A method, device, medium and product for analyzing global efficiency of unmanned swarm combat network

Abstract

The application discloses a kind of unmanned cluster combat network global efficiency analysis method, equipment, medium and product, it is related to unmanned cluster technical field.The method comprises: based on the interlayer connection relationship and interlayer connection relationship between the nodes in the perception class, decision class, influence class and target class in the architecture of unmanned cluster combat network Form relationship matrix;Determine the upper bound of path length based on the number of perception class nodes and the number of decision class nodes;Determine the shortest path length of effective combat closed loop from the target class node based on the number of perception class nodes and the number of decision class nodes;Determine the number of effective combat closed loop through the target class node corresponding to the shortest path length based on relationship matrix;Under the constraint of the upper bound of path length, determine the global efficiency of unmanned cluster combat network based on the shortest path length and the number of effective combat closed loop.The application can analyze the global efficiency of unmanned cluster combat network, to provide data basis for improving the overall combat effectiveness of unmanned cluster.

Description

Technical Field

[0001] The present application relates to the field of unmanned swarm technology, and in particular to a method, device, medium and product for analyzing the global efficiency of an unmanned swarm combat network. Background Art

[0002] Unmanned swarms are large-scale, complex systems composed of numerous unmanned intelligent devices, with complex and diverse internal interactions. Relying on advanced communication technologies for information exchange and feedback, these systems leverage dynamic interaction schemes and collaborative strategies to enable coordinated collaboration among individual unmanned intelligent devices, adapting to a constantly changing external environment and achieving multi-dimensional mission objectives within defined time and space domains. These systems demonstrate broad application potential and significant practical value across a wide range of military and civilian sectors.

[0003] Existing research often uses complex networks to characterize the internal interconnectedness of unmanned swarms. However, unmanned swarms involve a wide variety of unmanned intelligent devices, and their internal communication relationships are orderly and diverse, resulting in unmanned swarm combat networks characterized by heterogeneous nodes and directed links. Traditional network efficiency quantifies the speed of information transmission between nodes in a network. Information timeliness is fundamental to maximizing the effectiveness of each unmanned unit in a swarm and synchronously executing combat missions. Therefore, network efficiency is a key metric for measuring swarm performance. In an unmanned swarm combat network, network efficiency directly reflects the ability of unmanned units to coordinate information and respond quickly. A highly efficient combat network ensures the rapid transmission of commands and information between unmanned units, thereby improving the overall combat effectiveness of the swarm.

[0004] However, there is no known method to analyze the global efficiency of unmanned swarm combat networks. Summary of the Invention

[0005] The purpose of this application is to provide a global efficiency analysis method, equipment, medium and product for an unmanned swarm combat network, which can analyze the global efficiency of the unmanned swarm combat network and provide a data basis for improving the overall combat effectiveness of the unmanned swarm.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for analyzing the global efficiency of an unmanned swarm combat network, comprising:

[0008] In the unmanned swarm combat network architecture, the friendly nodes are classified into perception nodes, decision nodes, and influence nodes according to the functions of each unit and the role each unit plays in the actual combat environment.

[0009] The target tasks of the unmanned swarm combat network are used as target class nodes;

[0010] Based on the intra-layer connection relationship and inter-layer connection relationship among the perception nodes, the decision nodes, the influence nodes, and the target nodes in the unmanned swarm combat network architecture, a relationship matrix is ​​formed;

[0011] Determine an upper bound on the path length based on the number of the perception nodes and the number of the decision nodes;

[0012] Determining the shortest path length of an effective combat closed loop starting from the target node based on the number of the perception nodes and the number of the decision nodes; an effective combat closed loop refers to completing the target task through observation, adjustment, decision-making, and action by nodes in the unmanned swarm combat network; and the number of nodes involved in the effective combat closed loop is used as the path length of the effective combat closed loop;

[0013] Determine, based on the relationship matrix, the number of effective combat closed loops passing through the target node corresponding to the shortest path length;

[0014] Under the constraint of the upper bound of the path length, the global efficiency of the unmanned swarm combat network is determined based on the shortest path length and the number of effective combat closed loops.

