Target threat assessment method and device for unmanned underwater vehicle cluster, and electronic equipment

Abstract

The invention belongs to the technical field of situation analysis, and particularly discloses an unmanned underwater vehicle cluster target threat assessment method and device and electronic equipment. The method comprises the following steps: performing clustering analysis on a plurality of unmanned underwater vehicles in a target sea area, and determining a plurality of unmanned underwater vehicle clusters; determining a plurality of attribute indexes of each unmanned underwater vehicle cluster; and performing threat degree evaluation on each unmanned underwater vehicle cluster based on each attribute index of each unmanned underwater vehicle cluster, and determining a threat degree evaluation result of each unmanned underwater vehicle cluster relative to a defense target in the target sea area. According to the method and the device, the problem scale can be reduced, the UUV threat assessment efficiency can be improved, the behavior intention of the UUV group can be more accurately judged, the accuracy of the UUV threat assessment result can be improved, and the dynamic threat situation of the whole UUV can be quickly mastered.

Description

Technical Field

[0001] The present application belongs to the technical field of situation analysis, and more specifically, relates to a method, device and electronic equipment for assessing the threat of unmanned underwater vehicle cluster targets. Background Art

[0002] Unmanned underwater vehicles (UUVs) have the characteristics of good concealment, strong maneuverability, and small size, and are suitable for performing specific missions underwater for a long time. However, the resources and equipment that a single UUV can carry are relatively limited. In order to adapt to complex marine tasks, multiple UUVs are autonomously networked. Through the collaborative work of multiple UUVs, the environmental perception, target detection and confrontation capabilities of the multi-UUV system can be greatly improved. In a complex marine environment, facing multiple scattered UUV targets, in order to protect important targets in the sea area, it is first necessary to quickly and reasonably determine the threat level of each UUV in the relevant sea area.

[0003] At present, the existing UUV threat assessment method is usually to determine the threat situation of each UUV one by one, which makes the efficiency of UUV dynamic threat situation analysis extremely low. At the same time, since the possible correlation between each UUV is ignored, the accuracy of the final target threat assessment result is not high.

[0004] Therefore, how to better conduct threat assessment on UUV targets has become a technical problem that needs to be solved urgently in the industry. Summary of the invention

[0005] In view of the defects of the prior art, the purpose of this application is to better perform threat assessment on UUV targets, aiming to solve the problems of low efficiency of existing UUV threat level assessment and low accuracy of assessment results.

[0006] To achieve the above objectives, in a first aspect, the present application provides a method for assessing the threat of an unmanned underwater vehicle cluster target, comprising:

[0007] Conduct cluster analysis on multiple unmanned underwater vehicles in the target sea area to identify multiple unmanned underwater vehicle clusters;

[0008] Determining a plurality of attribute indicators of each of the unmanned underwater vehicle clusters;

[0009] A threat level assessment is performed on each unmanned underwater vehicle cluster based on various attribute indicators of each unmanned underwater vehicle cluster, and a threat level assessment result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area is determined.

[0010] Optionally, the performing threat assessment on each unmanned underwater vehicle cluster based on each attribute index of each unmanned underwater vehicle cluster to determine the threat assessment result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area includes:

[0011] Performing forward processing on each attribute index of each unmanned underwater vehicle cluster to determine a processed first cluster attribute matrix;

[0012] Calculating the weight of each attribute indicator in the first cluster attribute matrix to determine a second cluster attribute matrix after weighting each attribute indicator;

[0013] The positive and negative ideal solution proximity method is used to determine the threat assessment result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area.

[0014] Optionally, the step of performing weight calculation on each attribute indicator in the first cluster attribute matrix to determine a second cluster attribute matrix after weighted processing of each attribute indicator includes:

[0015] Performing statistical analysis on the differences and correlations of the attribute indicators of each unmanned underwater vehicle cluster to determine the amount of information corresponding to each attribute indicator;

[0016] Based on the amount of information corresponding to each of the attribute indicators, determine the objective weight information corresponding to each of the attribute indicators;

[0017] Determine the weight value corresponding to each of the attribute indicators based on the objective weight information and preset experience weight information corresponding to each of the attribute indicators;

[0018] Each attribute indicator in the first cluster attribute matrix is ​​weighted by using the weight value corresponding to each attribute indicator to obtain the second cluster attribute matrix.

[0019] Optionally, the using of the positive and negative ideal solution proximity method to determine the threat assessment result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area includes:

[0020] Based on each attribute indicator in the second cluster attribute matrix, determine the positive ideal solution and the negative ideal solution corresponding to each attribute indicator in each of the unmanned underwater vehicle clusters;

[0021] Using each attribute index in the second cluster attribute matrix, respectively calculating a first distance between each of the unmanned underwater vehicle clusters and a corresponding positive ideal solution, and a second distance between each of the unmanned underwater vehicle clusters and a corresponding negative ideal solution;

[0022] Based on the first distance and the second distance corresponding to each of the unmanned underwater vehicle clusters, a threat assessment result of each of the unmanned underwater vehicle clusters relative to the defense target in the target sea area is determined.

