damage assessment analysis to predict and output the corresponding target damage degree, target damage range, combat effectiveness loss and the corresponding impact of target damage on the combat situation; perform target damage visualization compilation based on the target damage degree, target damage range, combat effectiveness loss and the corresponding impact of target damage on the combat situation to generate combat target damage visualization compilation results.

[0009] Furthermore, the combat target data cleaning module includes the following functions:

[0010] Obtain geographical situation images of combat targets corresponding to the target area through satellite reconnaissance;

[0011] By integrating the combat intelligence reports and combat instructions corresponding to each target combat unit in the target area, the combat target text data can be obtained;

[0012] Performing local pixel ambiguity analysis on the combat target geographic situation image to obtain the local pixel ambiguity of the combat target image;

[0013] Based on the local pixel fuzziness of the combat target image, the combat target geographical situation image is subjected to fuzzy denoising and standardization to obtain a combat target situation standard image;

[0014] The combat target text data is cleaned according to text error correction standards to obtain standard combat target text data.

[0015] Furthermore, the text error correction and standard cleaning of the combat target text data includes:

[0016] Performing part-of-speech analysis and tagging on each word in the combat target text data to obtain combat target text part-of-speech tagging data;

[0017] Based on the part-of-speech tagging data of the combat target text, grammatical error correction analysis is performed on each word in the combat target text data to correct the corresponding typos and grammatical errors and unify the vocabulary expressions. At the same time, the corresponding special characters, punctuation marks and meaningless stop words are removed to obtain the combat target text correction data;

[0018] Through the common combat field data standards and coding system, data standardization processing is performed on the different sources and formats corresponding to the combat target text correction data to obtain the combat target standard text data.

[0019] Furthermore, the combat target feature fusion module includes the following functions:

[0020] Utilize convolutional neural networks and combine them with target images to construct corresponding target image feature extraction branches to output combat target image features corresponding to the target image;

[0021] Utilize the Transformer architecture and combine it with text data to build a corresponding target semantic damage feature extraction branch to output the semantic damage features of the combat target corresponding to the target text;

[0022] Connect the target image feature extraction branch and the target semantic damage feature extraction branch with the corresponding cross-modal feature association module to build a corresponding target feature analysis model to achieve the association and fusion between the target image features and the text semantics;

[0023] The standard image of the combat target situation and the standard text data of the combat target are input into the target feature analysis model for combat target driven analysis to output the corresponding combat target image features and text semantic damage features.

[0024] Furthermore, the target image feature extraction branch is specifically composed of a large-scale 5x5 convolution layer, a small-scale 3x3 convolution layer and a 1x1 pooling layer. The large-scale 5x5 convolution layer is used to extract the geometric shape and texture features of the combat target corresponding to the target image, and the small-scale 3x3 convolution layer is used to extract the position changes of the combat target and the surrounding environment situation characteristics corresponding to the target image at different time periods. The large-scale and small-scale corresponding features are reduced in dimension in the 1x1 pooling layer.

[0025] Furthermore, the target semantic damage feature extraction branch is specifically:

[0026] By performing combat target semantic segmentation on the text data in the corresponding input layer within the Transformer architecture, a combat target semantic segmentation set is generated;

[0027] By using the corresponding military semantic graph in the corresponding text encoding layer within the Transformer architecture, each combat target word or phrase in the combat target semantic word set is semantically encoded and represented. For each word or phrase, its corresponding combat domain concept in the military semantic graph is searched, and the relevant attributes and relationship codes corresponding to the combat domain concept are embedded in the corresponding combat target word or phrase to generate a combat target semantic encoding representation.

[0028] By extracting target damage features from the semantic encoding representation of combat targets in the corresponding last layer within the Transformer architecture, the target type, combat mission, and target damage description event logic chain corresponding to the combat target are extracted. By introducing additional constraints and reward mechanisms, the feature extraction branch's ability to extract the corresponding semantic features of combat targets is enhanced. If the corresponding combat target damage features are accurately extracted, positive rewards are given, while if incorrect or omitted features are extracted, penalties are given. The corresponding damage feature vector representation is obtained through the forward propagation calculation corresponding to the last layer to output the combat target image features corresponding to the target image.

[0029] Furthermore, the target damage visualization compilation module includes the following functions:

[0030] Obtain the corresponding combat target data to be evaluated, including the corresponding combat target situation image and combat target intelligence text;

[0031] The combat target data to be evaluated is input into the input layer of the joint combat target damage assessment model based on the large model to extract combat target features, so as to extract and receive the corresponding combat target image features and text semantic damage features that have undergone preprocessing and feature extraction;

[0032] The self-attention mechanism in the corresponding feature enhancement layer of the large-scale joint combat target damage assessment model is used to fuse the target image features and text semantic damage features, so as to highlight the relevant features corresponding to the combat target damage. The target damage-related features are obtained, including the combat target's running speed, combat capability, defense level, terrain concealment level, and position change.

[0033] Calculate the target damage degree based on the damage-related characteristics of the combat target to obtain the target damage degree; determine the damage range of the target damage degree based on the change in the combat target position to obtain the target damage range; calculate the loss of the combat mission parameters corresponding to the combat target using the combat effectiveness loss calculation formula based on the target damage degree and the target damage range to obtain the combat effectiveness loss; evaluate the impact of the combat geographical situation corresponding to the combat target based on the target damage degree to obtain the impact of the target damage on the combat situation;

[0034] Target damage visualization is performed based on the target damage degree, target damage range, combat effectiveness loss, and the corresponding impact of target damage on the combat situation to generate combat target damage visualization results.

[0035] Furthermore, the target damage degree is calculated using a target damage degree calculation formula, which is specifically:

[0036]

[0037] Where D is the target damage degree, v is the target running speed, k1 is the running speed weight, C is the target combat capability, k2 is the combat capability weight, and ... f is the defense level of the combat target, k3 is the defense level weight, D f,max is the maximum defense level corresponding to the combat target unit, H is the concealment level of the combat target terrain, k4 is the concealment level weight, S is the change in the combat target position, and k5 is the position change weight.

[0038] Furthermore, the combat effectiveness loss calculation formula is specifically as follows:

[0039]

[0040] Where L is the loss of combat effectiveness, D is the degree of target damage, R is the real-time completion progress of the combat target task, and R max is the maximum completion progress of the combat mission corresponding to the combat target, E is the combat target environment situation, T is the duration of the combat operation, and F D is the size of the target damage range, e is the base of the natural logarithm, and η is the correction coefficient for the loss of combat effectiveness.

[0041] Furthermore, the target damage visualization compilation according to the target damage degree, target damage range, combat effectiveness loss, and the impact of target damage on the combat situation includes:

[0042] Generate a heat map of target damage severity for each target area based on the target damage severity, to visually present the severity of damage to different target areas.

[0043] Create a three-dimensional dynamic model of the target damage range corresponding to the target area based on the target damage range to clearly display the damage status of the combat target and the surrounding environment;

[0044] Based on the impact of combat effectiveness loss on target damage on the combat situation, the effectiveness loss impact is mapped to generate a trend chart of combat effectiveness loss situation impact corresponding to the target area, helping to accurately grasp the impact trend of target damage on the overall combat situation;

[0045] The target damage degree heat map corresponding to the target area, the three-dimensional dynamic model of the target damage range, and the combat effectiveness loss situation impact trend map are visually compiled to generate the combat target damage visualization compilation results.

