An equipment combination scheme recommendation method for combat tasks

Abstract

The application discloses a kind of equipment combination scheme recommendation methods for combat mission, the method comprises: for new combat mission, determine similar task from historical combat mission;For each alternative equipment combination scheme, the similarity between the similar task and the new combat mission is calculated based on the applicability between the similar task and the equipment combination scheme, and the estimate value of the applicability between the equipment combination scheme and the new combat mission;According to the calculated estimate value, recommend equipment combination scheme for new combat mission.The application can solve the optimization configuration of equipment combination scheme and combat mission, support the combat effectiveness maximization of equipment for specific combat mission, and to a certain extent, optimize equipment selection, avoid the waste of resources caused by equipment planning to deviate from actual task demand.

Description

Technical Field

[0001] This invention relates to the field of data classification technology, and in particular to a method for recommending equipment combination schemes for combat missions. Background Technology

[0002] Within the complex and diverse equipment system, various types of equipment undertake different tasks and perform different functions. Therefore, different equipment is suited for different combat missions, and different combat missions rely on different equipment to be accomplished.

[0003] Combat missions are a collection of feasible future combat tasks full of uncertainties. It is incomplete to evaluate and select equipment capabilities solely from the perspective of equipment itself. This ignores the specific needs and autonomy requirements of combat missions for equipment. There are overlaps in the general performance of equipment, which leads to the loss of specific capabilities required for specific combat missions. This results in insufficient equipment support for specific missions and waste of resources. Therefore, finding the right equipment and optimizing the configuration for combat missions is crucial for the long-term development of equipment.

[0004] Therefore, it is necessary to provide a method for recommending equipment combination schemes for combat missions, solving the optimal configuration of equipment combination schemes and combat missions, supporting the maximization of equipment combat effectiveness for specific combat missions, and optimizing equipment selection to a certain extent, avoiding the waste of resources caused by equipment planning deviating from actual mission requirements. Summary of the Invention

[0005] In view of this, the purpose of this invention is to propose a method for recommending equipment combination schemes for combat missions, solve the optimal configuration of equipment combination schemes and combat missions, support the maximization of equipment combat effectiveness for specific combat missions, and optimize equipment selection to a certain extent, thereby avoiding resource waste caused by equipment planning deviating from actual mission requirements.

[0006] To achieve the above objectives, the present invention provides a method for recommending equipment combination schemes for combat missions, comprising:

[0007] To address new combat missions, identify similar missions from historical combat missions;

[0008] For each alternative equipment combination scheme, based on the applicability between the similar mission and the equipment combination scheme, and the similarity between the similar mission and the new combat mission, an estimated value of the applicability between the equipment combination scheme and the new combat mission is calculated.

[0009] Based on the calculated estimates, a recommended equipment combination scheme is proposed for the new combat mission.

[0010] Preferably, the step of calculating an estimate of the suitability of the equipment combination scheme for the new operational mission based on the applicability between the similar mission and the equipment combination scheme, and the similarity between the similar mission and the new operational mission, specifically includes:

[0011] Calculate the equipment combination scheme E according to the following formula 3. j Estimates of suitability with new operational missions

[0012]

[0013] In Formula 3, T new Indicates a new combat mission, C(T) new This represents a set of similar missions identified from historical combat missions. Indicates combat mission T i Equipment combination scheme E j The applicability between them; d represents the similarity between the calculated combat missions.

[0014] Preferably, the step of identifying similar missions from historical combat missions for a new combat mission specifically includes:

[0015] Based on the indicator vector of each combat mission, the similarity between combat missions is calculated;

[0016] Based on the similarity between combat missions, the interval fuzzy set agglomerative hierarchical clustering algorithm is used to cluster the combat missions.

[0017] In the clustering results, each combat mission in the cluster containing the new combat mission is identified as a similar mission to the new combat mission.

[0018] Preferably, the indicator vector of the combat mission includes multiple vector elements, each vector element corresponding to an interval number of an indicator; and

[0019] The interval number of the indicator is specifically calculated using the interval entropy weight method.

[0020] Preferably, the interval number of the indicator is calculated using the following method:

[0021] Based on the results of multiple measurements of each indicator, an interval fuzzy number decision matrix is ​​constructed;

[0022] Standardize the interval number decision matrix;

[0023] Based on the standardized interval fuzzy number decision matrix, the entropy value of each indicator is calculated;

[0024] Calculate the interval entropy weight of the indicator based on its entropy value;

[0025] After normalizing the interval entropy weights of the indicators, the interval number of the indicators is obtained.