[0023] Optionally, the performing forward processing based on each attribute index of each unmanned underwater vehicle cluster to determine a processed first cluster attribute matrix includes:

[0024] Divide each attribute index of each unmanned underwater vehicle cluster into a first type of index and a second type of index; the first type of index is used to characterize an index whose attribute index value is negatively correlated with its threat level, and the second type of index is used to characterize an index whose attribute index value is positively correlated with its threat level;

[0025] Based on the attribute indicators of each of the unmanned underwater vehicle clusters, determining an original cluster attribute matrix;

[0026] The first cluster attribute matrix is ​​obtained by performing corresponding forward processing based on each first type indicator and each second type indicator in the original cluster attribute matrix.

[0027] Optionally, performing cluster analysis on multiple unmanned underwater vehicles in the target sea area to determine multiple unmanned underwater vehicle clusters includes:

[0028] Using the density-based clustering algorithm, multiple unmanned underwater vehicles in the target sea area are clustered and analyzed to determine multiple unmanned underwater vehicle clusters.

[0029] Optionally, the method of using a density-based clustering algorithm to perform cluster analysis on multiple unmanned underwater vehicles in the target sea area to determine multiple unmanned underwater vehicle clusters includes:

[0030] Determine a circular area corresponding to the position of each unmanned underwater vehicle; the circular area is determined based on the position of the unmanned underwater vehicle as the center and a preset neighborhood parameter as the radius;

[0031] It is determined whether the number of unmanned underwater vehicles in each of the circular areas is greater than a preset density threshold, and a plurality of unmanned underwater vehicle clusters are obtained through a clustering algorithm.

[0032] In a second aspect, the present application provides an unmanned underwater vehicle cluster target threat assessment device, comprising:

[0033] A clustering module is used to perform cluster analysis on multiple unmanned underwater vehicles in the target sea area and determine multiple unmanned underwater vehicle clusters;

[0034] A processing module, used to determine a plurality of attribute indicators of each of the unmanned underwater vehicle clusters;

[0035] An evaluation module is used to perform threat level evaluation on each unmanned underwater vehicle cluster based on various attribute indicators of each unmanned underwater vehicle cluster, and determine the threat level evaluation result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area.

[0036] In a third aspect, the present application provides an electronic device comprising: at least one memory for storing programs; and at least one processor for executing the programs stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method described in the first aspect or any possible implementation of the first aspect.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0038] In a fifth aspect, the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method described in the first aspect or any possible implementation of the first aspect.

[0039] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0040] In general, the above technical solutions conceived by this application have the following beneficial effects compared with the prior art:

[0041] The present application provides a method, device and electronic equipment for assessing the threat of an unmanned underwater vehicle cluster target. By considering the task relevance between each UUV, multiple detected UUV single targets are divided into corresponding target clusters, and a multi-dimensional threat assessment and analysis is performed on the UUV cluster in combination with multiple attribute indicators of the UUV, which can reduce the scale of the problem, improve the efficiency of UUV threat assessment, more accurately judge the behavioral intentions of the UUV group, and improve the accuracy of the UUV threat assessment results, thereby quickly grasping the dynamic threat situation of the overall UUV. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flowchart of a method for assessing target threat of an unmanned underwater vehicle cluster provided in an embodiment of the present application;

[0043] Figure 2 It is a structural schematic diagram of an unmanned underwater vehicle cluster target threat assessment device provided in an embodiment of the present application;

[0044] Figure 3 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] The terms "first" and "second" in the specification and claims of this application are used to distinguish different objects rather than to describe a specific order of objects. For example, a first cluster attribute matrix and a second cluster attribute matrix are used to distinguish different cluster attribute matrices rather than to describe a specific order of cluster attribute matrices.

[0047] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0048] In the description of the embodiments of the present application, unless otherwise specified, “plurality” means two or more than two. For example, a plurality of UUV clusters refers to two or more than two UUV clusters, etc.

[0049] The embodiments of the present application are described below in conjunction with the drawings in the embodiments of the present application.

[0050] Figure 1 FIG. 1 is a flow chart of a method for assessing target threat of an unmanned underwater vehicle cluster provided in an embodiment of the present application. Figure 1 As shown, including:

[0051] Step S1, performing cluster analysis on multiple UUVs in the target sea area to determine multiple UUV clusters;

[0052] Step S2, determining multiple attribute indicators of each UUV cluster;

[0053] Step S3, performing threat assessment on each UUV cluster based on various attribute indicators of each UUV cluster, and determining the threat assessment result of each UUV cluster relative to the defense target in the target sea area.