[0046] Beneficial effects of the present invention:

[0047] The target damage assessment analysis and compilation system based on a large model proposed by the present invention is generally composed of a combat target data cleaning module, a combat target feature fusion module, a target damage assessment model establishment module, and a target damage visualization compilation module. Compared with the existing technology, the beneficial effect of this application is that satellite reconnaissance can reflect the geographical situation of the battlefield and the spatial position and movement of combat targets in real time through high-resolution images, providing accurate geographical data for subsequent combat decisions. These satellite images can reveal the enemy's military facilities, deployment status, and battlefield environment, ensuring that commanders can obtain timely and accurate intelligence. In addition, the intelligence reports and instructions of combat targets, after being combined, provide tactical and strategic background information to help analyze the intentions and trends of enemy actions. The data standardization and cleaning process is crucial to ensuring data consistency and accuracy. The original image data and text data often contain noise, incomplete information, or inconsistent formats. The data cleaning process can remove this invalid information and unify the data format, making it more suitable for subsequent model analysis. The cleaned combat target situation standard images and standard text data can improve the efficiency and accuracy of subsequent model processing data, providing a more reliable basis for target damage assessment. Secondly, by using convolutional neural networks (CNN) and Transformer architecture to build a large model for target feature analysis, standard images and standard text data of combat targets are input into the model for analysis. Convolutional neural networks (CNN) are good at processing image data. They can extract fine spatial features from the geographical situation images of combat targets, such as the shape, structure, position and other information of the target. These spatial features are very important for judging the type, importance and potential threat of the target. Through the deep learning characteristics of the CNN model, the system can automatically extract important features from the image, reducing the tedious work of manual feature design, and can discover complex patterns and potential attack targets. The Transformer architecture performs well in processing text data, especially in capturing In terms of long-distance dependencies, intelligence reports and instructions on combat targets often contain a large amount of textual information, including the enemy's strategic intentions, tactical layout, and current combat status. The Transformer model can effectively capture these long-distance semantic relationships through the self-attention mechanism and deeply understand the potential meaning in the text data. By combining the advantages of CNN and Transformer, the target feature analysis model can process image and text data simultaneously, thereby conducting a comprehensive analysis of combat targets. It can output the image features and textual semantic damage features of combat targets, providing detailed basic data for subsequent damage assessments, enabling decision makers to have a more comprehensive understanding of the situation of combat targets, thereby achieving a comprehensive assessment of different types of targets and damage situations.Then, by taking the target feature analysis model as the input layer, the entire damage assessment model can receive more detailed and comprehensive target data. These data not only include the target's geographic information, but also cover the target's textual semantic information, comprehensively and deeply describing the various dimensions of the combat target. Effectively transmitting these data to the assessment model can provide strong support for subsequent damage assessment. The feature enhancement layer can strengthen the model's attention to target features, improve the model's sensitivity to important features, and ensure that the model can effectively capture key data. The fusion reasoning layer can integrate data from multiple different sources (such as images and text) to form a comprehensive judgment. This multi-level processing method can enhance the model's reasoning ability and enable it to more accurately assess the damage effect of combat targets. Finally, by obtaining the situational images and intelligence texts of the combat targets, we can fully understand the current status and position of the targets, which provides the most direct input for subsequent damage assessment. The data includes the latest intelligence on the enemy targets, which can ensure that the assessment model has a full understanding of the current combat situation. The joint combat target damage assessment model based on the large model can accurately perform damage assessment analysis by inputting the data to be evaluated. Through comprehensive predictions of the target damage level, damage range, combat effectiveness loss, etc., it can help commanders understand the impact of different tactical plans on the targets, so that the model can achieve more effective reorganization means to enhance the accuracy and predictability of combat targets, thereby improving the accuracy of target damage assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0049] Figure 1 This is a schematic diagram of the modules of the target damage assessment and analysis compilation system based on a large model of the present invention;

[0050] Figure 2 for Figure 1 Functional flow diagram of the combat target data cleaning module;

[0051] Figure 3 for Figure 1 Schematic diagram of the functional flow of the combat target feature fusion module. DETAILED DESCRIPTION

[0052] The following is a clear and complete description of the technical system of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0053] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.

[0054] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0055] To achieve this, please refer to Figures 1 to 3 The present invention provides a target damage assessment and analysis compilation system based on a large model, the system comprising the following modules:

[0056] The combat target data cleaning module is used to obtain the corresponding combat target geographic situation image through satellite reconnaissance, and integrate the combat intelligence reports and combat instructions corresponding to the target combat unit to obtain combat target text data; the combat target geographic situation image and combat target text data are cleaned according to data standards to obtain the combat target situation standard image and combat target standard text data;

[0057] The combat target feature fusion module is used to build a corresponding target feature analysis model using convolutional neural networks and Transformer architecture. It then inputs the combat target situation standard image and combat target standard text data into the target feature analysis model to perform combat target driven analysis and output the corresponding combat target image features and text semantic damage features.

[0058] The target damage assessment model establishment module is used to take the target feature analysis large model as the input layer and build a joint combat target damage assessment model based on the large model based on the input layer, the preset feature enhancement layer, the fusion reasoning layer, and the output layer;

[0059] The target damage visualization compilation module is used to obtain the corresponding combat target data to be evaluated, including the corresponding combat target situation image and combat target intelligence text; input the corresponding combat target data to be evaluated into the joint combat target damage assessment model based on the large model to perform target damage assessment analysis to predict and output the corresponding target damage degree, target damage range, combat effectiveness loss and the corresponding impact of target damage on the combat situation; perform target damage visualization compilation based on the target damage degree, target damage range, combat effectiveness loss and the corresponding impact of target damage on the combat situation to generate combat target damage visualization compilation results.

[0060] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of the modules of the target damage assessment and analysis system based on a large model according to the present invention. In this example, the target damage assessment and analysis system based on a large model includes the following modules:

[0061] S1: Combat target data cleaning module, used to obtain the corresponding combat target geographic situation image through satellite reconnaissance, and integrate the combat intelligence reports and combat instructions corresponding to the target combat unit to obtain combat target text data; perform data standardization cleaning on the combat target geographic situation image and combat target text data to obtain the combat target situation standard image and combat target standard text data;

[0062] In an embodiment of the present invention, a satellite equipped with multiple imaging devices is controlled to enter an orbit above the target area. The high-resolution optical camera on the satellite photographs the target area in clear weather, acquiring clear images of the ground features. Synthetic aperture radar, unaffected by weather, generates images containing hidden target information by transmitting and receiving microwave signals. This image data is transmitted to a ground control center for splicing and fusion to obtain a geographical situation image of the combat target. Simultaneously, a dedicated data collection network is established and connected to the communication systems of the target combat units. Each combat unit uploads combat intelligence reports (such as the location and equipment of enemy forces) and combat instructions (such as offensive or defensive mission arrangements) via an encrypted channel. The collection network aggregates this text information to form combat target text data. For the image data, image enhancement algorithms are used to remove noise and adjust brightness, contrast, and resolution to a uniform standard, thereby obtaining a standard combat target situation image. Natural language processing tools are used to correct typos, standardize terminology, and remove stop words and special symbols for the text data, ultimately generating standard combat target text data.

[0063] S2: Combat target feature fusion module, which uses convolutional neural networks and the Transformer architecture to build a corresponding target feature analysis model. It then inputs standard combat target situation images and standard combat target text data into the target feature analysis model to perform combat target driven analysis and output corresponding combat target image features and text semantic damage features.

[0064] In an embodiment of the present invention, a large-scale target feature analysis model is built using the Python language combined with the deep learning framework TensorFlow. A convolutional neural network branch is constructed, consisting of a large-scale 5x5 convolutional layer, a small-scale 3x3 convolutional layer, and a 1x1 pooling layer. This is used to process standard images of combat target situations. The large-scale convolutional layer extracts the target's geometric shape and texture features, such as identifying the outline and surface camouflage of a tank. The small-scale convolutional layer captures changes in the target's position and the surrounding environmental situation at different time periods, such as analyzing the target's movement trajectory and surrounding terrain. The 1x1 pooling layer reduces the dimensionality of the extracted features. A text processing branch is constructed using the Transformer architecture to process standard combat target text data. Using a self-attention mechanism, the semantic relationship between words in the text is analyzed to extract semantic features such as combat target type, combat mission, and damage description. The image and text branches are connected to a cross-modal feature association module. The model inputs standard combat target situation images and standard combat target text data. The model achieves cross-modal fusion by calculating the association between image feature vectors and text semantic feature vectors, ultimately outputting combat target image features and text semantic damage features.

