Dynamic weight updating method and system for comprehensive disguise evaluation indexes

Abstract

The invention discloses a dynamic weight updating method, system and device for comprehensive disguise evaluation indexes and a storage medium, and the method comprises the steps: predetermining the initial weight of each index element in an evaluation index element complete set based on an expert consultation method, so as to build an initial disguise comprehensive evaluation model; determining an evaluation index element subset according to the basic information of the to-be-evaluated target; determining at least one invalid index by comparing an evaluation index element subset with the evaluation index element complete set, wherein the index elements in the evaluation index element subset are valid indexes; redistributing the initial weight of the at least one invalid index to the valid index according to a set weight distribution rule so as to establish a new camouflage comprehensive evaluation model; according to the method, the problem that the weight is difficult to readjust due to standard change in the camouflage comprehensive evaluation model is solved, and the application range of the whole comprehensive evaluation model is widened.

Description

Technical Field

[0001] The present invention relates to the technical field of camouflage evaluation, and in particular to a method and system for updating dynamic weights of comprehensive camouflage evaluation indicators. Background Art

[0002] Camouflage evaluation often requires combining multiple indicators into one indicator to evaluate the camouflage effect of the target. The most commonly used camouflage evaluation method is the camouflage evaluation comprehensive model, which combines multiple indicator elements such as optics, infrared, radar, and structure. The current camouflage evaluation comprehensive model mainly uses a large number of expert consultations to obtain the initial weights of the indicator elements in the model, and uses group decision-making methods to combine the initial weight results of a large number of experts into the final weights of the model indicators. The group decision-making methods include hierarchical analysis, BP neural network, genetic method, etc. The establishment of a camouflage evaluation comprehensive model requires a large number of expert participation, data processing and statistical analysis, and consumes a lot of manpower, financial resources and time. However, this evaluation model is often only applicable to one goal or task. When the evaluation goal or task changes, it is necessary to re-consult with experts and other processes, resulting in a waste of time and manpower.

[0003] Therefore, there is an urgent need to develop a dynamic weight updating method and system for comprehensive camouflage evaluation indicators to solve the above-mentioned problems. Summary of the invention

[0004] The purpose of the present invention is to provide a dynamic weight updating method and system for comprehensive camouflage evaluation indicators, so as to solve the technical problem that the evaluation model in the prior art is only applicable to one target or task, and when the evaluation target or task changes, it is necessary to re-consult with experts and other processes, resulting in a waste of time and manpower.

[0005] To achieve the above object, the present invention provides a method for updating the dynamic weight of a comprehensive camouflage evaluation index, the method comprising:

[0006] Step S1: predetermine the initial weight of each indicator element in the entire set of evaluation indicator elements based on the expert consultation method to establish an initial camouflage comprehensive evaluation model;

[0007] Step S2: Determine a subset of evaluation index elements based on the basic information of the target to be evaluated;

[0008] Step S3: determining at least one invalid indicator by comparing the evaluation indicator element subset with the entire set of evaluation indicator elements, wherein the indicator elements in the evaluation indicator element subset are valid indicators;

[0009] Step S4: reallocate the initial weight of at least one invalid indicator to the valid indicator according to the set weight allocation rule to obtain a new weight of the valid indicator, and then establish a new camouflage comprehensive evaluation model.

[0010] Optionally, in step S4, the set weight distribution rule is an average weight distribution method;

[0011] Assume there are N indicator elements, and the initial weight of the i-th indicator element is w i , i = 1 ~ N; if the jth indicator element is an invalid indicator, j = 1 ~ N and i ≠ j, the new weight w of the valid indicator is determined according to the average weighting method i 'for:

[0012]

[0013] Among them, the initial weight of the invalid indicator is w j , the number of valid indicators is M, M <N。

[0014] Optionally, in step S4, the set weight allocation rule is a linear decentralization method;

[0015] Assume there are N indicator elements, and the initial weight of the i-th indicator element is w i , i = 1 ~ N; if the jth indicator element is an invalid indicator, j = 1 ~ N and i ≠ j, the new weight w of the valid indicator is determined according to the linear decentralization method i 'for:

[0016]

[0017] Among them, the initial weight of the invalid indicator is w j , the number of valid indicators is M, M <N,∑ i≠j w i is the sum of the initial weights of the valid indicators.