[0054] Specifically, the target sea area described in the embodiment of the present application refers to the sea area for conducting UUV threat assessment, which can be specifically set according to actual measurement requirements.

[0055] The UUV cluster described in the embodiment of the present application is used to characterize a task cluster composed of multiple UUVs in a task collaboration relationship. Specifically, it can be obtained by using a cluster analysis algorithm to perform target clustering on each UUV based on the spatial topological correlation of the UUVs in the collaborative relationship and the spatial location information of the UUVs in the target sea area. Among them, each UUV target can only belong to a certain cluster.

[0056] The attribute indicators described in the embodiments of the present application refer to the attribute indicators of each UUV in each UUV cluster, which may include the static capability attribute indicators and dynamic motion attribute indicators of the UUV.

[0057] In an embodiment of the present application, in step S1, by considering the task correlation between each UUV, the topological correlation of each UUV in space can be combined, and a clustering algorithm, such as a density-based spatial clustering algorithm, can be used to perform cluster analysis on multiple UUVs in the target sea area, thereby obtaining multiple UUV clusters.

[0058] In an embodiment of the present application, in step S2, multiple attribute indicators of each UUV cluster are determined. Specifically, threat indicators are selected from the target attribute characteristics of the UUV cluster, including static capability attribute indicators of the UUV cluster and dynamic motion attribute indicators of the UUV cluster, and then these threat indicators are quantitatively modeled.

[0059] On the one hand, the static capability threat of UUV cluster targets is mainly determined by the capabilities of each UUV platform in the cluster, and the cluster capability is characterized by the superposition of single platform capabilities. For the threat capability of a single UUV platform, indicators such as mobility and attack capabilities can usually be considered.

[0060] Among them, the static capability threat index of UUV cluster targets is expressed as S G It can be expressed as:

[0061] S G =1-(1-S I ) n ;

[0062] Among them, S I It represents the static capability threat index of a single UUV platform, which is related to its maneuverability and attack capability, and n is the number of UUV platforms in the cluster.

[0063] In the formula, S I =a1A mobility +a2A strike ;

[0064] Among them, A modility , A strikeThey represent the maneuverability and attack capability of a single UUV platform respectively, a1 and a2 are their respective weights, and a1+a2=1.

[0065] On the other hand, the dynamic motion threat of UUV cluster targets is mainly reflected in the relative threat posed by the navigation state of UUV targets to the defense targets. Since the UUV cluster needs to maintain a certain formation or speed range during the execution of the mission, the cluster's motion attribute index can be reflected by the motion characteristic values ​​of each UUV platform in the cluster, for example, the speed threat index, distance threat index, etc. can be selected.

[0066] Among them, the speed threat index V sa The following calculation method can be used.

[0067]

[0068] Where v is the velocity of the UUV target, and its unit is meter per second.

[0069] Distance Threat Index D ss The following calculation method can be used.

[0070] The UUV cluster target that is far away poses no threat to the defense target. We can first calculate the distance dis between the center point of the UUV cluster and the defense target, and then calculate the distance threat index, that is:

[0071]

[0072] In the formula, d1 represents the maximum threat distance threshold, d2 represents the safety distance threshold, and k d Represents the distance coefficient.

[0073] Furthermore, in an embodiment of the present application, in step S3, a weight distribution calculation can be performed based on the importance of each attribute indicator of each UUV cluster, and weighted processing can be performed based on each attribute indicator of each UUV cluster, and the threat assessment result of each UUV cluster relative to the defense target in the target sea area can be determined using the positive and negative ideal solution proximity method.

[0074] The unmanned underwater vehicle cluster target threat assessment method of the embodiment of the present application divides the detected multiple UUV single targets into corresponding target clusters by considering the task correlation between each UUV, and performs a multi-dimensional threat assessment and analysis on the UUV cluster in combination with multiple attribute indicators of the UUV. It can reduce the scale of the problem, improve the efficiency of UUV threat assessment, more accurately judge the behavioral intention of the UUV, and improve the accuracy of the UUV threat assessment results, so as to quickly grasp the dynamic threat situation of the overall UUV.

[0075] Based on the content of the above embodiment, as an optional embodiment, step S1, performing cluster analysis on multiple UUVs in the target sea area to determine multiple UUV clusters, includes:

[0076] Using the density-based clustering algorithm, multiple UUVs in the target sea area are clustered and analyzed to determine multiple UUV clusters.

[0077] Specifically, in an embodiment of the present application, for dispersed UUV targets detected in the mission sea area, a density-based clustering analysis algorithm is used to group the UUVs, and multiple UUV mission clusters can be divided, and each UUV target can only belong to one cluster.

