A case-based reasoning method for recommending strategies for unmanned cluster operations

Abstract

The application relates to a case-based reasoning unmanned cluster action strategy recommendation method. The method applies case-based reasoning technology to the recommendation process of the action strategy of the unmanned cluster, provides a new action strategy recommendation method, and can quickly and reasonably find the most similar source case as the recommendation guidance of the action strategy of the target case through similarity comparison with historical cases, can recommend the action strategy of the target case of the unmanned cluster in an online state and an offline state, and can continuously improve the accuracy of the action strategy recommendation of the target case with the increase of historical source cases. In the process of finding the target source case, the method also provides a problem attribute similarity calculation method and a global case similarity calculation method, which are used for matching the target source case with the highest similarity from multiple source cases, can improve the accuracy of the found target source case, and improve the effectiveness of the action strategy recommendation of the target case.

Description

Technical Field

[0001] This application relates to the technical field of unmanned swarm operations, and more particularly to a method for recommending unmanned swarm operation strategies based on case-based reasoning. Background Technology

[0002] Unmanned swarms are a disruptive technology that changes the rules of confrontation. Through the close collaboration of individual unmanned equipment (such as drones), the overall capabilities of the swarm are greatly enhanced, giving it outstanding advantages that are difficult for individual unmanned equipment to match.

[0003] After receiving a task, unmanned swarms typically need to first determine their action strategy and then formulate an action plan based on that strategy. Currently, research on action strategies for unmanned swarms to perform tasks has become a hot topic, including research directions such as interval decision-making with adversarial game models, multi-agent reinforcement learning decision-making, and interference avoidance-first adversarial strategies. However, due to the autonomous, adversarial, and uncertain nature of unmanned swarm actions, the above research methods still have some shortcomings in the effectiveness of generating action strategies for unmanned swarms. Summary of the Invention

[0004] The first aspect of this application proposes a method for recommending unmanned swarm action strategies based on case-based reasoning, the method comprising:

[0005] Obtain the target case and multiple corresponding source cases of the unmanned cluster, and obtain multiple problem attributes of the case of the unmanned cluster, wherein the problem attributes are used to characterize the feature attributes of the problem of the case;

[0006] Calculate the similarity between the target case and the plurality of source cases among the target question attributes, wherein the target question attribute is any one of the plurality of question attributes;

[0007] Calculate the normalized values ​​of the multiple source cases on the target problem attribute, calculate the information entropy of the target problem attribute based on the normalized values, and calculate the weight value of the target problem attribute based on the information entropy;

[0008] Based on the similarity and the weight values, calculate the global similarity between the target case and the multiple source cases;

[0009] A target source case is selected from the plurality of source cases based on the global similarity, so as to guide the action strategy of the target case through the target source case.

[0010] In some implementations, calculating the normalized values ​​of the plurality of source cases on the target problem attribute includes:

[0011]

[0012] in, For source case S i The normalized value on the target problem attribute k. For source case S i The value of the target problem attribute k, min i,k max is the minimum value of the multiple source cases on the target problem attribute k. i,k Let k be the maximum value of the multiple source cases on the target problem attribute k, i≤I,l∈N + I represents the total number of the multiple source cases, k≤K,k∈N + K is the total number of the multiple problem attributes, and N is... + Let be the set of all positive integers;

[0013] The step of calculating the information entropy of the target problem attribute based on the normalized value includes:

[0014]

[0015] Among them, E k The information entropy of the target problem attribute k;

[0016] The step of calculating the weight value of the target problem attribute based on the information entropy includes:

[0017]

[0018] Where, ω k The weight value of the target problem attribute k.

[0019] In some implementations, calculating the global similarity between the target case and the plurality of source cases based on the similarity and the weight values ​​includes:

[0020]

[0021] Among them, Sim(S i ,T j ) is the target case T j With source case S i The global similarity between them, Sim(S i,k ,T j,k ) is the target case T j Heyuan Case S i The similarity between target problem attributes k, S i,k Used to characterize source case S i The target problem attribute k, T j,k Used to characterize target case T j The target problem attribute k.

[0022] In some implementations, when the target problem attribute is a deterministic problem attribute, calculating the similarity between the target case and the plurality of source cases among the target problem attributes includes:

[0023]

[0024] Among them, Sim(S i,k ,T j,k ) is the target case T j Heyuan Case S i The similarity between them in terms of deterministic problem attributes, S i,k Used to characterize source case S i Deterministic problem attribute k, T j,k Used to characterize target case T j The attribute k of the deterministic problem For source case S i The value of attribute k in a deterministic problem. For the target case T j The value of attribute k in a deterministic problem, max k The maximum value of the problem attribute k is min. k This represents the minimum value of the problem attribute k.