[0018] Optionally, in step S4, the set weight distribution rule is a nonlinear weighting method;

[0019] Assume there are N indicator elements, and the initial weight of the i-th indicator element is w i , i = 1 to N; the correlation matrix representing the correlation between the indicator elements is R, and the new weight w of the effective indicator is determined according to the nonlinear decentralization method i 'for

[0020]

[0021] Among them, v ijIt is the element in the i-th row and j-th column of the correlation matrix R, representing the i-th component of the j-th eigenvector.

[0022] Optionally, the method further comprises:

[0023] Step S5: using the new camouflage comprehensive evaluation model to evaluate the effective index to obtain an actual evaluation result of the effective index;

[0024] Step S6: dynamically updating the new weight of the effective indicator based on the actual evaluation result of the effective indicator.

[0025] Optionally, the step S6 specifically includes: dynamically updating the new weight of the effective indicator based on the relative error between the actual evaluation result of the effective indicator and the preset expected result.

[0026] Optionally, the step S6 specifically includes: dynamically updating the new weight of the effective indicator based on the difference between the actual evaluation result of the effective indicator and the mean of the actual evaluation results of the effective indicator.

[0027] On the other hand, the present invention also provides a dynamic weight updating system for comprehensive camouflage evaluation index, the system comprising:

[0028] An initial model building module is configured to predetermine the initial weight of each indicator element in the entire set of evaluation indicator elements based on an expert consultation method to establish an initial camouflage comprehensive evaluation model;

[0029] An indicator subset determination module is configured to determine an evaluation indicator element subset based on basic information of the target to be evaluated;

[0030] an invalid indicator determination module, which determines at least one invalid indicator by comparing the evaluation indicator element subset with the evaluation indicator element full set, wherein the indicator elements in the evaluation indicator element subset are valid indicators;

[0031] The weight updating module is configured to reallocate the initial weight of at least one invalid indicator to the valid indicator according to a set weight allocation rule to obtain a new weight of the valid indicator, thereby establishing a new camouflage comprehensive evaluation model.

[0032] On the other hand, the present invention also provides an electronic device, including: a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the dynamic weight updating method of the comprehensive camouflage evaluation index as described above is implemented.

[0033] In yet another aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for dynamically updating the weight of the comprehensive camouflage evaluation index as described above is implemented.

[0034] The method of the present invention has the following advantages:

[0035] The dynamic weight updating method of the comprehensive camouflage evaluation index proposed by the present invention first predetermines the initial weight of each indicator element in the full set of evaluation indicator elements based on the expert consultation method to establish an initial camouflage comprehensive evaluation model; then determines the evaluation indicator element subset according to the basic information of the target to be evaluated; then determines at least one invalid indicator by comparing the evaluation indicator element subset with the full set of evaluation indicator elements, and the indicator elements in the evaluation indicator element subset are valid indicators, thereby determining the deviation situation, and finally reallocates the initial weight of at least one invalid indicator to the valid indicator according to the set weight allocation rule to establish a new camouflage comprehensive evaluation model; the method is a method for adjusting different weights or parameters in decision-making or optimization problems to better adapt to changes in different task requirements. The method dynamically updates the weights of each indicator element according to the correlation between the indicator elements in the current full set of evaluation indicators to solve the problem that the weights are difficult to readjust due to standard changes in the camouflage comprehensive evaluation model, and improves the scope of application of the entire comprehensive evaluation model, so that when the evaluation target or task changes, it is no longer necessary to re-conduct the expert consultation process, saving time and labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of a flow chart of a method for updating a dynamic weight of a comprehensive camouflage evaluation index according to an embodiment of the present invention;

[0037] Figure 2 It is a structural block diagram of a dynamic weight updating system of a comprehensive camouflage evaluation index according to an embodiment of the present invention;

[0038] Figure 3 It is a schematic diagram of an electronic device application according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention. In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0040] On the one hand, see Figure 1 As shown, an embodiment of the present invention provides a method for updating a dynamic weight of a comprehensive camouflage evaluation index, the method comprising:

[0041] Step S1: predetermine the initial weight of each indicator element in the entire set of evaluation indicator elements based on the expert consultation method to establish an initial camouflage comprehensive evaluation model;

[0042] In this embodiment, it is necessary to first determine the full set of evaluation index elements U (U = {u1, u2, ...., u n}), and each indicator element u in the whole set i The weight of (i=1~n). The index elements involved are shown in Table 1 below:

[0043]

[0044]

[0045]

[0046] The following steps can usually be taken to obtain the indicator elements and their initial weights:

[0047] 1. Expert selection: Invite experts with experience in related fields, such as military experts, camouflage technicians, environmental scientists, etc.