[0078] The method of the embodiment of the present application, by considering the topological correlation of UUVs in collaborative task relationships in space, utilizes a density clustering algorithm that does not rely on distance metrics, but instead achieves clustering by finding high-density areas in the data space, so that it can discover clusters of any shape, not just circular or elliptical clusters. It is suitable for UUV clusters with complex distribution forms and helps to improve the accuracy of clustering analysis results.

[0079] Based on the content of the above embodiment, as an optional embodiment, a density-based clustering algorithm is used to perform cluster analysis on multiple UUVs in the target sea area to determine multiple UUV clusters, including:

[0080] Determine a circular area corresponding to the position of each UUV; the circular area is determined based on the position of the UUV as the center and the preset neighborhood parameter as the radius;

[0081] It is determined whether the number of unmanned underwater vehicles in each of the circular areas is greater than a preset density threshold, and a plurality of unmanned underwater vehicle clusters are obtained through a clustering algorithm.

[0082] Specifically, in the embodiment of the present application, the algorithm sets a preset neighborhood parameter eps and a preset density threshold minObjs, wherein eps represents the radius of a circular area centered on the UUV position, and minObjs represents the minimum number of UUV platforms in a circular area centered on the UUV position and eps as a radius. If the number of UUVs in the eps neighborhood that satisfies the target p is greater than the preset density threshold minObjs, the target p is defined as a core point.

[0083] More specifically, it is known that the UUV set U = (U1, U2, ..., U s ), the specific process of UUV target grouping is as follows:

[0084] Step S101, initialize the core target set Ω to an empty set, initialize the cluster group value k=0, set the unvisited target set τ=set U, and the current cluster partition C to an empty set.

[0085] Step S102, for e=1, 2, ..., s, find all core targets according to the following steps:

[0086] (1) Using spatial Euclidean distance as a metric, find the central target p e The subset N within the neighborhood with radius eps ε (p e );

[0087] (2) If the subset N ε (p e ) satisfies k>minObjs, then the target is identified as a core target and the target p e Add to the set Ω=Ω∪{p e}.

[0088] Step S103, determine whether there is a target in the core target set Ω. If The algorithm ends; otherwise, it goes to step S104.

[0089] Step S104: randomly select a core target p' from the target set Ω and initialize the core target queue Ω of the current group cur = {p′}, set the initial target set C n ={p′}, initialize the category number n=n+1, and update the target set τ=τ-{p′} that has not been visited.

[0090] Step S105: If the current core target queue Then the current cluster group set C n All the clusters have been generated, and the new cluster set C = {C1, C2, ..., C n} and the new core target set Ω = Ω - C n , go to step S103.

[0091] Step S106, select the current group core target set Ω cur Take a target q in the , take it as the center, and find all the sub-target sets N within the neighborhood with the neighborhood threshold eps as the radius ε (q), let △ = n ε (q)∩τ, update the current group target set C n =C n ∪△, and update the unvisited target set τ=τ-△, and go to step S105.

[0092] Finally, the clustering output is multiple UUV clusters, which can be represented as C1, C2, …, C n .

[0093] The method of the embodiment of the present application iteratively determines the number of UUV targets contained in the UUV neighborhood, finds the core objects of the UUV cluster, and takes each core object as the starting point to continuously expand the cluster clusters through density connection relationships. It can effectively realize clustering analysis of UUV targets distributed in different locations and improve the accuracy of UUV clustering analysis results.

[0094] Based on the content of the above embodiment, as an optional embodiment, step S3, based on each attribute index of each UUV cluster, performs threat assessment on each UUV cluster, and determines the threat assessment result of each UUV cluster relative to the defense target in the target sea area, including:

[0095] Perform positive processing on each attribute index of each UUV cluster to determine the attribute matrix of the first cluster after processing;

[0096] Calculate the weight of each attribute indicator in the first cluster attribute matrix to determine a second cluster attribute matrix after weighting each attribute indicator;

[0097] The positive and negative ideal solution proximity method is used to determine the threat assessment results of each UUV cluster relative to the defense targets in the target sea area.

[0098] Specifically, the first cluster attribute matrix described in the embodiment of the present application refers to a data matrix obtained by constructing each attribute index of each UUV cluster into a matrix form and then performing a forward processing on each attribute index.

[0099] The second cluster attribute matrix described in the embodiment of the present application refers to a data matrix obtained by weighting each attribute indicator in the first cluster attribute matrix.

[0100] In an embodiment of the present application, after acquiring each attribute index data of each UUV target in each UUV cluster, each attribute index of each UUV cluster may be used to perform forward processing to obtain a first cluster attribute matrix after forward processing.

[0101] Based on the content of the above embodiment, as an optional embodiment, forward processing is performed based on each attribute index of each UUV cluster to determine the processed first cluster attribute matrix, including:

[0102] The attribute indicators of each UUV cluster are divided into first-type indicators and second-type indicators; the first-type indicators are used to characterize indicators whose attribute indicator values ​​are negatively correlated with their threat levels, and the second-type indicators are used to characterize indicators whose attribute indicator values ​​are positively correlated with their threat levels;

[0103] Based on the various attribute indicators of each UUV cluster, the original cluster attribute matrix is ​​determined;

[0104] Based on each first type indicator and each second type indicator in the original cluster attribute matrix, corresponding forward processing is performed to obtain a first cluster attribute matrix.