[0025] In some implementations, when the target question attribute is a fuzzy question attribute, calculating the similarity between the target case and the plurality of source cases among the target question attributes includes:

[0026] Sim(S i,k ,T j,k )=1-d

[0027] Among them, Sim(S i,k ,T j,k ) is the target case T j Heyuan Case S i The similarity between them in terms of fuzzy problem attributes, S i,k Used to characterize source case S i The fuzzy problem attribute k, T j,k Used to characterize target case T j The fuzzy problem attribute k, d is the value of S based on the distance to the bulldozer. i,k With T j,k The similarity of attributes between them.

[0028] In some implementations, when the target question attribute is an interval-type question attribute, calculating the similarity between the target case and the plurality of source cases among the target question attributes includes:

[0029]

[0030] Among them, Sim(S i,k ,T j,k ) is the target case T j Heyuan Case S i The similarity between them in terms of attributes of interval-type problems, S i,k Used to characterize source case S i The interval-type problem with attribute k, T j,k Used to characterize target case T j The interval-type problem attribute k, For source case S i The value of attribute k in interval-type problems For the target case T j The value of attribute k in interval-type problems For measurement Length, For measurement Length, For measurement The length.

[0031] In some implementations, when the target question attribute is a categorized question attribute, calculating the similarity between the target case and the plurality of source cases among the target question attributes includes:

[0032]

[0033] Among them, Sim(S i,k ,T j,k ) is the target case T j With source case S i The similarity between them on attribute k in the classification problem, S i,k Used to characterize source case S i Classification problem attribute k, T j,k Used to characterize target case T j Problem attribute k, For source case S i The value of attribute k in the classification problem For the target case T j The value of attribute k in the classification problem, B p and B q Let be any two subspaces of the attribute value space for the classification problem.

[0034] A second aspect of this application provides a case-based reasoning-based unmanned swarm action strategy recommendation device, the case-based reasoning-based unmanned swarm action strategy recommendation device comprising:

[0035] The data acquisition unit is used to acquire the target case and multiple corresponding source cases of the unmanned cluster, as well as multiple problem attributes of the case of the unmanned cluster, wherein the problem attributes are used to characterize the problem of the case.

[0036] A similarity calculation unit is used to calculate the similarity between the target case and the plurality of source cases between the target question attribute, wherein the target question attribute is any one of the plurality of question attributes;

[0037] The weight value calculation unit is used to calculate the normalized value of the plurality of source cases on the target problem attribute, calculate the information entropy of the target problem attribute based on the normalized value, and calculate the weight value of the target problem attribute based on the information entropy.

[0038] A global similarity calculation unit is used to calculate the global similarity between the target case and the plurality of source cases based on the similarity and the weight value;

[0039] The source case recommendation unit is used to select a target source case from the multiple source cases based on the global similarity, so as to guide the action strategy of the target case through the target source case.

[0040] A third aspect of this application provides an electronic device, characterized in that it includes at least one controller and a memory for communicatively connecting with the controller; the memory stores instructions executable by the at least one controller, the instructions being executed by the at least one controller to cause the at least one controller to perform the case-based reasoning unmanned swarm action strategy recommendation method as described above.

[0041] A fourth aspect of this application provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed, it implements the case-based reasoning method for recommending unmanned swarm action strategies as described above.

[0042] This application proposes a case-based reasoning method for recommending action strategies for unmanned swarms. This method applies case-based reasoning technology to the recommendation process of action strategies for unmanned swarms, providing a novel approach. By comparing similarity with historical cases, it can quickly and reasonably find the most similar source case as a guide for recommending action strategies for target cases. It can recommend action strategies for target cases in both online and offline states, and the accuracy of target case action strategy recommendations continuously improves with the increase in historical source cases. Furthermore, this method provides methods for calculating problem attribute similarity and global case similarity during the target source case search process. These methods are used to match the target source case with the highest similarity from multiple source cases, improving the accuracy of target source case search and enhancing the effectiveness of target case action strategy recommendations.