[0048] 2. Questionnaire design: Design a questionnaire to ask experts to assess the importance of each indicator element. For example, a scoring system of 1 to 100 can be used, with 1 representing not important and 100 representing very important.

[0049] 3. Data collection: Collect and organize the experts’ ratings.

[0050] 4. Weighted average: Calculate the initial weight of each indicator element. The weighted average formula can be used for calculation. The specific formula is:

[0051]

[0052] Among them, w i is the indicator u i The initial weight, s ij is the jth expert's opinion on indicator factor u i The score of , m is the number of experts.

[0053] In order to make the sum of all weights equal to 1, the initial weights can also be normalized.

[0054] Step S2: Determine a subset of evaluation index elements based on the basic information of the target to be evaluated;

[0055] In this embodiment, when facing different evaluation objects or task objectives, corresponding evaluation index element subsets U are formulated. I , this subset comes from the full set of evaluation index elements, namely Therefore, some indicators may not exist, that is, invalid indicators, for example: U I ={u1,u3,u5,...,u n}.

[0056] In this embodiment, the basic information of the target to be evaluated specifically includes:

[0057] 1. Clarify the target to be evaluated: Understand the usage scenarios and requirements of the target to be evaluated in specific tasks, such as camouflage, detection or other purposes.

[0058] 2. Analyze the characteristics of the target to be evaluated: Identify the basic information of the target to be evaluated, such as type (vehicle, building, person), material, shape, size and functional characteristics.

[0059] 3. Consider environmental factors: Evaluate the environmental conditions of the target to be evaluated, such as light, geographical environment (city, forest, mountainous area), climate conditions (temperature, humidity, rainfall), etc.

[0060] 4. Reference historical data: Analyze historical evaluation data of similar targets in similar environments and tasks.

[0061] Select relevant indicators based on the above basic information, specifically: select the most relevant evaluation indicators according to the characteristics of the task or target and environment to be evaluated. For example, for camouflage tasks, the focus may be on color matching and texture similarity, while for detection tasks, the focus may be on the target's reflective characteristics and shape matching. Then formulate a subset of indicator elements, that is, group the selected indicator elements into subsets to ensure that these indicator elements can effectively evaluate the performance of the target to be evaluated in a specific task.

[0062] It should be noted that the above basic information may also include weight adjustment factors, that is, factors that determine the weights of evaluation indicators, such as the importance of the target, task priority, the impact of environmental changes on camouflage effects, etc. These factors will determine the dynamic weights of evaluation indicators.

[0063] For example, for the evaluation of equipment camouflage effect, the main indicator element subsets may include the following indicator elements:

[0064] A: Visibility, which evaluates the visibility of equipment under different environmental conditions.

[0065] B: Background fusion, the degree of fusion between equipment and background.

[0066] C: Target identification difficulty, the difficulty of the enemy identifying equipment.

[0067] D: Camouflage material characteristics, optical, thermal and electromagnetic properties of camouflage materials.

[0068] E: Environmental adaptability, the performance of camouflage effect in various weather and terrain conditions.

[0069] F: Camouflage persistence, the change and durability of camouflage effect over time.

[0070] Step S3: determining at least one invalid indicator by comparing the evaluation indicator element subset with the entire set of evaluation indicator elements, wherein the indicator elements in the evaluation indicator element subset are valid indicators;

[0071] In this embodiment, by comparing the evaluation index element subset U I Determine the invalid indicators with the full set of evaluation index elements U, for example: invalid indicators are u2, u4…, so that it can be determined that there is a deviation between the current solution and the target.

[0072] Step S4: reallocate the initial weight of at least one invalid indicator to the valid indicator according to the set weight allocation rule to obtain a new weight of the valid indicator, and then establish a new camouflage comprehensive evaluation model.