[0015] In a second aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the global efficiency analysis method of the unmanned cluster combat network described in any one of the above.

[0016] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for analyzing the global efficiency of an unmanned cluster combat network.

[0017] In a fourth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned methods for analyzing the global efficiency of an unmanned cluster combat network.

[0018] According to the specific embodiments provided in this application, this application has the following technical effects:

[0019] This application provides a method, device, equipment, medium and product for analyzing the global efficiency of an unmanned swarm combat network. By determining the upper bound of the path length of the shortest path length of an effective combat closed loop starting from a target node, a solid theoretical foundation can be laid for determining the global efficiency of the unmanned swarm combat network. On this basis, the global efficiency of the unmanned swarm combat network can be determined based on the shortest path length and the number of effective combat closed loops, thereby realizing the analysis of the global efficiency of the unmanned swarm combat network and providing a data basis for improving the overall combat effectiveness of the unmanned swarm. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 This is an application environment diagram of a method for analyzing the global efficiency of an unmanned swarm combat network in one embodiment of the present application;

[0022] Figure 2 A flowchart of a method for analyzing the global efficiency of an unmanned swarm combat network provided in one embodiment of the present application;

[0023] Figure 3 A schematic diagram showing the changes over time in the global efficiency of the unmanned swarm combat network (referred to as the global efficiency of the combat network) and the global efficiency of the traditional network under the random attack mode provided in one embodiment of the present application;

[0024] Figure 4 This is a schematic diagram showing the change in the number of combat rings over time in a random attack mode provided by an embodiment of the present application;

[0025] Figure 5 A schematic diagram showing the change in the number of connected node pairs over time in a random attack mode provided in one embodiment of the present application;

[0026] Figure 6 A schematic diagram showing the changes over time in the global efficiency of the unmanned swarm combat network (referred to as the global efficiency of the combat network) and the global efficiency of the traditional network under the maximum attack mode provided in one embodiment of the present application;

[0027] Figure 7 This is a schematic diagram showing the change in the number of combat rings over time in the maximum attack mode provided in one embodiment of the present application;

[0028] Figure 8This is a schematic diagram showing the change in the number of connected node pairs over time in the maximum attack mode provided by one embodiment of the present application;

[0029] Figure 9 This is a schematic diagram showing the changes over time in the global efficiency of the unmanned swarm combat network (referred to as the global efficiency of the combat network) and the global efficiency of the traditional network determined by this application under the maximum betweenness attack mode provided in one embodiment of this application;

[0030] Figure 10 This is a schematic diagram showing the change in the number of combat rings over time in the maximum betweenness attack mode provided in one embodiment of the present application;

[0031] Figure 11 A schematic diagram showing the change in the number of connected node pairs over time in a maximum betweenness attack mode provided in one embodiment of the present application;

[0032] Figure 12 A schematic diagram showing the change in average combat network efficiency over time determined by the present application under the TA mode provided in one embodiment of the present application;

[0033] Figure 13 A schematic diagram showing the change in average combat network efficiency over time determined by the present application in the SA mode provided in one embodiment of the present application;

[0034] Figure 14 A schematic diagram showing the change of the average combat network efficiency over time determined by the present application under the DA mode provided in one embodiment of the present application;

[0035] Figure 15 A schematic diagram showing the change in average combat network efficiency over time determined by the present application in the WA mode provided in one embodiment of the present application;

[0036] Figure 16 A schematic diagram showing the change in the average traditional network efficiency over time determined by the present application in the TA mode provided in one embodiment of the present application;

[0037] Figure 17 A schematic diagram showing the change in the average traditional network efficiency over time determined by the present application in the SA mode provided in one embodiment of the present application;

[0038] Figure 18 A schematic diagram showing the change of the average traditional network efficiency over time determined by the present application in the DA mode provided in one embodiment of the present application;

[0039] Figure 19 A schematic diagram showing the change in the average traditional network efficiency over time determined by the present application in the WA mode provided in one embodiment of the present application;