[0105] Specifically, the first type of indicators described in the embodiments of the present application are used to characterize indicators that are negatively correlated between the value of the attribute indicator and its threat level, that is, the smaller the value of this type of indicator, the greater the threat level of the UUV. For example, the distance threat index is a first type of indicator.

[0106] The second type of indicators described in the embodiments of the present application are used to characterize indicators that are positively correlated with the value of the attribute indicator and its threat level. That is, the smaller the value of this type of indicator, the smaller the threat level of the UUV. For example, static capability attribute indicators and speed threat index can both be classified as second type indicators.

[0107] Furthermore, in this embodiment, the UUV cluster target attribute matrix X, i.e., the original cluster attribute matrix, is constructed according to the multiple attribute indicators selected in step S2, and then the type of each attribute indicator is determined and the corresponding forward processing is performed to obtain the first cluster attribute matrix X′. The specific process is as follows:

[0108] Specifically, assuming that n UUV clusters are obtained through clustering algorithm, and m attribute indicators are selected by combining the dynamic motion attribute indicators and static capability attribute indicators of UUV, the UUV original cluster attribute matrix X can be constructed as follows:

[0109]

[0110] In the formula, x ij Represents the value of the jth attribute index of the i-th UUV cluster, 1≤i≤n, 1≤j≤m.

[0111] Furthermore, in this embodiment, corresponding positive processing is performed according to each first type indicator and each second type indicator in the original cluster attribute matrix X. Specifically, the following formula can be used to perform positive processing on each attribute indicator in the matrix X to obtain a positive standard matrix, that is, the first cluster attribute matrix X′.

[0112] Among them, for the first type of indicators, the positive processing method is:

[0113]

[0114] For the second type of indicators, the positive processing method is:

[0115]

[0116] In the formula, max(x ij ) and min(x ij ) represent the maximum and minimum values ​​of the jth attribute index of the n UUV clusters, respectively, and x′ ij is the jth attribute index value of the i-th UUV cluster after positive processing.

[0117] Finally, the first cluster attribute matrix X′ can be obtained, which is expressed as follows:

[0118]

[0119] The method of the embodiment of the present application, by representing each attribute indicator of each UUV cluster in the form of a matrix, and classifying and correspondingly forward processing each attribute indicator, can convert data of different dimensions and value ranges into a unified standard form, making the data more standardized and consistent, improving data quality and availability, and helping to improve the efficiency and accuracy of subsequent UUV threat assessment.

[0120] Furthermore, in an embodiment of the present application, after obtaining the first cluster attribute matrix X′, each attribute indicator in the first cluster attribute matrix X′ can be weighted, and a corresponding weight can be assigned to each attribute indicator, thereby determining a second cluster attribute matrix after weighted processing of each attribute indicator.

[0121] Based on the content of the above embodiment, as an optional embodiment, weight calculation is performed on each attribute indicator in the first cluster attribute matrix to determine a second cluster attribute matrix after weighted processing of each attribute indicator, including:

[0122] Perform statistical analysis on the differences and correlations of each attribute index of each UUV cluster to determine the amount of information corresponding to each attribute index;

[0123] Based on the amount of information corresponding to each attribute indicator, determine the objective weight information corresponding to each attribute indicator;

[0124] Determine the attribute weight value corresponding to each attribute indicator based on the objective weight information corresponding to each attribute indicator and the preset experience weight information;

[0125] Each attribute indicator in the first cluster attribute matrix is ​​weighted by using the attribute weight value corresponding to each attribute indicator to obtain a second cluster attribute matrix.

[0126] It should be noted that in different situations such as collaborative reconnaissance and collaborative attack, the influence of various attribute indicators on the threat assessment of UUV cluster targets is different. Conventional assessment cannot reflect the threat changes caused by the dynamic changes in the UUV cluster situation. The weights should be dynamically adjusted with the changes in the state values ​​of the attribute indicators. Therefore, it is necessary to introduce variable weight theory to solve this problem.

[0127] Specifically, in the embodiments of the present application, the methods for determining attribute weights mainly include subjective weighting method and objective weighting method. The subjective weighting method mainly assigns weights based on expert scores and is greatly affected by the subjective experience of experts; the weights of the objective method are mainly determined by data and can fully reflect the resolution information contained in objective data, but are greatly affected by data fluctuations. In order to solve the problem of being subjective or objective when determining weights, the subjective and objective weights are combined to obtain a combined weight.