[0073] To address the above deviations, the weights of invalid indicators are reset to 0, and their reduced weights are redistributed to other valid indicators according to the set weight distribution rules to generate a new camouflage comprehensive evaluation model.

[0074] The purpose of the embodiment of the present invention to provide a dynamic weight update method for comprehensive camouflage evaluation indicators is to enable the system to better approach the target or optimize performance. In practical applications, we often face multiple participants or factors, and the importance or contribution between them may change with the evaluation object and the purpose of the task. For example, the evaluation of a certain engineering target or equipment target will have different evaluation index compositions due to different targets. If expert consultation is used again to confirm the indicator weights, it will consume a lot of manpower, time and energy. Therefore, in order to make decisions or analyses more quickly and objectively, the weights are dynamically updated according to the correlation principle to form a new comprehensive evaluation model for camouflage effects.

[0075] It should be noted that the meaning of the correlation principle refers to the degree of association between two indicators, such as brightness contrast and grayscale similarity. These two indicators are used to characterize the difference in brightness between the target and the background image. The larger the brightness contrast, the lower the grayscale similarity tends to be. In other words, these two indicators both characterize the difference between the target and the background, and there will be a certain correlation.

[0076] For this special case, a method needs to be designed: for the generated deviation, the weight of the invalid indicator is reset to 0, and its reduced weight is redistributed to other valid indicators according to specific rules to generate a new camouflage effect comprehensive evaluation model. According to the characteristics of the indicator elements, this paper proposes three weight allocation methods: average weighting method, linear weighting method and nonlinear weighting method.

[0077] Optionally, in the method for updating the dynamic weight of the comprehensive camouflage evaluation index of the embodiment of the present invention, in step S4, the weight distribution rule set is the average weight distribution method;

[0078] Assume there are N indicator elements, and the initial weight of the i-th indicator element is w i , i = 1 ~ N; if the jth indicator element is an invalid indicator, j = 1 ~ N and i ≠ j, the new weight w of the valid indicator is determined according to the average weighting method i 'for:

[0079]

[0080] Among them, the initial weight of the invalid indicator is w j , the number of valid indicators is M, M <N。

[0081] Specifically, the average weighting method is suitable for dealing with situations where certain indicators are invalid or non-existent. The basic idea is to distribute the weights that should have been assigned to invalid indicators evenly to all other valid indicators to keep the total weight unchanged.

[0082] Assume there are N indicators, and the initial weight vector is: w = (w1, w2, ..., w N )

[0083] where w i represents the initial weight of the i-th indicator. If the j-th indicator is invalid, the weight can be redistributed according to the following rules based on the average weighting method:

[0084] First, calculate the number of valid indicators M, that is, M = N-1;

[0085] Then, the weight w of the invalid indicator j is j Set to 0;

[0086] For other valid indicators i, the new weight w i The calculation is shown in formula (1).

[0087] For example, if the total number of indicators is 5 and the number of invalid indicators is 1, then the number of valid indicators is 4. Assume that the invalid indicator w j The initial weight is 0.1, and the effective index w i The initial weight is 0.2, then, according to the average weighting method, the effective index wi The new weight of is 0.225.

[0088] Optionally, in the method for updating the dynamic weight of the comprehensive camouflage evaluation index of the embodiment of the present invention, in step S4, the weight allocation rule set is a linear decentralization method;

[0089] Assume there are N indicator elements, and the initial weight of the i-th indicator element is w i , i = 1 ~ N; if the jth indicator element is an invalid indicator, j = 1 ~ N and i ≠ j, the new weight w of the valid indicator is determined according to the linear decentralization method i 'for:

[0090]

[0091] Among them, the initial weight of the invalid indicator is w j , the number of valid indicators is M, M <N,∑ i≠j w i is the sum of the initial weights of the valid indicators.

[0092] Specifically, the linear decentralization method allocates the weights of invalid indicators to other valid indicators according to certain linear rules, and allocates them based on the initial weights of the invalid indicators.