[0065] S3: Target damage assessment model establishment module, which uses the target feature analysis large model as the input layer and constructs a joint combat target damage assessment model based on the large model based on the input layer, the preset feature enhancement layer, the fusion reasoning layer, and the output layer;

[0066] In an embodiment of the present invention, a previously constructed target feature analysis large model is used as the input layer of a large-model-based joint combat target damage assessment model, which is responsible for extracting the initial image and text features of the combat target. In the feature enhancement layer, the self-attention mechanism is used to further process the features output by the input layer. For example, higher weights are given to key target parts in image features and core damage descriptions in text features to highlight features related to target damage. In the fusion reasoning layer, a specific fusion algorithm is designed to deeply fuse the enhanced image features and text features. For example, matrix multiplication and nonlinear activation functions are used to explore the potential connections between cross-modal features and infer more comprehensive target damage-related information. Finally, an output layer is set to construct a suitable output function based on the results of the fusion reasoning layer to convert the target damage information into an interpretable format to prepare for subsequent evaluation and analysis, thereby completing the construction of a large-model-based joint combat target damage assessment model.

[0067] S4: Target damage visualization compilation module is used to obtain the corresponding combat target data to be evaluated, including the corresponding combat target situation image and combat target intelligence text; input the corresponding combat target data to be evaluated into the joint combat target damage assessment model based on the large model to perform target damage assessment analysis to predict and output the corresponding target damage degree, target damage range, combat effectiveness loss and the corresponding impact of target damage on the combat situation; perform target damage visualization compilation based on the target damage degree, target damage range, combat effectiveness loss and the corresponding impact of target damage on the combat situation to generate combat target damage visualization compilation results.

[0068] In an embodiment of the present invention, various reconnaissance methods, such as drone reconnaissance and ground intelligence collection stations, are used to obtain images of the target situation and textual intelligence of the target to be assessed. These data are then input into a previously constructed joint target damage assessment model based on a large model. The model's input layer (i.e., the target feature analysis large model) extracts image and text features. The feature enhancement layer highlights key features, and the fusion and reasoning layer deeply integrates and infers damage information. Ultimately, the output layer predicts the target damage level (e.g., a quantitative score based on target damage), the target damage range (demarcated based on target position changes and damage level), combat effectiveness loss (calculated by combining damage level with combat mission parameters), and the impact of target damage on the combat situation (analyzing changes in geographic situation, troop deployment, and other aspects). These assessment results are then visualized using tools such as geographic information system software and data visualization platforms. For example, different colors and ranges are used on a map to represent the target damage level and damage range, charts are used to display combat effectiveness loss, and text and arrows are used to indicate the impact of target damage on the combat situation. This ultimately generates a visualization of target damage, providing an intuitive basis for combat decision-making.

[0069] Furthermore, the combat target data cleaning module includes the following functions:

[0070] Obtain geographical situation images of combat targets corresponding to the target area through satellite reconnaissance;

[0071] By integrating the combat intelligence reports and combat instructions corresponding to each target combat unit in the target area, the combat target text data can be obtained;

[0072] Performing local pixel ambiguity analysis on the combat target geographic situation image to obtain the local pixel ambiguity of the combat target image;

[0073] Based on the local pixel fuzziness of the combat target image, the combat target geographical situation image is subjected to fuzzy denoising and standardization to obtain a combat target situation standard image;

[0074] The combat target text data is cleaned according to text error correction standards to obtain standard combat target text data.

[0075] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 The functional flow diagram of the combat target data cleaning module in this embodiment includes the following functions:

[0076] S11: Obtain geographical situation images of combat targets corresponding to the target area through satellite reconnaissance;

[0077] In an embodiment of the present invention, a reconnaissance satellite equipped with a high-resolution optical imaging device and a synthetic aperture radar (SAR) is controlled to fly over a target area. The optical imaging device on the satellite uses light of a specific wavelength band to photograph the target area and obtain an optical image of the target area, which can clearly present the shape, color and other features of ground objects, such as identifying buildings and roads. The SAR generates a radar image of the target area by transmitting and receiving microwave signals, penetrating interference such as clouds and vegetation, and is used to detect military facilities hidden under cover. The image data obtained by the optical imaging device and the SAR are fused and processed to generate a comprehensive and accurate image of the geographical situation of the combat target. The image data is then transmitted in real time to a ground control center for storage via a satellite data transmission link for subsequent analysis.

[0078] S12: Obtain combat target text data by integrating combat intelligence reports and combat orders corresponding to each target combat unit in the target area;

[0079] In an embodiment of the present invention, a combat data collection platform is established and connected to the communication system of each target combat unit in the target area. When the combat unit generates a combat intelligence report, such as discovering the location, equipment type and quantity of enemy troops, or receiving combat instructions issued by superiors, such as offensive and defensive task arrangements, these text information will be transmitted to the data collection platform through an encrypted communication link. The platform uses data parsing algorithms to classify and integrate the various types of text data received. For example, it summarizes the intelligence reports of different combat groups on the distribution of enemy tanks, and organizes the superior's coordinated combat instructions to each combat unit, and finally forms combat target text data covering comprehensive information. It is stored in the platform's database to provide a data basis for subsequent text processing.

[0080] S13: performing local pixel fuzziness analysis on the combat target geographic situation image to obtain local pixel fuzziness of the combat target image;

[0081] In an embodiment of the present invention, an image of a geographic situation of a combat target is processed by using image analysis software, such as the MATLAB image processing toolbox, and the image is divided into multiple local areas, each of which contains a certain number of pixels. For each local area, the second-order derivative of the pixel is calculated using the Laplace operator, and the edge clarity of the pixel is measured by analyzing the absolute value of the second-order derivative. For example, in a local area containing the edge of a building, if the absolute value of the second-order derivative of the pixel is large, it means that the edge of the area is clear and the blur is low; conversely, if the absolute value of the second-order derivative is small, the blur is high. Such calculations are performed on all local areas in the image to obtain the pixel blur value of each local area, and then generate local pixel blur data of the combat target image, which is used to evaluate the clarity of each part of the image.

[0082] S14: performing fuzzy denoising and standardization on the combat target geographic situation image based on the local pixel fuzziness of the combat target image to obtain a combat target situation standard image;

[0083] In an embodiment of the present invention, an adaptive median filtering algorithm is used to blur and denoise the image based on the local pixel blur data of the combat target image. For local areas with high blur, the size of the median filter window is increased to better remove noise and restore image details. For areas with low blur, the filter window size is kept small to avoid over-smoothing. For example, in a blurred forest area in the image, the median filter window is increased from 3×3 to 5×5 for denoising. After denoising, the brightness and contrast of the image are adjusted according to preset image normalization rules so that the grayscale value of the image is distributed within a specific range. At the same time, the resolution of the image is uniformly adjusted to a standard resolution, such as 1024×768 pixels, and finally a standard combat target situation image that meets the standard is generated, thereby improving the image quality for subsequent analysis.

[0084] S15: Perform text error correction and standard cleaning on the combat target text data to obtain standard combat target text data.

[0085] In an embodiment of the present invention, by using the natural language processing toolkit NLTK and custom military text error correction rules to process the combat target text data. First, use the词性标注 function of NLTK to label the词性 of each word in the text. Then, according to the pre-constructed military domain typo library and grammar rules, find and correct the typos and grammar errors in the text. For example, correct the misspelled "火跑" of "火炮" to "火炮", and correct the grammar error of "执行任务着" to "执行任务". Then, remove the special characters, punctuation marks, and meaningless stop words in the text, such as "@", "!", "的", "了", etc. Finally, according to the military term standard,统一 the vocabulary expression in the text, and convert the non-standard terms to standard terms, such as统一 "战车" to "坦克". After these processes, the standardized and accurate combat target standard text data is obtained.

[0086] Further, the text error correction and standard cleaning of the combat target text data include:

[0087] Perform词性分析 and标注 on each word in the combat target text data to obtain the combat target text词性标注 data;

[0088] In an embodiment of the present invention, by using the natural language processing toolkit NLTK (Natural Language Toolkit) to perform the词性分析 and标注 operation, split the combat target text data by sentence, and then process each word in each sentence one by one. For example, for the text "敌方坦克快速驶向我方阵地", the词性标注器 in NLTK will label "敌方" as a noun, "坦克" as a noun, "快速" as an adverb, "驶向" as a verb, "我方" as a pronoun, and "阵地" as a noun. Through such an operation, label the词性 of each word in the entire combat target text data, and finally generate the combat target text词性标注 data, providing a basis for subsequent grammar analysis and text processing.