[0128] In the embodiment of the present application, the weight vector of the target attribute of the UUV cluster is determined based on the subjective and objective combined weighting method, the subjective weight vector of the target attribute is determined according to expert experience and preference, and the objective weight vector of the target attribute is determined by a method based on the internal difference of the evaluation index and the conflict between the indexes. Then, the combined weight vector of the target attribute is obtained by weighted summation. The specific process is as follows:

[0129] First, we can assign weight values ​​to each attribute index based on expert experience and preference, thereby obtaining the preset experience weight information corresponding to each attribute index, and then obtain the subjective weight vector Y = (y1, y2, ..., y m ),satisfy Among them, y j Represents the weight value of the preset experience weight information corresponding to the jth attribute indicator in the UUV cluster.

[0130] Furthermore, statistical analysis of differences and correlations was performed on each attribute index of each UUV cluster to determine the amount of information corresponding to each attribute index.

[0131] Specifically, first, the internal differences of each attribute indicator of each UUV in each UUV cluster are calculated; second, the correlation of each attribute indicator with respect to other attribute indicators is calculated; finally, these two types of information are combined to obtain the amount of information contained in a single attribute indicator, and weights are assigned to each attribute indicator based on the amount of information.

[0132] Among them, the coefficient of variation σ can be used j To measure the internal differences of each attribute index, the calculation formula is:

[0133]

[0134] In the formula, is the average value of the jth attribute index of n UUV cluster targets, x ij is the value of the jth attribute indicator of the i-th UUV cluster target.

[0135] At the same time, the conflict coefficient τ can be used j To measure the correlation between each attribute index and other attribute indexes, the conflict between attribute indexes is based on the correlation coefficient between each attribute index. j The calculation formula is:

[0136]

[0137] Among them, ρ lj is the correlation coefficient between attribute l and attribute j, and its calculation formula is:

[0138] Next, calculate the information amount Q of the jth attribute index j , the calculation formula is as follows:

[0139]

[0140] It should be noted that Q j The larger the value, the greater the amount of information contained in the jth attribute index, and the greater the weight assigned to the attribute index.

[0141] Furthermore, based on the amount of information corresponding to each attribute indicator, the objective weight information corresponding to each attribute indicator can be determined, and then the objective weight vector V = (v1, v2, ..., v m ), the calculation formula of this process can be expressed as:

[0142]

[0143] Furthermore, based on the objective weight information and preset experience weight information corresponding to each attribute indicator, the weight value w corresponding to each attribute indicator can be determined by weighted summation. j , and then we can get the combined weight vector W of each attribute index = (w1,w2,…,w j …,w m ), where the weight value w j It can be expressed as follows:

[0144] w j =βy j +(1-β)v j ;

[0145] In the formula, β is the weighting coefficient.

[0146] Finally, the weight value w corresponding to each attribute indicator is used j For each attribute index x′ in the first cluster attribute matrix X′ ij By weighted processing, each attribute index x in the second cluster attribute matrix X″ can be obtained ij ″, its calculation method can be expressed as:

[0147] x ij ″=x ij ′*w j ;

[0148] Thus, according to each attribute index x in the second cluster attribute matrix ij ″, we can get the second cluster attribute matrix.

[0149] The method of the embodiment of the present application, by comprehensively combining the subjective and objective weights for each attribute indicator to obtain a combined weight, uses the subjective and objective combined weighting method to determine the weights of the UUV cluster attributes, which can effectively solve the problem of being too subjective or too objective when determining the attribute indicator weights, can reflect the dynamic changes in the UUV threat situation, and help to obtain a more scientific threat assessment result.

[0150] Furthermore, in an embodiment of the present application, after obtaining the second cluster attribute matrix, the positive and negative ideal solution proximity method can be used to determine the threat assessment result of each UUV cluster relative to the defense target in the target sea area.

[0151] The method of the embodiment of the present application can effectively improve the scientificity and objectivity of the threat assessment of UUV cluster targets by performing positive processing on each attribute indicator of each UUV cluster, calculating the weight of each attribute indicator by combining the subjective and objective combined weighting method, assigning weights to each attribute indicator, and finally ranking the threats based on the multi-attribute decision-making method.

[0152] Based on the content of the above embodiment, as an optional embodiment, the threat assessment result of each UUV cluster relative to the defense target in the target sea area is determined by using the positive and negative ideal solution proximity method, including:

[0153] Based on each attribute index x in the second cluster attribute matrix ij ″″ , determine the positive ideal solution and negative ideal solution corresponding to each attribute indicator in each UUV cluster;

[0154] Using the second cluster attribute matrix X ″″ Each attribute index x in ij ″″ , respectively calculating the first distance between each UUV cluster and the corresponding positive ideal solution, and the second distance between each UUV cluster and the corresponding negative ideal solution;

[0155] Based on the first distance and the second distance corresponding to each UUV cluster, a threat assessment result of each UUV cluster relative to the defense target in the target sea area is determined.