[0026] The fitness score is extracted from the fitness matrix; and the fitness matrix is ​​obtained by imputing missing values ​​using an interval collaborative filtering algorithm.

[0027] Preferably, the fitness matrix is ​​imputed for missing values ​​using the following method:

[0028] Based on the known suitability between combat missions and equipment combination schemes, an initial suitability matrix is ​​established.

[0029] Based on the common applicability between two combat missions, the similarity between two combat missions is calculated; and based on the common applicability between two equipment combination schemes, the similarity between two equipment combination schemes is calculated.

[0030] For the missing fitness r in the initial fitness matrix ui Based on the similarity between each pair of combat missions, calculate the set of similar nearest neighbors of combat mission u; and based on the similarity between each pair of equipment combination schemes, calculate the set of similar nearest neighbors of equipment combination scheme i.

[0031] Based on the applicability of similar neighbors of combat mission u to various equipment combination schemes, and the applicability of similar neighbors of equipment combination scheme i to various combat missions, predict the missing applicability r. ui .

[0032] The present invention also provides an electronic device, including a central processing unit, a signal processing and storage unit, and a computer program stored on the signal processing and storage unit and executable on the central processing unit, wherein the central processing unit executes the program to implement the recommended method for equipment combination schemes for combat missions as described above.

[0033] The present invention also provides a computer-readable storage medium storing a computer program that can be executed by at least one processor to cause the at least one processor to perform the steps of the method for recommending equipment combination schemes for combat missions as described above.

[0034] In the technical solution of this invention, for a new combat mission, similar missions are identified from historical combat missions; for each candidate equipment combination scheme, based on the applicability between the similar mission and the equipment combination scheme, and the similarity between the similar mission and the new combat mission, an estimated value of the applicability between the equipment combination scheme and the new combat mission is calculated; based on the calculated estimated value, an equipment combination scheme is recommended for the new combat mission. Based on the applicability between historical missions and equipment combination schemes, the optimal configuration of the equipment combination scheme and the new combat mission is solved, thereby supporting the maximization of equipment combat effectiveness for specific combat missions and optimizing equipment selection to a certain extent, avoiding resource waste caused by equipment planning deviating from actual mission requirements.

[0035] More preferably, in the technical solution of the present invention, the interval entropy weight method is used to calculate the degree of dispersion of the indicator attributes in the original data, thereby calculating the number of intervals of the indicators that reflect the weight of the indicator attributes, which has strong objectivity; thus, based on the more objective and accurate number of intervals of the indicators, a more accurate estimate of the applicability between the equipment combination scheme and the new combat mission can be calculated, making the configuration of the equipment combination scheme and the new combat mission more reasonable.

[0036] More preferably, in the technical solution of the present invention, the interval collaborative filtering algorithm is used to fill in the missing values ​​of the applicability matrix to reduce the sparsity of the original applicability matrix; based on the less sparsity applicability matrix, a more accurate estimate of the applicability between the equipment combination scheme and the new combat mission can be calculated, making the configuration of the equipment combination scheme and the new combat mission more reasonable. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 A flowchart illustrating a method for recommending equipment combination schemes for combat missions, provided in Embodiment 1 of the present invention;

[0039] Figure 2 This is a flowchart of a method for clustering combat missions using an interval fuzzy set agglomerative hierarchical clustering algorithm, provided in Embodiment 1 of the present invention.

[0040] Figure 3 This is a flowchart of a method for calculating the interval number of an index based on the interval entropy weight method, provided in Embodiment 2 of the present invention.

[0041] Figure 4 This is a flowchart of a method for imputing missing values ​​in an applicability matrix based on an interval collaborative filtering algorithm, provided in Embodiment 3 of the present invention.

[0042] Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to specific embodiments and accompanying drawings.

[0044] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0045] To address the problem of recommending equipment combination schemes based on combat missions, this invention provides a scheme that recommends equipment combination schemes tailored to combat missions. It uses the applicability of equipment combination schemes to combat missions as the basis for decision-making, and solves for the optimal configuration of equipment combination schemes and combat missions. This provides decision-makers with a rapid method for selecting equipment combination schemes, meeting the decision-making needs under time constraints in the pre-war stage. Furthermore, it supports maximizing the combat effectiveness of equipment for specific combat missions, optimizing equipment selection to a certain extent, and avoiding resource waste caused by equipment planning deviating from actual mission requirements.