[0089] Preferably, perform grammar error correction analysis between each word in the combat target text data based on the combat target text词性标注 data to correct the corresponding typos and grammar errors and统一 the vocabulary expression, and at the same time remove the corresponding special characters, punctuation marks, and meaningless stop words to obtain the combat target text correction data;

[0090] It should be noted that the terms "词性分析", "词性标注", and "统一" in the translation are placeholder terms that need to be accurately translated according to the specific context. Here, they are left in Chinese for the purpose of showing the structure of the translation.In the embodiment of the present invention, by applying a grammar error correction algorithm that combines rules and statistics, based on the词性标注数据, first, through a pre-constructed military field misspelled word library, the misspelled words in the text are searched for and corrected. For example, if "tank" is misspelled as "坦壳", it can be corrected through word library matching. For grammar errors, according to the common grammar rules of military texts, combined with the词性标注 information, judgment and correction are carried out. For example, for the subject-predicate-object collocation error such as "我方士兵勇敢战斗着敌人", it is adjusted to "我方士兵勇敢地战斗着,抗击敌人" according to the词性 and grammar rules. At the same time, the preset vocabulary is used to统一词汇表述, such as统一 "战车" to "坦克", and the stop word list in NLTK is used to remove meaningless stop words such as "的", "了", "在", etc., as well as special characters and punctuation marks, and finally the purified and standardized combat target text correction data is obtained.

[0091] Preferably, the combat target text correction data corresponding to different sources and different formats is subjected to data standardization processing through a general combat field data standard and coding system to obtain combat target standard text data.

[0092] In the embodiment of the present invention, by referring to international or industry-wide combat field data standards, such as military symbol standards such as MIL-STD-2525B and related coding systems, the combat target text correction data is processed. For data from different sources (such as intelligence reports, communication records, etc.) and different formats (such as plain text, XML format, etc.), it is first uniformly converted into a standard text format. For combat terms in the text, they are standardized according to the standard term list. For example, the non-standard "飞弹" is unified into the standard term "导弹". The numerical values, units, etc. in the text are standardized, such as统一 the distance unit to "meter". According to the coding system, the key information in the text is encoded, such as assigning specific codes to different types of combat targets. Finally, the combat target text correction data is converted into combat target standard text data that conforms to the general standard, which is convenient for subsequent unified processing and analysis in target damage assessment and analysis.

[0093] Furthermore, the combat target feature fusion module includes the following functions:

[0094] Utilize a convolutional neural network and combine it with the target image to construct a corresponding target image feature extraction branch to output the combat target image features corresponding to the target image;

[0095] Utilize the Transformer architecture and combine it with the text data to construct a corresponding target semantic damage feature extraction branch to output the combat target semantic damage features corresponding to the target text;

[0096] It should be noted that the "词性标注数据" in the translation is a placeholder that needs to be replaced with the actual correct content in Chinese. Also, the "统一词汇表述" and "统一" need to be replaced with the specific correct expressions according to the actual situation.Connect the target image feature extraction branch and the target semantic damage feature extraction branch with the corresponding cross-modal feature association module to build a corresponding target feature analysis model to achieve the association and fusion between the target image features and the text semantics;

[0097] The standard image of the combat target situation and the standard text data of the combat target are input into the target feature analysis model for combat target driven analysis to output the corresponding combat target image features and text semantic damage features.

[0098] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Schematic diagram of the functional flow of the combat target feature fusion module in this embodiment. The combat target feature fusion module includes the following functions:

[0099] S21: Utilize the convolutional neural network and combine it with the target image to construct a corresponding target image feature extraction branch to output the combat target image features corresponding to the target image;

[0100] In an embodiment of the present invention, a convolutional neural network is constructed by using the Python programming language in combination with the deep learning framework TensorFlow. A target image is input into the network. In a large-scale 5x5 convolution layer, a convolution operation is performed on the image using multiple 5x5 convolution kernels. For example, for a target image containing an enemy tank, a 5x5 convolution kernel slides across the image. By calculating the dot product between the convolution kernel and a local area of ​​the image, geometric features of the tank, such as outline lines and turret shape, and texture features, such as the camouflage pattern texture on the tank surface, are extracted. In a small-scale 3x3 convolution layer, convolution operations are also performed on target images at different time periods to extract characteristics of changes in the position of the combat target, such as changes in the coordinate position of the tank at different times, as well as characteristics of the surrounding environment, such as the surrounding terrain and the distribution of other military facilities. Finally, in a 1x1 pooling layer, dimensionality reduction processing is performed on the features extracted by the large-scale 5x5 convolution layer and the small-scale 3x3 convolution layer to reduce the number of features and reduce computational complexity, and ultimately output the combat target image features corresponding to the target image.

[0101] S22: Utilize the Transformer architecture and combine it with text data to construct a corresponding target semantic damage feature extraction branch to output the semantic damage features of the combat target corresponding to the target text;

[0102] In an embodiment of the present invention, a target semantic damage feature extraction branch based on the Transformer architecture is constructed by using the natural language processing toolkit NLTK and the deep learning framework PyTorch. First, the text data is preprocessed, and the word segmentation tool in NLTK is used to segment the target text into words or phrases to remove noise such as stop words. For example, for a text describing a combat situation, "The enemy tank was hit by our artillery fire near the bridge, and part of the armor was damaged," the word segmentation results in "enemy," "tank," "near," "bridge," "by," "our," "artillery fire," "hit," "part," "armor," "damaged," etc. These segmented text sequences are then input into the Transformer architecture. The self-attention mechanism in the Transformer calculates the association weight between each word and other words, thereby capturing the semantic relationship in the text. For example, the association weight between "tank" and "armor" and "damaged" will be higher, indicating that they are semantically closely related. Through the multi-layer processing of the Transformer architecture, the semantic features of combat target damage in the text are extracted, and finally the combat target semantic damage features corresponding to the target text are output.

[0103] S23: Connecting the target image feature extraction branch and the target semantic damage feature extraction branch with the corresponding cross-modal feature association module to construct a corresponding target feature analysis model to achieve the association and fusion between the target image features and the text semantics;

[0104] In an embodiment of the present invention, a customized cross-modal feature association module is adopted, which is constructed based on matrix operations and fusion algorithms. The previously constructed target image feature extraction branch and the constructed target semantic damage feature extraction branch are connected to the cross-modal feature association module. The combat target image features output by the target image feature extraction branch are expressed in the form of feature vectors, and the combat target semantic damage features output by the target semantic damage feature extraction branch are also converted into vector form. The cross-modal feature association module establishes an association relationship between the image feature vector and the semantic feature vector by calculating the cosine similarity between the two. For example, when a damaged tank is shown in the image and the text describes "tank armor is damaged", the cross-modal feature association module can identify the association between features such as the tank's geometric shape and damaged parts in the image features and semantic features such as "tank" and "damaged" in the text, and fuse the two to construct a large target feature analysis model, so that the model can comprehensively utilize the information of the image and text for subsequent analysis.

[0105] S24: Input the combat target situation standard image and combat target standard text data into the target feature analysis large model to perform combat target driven analysis to output the corresponding combat target image features and text semantic damage features.

[0106] In an embodiment of the present invention, a large amount of standard images of combat target situations and standard text data of combat targets are collected. These data are strictly screened and labeled to ensure accuracy and consistency. The standard images of combat target situations are input into the target image feature extraction branch of the target feature analysis model. According to the previous method, the large-scale 5x5 convolution layer, the small-scale 3x3 convolution layer and the 1x1 pooling layer are sequentially passed to extract the combat target image features corresponding to the image. At the same time, the standard text data of combat targets are input into the target semantic damage feature extraction branch. After being processed by the Transformer architecture, the text semantic damage features are extracted. The cross-modal feature association module in the target feature analysis model performs association analysis on the extracted image features and text semantic features, further optimizes and integrates these features, and finally outputs the combat target image features and text semantic damage features after combat target driven analysis, providing accurate and comprehensive feature data for subsequent target damage assessment.