[0040] Figure 20A schematic diagram showing the change in the average number of combat rings over time determined by the present application in the TA mode provided in one embodiment of the present application;

[0041] Figure 21 A schematic diagram showing the change in the average number of combat rings over time determined by the present application in the SA mode provided in one embodiment of the present application;

[0042] Figure 22 A schematic diagram showing the change in the average number of combat rings over time determined by the present application under the DA mode provided in one embodiment of the present application;

[0043] Figure 23 A schematic diagram showing the change in the average number of combat rings over time determined by the present application in the WA mode provided in one embodiment of the present application;

[0044] Figure 24 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0046] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0047] The technical solutions provided in this application include:

[0048] (1) Definition of global efficiency of combat network in heterogeneous directed networks.

[0049] Unmanned swarm networks are different from ordinary homogeneous networks or single-layer networks. They are composed of multiple heterogeneous nodes and a large number of heterogeneous relationships. This application relies on the interactive network of unmanned swarms and regards each unit in the swarm as a single node in the network. In the unmanned swarm combat network architecture, according to the functions of each unit and the role it plays in the actual environment, the friendly nodes can be divided into perception nodes S, decision nodes D, and influence nodes W, and the target task is set as the target node T.

[0050] In the framework of complex network theory, the network efficiency between two nodes is defined as the inverse of the shortest distance between the two points, reflecting the speed of information transmission between nodes. The global efficiency of the entire network is defined as the average of the efficiencies between all pairs of nodes on the network, providing a comprehensive evaluation of the overall performance of the network. However, in the specific heterogeneous directed network of the unmanned swarm combat network, traditional network efficiency indicators need to be adjusted accordingly to adapt to its inherent characteristics. Considering that the inter-node association pattern of the unmanned swarm combat network is fixed within a limited scope, this application proposes a definition of the combat network efficiency of the unmanned swarm combat network and the global efficiency of the combat network based on the OODA loop theory and the unmanned swarm combat process. Among them, OODA is the abbreviation of Observe (Oberve), Adjust (Orient), Decision (Decide) and Act (Act).

[0051] Definition 1: Operation network efficiency refers to the efficiency of an effective operation closed loop of a target class node in the operation network, that is, the reciprocal of the shortest path distance from a target class node to form an effective operation closed loop in the operation network topology, as shown in the following formula (1):

[0052]

[0053] in, is the number of target class nodes n in the combat network at time t T To form an effective closed-loop network efficiency, is the shortest path length of the node OODA loop in the combat network at time t.

[0054] The combat network efficiency reflects the transmission efficiency of the network when achieving a closed loop between target nodes, providing a direct assessment of the transmission and response capabilities of the unmanned swarm combat network. For a typical unmanned swarm effective combat network, that is, the average value of the maximum efficiency of the combat network in forming an effective combat closed loop (T→S→D→W→T) between target nodes, perception nodes, decision nodes, influence nodes, and target nodes. In a general combat network under the conditions of "resource sharing and information fusion", any t n Indirect connections need to go through the perception node s i , decision node d j , influence class node w m Three types of nodes, therefore in a conventional effective combat network A general unmanned swarm combat network includes seven types of OODA loops, namely, the typical OODA loop, the OODA loop with information sharing, the OODA loop with collaborative decision-making, the OODA loop with information sharing and collaborative decision-making, the OODA loop with information feedback, the OODA loop with information sharing and feedback, and the OODA loop with collaborative decision-making and information feedback.

[0055] Definition 2: Operation network global efficiency is the average efficiency of the effective operation closed loop formed by all target nodes in the cluster operation network. That is, the average of the maximum efficiency of the operation network starting from the target node and returning to the target node through the operation network to form an effective operation closed loop. The global real-time efficiency of the cluster operation network can be expressed as:

[0056]

[0057] Among them, N T is the total number of target-type nodes T in the combat network, and N is the total number of effective combat closed loops of all target-type nodes in the combat network.