[0046] The technical solutions of the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0047] Example 1

[0048] Embodiment 1 of the present invention provides a method for recommending equipment combination schemes for combat missions, the specific process of which is as follows: Figure 1 As shown, it includes the following steps:

[0049] Step S101: For new combat missions, identify similar missions from historical combat missions;

[0050] In this step, the similarity between combat missions is calculated based on the indicator vector of each combat mission. Then, based on the similarity between combat missions, a clustering algorithm is used to cluster the combat missions. Combat missions clustered in the same cluster as the new combat mission are identified as similar tasks to the new combat mission. Basic clustering methods include hierarchical clustering, partition-based clustering, and density-based clustering methods.

[0051] Specifically, the indicator vector of the combat mission includes multiple vector elements, each vector element corresponding to the interval number of an indicator; the similarity between combat missions can be calculated according to the following formula 1:

[0052]

[0053] In formula 1, These represent the indicator vectors for the two combat missions, respectively. They represent The lower and upper limits of the interval number of the i-th indicator; They represent The lower and upper limits of the interval number of the i-th indicator; ω i Let m represent the importance of the i-th indicator; m is the total number of vector elements (indicators) in the indicator vector.

[0054] As a preferred implementation method, an interval fuzzy set agglomerative hierarchical clustering algorithm can be used to cluster combat missions, which facilitates the clustering of interval fuzzy information. The specific process is as follows: Figure 2 As shown, it includes the following sub-steps:

[0055] Sub-step S201: In the initial state of clustering, each combat mission is treated as a separate cluster, and the index vector of the combat mission is used as the cluster center.

[0056] Sub-step S202: Based on the similarity between combat missions, merge combat missions with similarity greater than the similarity threshold into one cluster;

[0057] That is, clusters with similarity greater than a similarity threshold are merged based on the similarity between the cluster centers.

[0058] Sub-step S203: For the new clusters obtained by merging, calculate the cluster center of the cluster;

[0059] Specifically, the cluster center can be calculated using the following formula 2:

[0060]

[0061] In Formula 2, μ represents the calculated cluster center. The index vector represents the n combat missions in the cluster; Let m represent the lower and upper bounds of the interval number of the j-th indicator in the indicator vector of the i-th combat mission; m is the total number of vector elements (indicators) in the indicator vector.

[0062] Sub-step S204: Based on the similarity between the cluster centers, merge clusters with similarity greater than the similarity threshold.

[0063] Sub-step S205: Determine whether the number of combat missions in the cluster where the new combat mission is located has reached or exceeded the set limit; if not, jump to sub-step S203 to continue clustering; if yes, execute sub-step S206 to end clustering.

[0064] Sub-step S206: End clustering.

[0065] For example, when the number of combat missions in the cluster most similar to the new combat mission reaches the threshold for terminating clustering. Clustering stops when a threshold is set. In this example, the threshold is set. The composition of the clusters when the clustering termination condition is met is shown in Table 1 below.

[0066] Table 1

[0067]

[0068] In fact, the number of intervals for each indicator in the indicator vector reflects the weight of the indicator attribute, and determining the weight of the indicator attribute is a key issue in multi-attribute decision-making. Decision-makers have different preferences for different indicators, and different decision-makers often hold different attitudes towards the same indicator. This makes it difficult for subjectively determined weights of decision indicator attributes to be accepted by most decision-makers.

[0069] Based on this, the technical solution of this invention uses the interval entropy weight method to calculate the dispersion of indicator attributes in the original data, thereby calculating the number of intervals of the indicator that reflects the weight of the indicator attributes, which has strong objectivity. The specific method for calculating the number of intervals of the indicator according to the interval entropy weight method will be described in detail later.

[0070] Step S102: Based on the applicability between the similar tasks and each equipment combination scheme, and the similarity between the similar tasks and the new combat tasks, calculate the estimated value of the applicability between each equipment combination scheme and the new combat tasks.

[0071] In this step, for each alternative equipment combination scheme, based on the applicability between the similar mission and the equipment combination scheme, and the similarity between the similar mission and the new combat mission, an estimated value of the applicability between the equipment combination scheme and the new combat mission is calculated.

[0072] Specifically, the equipment combination scheme E can be calculated according to the following formula 3. j Estimates of suitability with new operational missions

[0073]

[0074] In Formula 3, T new Indicates a new combat mission, C(T) new This represents a set of similar missions identified from historical combat missions. Indicates combat mission T i Equipment combination scheme E j The applicability between them; d represents the similarity between the calculated combat missions, which can be calculated according to Formula 1 above.