[0107] Furthermore, the target image feature extraction branch is specifically composed of a large-scale 5x5 convolution layer, a small-scale 3x3 convolution layer and a 1x1 pooling layer. The large-scale 5x5 convolution layer is used to extract the geometric shape and texture features of the combat target corresponding to the target image, and the small-scale 3x3 convolution layer is used to extract the position changes of the combat target and the surrounding environment situation characteristics corresponding to the target image at different time periods. The large-scale and small-scale corresponding features are reduced in dimension in the 1x1 pooling layer.

[0108] Furthermore, the target semantic damage feature extraction branch is specifically:

[0109] By performing combat target semantic segmentation on the text data in the corresponding input layer within the Transformer architecture, a combat target semantic segmentation set is generated;

[0110] In an embodiment of the present invention, a professional Chinese word segmentation tool, such as Jieba Word Segmentation, is used at the input layer of the Transformer architecture to process the input text data. For texts describing combat objectives, word segmentation operations are performed sentence by sentence. For example, for the text "enemy tank clusters are performing assault missions in plain areas", Jieba Word Segmentation divides it into words or phrases such as "enemy", "tank clusters", "in", "plain areas", "execution", and "assault missions". All the words or phrases after segmentation are summarized to form a semantic word segmentation set of combat objectives. During the word segmentation process, a military terminology dictionary is constructed in advance for professional terms in the military field and is imported into the word segmentation tool to ensure that professional terms such as "tank clusters" and "assault missions" can be accurately segmented to improve the accuracy and professionalism of word segmentation, and finally a semantic word segmentation set of combat objectives is generated.

[0111] Preferably, the corresponding military semantic graph is used in the corresponding text encoding layer within the Transformer architecture to perform semantic encoding representation on each combat target word or phrase in the combat target semantic word set, so as to find the corresponding combat domain concept in the military semantic graph for each word or phrase, and embed the relevant attributes and relationship codes corresponding to the combat domain concept into the corresponding combat target word or phrase to generate a combat target semantic encoding representation;

[0112] In an embodiment of the present invention, a pre-built military semantic graph is loaded into the text encoding layer of the Transformer architecture. The graph contains a large number of military domain concepts and their attributes and relationships. For each word or phrase in the combat target semantic segmentation set, such as "tank cluster", a search and match is performed in the military semantic graph to find the combat domain concept corresponding to "tank cluster", whose attributes include "equipment type" as "armored vehicle", "combat capability" as "having strong firepower and assault capability", etc., and relationships include "belonging to" a certain combat unit, etc. These attributes and relationships are embedded in the representation of the word "tank cluster" in a specific encoding method, such as vector encoding. This operation is performed on all words or phrases in the combat target semantic segmentation set, and finally a combat target semantic encoding representation containing rich semantic information is generated. For example, after encoding, "tank cluster" not only retains its own meaning, but also carries its relevant attributes and relationship information in the military field for subsequent analysis.

[0113] Preferably, target damage features are extracted from the semantic encoding representation of the combat target in the corresponding last layer within the Transformer architecture to extract the target type, combat mission, and target damage description event logic chain corresponding to the combat target, and by introducing additional constraints and reward mechanisms, the feature extraction branch's ability to extract the corresponding semantic features of the combat target is enhanced. If the corresponding combat target damage features are accurately extracted, positive rewards are given, while if incorrect or omitted features are extracted, penalties are given, and the corresponding damage feature vector representation is obtained through the forward propagation calculation corresponding to the last layer to output the combat target image features corresponding to the target image.

[0114] In the embodiment of the present invention, the semantic coding representation of the combat target is processed by using a designed feature extraction algorithm at the last layer of the Transformer architecture. For the target type, it is judged by identifying the key information in the words or phrases. For example, "tank cluster" clearly indicates that its target type is an armored combat target. For the combat mission, the words and relationships related to the mission in the semantic coding representation are analyzed. If there is "execution assault mission", the combat mission is determined to be assault. When extracting the logical chain of the target damage description event, the logical connections such as the causal relationship between the elements in the semantic coding representation are sorted out, and additional constraints are introduced, such as stipulating the extracted target damage features. It must conform to military common sense and actual combat conditions, and establish a reward mechanism. If features such as target type, combat mission, and logical chain of target damage description events are accurately extracted, positive rewards will be given, such as increasing the weight of the feature extraction branch; if incorrect or omitted features are extracted, such as misjudging the target type of a "tank cluster" as an aerial target, penalties will be given, such as reducing the weight. Finally, through forward propagation calculations, the extracted features will be converted into damage feature vector representations, and the output will be used as the combat target image features corresponding to the target image. For example, after a series of calculations, a feature vector containing information such as target type and combat mission will be generated to provide key data for subsequent target damage assessments.

[0115] Furthermore, the target damage visualization compilation module includes the following functions:

[0116] Obtain the corresponding combat target data to be evaluated, including the corresponding combat target situation image and combat target intelligence text;

[0117] In an embodiment of the present invention, data of the combat target to be evaluated is obtained through a variety of intelligence collection methods. High-definition cameras carried by drones, satellites, etc. are used to photograph the combat area to obtain combat target situation images. These images cover information such as the appearance and surrounding environment of the combat target. For example, the architectural layout, facilities and equipment of the enemy military base can be photographed. At the same time, combat target intelligence text is obtained through intelligence personnel collection, communication monitoring, etc. The text content includes detailed information on the combat target, such as the type of combat target (tank, aircraft, etc.), combat capability parameters, running speed and other related intelligence data. The obtained combat target situation images and combat target intelligence text are sorted and stored to finally form the combat target data to be evaluated.

[0118] Preferably, the combat target data to be evaluated is input into the input layer corresponding to the large-scale joint combat target damage assessment model to extract combat target features, so as to extract and receive the corresponding combat target image features and text semantic damage features that have undergone preprocessing and feature extraction;

[0119] In an embodiment of the present invention, previously acquired combat target data is input into the input layer of a large-scale joint combat target damage assessment model. For combat target situation images, image preprocessing techniques are used, such as normalizing the brightness and contrast of the image. Then, a convolutional neural network (CNN) is used to extract features from the image. For example, multiple convolutional layers and pooling layers are used to extract features such as the shape, size, and color of the combat target in the image. For combat target intelligence text, text preprocessing is first performed, including noise removal (such as special characters and useless punctuation) and word segmentation. Then, word embedding techniques in natural language processing (such as Word2Vec and GloVe) are used to convert the text into a vector representation. Then, a recurrent neural network (RNN) or its variants (such as LSTM and GRU) are used to extract semantic damage features in the text, such as semantic information related to the combat target's weaknesses and defense capabilities. Finally, the preprocessed and feature-extracted combat target image features and text semantic damage features are extracted and received.

[0120] Preferably, the self-attention mechanism in the corresponding feature enhancement layer of the large-scale joint combat target damage assessment model is used to fuse the combat target image features and the text semantic damage features, so as to highlight the relevant features corresponding to the combat target damage and obtain the combat target damage-related features, including the combat target running speed, combat target combat capability, combat target defense level, combat target terrain concealment level, and combat target position change;

[0121] In an embodiment of the present invention, a self-attention mechanism is used in a feature enhancement layer of a large-model-based joint combat target damage assessment model to fuse the extracted combat target image features and text semantic damage features, and the image features and text features are respectively represented as feature vectors. By calculating the attention weights between different feature vectors, the model can focus on important features related to combat target damage. For example, when calculating the attention weights, higher weights are given to text features describing the degree of defense of the combat target and features of defense facilities displayed in the image to highlight their importance in damage assessment. These features are fused by weighted summation to obtain combat target damage-related features. By further analyzing and extracting the fused features, specific damage-related features such as the combat target's running speed, combat capability, defense degree, terrain concealment of the combat target, and position change of the combat target are determined.