[0058] In an unmanned swarm combat network, an effective closed-loop combat loop for a target-type node represents the complete process from mission initiation to goal achievement. Global combat network efficiency quantifies the efficiency of the unmanned swarm combat network in achieving its own closed-loop combat loop for each target-type node, reflecting the network's overall performance and collaborative combat capabilities.

[0059] (2) Calculation of global efficiency of combat network in heterogeneous directed networks.

[0060] According to the definition of the global efficiency of the combat network given in the above step (1), the intra-layer and inter-layer connection relationships of the detection layer, decision layer, attack layer and target layer of the cluster combat network are represented by matrices. Based on this, the global efficiency of the combat network is calculated.

[0061] Global Efficiency of Operational Network (NE) on The total number of effective combat closed loops N of all target-type nodes in the combat network and the number of nodes t in the combat network are n The shortest path length of a valid OODA loop According to the definition of combat network In a directed swarm combat network, given a fixed number of nodes, the shortest path length of an effective combat closed loop formed on each target-type node is limited to a maximum theoretical value, i.e., there is an upper bound. Therefore, the following theorem is necessary:

[0062] When the number of nodes is fixed, the shortest path length of the effective combat closed loop starting from the target class node in the cluster combat network has an upper bound M, and:

[0063] M=2+N S +N D (3)

[0064] Among them, N S represents the number of perception nodes S, N D Indicates the number of decision nodes D.

[0065] The proof process of the above theorem is as follows: According to the combat network node association pattern, observing the structure of the OODA loop, it is not difficult to find that any valid OODA loop contains and only contains one target node T and one influence node W. In other words, there is only one edge of each of the three types of T→S, D→W, and W→T in the valid OODA loop. Therefore, the length of the shortest path of an effective combat closed loop is determined by the number of detection nodes S and the number of decision nodes D in the closed loop. At this time, if there is an upper bound of the valid OODA loop, it should contain the full number of detection nodes S and decision nodes D. Assume that the OODA loop is in, Represents 1 to N S +N D The shortest path length of this effective combat closed loop is If you want to build a longer OODA loop, you need to select two nodes (let them be and )Add an edge However, due to the nature of the shortest path, M The effective OODA loop shortest path length of the departure remains unchanged.

[0066] The existence of the above theorem reveals the following key characteristics of unmanned swarm combat networks from the two dimensions of application and computation:

[0067] First, the above theorem means that in the actual application of unmanned swarm combat networks, no matter how the scale of the network expands, the effective information transmission in unmanned swarm combat will eventually reach a clear end point, thus eliminating the possibility of infinite information loops and ensuring that combat commands and information can be transmitted efficiently and orderly in the ever-changing battlefield environment.

[0068] Second, the above theorem is of great significance in the calculation of network efficiency of unmanned swarm combat. The problem of the rapid increase in computational complexity of N when it tends to infinity prevents the high complexity of link analysis and lays a theoretical foundation for building a global efficiency algorithm for unmanned swarm combat networks.

[0069] In order to calculate the total number N of the effective operational closed loops of the target class node, the number of the closed loops with the shortest path length of the effective operational closed loops of the target class node T as l is The calculation formula of N is as follows:

[0070]

[0071] In the actual application process, based on the definition and determination mode given above, the concept and principle of the global efficiency analysis method of the unmanned cluster operational network provided in the application are as follows:

[0072] Firstly, based on the OODA loop theory and the cluster operational process, a definition of the unmanned cluster operational network efficiency and the global efficiency of the operational network under the complex network theory framework is proposed. Then, the boundedness theorem of the shortest path length of the effective operational closed loops starting from the target class node in the unmanned cluster operational network is proved, which lays the theoretical foundation for the global efficiency calculation method of the unmanned cluster operational network.