[0075] For example, as can be seen from Table 1 above, the cluster with the highest similarity to the new combat mission is s3. According to Formula 3, the attribute values ​​of the missions in the cluster are integrated to obtain the estimated values ​​of the applicability of each scheme to the new mission, as shown in Table 2.

[0076] Table 2

[0077]

[0078] The suitability between combat missions and equipment combination schemes is extracted from the suitability matrix. In the combat mission-oriented equipment combination scheme recommendation problem, the suitability between equipment and combat missions is a crucial reference for optimizing equipment and mission configuration. However, in reality, due to the high complexity of equipment performance and combat mission information, the historical mission-equipment suitability matrix often contains a large number of missing values. Therefore, how to fill in the missing suitability values ​​based on the original suitability data is key to whether the agile decision-making method for combat mission-oriented weapon and equipment combination schemes can achieve optimized equipment and mission configuration. Thus, in this invention, an interval collaborative filtering algorithm is used to fill in the missing values ​​in the suitability matrix; the specific method will be detailed later.

[0079] Step S103: Based on the estimated applicability of each equipment combination scheme to the new combat mission, recommend an equipment combination scheme for the new combat mission.

[0080] Specifically, the estimated applicability of each equipment combination scheme to the new combat mission can be sorted from largest to smallest; and the equipment combination scheme with the highest estimated value can be recommended for the new combat mission.

[0081] For example, by comparing the estimated applicability values ​​in Table 2 above pairwise, the final ranking is as follows:

[0082] e13 >e4>e 19 >e3>e5>e7>e2>e 12 >e 18 >e 10 >e 15 >e8>e 11 >e6>e 20 >e 17 >e 14 >e1>e 16 >e9.

[0083] In the technical solution of Embodiment 1 of the present invention, for a new combat mission, similar missions are identified from historical combat missions; for each candidate equipment combination scheme, based on the applicability between the similar mission and the equipment combination scheme, and the similarity between the similar mission and the new combat mission, an estimated value of the applicability between the equipment combination scheme and the new combat mission is calculated; based on the calculated estimated value, an equipment combination scheme is recommended for the new combat mission. Based on the applicability between historical missions and equipment combination schemes, the optimal configuration of the equipment combination scheme and the new combat mission is solved, thereby supporting the maximization of equipment combat effectiveness for specific combat missions and optimizing equipment selection to a certain extent, avoiding resource waste caused by equipment planning deviating from actual mission requirements.

[0084] Example 2

[0085] Embodiment 2 of the present invention provides a method for calculating the interval number of an index based on the interval entropy weight method, the specific process of which is as follows: Figure 3 As shown, it includes the following steps:

[0086] Step S301: Based on the results of multiple measurements of each indicator, construct an interval fuzzy number decision matrix;

[0087] Specifically, the index set Q = Q1, Q2, ..., Q m This includes m indicators, which can be indicators of combat missions or indicators of equipment combination schemes; the set of measurement objects S = S1, S2, ..., Sn is obtained by performing n measurements on each indicator in the indicator set. n The i-th measurement yields the j-th index Q. j The attribute value is the interval number. Constructing an interval fuzzy number decision matrix

[0088]

[0089] Step S302: Calculate the interval number decision matrix. Standardize the process;

[0090] Specifically, if the indicator Qj If it is a benefit-type indicator, then it is calculated according to the following formula 4. Standardization results

[0091]

[0092] Right now:

[0093] If the indicator Q j If it is a cost-type indicator, then it is calculated according to the following formula 5. Standardization results

[0094]

[0095] Right now:

[0096] It can be seen that:

[0097] For example, the set of indicators to be evaluated for a combat mission is Q = {q1,q2,q3,q4,q5}, which are: joint ground capability q1, joint air capability q2, joint maritime capability q3, specific deterrence capability q4, and joint mobility capability q5.

[0098] There are a total of 20 historical combat missions T={t1,t2,...,t 20 The evaluation yielded 20 equipment combination schemes E = {e1, e2, ..., e}. 20} Available for selection;

[0099] According to Formula 4, the interval decision matrix of the historical task is standardized to obtain the normalized interval decision matrix as follows:

[0100]

[0101] Step S303: Calculate the entropy value of each index based on the standardized interval fuzzy number decision matrix;

[0102] Specifically, in order to determine the j-th index Q j entropy value The following two optimization models, as shown in Equation 6-9, can be obtained:

[0103]

[0104]

[0105]

[0106]

[0107] For example, the P mentioned above T The interval entropy values ​​obtained by solving the optimization model according to Formula 6-9 are as follows:

[0108] H T = [[-0.99,0.93],[-0.99,0.94],[-0.99,0.93],[-0.99,0.91],[-0.99,0.94]].