[0093] Assume there are N indicators, and the initial weight vector is: w = (w1, w2, ..., w N )

[0094] where w i Represents the initial weight of the i-th indicator. If the j-th indicator is invalid, according to the linear decentralization method, the weight can be redistributed according to the following rules:

[0095] First, determine the initial weight w of the invalid indicator j j ;

[0096] Then, calculate the initial weight sum of the effective indicators ∑ i≠j w i ;

[0097] For other valid indicators i, the new weight w` i The calculation is shown in the above formula (2).

[0098] For example, the number of invalid indicators is 1, and the invalid indicator w j The initial weight is 0.1, and the effective index w i The initial weight of is 0.2, and the sum of the initial weights of the effective indicators is ∑ i≠j w i is 2. According to the average weighting method, the new weight of the effective indicator is 0.21.

[0099] Optionally, in the method for updating the dynamic weight of the comprehensive camouflage evaluation index of the embodiment of the present invention, in step S4, the weight distribution rule set is a nonlinear weighting method;

[0100] Assume there are N indicator elements, and the initial weight of the i-th indicator element is w i , i = 1 to N; the correlation matrix representing the correlation between the indicator elements is R, and the new weight w of the effective indicator is determined according to the nonlinear decentralization method i 'for

[0101]

[0102] Among them, v ij It is the element in the i-th row and j-th column of the correlation matrix R, representing the i-th component of the j-th eigenvector.

[0103] Specifically, the indicator relevance decentralization method is a weight redistribution method that takes into account the relevance between indicators. In this method, the weight of each indicator is not only based on its own importance, but also takes into account the degree of relevance with other indicators to more accurately reflect the contribution of each indicator to the overall evaluation.

[0104] Assume there are N indicators, and the initial weight vector is: w = (w1, w2, ..., w N )

[0105] The correlation matrix R describes the correlation between the indicators and is used to measure the linear relationship between multiple variables. The correlation matrix R is an N*N matrix, where R ij represents the correlation coefficient between indicator i and indicator j. The new weight w of indicator i i It can be calculated by following the steps below:

[0106] (1) Collect data: Prepare a data set where each row represents a sample and each column represents a variable.

[0107] (2) Standardizing data: Calculate the mean and standard deviation of each variable and transform the data into a standard normal distribution with zero mean and unit variance.

[0108] (3) Calculate the covariance matrix: For two variables X and Y, the covariance formula is:

[0109]

[0110] Where n is the number of samples, and is the mean of X and Y.

[0111] (4) Calculate the correlation coefficient: The correlation coefficient formula is:

[0112] Corr(X,Y)=(Cov(X,Y)) / (σ_Xσ_Y) (6)

[0113] where σ_X and σ_Y are the standard deviations of X and Y.

[0114] (5) Construct the correlation matrix: Each element r in the matrix ij It represents the correlation coefficient between the i-th variable and the j-th variable.

[0115] (6) Calculate the eigenvalue decomposition of the correlation matrix R and obtain the eigenvalues ​​γ1, γ2, …, γ N and the corresponding eigenvectors v1, v2, ..., v N .

[0116] According to the initial weight w of indicator i i and the eigenvector v of the correlation matrix i , calculate the new weight w` i As shown in the above formula (3).

[0117] For example, take the index elements involved in the physical characteristics evaluation under optics as an example:

[0118] Indicator name Initial weight of indicators Is it effective? New weights (correlation matrix) Chromatic Aberration 22.01％ yes 23.84％ Average brightness contrast 12.10％ no 0.00％ Spectral brightness contrast 2.69％ yes 4.16％ Spectral distance 14.42％ yes 17.36％ Spectral angle 5.15％ yes 7.72％ Spectral channels 17.12％ yes 18.95％ Brightness coefficient 4.7％ yes 5.06％ Spot size 21.81％ yes 22.91％

[0119] The corresponding correlation matrix R:

[0120]

[0121]

[0122] Optionally, the method for updating the dynamic weight of the comprehensive camouflage evaluation index of the embodiment of the present invention further includes:

[0123] Step S5: using the new camouflage comprehensive evaluation model to evaluate the effective index to obtain an actual evaluation result of the effective index;

[0124] Step S6: dynamically updating the new weight of the effective indicator based on the actual evaluation result of the effective indicator.

[0125] Optionally, step S6 in the dynamic weight updating method of the comprehensive camouflage evaluation index in the embodiment of the present invention is specifically: dynamically updating the new weight of the effective index based on the relative error between the actual evaluation result of the effective index and the preset expected result.