[0156] Specifically, in the embodiment of the present application, based on each attribute index x in the second cluster attribute matrix ij ″″ , According to the following formula, the positive ideal solution and negative ideal solution corresponding to each attribute index in each UUV cluster can be determined.

[0157] Determine the positive ideal solution S + and negative ideal solution S - The calculation method is as follows:

[0158]

[0159] In the formula, represents the maximum value of the jth attribute index in each UUV cluster; It represents the minimum value of the jth attribute index in each UUV cluster.

[0160] Furthermore, using each attribute index x in the second cluster attribute matrix ij ″, calculate the first distance d between each UUV cluster and the corresponding positive ideal solution i + , and the second distance d between each UUV cluster and the corresponding negative ideal solution i - , the process can be expressed as follows:

[0161]

[0162] Furthermore, according to the first distance d corresponding to each UUV cluster i + and the second distance d i - , calculate the relative closeness δ of each UUV cluster according to the following calculation formula i , and then the threat assessment result of each UUV cluster relative to the defense target in the target sea area can be determined. Among them, the relative closeness δ i It can be expressed as follows:

[0163]

[0164] Based on the above calculation process, when δ i The closer it is to 1, the closer it is to 1, indicating that the i-th UUV cluster is to the positive ideal solution S +The closer it is, the higher its threat ranking result is, and vice versa, it means that the threat ranking result of the UUV cluster is lower. Therefore, according to the above calculation method, a ranking table of the threat capability assessment of each UUV cluster relative to the defense target in the target sea area can be obtained.

[0165] The method of the embodiment of the present application analyzes and evaluates the target threat degree based on UUV cluster targets, and obtains the ranking result of UUV cluster target threats by implementing steps such as constructing a cluster target attribute indicator matrix, normalizing attribute values, determining attribute weights, and ranking cluster target threat capabilities. The threat capability of UUVs in a situation can be evaluated more scientifically and objectively, and the evaluation result has high accuracy and efficiency.

[0166] The UUV cluster target threat assessment device provided in the present application is described below. The UUV cluster target threat assessment device described below and the UUV cluster target threat assessment method described above can be referenced to each other.

[0167] Figure 2 is a schematic diagram of the structure of the UUV cluster target threat assessment device provided in an embodiment of the present application, such as Figure 2 As shown, including:

[0168] The clustering module 10 is used to perform cluster analysis on multiple UUVs in the target sea area to determine multiple UUV clusters;

[0169] A processing module 20, for determining a plurality of attribute indicators of each UUV cluster;

[0170] The evaluation module 30 is used to evaluate the threat level of each UUV cluster based on each attribute index of each UUV cluster, and determine the threat level evaluation result of each UUV cluster relative to the defense target in the target sea area.

[0171] It can be understood that the detailed functional implementation of each of the above-mentioned units / modules can be found in the introduction of the aforementioned method embodiment, and will not be repeated here.

[0172] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0173] The unmanned underwater vehicle cluster target threat assessment device of the embodiment of the present application divides the detected multiple UUV single targets into corresponding target clusters by considering the task correlation between each UUV, and performs multi-dimensional threat assessment and analysis on the UUV cluster in combination with multiple attribute indicators of the UUV. It can reduce the scale of the problem and improve the efficiency of UUV threat assessment, while more accurately judging the behavioral intentions of the UUV group and improving the accuracy of the UUV threat assessment results, thereby quickly grasping the dynamic threat situation of the overall UUV.

[0174] Based on the method in the above embodiment, the embodiment of the present application provides an electronic device, such as Figure 3 As shown, the electronic device may include: a processor (Processor) 310, a communication interface (CommunicationsInterface) 320, a memory (Memory) 330 and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the method in the above embodiment.

[0175] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application.

[0176] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the method in the above embodiment.

[0177] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the method in the above embodiment.

[0178] It is understandable that the processor in the embodiment of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0179] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0180] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0181] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

[0182] It should be understood that expressions such as "including" and "may include" that may be used in the present application indicate the existence of the disclosed functions, operations, or constituent elements, and do not limit one or more additional functions, operations, and constituent elements. In the present application, terms such as "including" and / or "having" may be interpreted as indicating specific characteristics, numbers, operations, constituent elements, components, or combinations thereof, but may not be interpreted as excluding the existence or possibility of adding one or more other characteristics, numbers, operations, constituent elements, components, or combinations thereof.

[0183] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for assessing the threat of an unmanned underwater vehicle cluster, characterized in that: include: Conduct cluster analysis on multiple unmanned underwater vehicles in the target sea area to identify multiple unmanned underwater vehicle clusters; Determining a plurality of attribute indicators of each of the unmanned underwater vehicle clusters; A threat level assessment is performed on each unmanned underwater vehicle cluster based on various attribute indicators of each unmanned underwater vehicle cluster, and a threat level assessment result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area is determined.