[0043] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a schematic diagram of the case reasoning process provided in the embodiments of this application;

[0046] Figure 2 This is a flowchart illustrating the unmanned swarm action strategy recommendation method based on case reasoning provided in the embodiments of this application;

[0047] Figure 3 This is a schematic diagram of the structure of the unmanned swarm action strategy recommendation device based on case reasoning provided in the embodiments of this application;

[0048] Figure 4 This is an architectural diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] The following describes the technical concepts used in this application:

[0051] (1) Case-Based Reasoning (CBR) is a knowledge reasoning method that solves problems by imitating human thinking and reasoning patterns. CBR mainly uses historical experience to solve similar current problems and has unique advantages such as weak dependence on domain knowledge, intuitive case expression, efficient problem solving, and continuous knowledge accumulation.

[0052] Reference Figure 1 Currently, the most commonly used case-based reasoning framework is the 4R framework, which consists of four parts: Retrieve, Reuse, Revise, and Retain. When this framework runs, it first represents the problem to be solved in the real world as a target case. Then, it uses case retrieval to match the source case with the highest similarity from the historical case library. If the source case can be directly used to solve the target case, then case reuse is used to complete the case reasoning process. Finally, based on the solution and effect of the target case, it can be stored as a new case in the historical case library for use in solving subsequent real-world problems.

[0053] From a knowledge reasoning perspective, case representation is a knowledge modeling process that uses cases to represent real-world problems and their solutions, with relatively low reliance on domain knowledge. Case retrieval, case reuse, and case revision can be understood as the application of knowledge from historical case data, combining intuitiveness and efficiency. Case preservation is a process of accumulating knowledge from case data, thereby continuously enhancing case-based reasoning capabilities.

[0054] (2) Action strategy: The action strategy of unmanned swarm is an important prerequisite for the formulation of action plans for unmanned swarm. The action plans under different action strategies are quite different, and multiple different action plans can be formulated under the same strategy.

[0055] This application employs CBR technology to recommend unmanned swarm action strategies, and utilizes problem attribute similarity and global case similarity calculation methods when selecting source cases for target cases to improve the accuracy of source case selection.

[0056] Reference Figure 2 This application proposes a method for recommending unmanned swarm action strategies based on case-based reasoning. This method includes the following steps S110 to S150:

[0057] Step S110: Obtain the target case and multiple corresponding source cases of the unmanned cluster, and obtain multiple problem attributes of the case of the unmanned cluster.

[0058] An unmanned swarm can be a swarm of drones, a swarm of robots, robot dogs, or fixed unmanned devices, or a swarm of drones, robots, and robot dogs that are mutually integrated; no specific limitations are made here.

[0059] A target case refers to the representation of the problem to be solved by the unmanned swarm. For CBR (Content-Based Response) technology, a case typically includes three parts: problem description, solution, and solution effect. However, when applying CBR technology to the recommendation problem of unmanned swarm action strategies, the problem description is a standardized representation of information such as the unmanned swarm's mission, forces, and scenario. The solution mainly consists of various types of action strategies, and the solution effect includes the achievement of the objective and the friendly forces' casualties. It should be noted that the action strategies can be set according to the actual operation of the unmanned swarm; no restrictions are imposed here.

[0060] Source cases refer to cases in the historical case library that are relevant to the target case. The historical case library is a database of historical source cases collected from unmanned clusters through various means, and it can be pre-defined. The multiple source cases here can be all the cases in the entire historical case library, or a subset of source cases extracted from the historical case library.

[0061] Because the target case is a problem to be solved, the source case includes: problem description, solution, and solution effects. Problem attributes are the characteristic attributes used to characterize the problem in the case, and the problem description can be standardized by extracting these characteristic attributes.

[0062] It is worth noting that each source case has a corresponding action strategy. The correspondence between the source case and the action strategy can be set in advance. Since the setting of the action strategy and its relationship with the source case are not the focus of this application, and the action strategy is general knowledge in the field, it will not be described in detail here.

[0063] In step S110, the target case and multiple source cases of the unmanned cluster are obtained first. The purpose is to find the target source case that is most similar to the target case from the multiple source cases. Then, the action strategy of the target case can be implemented according to the action strategy corresponding to the case.

[0064] Step S120: Calculate the similarity between the target case and multiple source cases in terms of target problem attributes.

[0065] The target question attribute in step S120 is any one of multiple question attributes. Since there are multiple question attributes, the similarity between the target case and the multiple source cases is calculated differently for each attribute. For the same question attribute, the similarity calculation method between the target case and the multiple source cases is the same; the similarity calculation method can use methods such as Euclidean distance or bulldozer distance. See the subsequent embodiments for details.