[0109] Step S304: Calculate the interval entropy weight of the indicator based on its entropy value;

[0110] Specifically, the j-th index Q is obtained. j entropy value Then, the j-th indicator Q j Interval entropy weight It can be calculated using the following formula 10:

[0111]

[0112] Formula 10 above can also be written as Formula 11:

[0113]

[0114] For example, the H mentioned above T The interval entropy weight (weight interval) of each indicator can be calculated using Formula 10:

[0115]

[0116] The mean of the attribute weight interval can be selected as the final weight vector, that is:

[0117] ω T =[0.203,0.216,0.165,0.236,0.180].

[0118] Step S305: After normalizing the interval entropy weights of the indicator, the number of intervals of the indicator is obtained.

[0119] Specifically, the j-th indicator Q j Interval entropy weight Normalization is performed, as shown in Formula 12:

[0120]

[0121] In formula 12,

[0122] Formula 12 above can also be written as shown in Formula 13:

[0123]

[0124] Given that the interval number of an indicator in an indicator vector reflects the weight of its attributes, and determining the weight of these attributes is a key issue in multi-attribute decision-making, and considering that decision-makers have different preferences for different indicators, and that different decision-makers often hold different attitudes towards the same indicator, it is difficult for subjectively determined weights of decision indicator attributes to be accepted by most decision-makers.

[0125] Based on this, in the technical solution of Embodiment 2 of the present invention, the interval entropy weight method is used to calculate the degree of dispersion of the indicator attributes in the original data, thereby calculating the number of intervals of the indicators that reflect the weight of the indicator attributes, which has strong objectivity; thus, based on the more objective and accurate number of intervals of the indicators, a more accurate estimate of the applicability between the equipment combination scheme and the new combat mission can be calculated, making the configuration of the equipment combination scheme and the new combat mission more reasonable.

[0126] Example 3

[0127] Embodiment 3 of the present invention provides a method for imputing missing values ​​in the fitness matrix based on an interval collaborative filtering algorithm. The specific process is as follows: Figure 4 As shown, it includes the following steps:

[0128] Step S401: Based on the known suitability between combat missions and equipment combination schemes, establish an initial suitability matrix;

[0129] Specifically, assume that the set of combat missions consisting of m historical combat missions is T = T1, T2, ..., T m The set of n equipment combination schemes is E = E1, E2, ..., E n The j-th equipment combination scheme is applicable to the i-th combat mission T. i The applicability is the interval number Establish an initial fitness matrix composed of interval numbers.

[0130]

[0131] Step S402: Calculate the similarity between two combat missions based on their common applicability; and calculate the similarity between two equipment combination schemes based on their common applicability.

[0132] Specifically, the Pearson correlation coefficient can be used to measure the similarity between combat missions because it is easy to implement and has higher accuracy compared to other similarity calculation methods. This method calculates similarity based on the common applicability between two combat missions a and u, as shown in Formula 14:

[0133]

[0134] In Formula 14, Sim(a,u) represents the similarity between combat mission a and combat mission u, I(a)∩I(u) represents the set of equipment combination schemes that have common applicability between combat missions a and u, and equipment combination scheme i belongs to I(a)∩I(u), r ai This indicates the suitability of equipment combination scheme i for combat mission a. This represents the average applicability of combat mission a. Clearly, Sim(a,u)∈[0,1], and a larger Sim(a,u) value means that combat mission a is more similar to u.

[0135] Among them, the equipment combination scheme with common applicability between combat missions a and u refers to the equipment combination scheme that is judged to have common applicability between combat missions a and u if the applicability between the equipment combination scheme and combat mission a is not missing in the initial applicability matrix, and the applicability between the equipment combination scheme and combat mission u is also not missing.

[0136] Similarly, similarity is calculated based on the common applicability between the two equipment combination schemes i and j, and the specific calculation formula is shown in Formula 15:

[0137]

[0138] In Formula 15, Sim(i,j) represents the similarity between equipment combination schemes i and j, U(i)∩U(j) represents the set of combat missions that have common applicability between equipment combination schemes i and j, and combat mission u belongs to U(i)∩U(j); ui This indicates the suitability of scheme i for combat mission u. Let Sim(i,j) represent the average applicability of scheme i. Clearly, Sim(i,j)∈[0,1], and a larger Sim(i,j) value means that scheme i is more similar to scheme j.