[0126] Specifically, the formula for dynamically updating the weight in this embodiment can be expressed as:

[0127]

[0128] Where: wi is the current weight of the i-th indicator element, w i ' is the updated weight of the i-th indicator element, β is the adjustment factor used to control the magnitude of the weight update, E i is the actual evaluation result of the i-th indicator element, It is the preset expected result of the i-th indicator element.

[0129] Among them, the formula It represents the relative error between the actual evaluation result and the preset expected result. The adjustment factor β determines the strength of the update. If the actual result is higher than the expected result, the weight will increase, otherwise it will decrease.

[0130] Optionally, in the method for updating the dynamic weight of the comprehensive camouflage evaluation index in the embodiment of the present invention, step S6 is specifically: dynamically updating the new weight of the effective index based on the difference between the actual evaluation result of the effective index and the mean of the actual evaluation result of the effective index.

[0131] Specifically, the formula for dynamically updating the weight in this embodiment can be expressed as:

[0132] w` i =w i +k·(E i -E) (8)

[0133]

[0134] in, is the mean of the actual evaluation results of the effective indicators; k is the adjustment factor that controls the intensity of the update; this formula determines whether to increase or decrease the weight of the indicator by comparing the actual evaluation results of each indicator element with the mean result.

[0135] In summary, the dynamic weight updating method of the comprehensive camouflage evaluation index proposed in the embodiment of the present invention first predetermines the initial weight of each indicator element in the full set of evaluation indicator elements based on the expert consultation method to establish an initial camouflage comprehensive evaluation model; then determines the evaluation indicator element subset according to the basic information of the target to be evaluated; then determines at least one invalid indicator by comparing the evaluation indicator element subset with the full set of evaluation indicator elements, and the indicator elements in the evaluation indicator element subset are valid indicators, thereby determining the deviation situation, and finally reallocates the initial weight of at least one invalid indicator to the valid indicator according to the set weight allocation rule to establish a new camouflage comprehensive evaluation model; the dynamic weight updating method is a method used to adjust different weights or parameters in decision-making or optimization problems to better adapt to changes in different task requirements. The dynamic weight updating method of the comprehensive camouflage evaluation index proposed in the embodiment of the present invention dynamically updates the weights of each indicator element according to the correlation between the indicator elements in the current full set of evaluation indicators, so as to solve the problem that the weights are difficult to readjust due to the change of standards in the camouflage comprehensive evaluation model, and improves the scope of application of the entire comprehensive evaluation model, so that when the evaluation target or task changes, it is no longer necessary to re-conduct the expert consultation process, saving time and labor costs.

[0136] On the other hand, see Figure 2 As shown, the embodiment of the present invention also provides a dynamic weight updating system for comprehensive camouflage evaluation indicators, the system comprising:

[0137] The initial model building module 10 is configured to predetermine the initial weight of each indicator element in the entire set of evaluation indicator elements based on the expert consultation method to establish an initial camouflage comprehensive evaluation model;

[0138] The indicator subset determination module 20 is configured to determine the evaluation indicator element subset according to the basic information of the target to be evaluated;

[0139] An invalid indicator determination module 30 determines at least one invalid indicator by comparing the evaluation indicator element subset with the evaluation indicator element full set, wherein the indicator elements in the evaluation indicator element subset are valid indicators;

[0140] The weight updating module 40 is configured to reallocate the initial weight of at least one invalid indicator to the valid indicator according to a set weight allocation rule to obtain a new weight of the valid indicator, thereby establishing a new camouflage comprehensive evaluation model.

[0141] On the other hand, an embodiment of the present invention further provides an electronic device, including: a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, a dynamic weight updating method for a comprehensive camouflage evaluation index as described in the above embodiment is implemented.