[0073] Based on this, the embodiment of the application provides a global efficiency analysis method of an unmanned cluster operational network, which can be applied to, for example Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store data that server 104 needs to process. The data storage system can be set up separately, integrated with server 104, or located in the cloud or on other servers. Terminal 102 can send the unmanned swarm combat network architecture to server 104. After receiving the unmanned swarm combat network architecture, server 104 categorizes its own nodes based on the functions of each unit and the role each unit plays in the actual combat environment, resulting in perception nodes, decision nodes, and influence nodes. The target tasks of the unmanned swarm combat network are used as target nodes. A relationship matrix is ​​formed based on the intra-layer and inter-layer connection relationships between perception nodes, decision nodes, influence nodes, and target nodes in the unmanned swarm combat network architecture. An upper bound on the path length is determined based on the number of perception nodes and decision nodes. The shortest path length of a valid combat closed loop starting from a target node is determined based on the number of perception nodes and decision nodes. The number of valid combat closed loops passing through the target node corresponding to the shortest path length is determined based on the relationship matrix. Under the upper bound constraint of the path length, the global efficiency of the unmanned swarm combat network is determined based on the shortest path length and the number of effective combat closed loops. The server 104 can provide feedback on the obtained global efficiency analysis results of the unmanned swarm combat network to the terminal 102. In addition, in some embodiments, the global efficiency analysis method of the unmanned swarm combat network can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly perform the global efficiency analysis of the unmanned swarm combat network architecture, or the server 104 can obtain the unmanned swarm combat network architecture from a data storage system and perform the global efficiency analysis on the unmanned swarm combat network architecture.

[0074] Terminal 102 may include, but is not limited to, various desktop computers, laptops, smartphones, tablet computers, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers, or may be a cloud server.

[0075] In an exemplary embodiment, Figure 2 As shown, a method for analyzing the global efficiency of an unmanned swarm combat network is provided. The method is executed by a computer device, specifically a computer device such as a terminal or a server, or a terminal and a server. In the embodiment of the present application, the method is applied to Figure 1The server 104 in FIG. 1 is used as an example to illustrate the process, including the following steps 200 to 206.

[0076] in:

[0077] Step 200: In the unmanned swarm combat network architecture, the own nodes are classified according to the functions of each unit and the role played by each unit in the actual combat environment to obtain perception nodes, decision nodes and influence nodes.

[0078] Step 201: The target task of the unmanned swarm combat network is used as a target class node.

[0079] Step 202: Based on the intra-layer connection relationship and inter-layer connection relationship among the perception nodes, decision nodes, impact nodes, and target nodes in the unmanned swarm combat network architecture, a relationship matrix is ​​formed.

[0080] Step 203: Determine the upper bound of the path length based on the number of perception nodes and the number of decision nodes.

[0081] Step 204: Based on the number of perception nodes and decision nodes, the shortest path length of an effective combat loop starting from the target node is determined. An effective combat loop refers to the completion of a target mission by nodes in the unmanned swarm combat network through observation, adjustment, decision-making, and action. The number of nodes involved in the effective combat loop is used as the path length of the effective combat loop.

[0082] Step 205: Determine the number of effective combat closed loops passing through the target class node corresponding to the shortest path length based on the relationship matrix.

[0083] Step 206: Under the constraint of the upper bound of the path length, determine the global efficiency of the unmanned swarm combat network based on the shortest path length and the number of effective combat closed loops.

[0084] Implementing the above steps 200 to 206 can analyze the global efficiency of the unmanned swarm combat network, so as to provide a data basis for improving the overall combat effectiveness of the unmanned swarm.

[0085] In another exemplary embodiment of the present application, the implementation process of step 205 can be described as follows:

[0086] (11) Based on the relationship matrix, the effective combat closed loop length starting from the target class node is obtained as the matrix eigenvalue of the shortest path length.

[0087] (12) Determine the number of effective combat closed loops based on the matrix eigenvalues.

[0088] In another exemplary embodiment of the present application, the method for determining the global efficiency of the unmanned swarm combat network provided by the present application may also be:

[0089] (21) Based on the number of effective combat closed loops, the total number of all effective combat closed loops in the unmanned swarm combat network is determined under the constraint of the upper bound of the path length.

[0090] (22) The reciprocal of the shortest path length of the effective combat closed loop starting from the target class node is taken as the efficiency of the effective combat closed loop of the corresponding target class node.

[0091] (23) Based on the total number of target class nodes, the efficiency of the effective combat closed loop of each target class node is weighted and summed to obtain the initial efficiency.