[0122] Preferably, the target damage degree is calculated based on damage-related characteristics of the combat target to obtain the target damage degree; the damage range of the target damage degree is determined based on the change in the position of the combat target to obtain the target damage range; based on the target damage degree and the target damage range, the combat mission parameters corresponding to the combat target are calculated using a combat effectiveness loss calculation formula to obtain the combat effectiveness loss; based on the target damage degree, the impact of the combat geographical situation corresponding to the combat target is evaluated to obtain the impact of the target damage on the combat situation;

[0123] In an embodiment of the present invention, a suitable target damage degree calculation formula is formed by combining the operation speed of the combat target, the combat capability of the combat target, the defense degree of the combat target, the maximum defense degree corresponding to the combat target unit, the terrain concealment degree of the combat target, the size of the change in the position of the combat target and the corresponding weights for quantitative calculation. In addition, the target damage degree calculation formula can also use any target damage assessment algorithm in this field to replace the target damage degree calculation process, and is not limited to the target damage degree calculation formula. For example, the weight of the combat target defense degree is set to 0.4, the weight of the combat capability is set to 0.3, the weight of the operation speed is set to 0.1, and the weight of the terrain concealment degree is set to 0.2. Quantification is performed based on the specific values ​​of these characteristics, such as the defense degree is represented by the integrity rate of the defense facilities, and the combat capability is represented by the performance parameters of weapons and equipment and the comprehensive score of personnel quality, so as to quantify the target damage degree. Obtain position change information of combat targets. This information can be obtained in real time through satellite positioning systems, drone reconnaissance, and other means. Based on the target damage level, set the impact radius corresponding to different damage levels. For example, when the target damage level is 0-0.3, the impact radius is 100 meters; when it is 0.3-0.6, the impact radius is 200 meters; and when it is 0.6-1, the impact radius is 300 meters. Based on the initial position and position change trajectory of the combat target, combined with the impact radius corresponding to the target damage level, draw a circular area with the corresponding radius on the map with the target position as the center to determine the damage range. For example, if a combat target is initially located at map coordinates (100, 100) and moves to (150, 150) after a period of time, its target damage level is 0.6. Then, draw a circular area with (150, 150) as the center and a radius of 300 meters. This area is the target damage range.At the same time, by combining the target damage degree and the target damage range, the combat mission parameters corresponding to the combat target (including the real-time completion progress of the combat target task, the maximum completion progress required for the combat mission corresponding to the combat target, the combat target environmental situation and the duration of the combat operation) and combining the corresponding correction coefficient, a suitable combat effectiveness loss calculation formula is formed for calculation to quantify the combat effectiveness loss corresponding to the combat target. In addition, the combat effectiveness loss calculation formula can also use any combat effectiveness loss assessment method in this field to replace the loss calculation process, and is not limited to the combat effectiveness loss calculation formula. Then, by analyzing the geographical situation of the area where the combat target is located, including information such as topography (such as mountains, rivers, plains, etc.), the location of major transportation routes, etc., according to the target damage degree, its impact on the geographical situation is evaluated. For example, if the combat target is located at a traffic intersection On important roads, when the degree of damage to the target is high, it will cause blockage or damage to the main traffic arteries, affecting the mobility of the troops and the transportation of supplies. Assessment standards for the impact of different degrees of damage on the geographical situation are set. For example, when the degree of damage is 0-0.3, the impact on the geographical situation is small, causing only minor local obstructions; when it is 0.3-0.6, it affects the use of some traffic routes or key terrain; when it is 0.6-1, it causes traffic paralysis or the complete loss of combat value of key terrain. According to these standards, combined with the specific location and degree of damage of the combat target, the combat geographical situation is evaluated to obtain the impact of the target damage on the combat situation. For example, a combat target located on an important bridge has a damage degree of 0.8. According to the standard, it can be judged that the bridge can no longer be used normally, seriously affecting the traffic situation in the surrounding area, and thus having a significant impact on the overall combat situation. Finally, the corresponding impact of the target damage on the combat situation is obtained.

[0124] Preferably, target damage visualization compilation is performed based on the target damage degree, target damage range, combat effectiveness loss, and the corresponding impact of target damage on the combat situation to generate a combat target damage visualization compilation result.

[0125] In an embodiment of the present invention, by utilizing professional visualization tools (such as geographic information system software, data visualization platform, etc.), the target damage degree, target damage range, combat effectiveness loss, and the impact of target damage on the combat situation are integrated and visualized. For the target damage degree, the damage degree of different areas is indicated on the map by color coding or numerical annotation. For the target damage range, the boundary of the damaged area is drawn on the map. The combat effectiveness loss can be displayed in the form of charts (such as bar charts, line charts, etc.) to compare the losses of different combat missions. The impact of target damage on the combat situation can be marked on the map or chart by text descriptions and arrow indicators, etc., to indicate the affected geographical factors and combat links. These visualization elements are reasonably arranged and typeset, and necessary legends and explanatory notes are added to finally generate a visualization compilation result of combat target damage, providing an intuitive and clear reference basis for combat command and decision-making.

[0126] Furthermore, the target damage degree is calculated using a target damage degree calculation formula, which is specifically:

[0127]

[0128] Where D is the target damage degree, v is the target running speed, k1 is the running speed weight, C is the target combat capability, k2 is the combat capability weight, and ... f is the defense level of the combat target, k3 is the defense level weight, D f,max is the maximum defense level corresponding to the combat target unit, H is the concealment level of the combat target terrain, k4 is the concealment level weight, S is the change in the combat target position, and k5 is the position change weight.

[0129] The present invention obtains a target damage degree calculation formula by using a specific mathematical model and verification, which is used to calculate the target damage degree based on the damage-related characteristics of the combat target. The formula fully considers the target damage degree D, the combat target running speed v, the running speed weight k1, the combat target combat capability C, the combat capability weight k2, the combat target defense degree D f , defense degree weight k3, the maximum defense degree D corresponding to the combat target unit f,max , the concealment degree H of the combat target terrain, the concealment degree weight k4, the change size S of the combat target position, the position change weight k5, and the mutual correlation between the target damage degree D and the above parameters form a functional relationship This target damage calculation formula integrates multiple key characteristics of a target (such as speed, combat capability, defense, terrain concealment, and positional changes) to calculate the target's damage. This multi-dimensional assessment approach comprehensively considers the target's physical properties and environmental factors, making the damage calculation more accurate and realistic. By combining weights for different factors, the emphasis on each factor can be flexibly adjusted, resulting in a more reasonable damage assessment. By incorporating dynamic changes in parameters such as the target's defense, combat capability, concealment, and positional changes, the formula can provide real-time damage calculations as the battlefield environment changes. This provides commanders with more timely and accurate decision-making support, enabling them to quickly respond to diverse combat scenarios and assess target vulnerability and strike effectiveness. Each factor in the formula has a corresponding weight, which can be adjusted based on different combat missions and tactical requirements. This provides flexibility in operational planning, allowing the emphasis on each factor to be optimized based on actual conditions, ensuring the most appropriate damage assessment under specific conditions. For example, in urban warfare, terrain concealment is more important, while in traditional combat, target speed is more critical. This calculation formula not only considers the target's physical characteristics (such as speed, capabilities, and defenses), but also its positional changes during combat. This helps assess the target's vulnerability at different stages of combat. This comprehensive analysis can provide more refined information for actual strike decisions, making strike effects more precise. By calculating the degree of target damage, the formula can provide direct quantitative data for subsequent calculations of combat effectiveness losses. This makes the expected target destruction effect in the combat plan more specific and allows for further analysis based on multiple factors (such as mission completion progress, environmental situation, and combat duration), supporting the development of more strategic combat plans.

[0130] Furthermore, the combat effectiveness loss calculation formula is specifically as follows:

[0131]

[0132] Where L is the loss of combat effectiveness, D is the degree of target damage, R is the real-time completion progress of the combat target task, and R max is the maximum completion progress of the combat mission corresponding to the combat target, E is the combat target environment situation, T is the duration of the combat operation, and F D is the size of the target damage range, e is the base of the natural logarithm, and η is the correction coefficient for the loss of combat effectiveness.