[0066] Step S130: Calculate the normalized values ​​of multiple source cases on the target problem attribute, calculate the information entropy of the target problem attribute based on the normalized values, and calculate the weight value of the target problem attribute based on the information entropy.

[0067] Because the similarity calculation between cases depends on the similarity of problem attributes and the weight of those attributes, this implementation method addresses the issue of attribute weight allocation by starting with the data and assigning attribute weights according to the dispersion of the problem attribute data, thereby improving discriminability. This embodiment considers the dispersion of problem attribute data and uses the entropy weight method to calculate the weights of problem attributes. This is because the entropy weight method uses the concept of index variation in information entropy to characterize the dispersion of attribute data. Therefore, if the data variation of a certain problem attribute index is large, the attribute plays a more prominent role in distinguishing different action cases, and thus should be assigned a larger weight. Conversely, low-weight problem attributes have poor discriminability. The calculation process includes data standardization, calculating index variability, calculating information entropy, and determining weights.

[0068] In some embodiments of this application, step S130 can be calculated in the following manner:

[0069] Step S131: Calculate the normalized values ​​of multiple source cases on the target problem attribute, including:

[0070]

[0071] in, For source case S i The normalized value on the target problem attribute k. For source case S i The value of the target problem attribute k, min i,k max is the minimum value of multiple source cases on the target problem attribute k. i,k Let i be the maximum value of multiple source cases on the target problem attribute k, i ≤ I, i ∈ N. + I represents the total number of source cases, k≤K,k∈N + K is the total number of multiple problem attributes, N + Let be the set of all positive integers.

[0072] Step S132: Calculate the information entropy of the target problem attribute based on the normalized value, including:

[0073]

[0074] Among them, E k Let k be the information entropy of the target problem attribute k.

[0075] Step S133: Calculate the weight values ​​of the target problem attributes based on information entropy, including:

[0076]

[0077] Where, ω k The weight value of the target problem attribute k.

[0078] Step S140: Calculate the global similarity between the target case and multiple source cases based on the similarity and weight values.

[0079] After obtaining the similarity between the target case and multiple source cases in terms of target question attributes, as well as the weight values ​​corresponding to different question attributes, we can use a weighted summation method to calculate the global similarity between the target case and multiple source cases.

[0080] In some embodiments of this application, step S140 calculates the global similarity between the target case and multiple source cases using the following formula:

[0081]

[0082] Among them, Sim(S i ,T j ) is the target case T j With source case S i The global similarity between them, Sim(S i,k ,T j,k ) is the target case T j Heyuan Case S i The similarity between target problem attributes k, S i,k Used to characterize source case S i The target problem attribute k, T j,k Used to characterize target case T j The target problem attribute k.

[0083] Step S150: Select the target source case from multiple source cases based on global similarity, so as to guide the action strategy of the target case through the target source case.

[0084] This step obtains the global similarity between the target case and the source cases, selects the source case with the highest global similarity (here referred to as the target source case), and then proceeds according to... Figure 1The provided CBR technical solution guides the action strategy of the target case through the target source case. It should also be noted that CBR calculation also includes case correction. The embodiments of this application do not involve improvements to the correction steps, so they will not be described in detail here.

[0085] The case-based reasoning-based unmanned swarm action strategy recommendation method provided in this embodiment has at least the following effects:

[0086] This method applies case-based reasoning techniques to the recommendation process of action strategies for unmanned swarms, providing a novel approach. By comparing similarity with historical cases, it can quickly and reasonably find the most similar source case as a guide for recommending action strategies for target cases. It can recommend action strategies for target cases in both online and offline states, and the accuracy of target case action strategy recommendations continuously improves with the increase in historical source cases. Furthermore, this method provides methods for calculating problem attribute similarity and global case similarity during the target source case search process. These methods are used to match the target source case with the highest similarity from multiple source cases, improving the accuracy of target source case search and enhancing the effectiveness of target case action strategy recommendations.

[0087] In some embodiments of this application, unmanned swarm operations exhibit typical characteristics such as autonomy, adversarial nature, and uncertainty. For example, the effectiveness of the operation is closely related to the target's protection level and air defense capabilities, the swarm's equipment size and payload quantity, and the external electromagnetic and physical environment. Except for some attributes such as swarm equipment, which can be obtained with precise values, most information concerning the target and the external environment is fuzzy and uncertain. Therefore, the problem attributes of unmanned swarm operation cases are divided into four categories: deterministic (e.g., the number of attacking drones), fuzzy (e.g., the robustness of target facilities), interval-based (e.g., the target's reaction radius), and categorical (e.g., physical weather), and corresponding attribute similarity calculation models are designed for each type.