[0092] (24) The ratio of the initial efficiency to the total number of all effective combat closed loops in the unmanned swarm combat network is taken as the global efficiency of the unmanned swarm combat network.

[0093] In actual application, the implementation process of the above steps (21) to (24) can be: in the unmanned swarm combat network, the effective combat closed loop length starting from the target class node is the shortest path length, or the number of nodes passing through is the matrix of the shortest path length l is set as A l , matrix A l The diagonal elements of Indicates passing through node t n The number of combat closed loops with a path length of l.

[0094] When l=4, A 4 =A TS A SD A DW A WT When l=5, ...and so on.

[0095] In summary, according to the physical meaning of the product of the correlation matrix:

[0096]

[0097] in, Represents the matrix A l tth n eigenvalues, n l represents the number of effective combat closed loops. Substituting into formula (4) we can get:

[0098]

[0099] Substituting into formula (2), the global efficiency of the unmanned swarm combat network can be obtained as:

[0100]

[0101] In the formula, NE on(t) represents the global efficiency of the unmanned swarm combat network at time t.

[0102] In another exemplary embodiment of the present application, by establishing a 105-node unmanned cluster network including 20 target-type nodes, 45 perception-type nodes, 10 decision-type nodes and 30 influence-type nodes as an example, the global efficiency of the combat network is compared with the global efficiency of the traditional network in a variety of different simulation scenarios to verify the effectiveness of the resilience assessment model based on the global efficiency of the combat network.

[0103] Analysis 1: Figures 3 to 5 The global efficiency of the combat network under random attack mode, the global efficiency of the traditional network, the number of effective combat rings in the combat network and the number of connected node pairs change over time. Figures 3 to 5 As can be seen, in the random attack mode, due to the redundancy and synergy of swarm combat network resources, the global efficiency of the combat network initially remains stable. However, as more and more nodes fail, the global efficiency of the combat network begins to slowly decline. When the number of failed nodes exceeds a certain threshold, the number of effective OODA loops in the swarm combat network drops sharply, and the global efficiency of the combat network begins to rapidly drop to zero. In contrast, the global efficiency of traditional networks initially increases and then decreases during the initial node failure process. This phenomenon is due to the presence of numerous connected node pairs with long shortest paths in multi-layer directed networks. As nodes in the combat network gradually fail, the number of connected node pairs in the network rapidly decreases, the network structure becomes increasingly streamlined, and the efficiency of information transmission improves. Ultimately, as the number of connected node pairs decreases to zero, the global efficiency of the traditional network also rapidly drops to zero.

[0104] Analysis 2: Figures 6 to 8 The global efficiency of the combat network under the maximum attack mode, the global efficiency of the traditional network, the number of effective combat rings in the combat network, and the number of connected node pairs change over time. Figures 6 to 8It can be seen that the global efficiency of the combat network in the maximum attack mode changes in a similar manner to that in the random failure scenario. Although it remains in the initial stable state for a longer period, this phenomenon is due to the stability of the number of effective OODA loops in the initial phase of the maximum failure. However, the global efficiency of the traditional network slowly decreases in the early stages of node failure, reaches an early low point, then gradually rises, and then rapidly declines after the number of connected node pairs in the network drops to zero. This phenomenon is because, in the early stages of node failure, the number of connected node pairs in the network decreases more slowly than in the random failure mode, making the number relatively more stable and the network structure less altered. Second, the failure of the node with the highest degree in the combat network reduces the number of connected node pairs with shortest paths, resulting in a decrease in network efficiency. As the failure process progresses, the rate of decline in the number of connected node pairs in the network gradually accelerates, the combat network becomes simpler, and the global efficiency of the traditional network begins to increase. Ultimately, as the number of connected node pairs decreases to zero, the global efficiency of the traditional network also rapidly decreases to zero.