[0133] The present invention obtains a combat effectiveness loss calculation formula by using a specific mathematical model and verifying it, which is used to calculate the loss of combat mission parameters corresponding to combat targets. The combat effectiveness loss calculation formula involves multiple key factors, such as target damage level, mission progress, environmental situation, combat time, damage range, etc. The combined effect of these factors helps to accurately reflect the combat effectiveness loss and can effectively quantify the changing situations that occur in combat. By comprehensively considering the damage to the combat target, the progress of mission execution, environmental changes, etc., the calculation of combat effectiveness loss is ensured to be more accurate and comprehensive. To express the task progress, this ratio can reflect the completion of the task at different time points and promptly reflect the impact of task progress on combat effectiveness. If the task progress is slow or fails to reach the required maximum progress, the combat effectiveness loss will increase accordingly. This design enables the formula to dynamically adapt to the changes in task completion during the combat process and calculate the combat effectiveness loss in real time. By introducing the combat duration and exponential decay e -T The formula reflects the impact of time on combat effectiveness loss. As combat duration increases, certain attrition effects intensify, especially during sustained strikes and attrition. This exponential decay term effectively simulates the exacerbating effect of increased combat time on effectiveness loss. The formula incorporates the environmental situation of the combat target as a key factor, reflecting the impact of the specific environmental conditions in the combat area on combat effectiveness. Different environmental conditions (such as weather, terrain, and enemy situation) have varying impacts on the execution and effectiveness of combat missions. This factor enables adaptive analysis of environmental situation, further improving the accuracy of combat effectiveness loss calculations. The formula measures the impact of the damage range on combat effectiveness loss by measuring the damage range. A larger damage range means more comprehensive destruction of the target, resulting in a greater impact on combat effectiveness loss. The inclusion of this factor allows the formula to reflect the widespread and impactful nature of target damage on the battlefield, providing a more accurate calculation of combat effectiveness loss. In addition, the correction coefficient in this formula provides flexible adjustment space for the calculation of combat effectiveness loss, and the results can be fine-tuned according to changes in the actual combat environment or special circumstances. This correction mechanism makes the formula more adaptable in different combat situations and can more accurately reflect the complex situations in actual combat. In summary, this formula fully considers the combat effectiveness loss L, the target damage degree D, the real-time completion progress R of the combat target task, and the maximum completion progress R of the combat task corresponding to the combat target. max , combat target environment situation E, combat operation duration T, target damage range F D , the base of the natural logarithm e, the correction coefficient η of the combat effectiveness loss, and the correlation between the combat effectiveness loss L and the above parameters form a functional relationship This formula can realize the loss calculation process of combat mission parameters corresponding to combat targets. At the same time, by introducing the correction coefficient η of combat effectiveness loss, it can be adjusted according to the errors occurring in the calculation process, thereby improving the accuracy and applicability of the combat effectiveness loss calculation formula.

[0134] Furthermore, the target damage visualization compilation according to the target damage degree, target damage range, combat effectiveness loss, and the impact of target damage on the combat situation includes:

[0135] Generate a heat map of target damage severity for each target area based on the target damage severity, to visually present the severity of damage to different target areas.

[0136] In an embodiment of the present invention, damage level data for specific locations within a target area is collected. This data is derived from various sensor monitoring information, frontline reconnaissance reports, and the like. Using geographic information system (GIS) technology, the target area is divided into a grid, with each grid corresponding to a specific geographic coordinate location. Based on the damage level of the targets within each grid, such as indicators such as the proportion of buildings damaged and the number of casualties, corresponding values ​​are assigned. A heat map generation algorithm is employed, with different color mapping rules set. For example, areas with low damage levels are mapped to green, areas with medium damage levels to yellow, and areas with high damage levels to red. The damage level values ​​for each grid are visualized according to the color mapping rules to generate a target damage level heat map corresponding to the target area. For example, in a target damage assessment within an urban area, the above method can be used to generate a heat map by analyzing the building damage and casualty data for each block, visually displaying which blocks are severely damaged and which are relatively lightly damaged, ultimately generating a target damage level heat map.

[0137] Preferably, a three-dimensional dynamic model of the target damage range corresponding to the target area is produced according to the target damage range to clearly display the target damage status corresponding to the combat target and the surrounding environment;

[0138] In an embodiment of the present invention, three-dimensional modeling of the target area is performed using three-dimensional modeling software (such as 3dsMax, Maya, etc.) and geographic information data to import high-precision terrain data and construct the topography of the target area, including geographical features such as mountains, rivers, and roads. Based on the collected target damage range information, such as which buildings were destroyed and which facilities were damaged, the damaged targets are marked and modeled in the three-dimensional model. To achieve dynamic display, the model's animation keyframes are set in combination with time series data. For example, the target damage process is gradually displayed according to the time course of the combat, first showing partial structural damage to the building, and then showing the complete collapse of the building over time. By setting the camera perspective and animation path, the target damage range can be displayed from different angles and distances. For example, when simulating the target damage situation in an urban combat, the model can clearly show the damage changes of the combat target and the surrounding environment, and ultimately generate a three-dimensional dynamic model of the target damage range.

[0139] Preferably, the effectiveness loss impact is mapped based on the impact of the combat effectiveness loss on the target damage on the combat situation, so as to generate a combat effectiveness loss situation impact trend map corresponding to the target area, and help accurately grasp the impact trend of the target damage on the overall combat situation;

[0140] In an embodiment of the present invention, by clarifying various evaluation indicators of combat effectiveness, such as the proportion of troop losses, the rate of damage to weapons and equipment, and the degree of mission completion, the impact of target damage on various combat effectiveness indicators is analyzed based on the target damage situation. A mathematical model is established to quantify the relationship between the degree of target damage and combat effectiveness loss. For example, it is set that for every certain number of weapons and equipment destroyed, combat effectiveness will decrease by a corresponding proportion. With time as the horizontal axis and combat effectiveness loss as the vertical axis, a scatter plot is drawn based on the target damage situation at different time points and the corresponding combat effectiveness loss data. Then, a curve fitting algorithm (such as the least squares method) is used to fit the scatter plot to obtain a curve that can reflect the trend of combat effectiveness loss over time. Key time points and corresponding combat events are marked on the curve to generate a combat effectiveness loss situation impact trend chart corresponding to the target area. Through this chart, the changing trend of combat effectiveness loss as target damage occurs and develops can be clearly seen, thereby accurately grasping the impact of target damage on the overall combat situation.

[0141] Preferably, the target damage degree heat map corresponding to the target area, the target damage range three-dimensional dynamic model and the combat effectiveness loss situation impact trend map are visually compiled for target damage to generate a combat target damage visualization compilation result.

[0142] In an embodiment of the present invention, a heat map of target damage degree, a three-dimensional dynamic model of target damage range, and a trend map of impact of combat effectiveness loss situation are integrated by utilizing professional visualization integration software (such as Adobe After Effects, Tableau, etc.). During the integration process, a reasonable layout and interaction method are set. For example, the heat map is placed on one side of the interface as a visual display of the overall damage situation; the three-dimensional dynamic model is placed in the center of the interface, and the user can view the target damage range from different angles through interactive operations (such as mouse dragging, zooming, etc.); the trend map of impact of combat effectiveness loss situation is placed on the other side to facilitate user comparison and analysis, add necessary text descriptions, legends and annotations, explain and mark each visualization element, set animation transition effects, and make the switching between different visualization elements smoother and more natural, and finally generate a complete, intuitive and easy-to-understand visualization compilation result of combat target damage, providing a clear reference basis for combat command and decision-making.