[0088] (1) When the target problem attribute is a deterministic problem attribute, calculate the similarity between the target case and multiple source cases in terms of the target problem attribute, including:

[0089]

[0090] Among them, Sim(S i,k ,T j,k ) is the target case T j Heyuan Case S i The similarity between them in terms of deterministic problem attributes, S i,k Used to characterize source case S i Deterministic problem attribute k, T j,k Used to characterize target case T jThe attribute k of the deterministic problem For source case S i The value of attribute k in a deterministic problem. For the target case T j The value of attribute k in a deterministic problem, max k The maximum value of the problem attribute k is min. k Sim(S) represents the minimum value of the problem attribute k. i,k ,T j,k The similarity value of ) ranges from [0,1].

[0091] (2) When the target question attribute is a fuzzy question attribute, calculate the similarity between the target case and multiple source cases in terms of the target question attribute, including:

[0092] The bulldozer distance represents the optimal distance between two distributions. Here, it is used to calculate the optimal distance between distributions represented by the triangular fuzzy number and serves as the similarity between problem attributes.

[0093] First, let's remember the problem attribute a. k The value space of is The problem attribute values ​​represented by triangular fuzzy numbers are given in the following formula:

[0094]

[0095] Secondly, we define a formula for calculating attribute similarity based on bulldozer distance:

[0096] Sim(S i,k ,T j,k )=1-d (6)

[0097] Among them, Sim(S i,k ,T j,k ) is the target case T j Heyuan Case S i The similarity of attributes between fuzzy problem types, S i,k Used to characterize source case S i The fuzzy problem attribute k, T j,k Used to characterize target case T j The fuzzy problem attribute k, d is the value of S based on the distance to the bulldozer. i,k With T j,k The similarity of attributes between them, d is used To indicate, Based on the triangular fuzzy number distribution, its calculation formula is given as follows:

[0098]

[0099] in,

[0100] (3) When the target question attribute is an interval-type question attribute, calculate the similarity between the target case and multiple source cases in terms of the target question attribute, including:

[0101] Interval-type numerical similarity is typically calculated using the Jaccard coefficient, which, while offering good leniency, is somewhat lacking in discriminative power. Therefore, this paper employs an improved Jaccard coefficient method to calculate attribute similarity for interval-type problems:

[0102]

[0103] Among them, Sim(S i,k ,T j,k ) is the target case T j Heyuan Case S i The similarity between them in terms of attributes of interval-type problems, S i,k Used to characterize source case S i The interval-type problem with attribute k, T j,k Used to characterize target case T j The interval-type problem attribute k, For source case S i The value of attribute k in interval-type problems For the target case T j The value of attribute k in interval-type problems. and For interval numbers, that is, the interval [x] formed by the minimum and maximum values. - ,x + ], L(·) is a function that measures the length of an interval. For measurement Length, For measurement Length, For measurement The length.

[0104] (4) When the target question attribute is a categorized question attribute, calculate the similarity between the target case and multiple source cases in terms of the target question attribute, including:

[0105] The similarity calculation of attributes in classification problems is relatively subjective. To facilitate processing, the value space of the attributes in classification problems {b1, b2, ..., b...} is first defined. n} is divided into several subspaces {B1, B2, ..., B} n′}. Each subspace contains multiple similar attribute values, typically n ≥ n′. The attribute S for the classification problem is given. i,k and T j,k Similarity calculation formula:

[0106]

[0107] Among them, Sim(S i,k ,T j,k ) is the target case T j With source case S i The similarity between them on attribute k in the classification problem, S i,k Used to characterize source case S i Classification problem attribute k, T j,k Used to characterize target case T j Problem attribute k, For source case S i The value of attribute k in the classification problem For the target case T j The value of attribute k in the classification problem, B p and B q Let be any two subspaces of the attribute value space for the classification problem.

[0108] This implementation classifies the problem attributes of unmanned swarm action cases into deterministic, fuzzy, interval, and categorical types, and designs corresponding attribute similarity calculation models for each type, enriching the problem description of the target case and improving the accuracy of finding the most similar source case for the target case.

[0109] To verify the practicality of this application, a set of experimental examples are provided below:

[0110] (1) Experimental background;

[0111] The scenario is based on a Red Force unmanned swarm attacking Blue Force ground facilities. The Red Force's unmanned equipment includes several attack and reconnaissance drones, which can form groups to conduct swarm operations as needed. The Blue Force has deployed several anti-drone equipment on its ground facilities. The task is to recommend the most suitable Red Force unmanned swarm operation strategy for several typical Blue Force ground facilities, and to guide the formulation of the Red Force's unmanned swarm operation plan.