[0139] Among them, the combat mission with common applicability between equipment combination schemes i and j refers to the combat mission being judged to have common applicability between equipment combination schemes i and j if the applicability between a combat mission and equipment combination scheme i is not missing in the initial applicability matrix, and the applicability between the equipment combination scheme and combat mission u is also not missing.

[0140] Furthermore, the inventors of this invention considered that the collaborative filtering algorithm based on Pearson correlation coefficient achieves better results than other algorithms because it takes into account the uniqueness of the suitability of combat missions. However, the Pearson correlation coefficient may overestimate the similarity of combat missions with fewer suitability records. Therefore, as a better implementation, this invention employs a method of adding a significance weighting factor to reduce the weight of similarity between combat missions with fewer suitability records. This method uses the following formulas 16 and 17 to optimize the similarity calculated above, obtaining the optimized similarity calculation result:

[0141]

[0142]

[0143] Here, γ and δ are both set significance adjustment parameters, which can be adjusted appropriately according to the sparsity of the original applicability matrix. For example, the significance adjustment parameter γ = δ = 3 can be set.

[0144] Step S403: For the missing fitness r in the initial fitness matrix ui Based on the similarity between each pair of combat missions, calculate the set of similar nearest neighbors of combat mission u; and based on the similarity between each pair of equipment combination schemes, calculate the set of similar nearest neighbors of equipment combination scheme i.

[0145] Specifically, similar neighbor selection is a crucial step in predicting missing applicability. If the selected similar neighbors have low similarity to the target mission, the prediction of missing applicability will be inaccurate, ultimately affecting the prediction results. To overcome the shortcomings of conventional TopN nearest neighbor selection algorithms, a threshold η is introduced; if the similarity is greater than η, it is selected as a similar neighbor.

[0146] Therefore, for each missing applicability r ui The set S(u) consisting of the similar nearest neighbors of combat mission u is defined as follows: S(u) = {u a |Sim'(u a ,u)>η,u a ≠u};

[0147] Where Sim'(u a ,u) is obtained from the above formula 16, where η is the task similarity threshold.

[0148] Similarly, for each missing applicability r ui The set S(i) of similar nearest neighbors of equipment combination scheme i is defined as follows: S(i) = {i k |Sim'(i k ,i)>θ,i k≠i};

[0149] Where Sim'(i k i) Obtained from Formula 17 above, θ is the scheme similarity threshold. Clearly, the settings of parameters η and θ are crucial; excessively large values ​​will result in insufficient similar neighbors, while excessively small values ​​will result in an excessive number of similar neighbors. The selection of parameters η and θ can be appropriately adjusted based on the sparsity of the original fitness matrix and the prediction results. For example, η = θ = 0.7 can be set.

[0150] Step S404: Based on the applicability of similar neighbors of combat mission u to each equipment combination scheme, and the applicability of similar neighbors of equipment combination scheme i to each combat mission, predict the missing applicability r. ui ;

[0151] Specifically, it is obvious that using only a mission-based approach or only a scenario-based approach to predict missing applicability may overlook valuable information that makes the prediction more accurate. Therefore, in the technical solution of this invention, the two approaches are systematically combined.

[0152] Therefore, in this step, the applicability r of the missing value is... ui Based on the similar nearest neighbor sets S(u) and S(i) of the combat mission u and equipment combination scheme i, the prediction method for missing applicability is as follows:

[0153] if This means that neither the combat mission u nor the equipment combination scheme i has similar nearest neighbors, therefore [0,0] is used as r. ui The predicted value fills r ui .

[0154] if When both the combat mission u and the equipment combination scheme i have similar nearest neighbors, the applicability r is missing. ui The predicted value P(r) ui The calculation is shown in Formula 18:

[0155]

[0156] Where λ is a parameter set with a value range of [0,1], which can adjust the proportion of the two methods based on combat mission and equipment combination scheme; S(u) and S(i) represent the sets of similar nearest neighbors of combat mission u and equipment combination scheme i, respectively. The average applicability of the nearest neighbor a of the combat mission u; The average applicability of the similar nearest neighbors k of equipment combination scheme i is represented; represents the average applicability of combat mission u and equipment combination scheme i in the initial applicability matrix, respectively.