2. The unmanned underwater vehicle swarm target threat assessment method according to claim 1, characterized in that: The step of performing threat assessment on each unmanned underwater vehicle cluster based on each attribute index of each unmanned underwater vehicle cluster and determining a threat assessment result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area includes: Performing forward processing on each attribute index of each unmanned underwater vehicle cluster to determine a processed first cluster attribute matrix; Calculating the weight of each attribute indicator in the first cluster attribute matrix to determine a second cluster attribute matrix after weighting each attribute indicator; The positive and negative ideal solution proximity method is used to determine the threat assessment result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area.

3. The unmanned underwater vehicle cluster target threat assessment method according to claim 2, characterized in that: The step of performing weight calculation on each attribute indicator in the first cluster attribute matrix to determine a second cluster attribute matrix after weighting each attribute indicator includes: Performing statistical analysis on the differences and correlations of the attribute indicators of each unmanned underwater vehicle cluster to determine the amount of information corresponding to each attribute indicator; Based on the amount of information corresponding to each of the attribute indicators, determine the objective weight information corresponding to each of the attribute indicators; Determine the weight value corresponding to each of the attribute indicators based on the objective weight information and preset experience weight information corresponding to each of the attribute indicators; Each attribute indicator in the first cluster attribute matrix is ​​weighted by using the weight value corresponding to each attribute indicator to obtain the second cluster attribute matrix.

4. The unmanned underwater vehicle cluster target threat assessment method according to claim 2, characterized in that: The method of using the positive and negative ideal solution proximity method to determine the threat assessment result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area includes: Based on each attribute index in the second cluster attribute matrix, determine the positive ideal solution and the negative ideal solution corresponding to each attribute index in each of the unmanned underwater vehicle clusters; Using each attribute index in the second cluster attribute matrix, respectively calculating a first distance between each of the unmanned underwater vehicle clusters and a corresponding positive ideal solution, and a second distance between each of the unmanned underwater vehicle clusters and a corresponding negative ideal solution; Based on the first distance and the second distance corresponding to each of the unmanned underwater vehicle clusters, a threat assessment result of each of the unmanned underwater vehicle clusters relative to the defense target in the target sea area is determined.

5. The method for assessing target threat of an unmanned underwater vehicle swarm according to claim 2, characterized in that: The method of performing forward processing based on each attribute index of each unmanned underwater vehicle cluster to determine a processed first cluster attribute matrix includes: Divide each attribute index of each unmanned underwater vehicle cluster into a first type of index and a second type of index; the first type of index is used to characterize an index whose attribute index value is negatively correlated with its threat level, and the second type of index is used to characterize an index whose attribute index value is positively correlated with its threat level; Based on the attribute indicators of each of the unmanned underwater vehicle clusters, determining an original cluster attribute matrix; The first cluster attribute matrix is ​​obtained by performing corresponding forward processing based on each first type indicator and each second type indicator in the original cluster attribute matrix.

6. The method for assessing target threat of an unmanned underwater vehicle swarm according to any one of claims 1 to 5, characterized in that: The cluster analysis of multiple unmanned underwater vehicles in the target sea area to determine multiple unmanned underwater vehicle clusters includes: Using the density-based clustering algorithm, multiple unmanned underwater vehicles in the target sea area are clustered and analyzed to determine multiple unmanned underwater vehicle clusters.

7. The method for assessing target threat of an unmanned underwater vehicle swarm according to claim 6, characterized in that: The method of using a density-based clustering algorithm to perform cluster analysis on multiple unmanned underwater vehicles in the target sea area to determine multiple unmanned underwater vehicle clusters includes: Determine a circular area corresponding to the position of each unmanned underwater vehicle; the circular area is determined based on the position of the unmanned underwater vehicle as the center and a preset neighborhood parameter as the radius; It is determined whether the number of unmanned underwater vehicles in each of the circular areas is greater than a preset density threshold, and a plurality of unmanned underwater vehicle clusters are obtained through a clustering algorithm.

8. An unmanned underwater vehicle cluster target threat assessment device, characterized in that: include: A clustering module is used to perform cluster analysis on multiple unmanned underwater vehicles in the target sea area and determine multiple unmanned underwater vehicle clusters; A processing module, used to determine a plurality of attribute indicators of each of the unmanned underwater vehicle clusters; An evaluation module is used to perform threat level evaluation on each unmanned underwater vehicle cluster based on various attribute indicators of each unmanned underwater vehicle cluster, and determine the threat level evaluation result of each unmanned underwater vehicle cluster relative to the defense target in the target sea area.

9. An electronic device, characterized in that: include: at least one memory for storing a computer program; At least one processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program runs on a processor, the processor is caused to execute the method according to any one of claims 1 to 7.

Images