[0112] (2) Experimental analysis;

[0113] The case study includes: problem description, solution, and solution effectiveness. Based on the experimental scenario, the problem attributes of the unmanned swarm operation case are first identified, mainly including three aspects: Red Force equipment information, Blue Force target information, and operational environment information. Specifically, Red Force equipment information represents the main force carrying out the operation, with selected attributes including the number of offensive drones (a1), the number of reconnaissance drones (a2), and the operational radius (a3). Blue Force target information reflects the basic situation of the target objects, with selected attributes including the strength of facilities (a4), the number of anti-drone equipment (a5), the number of targets (a6), and the reaction distance (a7). Operational environment information reflects the environmental factors that have a significant impact on unmanned swarm operations, with selected attributes including physical weather (a8) and electromagnetic environment (a9).

[0114] Among them, a1, a2, a5, and a6 are deterministic problem attributes, and their values ​​are exact values.

[0115] a3 and a7 are essentially intervals from 0 to the maximum radius, and should be considered as attributes of interval-type problems, with values ​​taking interval values.

[0116] a4 and a9 are usually described qualitatively and their values ​​have a certain continuity. They should be regarded as fuzzy problem attributes and their values ​​are triangular fuzzy numbers.

[0117] a8 has classification characteristics, such as sunny (5), cloudy (4), rainy (3), snowy (2) and foggy (1), and should be processed according to the classification problem attributes, taking the value of one of the types.

[0118] For ease of processing, a4 and a9 need to be graded first. a4 can be classified as fragile (1), poor (2), good (3), and strong (4), while a9 can be classified as poor (1), poor (2), average (3), good (4), and good (5).

[0119] Secondly, the solution attribute of the source case is the action strategy adopted (r1), which takes one of several action strategies. Here, we assume there are 6 action strategies (effect-first strategy AT1, time-first strategy AT2, cost-first strategy AT3, effect-averse strategy AT4, time-averse strategy AT5, cost-averse strategy AT6), i.e., r1∈{AT1,AT2,AT3,AT4,AT5,AT6}. Finally, the operational effects of the solution include goal achievement (e1) and cost-effectiveness ratio (e2).

[0120] Among them, the target achievement attribute value may be success or failure, but in this experiment, all cases are set to success, i.e., e1 = Yes; the cost-effectiveness attribute value is represented by dividing the number of red team drones lost by the number of blue team anti-drone equipment and ground facilities, i.e., e2 ∈ [0,1].

[0121] To verify the performance of the method, publicly available drone operation cases were searched online. The problems, solution attributes, and execution effects were identified. Some unpublished data was manually supplemented, resulting in a dataset with 10 source cases (S1-S2). 10 The historical case library is used. Regarding target cases, four typical blue team ground facility scenarios (T1-T4) are designed, as shown in Table 1.

[0122]

[0123] Table 1

[0124] To calculate the global similarity between the four target cases and all source cases, the attribute similarity calculation process needs to be explained first. First, a1, a2, a3, a5, a6, and a7 are deterministic and interval-type problem attributes, which can be calculated according to the above formulas (5) and (6). Second, a8 is a categorical problem attribute, which is divided into subspaces B1 = {5,4}, B2 = {3,2}, and B3 = {1} according to the influence of weather on drone operations. Finally, a4 and a9 are fuzzy problem attributes, and the calculation process is relatively complex. Here, we take a4 as an example. Its value space is a4∈{1,2,3,4}, then t = 3. The value of attribute s4 is represented by the triangular fuzzy number, and the source case S is given. i With target case T j The similarity calculation results for all possible values ​​of the a4 attribute are shown in Table 2.

[0125]

[0126] Table 2

[0127] Based on this, the global similarity calculation results between all target cases and source cases are shown in Table 3. Taking T1 as an example, the similarity results between the target case and the source case are shown in Table 4. The question attribute weight ω is calculated based on the entropy weight method. k =(0.1741,0.015,0.174,0.094,0.102,0.164,0.201,0.035,0.04).