[0157] if When, i.e., the combat mission u has no similar nearest neighbors while the equipment combination scheme i has similar nearest neighbors, the applicability r is missing. ui The predicted value P(r) ui The calculation is shown in Formula 19:

[0158]

[0159] if When a combat mission u has similar neighbors but equipment combination scheme i does not, the applicability r is missing. ui The predicted value P(r) ui The calculation is shown in Formula 20:

[0160]

[0161] Considering that the suitability of equipment to combat missions is an important reference for optimizing the configuration of equipment and combat missions in the equipment combination scheme recommendation problem oriented towards combat missions, in reality, due to the high complexity of equipment performance information and combat mission information, there are often a large number of missing values ​​in the historical mission and equipment suitability matrix. Therefore, how to fill in the missing suitability based on the original suitability data is the key to whether the agile decision-making method of weapon and equipment combination scheme oriented towards combat missions can achieve the optimal configuration of equipment and combat missions.

[0162] Therefore, in the technical solution of Embodiment 3 of the present invention, the interval collaborative filtering algorithm is used to fill in the missing values ​​of the applicability matrix to reduce the sparsity of the original applicability matrix; based on the less sparsity applicability matrix, a more accurate estimate of the applicability between the equipment combination scheme and the new combat mission can be calculated, making the configuration of the equipment combination scheme and the new combat mission more reasonable.

[0163] Example 4

[0164] Figure 5 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0165] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, to execute relevant programs in order to implement the recommended equipment combination scheme for combat missions provided in the embodiments of this specification.

[0166] The memory 1020 can be implemented in the form of ROM (Read-Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0167] The input / output interface 1030 is used to connect input / output modules, which can be connected to a nonlinear receiver to receive information and realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0168] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0169] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0170] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0171] This application also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the steps of the method for recommending equipment combination schemes for combat missions in the embodiments.

[0172] In this embodiment, the computer-readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the computer-readable storage medium can be an internal storage unit of a computer device, such as the hard disk or memory of the computer device. In other embodiments, the computer-readable storage medium can also be an external storage device of the computer device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the computer device. Of course, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the computer device. In this embodiment, the computer-readable storage medium is typically used to store the operating system and various application software installed on the computer device, such as the program code of the equipment combination scheme recommendation method for combat missions in this embodiment. In addition, the computer-readable storage medium can also be used to temporarily store various types of data that have been output or will be output.

[0173] In the technical solution of this invention, for a new combat mission, similar missions are identified from historical combat missions; for each candidate equipment combination scheme, based on the applicability between the similar mission and the equipment combination scheme, and the similarity between the similar mission and the new combat mission, an estimated value of the applicability between the equipment combination scheme and the new combat mission is calculated; based on the calculated estimated value, an equipment combination scheme is recommended for the new combat mission. Based on the applicability between historical missions and equipment combination schemes, the optimal configuration of the equipment combination scheme and the new combat mission is solved, thereby supporting the maximization of equipment combat effectiveness for specific combat missions and optimizing equipment selection to a certain extent, avoiding resource waste caused by equipment planning deviating from actual mission requirements.

[0174] More preferably, in the technical solution of the present invention, the interval entropy weight method is used to calculate the degree of dispersion of the indicator attributes in the original data, thereby calculating the number of intervals of the indicators that reflect the weight of the indicator attributes, which has strong objectivity; thus, based on the more objective and accurate number of intervals of the indicators, a more accurate estimate of the applicability between the equipment combination scheme and the new combat mission can be calculated, making the configuration of the equipment combination scheme and the new combat mission more reasonable.

[0175] More preferably, in the technical solution of the present invention, the interval collaborative filtering algorithm is used to fill in the missing values ​​of the applicability matrix to reduce the sparsity of the original applicability matrix; based on the less sparsity applicability matrix, a more accurate estimate of the applicability between the equipment combination scheme and the new combat mission can be calculated, making the configuration of the equipment combination scheme and the new combat mission more reasonable.

[0176] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0177] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this disclosure (including the claims) is limited to these examples; within the framework of this invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in the details for the sake of brevity.