[0105] Analysis 3: Figures 9 to 11 The global efficiency of the combat network under the maximum betweenness attack mode, the global efficiency of the traditional network, the number of effective combat rings in the combat network, and the number of connected node pairs change over time. Figures 9 to 11 As can be seen, the trend in the global efficiency of the combat network under the maximum betweenness attack model is similar to that under the maximum degree failure scenario, with a gradual decline beginning as the number of valid OODA loops begins to decrease. Compared to the maximum degree failure scenario, the global efficiency of the traditional network shows a less pronounced decline in the early stages of node failure under the maximum betweenness attack model, remaining almost stable, and then continuing to rise and then decline.

[0106] Analysis 4: Figures 12 to 23 The global efficiency of the combat network under the attack mode of the specified node type, the global efficiency of the traditional network, the number of effective combat rings in the combat network and the number of connected node pairs change over time. Figures 12 to 23In the proposed design, node failure scenarios are designed based on the node types of the unmanned swarm network, with corresponding node failure modes: target node failure (TA), sensor node failure (SA), decision node failure (DA), and influence node failure (WA). The TA mode indicates that, after obtaining relevant information about our forces, the enemy quickly changes and conceals related activities, rendering the target strategically unavailable. In the designated node attack mode, the failure of target and influence nodes will not impact the overall efficiency of the operational network until the OODA loop disappears in the swarm network. Detection and decision nodes will only slightly impact the overall efficiency of the operational network until the OODA loop disappears. However, with the failure of target and influence nodes, the global efficiency of the traditional network gradually increases. With the loss of detection and decision nodes, the global efficiency of the traditional network first gradually decreases. When the number of detection and decision nodes falls below a certain threshold, the global efficiency of the traditional network increases rapidly. With the failure of target and influence nodes, the number of active OODA loops decreases linearly. As detection and decision-making nodes disappear, the number of effective OODA loops initially remains stable, then gradually decreases at an accelerated rate. Therefore, to maintain the overall efficiency of the unmanned swarm combat network, more resources should be invested in maintaining detection and decision-making nodes.

[0107] In various attack modes, the global efficiency of an unmanned swarm combat network should generally decrease over time. However, case studies show that traditional network global efficiency shows a trend of first increasing and then decreasing, which makes it difficult to reflect the changes in the global efficiency of an unmanned swarm combat network. In contrast, the global efficiency of the combat network better reflects the decline in the global efficiency of an unmanned swarm combat network, further confirming the effectiveness and superiority of the global efficiency of the combat network in characterizing the global efficiency of an unmanned swarm combat network.

[0108] This application proposes a method for calculating the global efficiency of unmanned swarm combat networks based on the boundedness theorem of the shortest path length of an effective combat closed loop in an unmanned swarm combat network. By simulating the global efficiency of the combat network under various attack scenarios and comparing it with the global efficiency of traditional networks, the effectiveness and superiority of the global efficiency of the unmanned swarm combat network are analyzed and verified.

[0109] In summary, based on the OODA loop theory and the unmanned swarm combat process, this application proposes a definition of the efficiency and global efficiency of an unmanned swarm combat network within the framework of complex network theory. Subsequently, this application proves the boundedness theorem for the shortest path length of an effective combat closed loop starting from a target-class node in an unmanned swarm combat network, laying a solid theoretical foundation for calculating the global efficiency of an unmanned swarm combat network. Furthermore, this application further proposes a method for calculating the global efficiency of an unmanned swarm combat network. Finally, through case analysis, a comparison is made between the global efficiency improvement scheme for an unmanned swarm combat network and the efficiency of a traditional network. It is found that under various attack modes, the global efficiency of the traditional network shows a trend of first increasing and then decreasing, while the global efficiency of the combat network can better reflect the decline in the global efficiency of the unmanned swarm combat network. This further confirms the effectiveness and superiority of the global efficiency of the combat network in characterizing the global efficiency of an unmanned swarm combat network. This application provides an innovative analysis method based on the global efficiency of the combat network for unmanned swarm combat networks, revealing the important role of combat network efficiency in unmanned swarm combat networks.

[0110] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 24 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O) and a communication interface. The processor, memory and input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store global efficiency analysis data of unmanned cluster combat networks. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, a method for global efficiency analysis of unmanned cluster combat networks is implemented.