[0128]

[0129]

[0130] Table 3

[0131] <![CDATA[S1]]> 0.5 0.333 0.775 0.599 0.333 0.8 0.707 1 0.805 <![CDATA[S2]]> 0.5 0.667 1 1 0.667 0.8 0.866 0.7 0.441 <![CDATA[S3]]> 0.667 0.667 0.775 0.649 1 1 0.612 0.3 1 <![CDATA[S4]]> 0.333 1 0.816 0.599 0.667 0.6 0.707 0.3 0.473 <![CDATA[S5]]> 0.667 0.667 0.926 0.739 1 0.6 0.935 0.3 0.736 <![CDATA[S6]]> 0.5 0.333 0.775 1 1 0.6 0.707 0.7 0.805 <![CDATA[S7]]> 0.667 0.333 0.739 0.599 0.667 0.8 0.866 0.3 0.805 <![CDATA[S8]]> 0.333 0.667 0.866 0.649 0.667 0.8 0.671 0.3 0.441 <![CDATA[S9]]> 1 0.333 1 0.649 0.667 1 0.707 0.3 0.736 <![CDATA[S 10 ]]> 0.667 0.667 0.775 1 1 0.4 0.758 0.3 0.473

[0132] Table 4

[0133] (3) Experimental conclusions;

[0134] The recommendation results for the four target cases are summarized in Table 5.

[0135] <![CDATA[T1]]> <![CDATA[S9]]> AT3 Cost-first strategy <![CDATA[T2]]> <![CDATA[S1]]> AT3 Cost-first strategy <![CDATA[T3]]> <![CDATA[S2]]> AT1 Results-oriented strategy <![CDATA[T4]]> <![CDATA[S8]]> AT2 Time-first strategy

[0136] Table 5

[0137] Reference Figure 3 One embodiment of this application provides a case-based reasoning-based unmanned swarm action strategy recommendation device, which includes:

[0138] The data acquisition unit is used to acquire the target case and multiple corresponding source cases of the unmanned cluster, as well as multiple problem attributes of the case of the unmanned cluster. The problem attributes are used to characterize the problem of the case.

[0139] The similarity calculation unit is used to calculate the similarity between the target case and multiple source cases in terms of the target question attribute, where the target question attribute is any one of the multiple question attributes.

[0140] The weight value calculation unit is used to calculate the normalized value of multiple source cases on the target problem attribute, calculate the information entropy of the target problem attribute based on the normalized value, and calculate the weight value of the target problem attribute based on the information entropy.

[0141] The global similarity calculation unit is used to calculate the global similarity between the target case and multiple source cases based on similarity and weight values.

[0142] The source case recommendation unit is used to select the target source case from multiple source cases based on global similarity, so as to guide the action strategy of the target case through the target source case.

[0143] It should be noted that this embodiment is based on the same inventive concept as the above method embodiment, therefore the relevant content of the above method embodiment is also applicable to this embodiment, and will not be described in detail here.

[0144] Reference Figure 4 This application also provides an electronic device, which includes:

[0145] At least one memory;

[0146] At least one processor;

[0147] At least one program;

[0148] The program is stored in memory, and the processor executes at least one program to implement the case-based reasoning method for recommending unmanned swarm action strategies described above in this disclosure.

[0149] This electronic device can be any smart terminal, including mobile phones, tablets, personal digital assistants (PDAs), and in-vehicle computers.

[0150] The electronic devices according to embodiments of this application will now be described in detail.

[0151] The processor 1600 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0152] The memory 1700 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 1700 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the program code is stored in the memory 1700 and is called and executed by the processor 1600 to execute the case-based reasoning unmanned swarm action strategy recommendation method of the embodiments of this application.

[0153] The input / output interface 1800 is used to implement information input and output.

[0154] The communication interface 1900 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0155] Bus 2000 transmits information between various components of the device (e.g., processor 1600, memory 1700, input / output interface 1800, and communication interface 1900);

[0156] The processor 1600, memory 1700, input / output interface 1800 and communication interface 1900 are connected to each other within the device via bus 2000.

[0157] This application embodiment also provides a storage medium, which is a computer-readable storage medium storing computer-executable instructions for causing a computer to execute the above-described case-based reasoning method for recommending unmanned swarm action strategies.

[0158] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0159] The embodiments described in this application are intended to more clearly illustrate the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0160] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0161] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0162] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0163] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0164] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0165] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0166] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0167] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0168] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0169] The above is a detailed description of the preferred embodiments of this application. However, the embodiments of this application are not limited to the above-described implementation methods. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the embodiments of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of the embodiments of this application.