[0142] Figure 3 is a structural diagram of an electronic device according to an embodiment of the present invention, such as Figure 3 As shown, the electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, near field communication (NFC) or other technologies. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc. Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a structural diagram of the part related to the technical solution of the present disclosure, and does not constitute a limitation on the electronic device to which the technical solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0143] On the other hand, the embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the dynamic weight updating method of the comprehensive camouflage evaluation index as described in the above embodiment is implemented. A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0144] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A dynamic weight updating method for comprehensive camouflage evaluation index, characterized in that: The method comprises: Step S1: predetermine the initial weight of each indicator element in the entire set of evaluation indicator elements based on the expert consultation method to establish an initial camouflage comprehensive evaluation model; Step S2: Determine a subset of evaluation index elements based on the basic information of the target to be evaluated; Step S3: determining at least one invalid indicator by comparing the evaluation indicator element subset with the entire set of evaluation indicator elements, wherein the indicator elements in the evaluation indicator element subset are valid indicators; Step S4: reallocate the initial weight of at least one invalid indicator to the valid indicator according to the set weight allocation rule to obtain a new weight of the valid indicator, and then establish a new camouflage comprehensive evaluation model.

2. The dynamic weight updating method of the comprehensive camouflage evaluation index according to claim 1 is characterized in that: In step S4, the set weight distribution rule is the average weight distribution method; Assume there are N indicator elements, and the initial weight of the i-th indicator element is w i , i = 1 ~ N; if the jth indicator element is an invalid indicator, j = 1 ~ N and i ≠ j, the new weight w of the valid indicator is determined according to the average weighting method i 'for: Among them, the initial weight of the invalid indicator is w j , the number of valid indicators is M, M <N。 3. The dynamic weight updating method of the comprehensive camouflage evaluation index according to claim 1 is characterized in that: In the step S4, the set weight distribution rule is a linear decentralization method; Assume there are N indicator elements, and the initial weight of the i-th indicator element is w i , i = 1 ~ N; if the jth indicator element is an invalid indicator, j = 1 ~ N and i ≠ j, the new weight w of the valid indicator is determined according to the linear decentralization method i 'for: Among them, the initial weight of the invalid indicator is w j , the number of valid indicators is M, M <N,∑ i≠j w i is the sum of the initial weights of the valid indicators.

4. The dynamic weight updating method of the comprehensive camouflage evaluation index according to claim 1 is characterized in that: In the step S4, the set weight distribution rule is a nonlinear weighting method; Assume there are N indicator elements, and the initial weight of the i-th indicator element is w i , i = 1 to N; the correlation matrix representing the correlation between the indicator elements is R, and the new weight w of the effective indicator is determined according to the nonlinear decentralization method i ’ for Among them, v ij It is the element in the i-th row and j-th column of the correlation matrix R, representing the i-th component of the j-th eigenvector.

5. The dynamic weight updating method of the comprehensive camouflage evaluation index according to any one of claims 1 to 4, characterized in that: The method further comprises: Step S5: using the new camouflage comprehensive evaluation model to evaluate the effective index to obtain an actual evaluation result of the effective index; Step S6: dynamically updating the new weight of the effective indicator based on the actual evaluation result of the effective indicator.

6. The dynamic weight updating method of the comprehensive camouflage evaluation index according to claim 5 is characterized in that: The step S6 specifically includes: dynamically updating the new weight of the effective indicator based on the relative error between the actual evaluation result of the effective indicator and the preset expected result.

7. The dynamic weight updating method of the comprehensive camouflage evaluation index according to claim 5 is characterized in that: The step S6 specifically includes: dynamically updating the new weight of the effective indicator based on the difference between the actual evaluation result of the effective indicator and the mean of the actual evaluation result of the effective indicator.

8. A dynamic weight updating system for comprehensive camouflage evaluation index, characterized in that: The system comprises: An initial model building module is configured to predetermine the initial weight of each indicator element in the entire set of evaluation indicator elements based on an expert consultation method to establish an initial camouflage comprehensive evaluation model; An indicator subset determination module is configured to determine an evaluation indicator element subset based on basic information of the target to be evaluated; an invalid indicator determination module, which determines at least one invalid indicator by comparing the evaluation indicator element subset with the evaluation indicator element full set, wherein the indicator elements in the evaluation indicator element subset are valid indicators; The weight updating module is configured to reallocate the initial weight of at least one invalid indicator to the valid indicator according to a set weight allocation rule to obtain a new weight of the valid indicator, thereby establishing a new camouflage comprehensive evaluation model.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the dynamic weight updating method of the comprehensive camouflage evaluation index according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the dynamic weight updating method of the comprehensive camouflage evaluation index as described in any one of items 1-7 is implemented.

Images