[0178] Additionally, to simplify the description and discussion, and to avoid obscuring the invention, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the invention, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which the invention will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) are set forth to describe exemplary embodiments of the invention, it will be apparent to those skilled in the art that the invention may be practiced without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0179] Although the invention has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0180] The embodiments of this invention are intended to cover all such substitutions, modifications, and variations falling within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for recommending equipment combination schemes for combat missions, comprising: To address new combat missions, identify similar missions from historical combat missions; For each alternative equipment combination scheme, based on the applicability between the similar mission and the equipment combination scheme, and the similarity between the similar mission and the new combat mission, an estimated value of the applicability between the equipment combination scheme and the new combat mission is calculated. Based on the calculated estimates, recommend equipment combination schemes for new combat missions; The calculation of the estimated applicability of the equipment combination scheme to the new combat mission based on the applicability between the similar mission and the equipment combination scheme, and the similarity between the similar mission and the new combat mission, specifically includes: Calculate the equipment combination scheme according to the following formula 3. Estimates of suitability with new operational missions : (Formula 3) In formula 3, Indicates a new combat mission. This refers to a set of similar missions identified from historical combat missions. Indicates combat mission Equipment combination scheme Applicability between them; Indicates the similarity between calculated combat missions; The fitness score is extracted from the fitness matrix; and the fitness matrix is ​​specifically obtained after imputing missing values ​​using an interval collaborative filtering algorithm.

2. The method according to claim 1, characterized in that, The method of identifying similar tasks from historical combat missions in response to new combat missions specifically includes: Based on the indicator vector of each combat mission, the similarity between combat missions is calculated; Based on the similarity between combat missions, the interval fuzzy set agglomerative hierarchical clustering algorithm is used to cluster the combat missions. In the clustering results, each combat mission in the cluster containing the new combat mission is identified as a similar mission to the new combat mission.

3. The method according to claim 2, characterized in that, The indicator vector for the combat mission includes multiple vector elements, each vector element corresponding to an interval number of an indicator; and The interval number of the indicator is specifically calculated using the interval entropy weight method.

4. The method according to claim 3, characterized in that, The interval number of the indicator is calculated using the following method: Based on the results of multiple measurements of each indicator, an interval fuzzy number decision matrix is ​​constructed; Standardize the interval number decision matrix; Based on the standardized interval fuzzy number decision matrix, the entropy value of each indicator is calculated; Calculate the interval entropy weight of the indicator based on its entropy value; After normalizing the interval entropy weights of the indicators, the interval number of the indicators is obtained.

5. The method according to claim 1, characterized in that, The fitness matrix is ​​imputed for missing values ​​using the following method: Based on the known suitability between combat missions and equipment combination schemes, an initial suitability matrix is ​​established. Calculate the similarity between pairs of combat missions based on their common applicability. And based on the common applicability between two equipment combination schemes, calculate the similarity between two equipment combination schemes; For the missing applicability in the initial applicability matrix Based on the similarity between pairs of combat missions, calculate the combat mission. The set of similar nearest neighbors; and the calculation of equipment combination schemes based on the similarity between pairwise equipment combination schemes. A set of similar nearest neighbors; Based on combat mission The applicability of similar neighbors to various equipment combination schemes, and the equipment combination schemes The applicability of similar neighbors to various combat missions, predicting the missing applicability. .

6. The method according to claim 5, characterized in that, Based on combat missions The applicability of similar neighbors to various equipment combination schemes, and the equipment combination schemes The applicability of similar neighbors to various combat missions, predicting the missing applicability. Specifically, it includes: if Then there is a lack of applicability. Predicted value The calculation is shown in Formula 18: if Time, i.e., combat mission There is no similar nearest neighbor equipment combination scheme The existence of similar nearest neighbors results in a lack of applicability. Predicted value The calculation is shown in Formula 19: if Time, i.e., combat mission There are similar neighboring equipment combination schemes In the absence of similar nearest neighbors, there is a lack of applicability. Predicted value The calculation is shown in Formula 20: in The set value range is The parameters can be adjusted to vary the proportion between the two methods: combat mission-based and equipment combination-based. , They represent combat missions. Equipment combination scheme The set of similar nearest neighbors; Indicates combat mission Similar neighbors Average applicability; Indicates equipment combination scheme Similar neighbors Average applicability; , These represent the combat missions in the initial suitability matrix. Equipment combination scheme Average applicability.

7. An electronic device comprising a central processing unit, a signal processing and storage unit, and a computer program stored on the signal processing and storage unit and executable on the central processing unit, characterized in that, When the central processing unit executes the program, it implements the method as described in any one of claims 1-6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that can be executed by at least one processor to cause the at least one processor to perform the steps of the method for recommending equipment combination schemes for combat missions as described in any one of claims 1-6.

Images