Claims

1. A method for recommending unmanned swarm action strategies based on case-based reasoning, characterized in that, The case-based reasoning-based unmanned swarm action strategy recommendation method includes: Obtain the target case and multiple corresponding source cases of the unmanned cluster, and obtain multiple problem attributes of the case of the unmanned cluster, wherein the problem attributes are used to characterize the feature attributes of the problem of the case; Calculate the similarity between the target case and the plurality of source cases in terms of a target question attribute, wherein the target question attribute is any one of the plurality of question attributes; Calculate the normalized values ​​of the multiple source cases on the target problem attribute, calculate the information entropy of the target problem attribute based on the normalized values, and calculate the weight value of the target problem attribute based on the information entropy; the calculation of the normalized values ​​of the multiple source cases on the target problem attribute includes: in, For the source case In the target problem attributes Normalized value on, For the source case In the target problem attributes The values ​​in For the multiple source cases in the target problem attributes The minimum value on, For the multiple source cases in the target problem attributes The maximum value on, , The total number of the multiple source cases. , The total number of the multiple problem attributes. Let be the set of all positive integers; The step of calculating the information entropy of the target problem attribute based on the normalized value includes: in, For the target problem attributes Information entropy; The step of calculating the weight value of the target problem attribute based on the information entropy includes: in, For the target problem attributes The weight value; When the target question attribute is a deterministic question attribute, calculating the similarity between the target case and the plurality of source cases in terms of the target question attribute includes: in, For the target case Heyuan Case The similarity between them in terms of deterministic problem attributes Used for characterizing source cases Deterministic problem attributes , Used to characterize target cases Deterministic problem attributes , For the source case In the properties of deterministic problems The values ​​in For the target case In the properties of deterministic problems The values ​​in For the problem attributes The maximum value that can be taken. For the problem attributes The minimum value that can be taken; Based on the similarity and the weight values, calculate the global similarity between the target case and the multiple source cases; Based on the global similarity, a target source case is selected from the multiple source cases to guide the action strategy of the target case.

2. The method for recommending unmanned swarm action strategies based on case-based reasoning according to claim 1, characterized in that, The step of calculating the global similarity between the target case and the plurality of source cases based on the similarity and the weight value includes: in, For the target case With source case Global similarity between them For the target case Heyuan Case In the target problem attributes Similarity between them Used for characterizing source cases Target problem attributes , Used to characterize target cases Target problem attributes .

3. The method for recommending unmanned swarm action strategies based on case-based reasoning according to claim 1, characterized in that, When the target question attribute is a fuzzy question attribute, calculating the similarity between the target case and the plurality of source cases among the target question attributes includes: in, For the target case Heyuan Case The similarity between them in terms of fuzzy problem attributes Used for characterizing source cases Fuzzy problem attributes , Used to characterize target cases Fuzzy problem attributes , For bulldozer distance calculation and The similarity of attributes between them.

4. The method for recommending unmanned swarm action strategies based on case-based reasoning according to claim 1, characterized in that, When the target question attribute is an interval-type question attribute, calculating the similarity between the target case and the plurality of source cases among the target question attributes includes: in, For the target case Heyuan Case The similarity between them in terms of attributes of interval-type problems Used for characterizing source cases Interval-type problem attributes , Used to characterize target cases Interval-type problem attributes , For the source case In the properties of interval-type problems The values ​​in For the target case In the properties of interval-type problems The values ​​in For measurement Length, For measurement Length, For measurement The length.

5. The method for recommending unmanned swarm action strategies based on case-based reasoning according to claim 1, characterized in that, When the target question attribute is a categorized question attribute, calculating the similarity between the target case and the plurality of source cases among the target question attributes includes: in, For the target case With source case Between the attributes of the classification problem Similarity on Used for characterizing source cases Classification of problem attributes , Used to characterize target cases Problem attributes , For the source case In the classification of problem attributes The values ​​in For the target case In the classification of problem attributes The values ​​in and Let A and B be any two subspaces of the attribute value space for the classification problem.

6. A case-based reasoning-based unmanned swarm action strategy recommendation device, characterized in that, The case-based reasoning unmanned swarm action strategy recommendation device is used to execute the case-based reasoning unmanned swarm action strategy recommendation method according to any one of claims 1 to 5.

7. An electronic device, characterized in that, It includes at least one controller and a memory for communicatively connecting with the controller; the memory stores instructions executable by the at least one controller, the instructions being executed by the at least one controller to cause the at least one controller to perform the case-based reasoning unmanned swarm action strategy recommendation method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the case-based reasoning method for recommending unmanned swarm action strategies as described in any one of claims 1 to 5.

Images