[0111] Those skilled in the art will understand that Figure 24The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application and does not constitute a limitation on the computer device to which the solution of the present application is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the above-mentioned method embodiments when executing the computer program.

[0112] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0113] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0114] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0115] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0116] The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may include, but are not limited to, general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units based on quantum computing, and the like.

[0117] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0118] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above examples is only intended to help understand the method and core concept of this application. At the same time, for those skilled in the art, based on the concept of this application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for analyzing the global efficiency of an unmanned swarm combat network, characterized in that: The global efficiency analysis method of the unmanned swarm combat network includes: In the unmanned swarm combat network architecture, the friendly nodes are classified into perception nodes, decision nodes, and influence nodes according to the functions of each unit and the role each unit plays in the actual combat environment. The target tasks of the unmanned swarm combat network are used as target class nodes; Based on the intra-layer connection relationship and inter-layer connection relationship among the perception nodes, the decision nodes, the influence nodes, and the target nodes in the unmanned swarm combat network architecture, a relationship matrix is ​​formed; Determine an upper bound on the path length based on the number of the perception nodes and the number of the decision nodes; Determining the shortest path length of an effective combat closed loop starting from the target node based on the number of the perception nodes and the number of the decision nodes; an effective combat closed loop refers to completing the target task through observation, adjustment, decision-making, and action by nodes in the unmanned swarm combat network; and the number of nodes involved in the effective combat closed loop is used as the path length of the effective combat closed loop; Determine, based on the relationship matrix, the number of effective combat closed loops passing through the target node corresponding to the shortest path length; Under the constraint of the upper bound of the path length, the global efficiency of the unmanned swarm combat network is determined based on the shortest path length and the number of effective combat closed loops.

2. The method for analyzing the global efficiency of an unmanned swarm combat network according to claim 1, characterized in that: Based on the number of the perception nodes and the number of the decision nodes, the formula M=2+N is used. S +N D Determine the upper bound of the path length; Among them, M represents the upper limit of the path length, N S Indicates the number of perception nodes, N D Indicates the number of decision nodes.

3. The method for analyzing the global efficiency of an unmanned swarm combat network according to claim 1, characterized in that: Determining the number of effective combat closed loops passing through the target node corresponding to the shortest path length based on the relationship matrix includes: Obtaining, based on the relationship matrix, a matrix eigenvalue whose effective combat closed loop length starting from the target class node is the shortest path length; The number of effective combat closed loops is determined based on the matrix eigenvalues.

4. The method for analyzing the global efficiency of an unmanned swarm combat network according to claim 1, characterized in that: The formula for determining the global efficiency of the unmanned swarm combat network is expressed as: In the formula, NE on (t) represents the global efficiency of the unmanned swarm combat network at time t, M represents the upper bound of the path length, l represents the shortest path length, and n l Indicates the number of effective combat closed loops.

5. The method for analyzing the global efficiency of an unmanned swarm combat network according to claim 1, characterized in that: The unmanned swarm combat network global efficiency analysis method further includes: Based on the number of valid combat closed loops, the total number of all valid combat closed loops in the unmanned swarm combat network is determined under the constraint of the upper limit of the path length.

6. The method for analyzing the global efficiency of an unmanned swarm combat network according to claim 5, characterized in that: The unmanned swarm combat network global efficiency analysis method further includes: The reciprocal of the shortest path length of the effective combat closed loop starting from the target node is used as the efficiency of the effective combat closed loop of the corresponding target node; Based on the total number of target nodes, the efficiency of the effective combat closed loop of each target node is weighted and summed to obtain the initial efficiency; The ratio of the initial efficiency to the total number of all effective combat closed loops in the unmanned swarm combat network is taken as the global efficiency of the unmanned swarm combat network.

7. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the global efficiency analysis method for an unmanned swarm combat network according to any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for analyzing the global efficiency of an unmanned swarm combat network according to any one of claims 1 to 6 is implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for analyzing the global efficiency of an unmanned swarm combat network according to any one of claims 1 to 6 is implemented.

Images