[0143] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0144] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A target damage assessment and analysis system based on a large model, characterized by: Includes the following modules: The combat target data cleaning module is used to obtain the corresponding combat target geographic situation image through satellite reconnaissance, and integrate the combat intelligence reports and combat instructions corresponding to the target combat unit to obtain combat target text data; the combat target geographic situation image and combat target text data are cleaned according to data standards to obtain the combat target situation standard image and combat target standard text data; The combat target feature fusion module is used to build a corresponding target feature analysis model using convolutional neural networks and Transformer architecture. It then inputs the combat target situation standard image and combat target standard text data into the target feature analysis model to perform combat target driven analysis and output the corresponding combat target image features and text semantic damage features. The target damage assessment model establishment module is used to take the target feature analysis large model as the input layer and build a joint combat target damage assessment model based on the large model based on the input layer, the preset feature enhancement layer, the fusion reasoning layer, and the output layer; The target damage visualization compilation module is used to obtain the corresponding combat target data to be evaluated, including the corresponding combat target situation image and combat target intelligence text; the corresponding combat target data to be evaluated is input into the joint combat target damage assessment model based on the large model to perform target damage assessment analysis, and the corresponding target damage degree, target damage range, combat effectiveness loss, and the impact of target damage on the combat situation are predicted and output; Target damage visualization is performed based on the target damage degree, target damage range, combat effectiveness loss, and the corresponding impact of target damage on the combat situation to generate combat target damage visualization results.

2. The target damage assessment and analysis compilation system based on a large model according to claim 1 is characterized in that: The combat target data cleaning module includes the following functions: Obtain geographical situation images of combat targets corresponding to the target area through satellite reconnaissance; By integrating the combat intelligence reports and combat instructions corresponding to each target combat unit in the target area, the combat target text data can be obtained; Performing local pixel ambiguity analysis on the combat target geographic situation image to obtain the local pixel ambiguity of the combat target image; Based on the local pixel fuzziness of the combat target image, the combat target geographical situation image is subjected to fuzzy denoising and standardization to obtain a combat target situation standard image; The combat target text data is cleaned according to text error correction standards to obtain standard combat target text data.

3. The target damage assessment and analysis compilation system based on a large model according to claim 2 is characterized in that: The text error correction and standard cleaning of combat target text data includes: Performing part-of-speech analysis and tagging on each word in the combat target text data to obtain combat target text part-of-speech tagging data; Based on the part-of-speech tagging data of the combat target text, grammatical error correction analysis is performed on each word in the combat target text data to correct the corresponding typos and grammatical errors and unify the vocabulary expressions. At the same time, the corresponding special characters, punctuation marks and meaningless stop words are removed to obtain the combat target text correction data; Through the common combat field data standards and coding system, data standardization processing is performed on the different sources and formats corresponding to the combat target text correction data to obtain the combat target standard text data.

4. The target damage assessment and analysis compilation system based on a large model according to claim 1 is characterized in that: The combat target feature fusion module includes the following functions: Utilize convolutional neural networks and combine them with target images to construct corresponding target image feature extraction branches to output combat target image features corresponding to the target image; Utilize the Transformer architecture and combine it with text data to build a corresponding target semantic damage feature extraction branch to output the semantic damage features of the combat target corresponding to the target text; Connect the target image feature extraction branch and the target semantic damage feature extraction branch with the corresponding cross-modal feature association module to build a corresponding target feature analysis model to achieve the association and fusion between the target image features and the text semantics; The standard image of the combat target situation and the standard text data of the combat target are input into the target feature analysis model for combat target driven analysis to output the corresponding combat target image features and text semantic damage features.

5. The target damage assessment and analysis compilation system based on a large model according to claim 4 is characterized in that: The target image feature extraction branch is specifically composed of a large-scale 5x5 convolution layer, a small-scale 3x3 convolution layer and a 1x1 pooling layer. The large-scale 5x5 convolution layer is used to extract the geometric shape and texture features of the combat target corresponding to the target image, the small-scale 3x3 convolution layer is used to extract the position changes of the combat target and the surrounding environment situation characteristics corresponding to the target image at different time periods, and the large-scale and small-scale corresponding features are reduced in dimension in the 1x1 pooling layer.

6. The target damage assessment analysis and compilation system based on a large model according to claim 4 is characterized in that: The target semantic damage feature extraction branch is specifically: By performing combat target semantic segmentation on the text data in the corresponding input layer within the Transformer architecture, a combat target semantic segmentation set is generated; By using the corresponding military semantic graph in the corresponding text encoding layer within the Transformer architecture, each combat target word or phrase in the combat target semantic word set is semantically encoded and represented. For each word or phrase, its corresponding combat domain concept in the military semantic graph is searched, and the relevant attributes and relationship codes corresponding to the combat domain concept are embedded in the corresponding combat target word or phrase to generate a combat target semantic encoding representation. By extracting target damage features from the semantic encoding representation of combat targets in the corresponding last layer within the Transformer architecture, the target type, combat mission, and target damage description event logic chain corresponding to the combat target are extracted. By introducing additional constraints and reward mechanisms, the feature extraction branch's ability to extract the corresponding semantic features of combat targets is enhanced. If the corresponding combat target damage features are accurately extracted, positive rewards are given, while if incorrect or omitted features are extracted, penalties are given. The corresponding damage feature vector representation is obtained through the forward propagation calculation corresponding to the last layer to output the combat target image features corresponding to the target image.

7. The target damage assessment analysis and compilation system based on a large model according to claim 1 is characterized in that: The target damage visualization compilation module includes the following functions: Obtain the corresponding combat target data to be evaluated, including the corresponding combat target situation image and combat target intelligence text; The combat target data to be evaluated is input into the input layer of the joint combat target damage assessment model based on the large model to extract combat target features, so as to extract and receive the corresponding combat target image features and text semantic damage features that have undergone preprocessing and feature extraction; The self-attention mechanism in the corresponding feature enhancement layer of the large-scale joint combat target damage assessment model is used to fuse the target image features and text semantic damage features, so as to highlight the relevant features corresponding to the combat target damage. The target damage-related features are obtained, including the combat target's running speed, combat capability, defense level, terrain concealment level, and position change. Calculate the target damage degree based on the damage-related characteristics of the combat target to obtain the target damage degree; Determine the damage range of the target based on the change in the position of the combat target to obtain the target damage range; Based on the target damage degree and target damage range, the combat effectiveness loss calculation formula is used to calculate the loss of combat mission parameters corresponding to the combat target to obtain the combat effectiveness loss; Conduct an impact assessment on the geographical situation corresponding to the combat target based on the degree of target damage to obtain the impact of target damage on the combat situation; Target damage visualization is performed based on the target damage degree, target damage range, combat effectiveness loss, and the corresponding impact of target damage on the combat situation to generate combat target damage visualization results.

8. The target damage assessment and analysis compilation system based on a large model according to claim 7 is characterized in that: The target damage degree is calculated using a target damage degree calculation formula, which is specifically: Where D is the target damage degree, v is the target running speed, k1 is the running speed weight, C is the target combat capability, k2 is the combat capability weight, and ... f is the defense level of the combat target, k3 is the defense level weight, D f,max is the maximum defense level corresponding to the combat target unit, H is the concealment level of the combat target terrain, k4 is the concealment level weight, S is the change in the combat target position, and k5 is the position change weight.

9. The target damage assessment analysis and compilation system based on a large model according to claim 7 is characterized in that: The calculation formula for combat effectiveness loss is as follows: Where L is the loss of combat effectiveness, D is the degree of target damage, R is the real-time completion progress of the combat target task, and R max is the maximum completion progress of the combat mission corresponding to the combat target, E is the combat target environment situation, T is the duration of the combat operation, and F D is the size of the target damage range, e is the base of the natural logarithm, and η is the correction coefficient for the loss of combat effectiveness.

10. The target damage assessment and analysis compilation system based on a large model according to claim 7 is characterized in that: The target damage visualization compilation according to the target damage degree, target damage range, combat effectiveness loss, and the impact of target damage on the combat situation includes: Generate a heat map of target damage severity for each target area based on the target damage severity, to visually present the severity of damage to different target areas. Create a three-dimensional dynamic model of the target damage range corresponding to the target area based on the target damage range to clearly display the damage status of the combat target and the surrounding environment; Based on the impact of combat effectiveness loss on target damage on the combat situation, the effectiveness loss impact is mapped to generate a trend chart of combat effectiveness loss situation impact corresponding to the target area, helping to accurately grasp the impact trend of target damage on the overall combat situation; The target damage degree heat map corresponding to the target area, the three-dimensional dynamic model of the target damage range, and the combat effectiveness loss situation impact trend map are compiled for target damage visualization to generate the combat target damage visualization compilation result.

Images