Intelligent evaluation-based target strike prioritization method, apparatus, device, and medium

Abstract

The application discloses a target attack priority ranking method and device based on intelligent evaluation, equipment and a medium, and relates to the technical field of data processing.The method comprises the following steps: a target attack priority ranking evaluation index system is constructed; the evaluation index system comprises first-layer indexes and second-layer indexes; the first-layer indexes at least comprise category-type indexes, and the second-layer indexes are used for predicting and evaluating the category-type indexes in the first-layer indexes; a target evaluation decision matrix is constructed based on the first-layer indexes, wherein the values of the category-type indexes in the first-layer indexes are calculated by using an intelligent evaluation method based on a neural network; the weights of the first-layer indexes are calculated by using an entropy weight method; the closeness degrees of the targets are calculated by using a TOPSIS method; the comprehensive correlation degrees of the targets are calculated by using a grey correlation analysis method; the comprehensive evaluation values of the targets are weighted and calculated based on the closeness degrees and the comprehensive correlation degrees; and the targets are ranked according to the comprehensive evaluation values. The application greatly improves the scientificity, objectivity and reliability of the target ranking result.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, device and medium for prioritizing target strikes based on intelligent assessment. Background Technology

[0002] In target strike decision-making scenarios, how to scientifically, quickly, and accurately prioritize targets to ensure the scientific, objective, and reliable nature of the prioritization decision is of great significance for improving target strike effectiveness and optimizing resource utilization.

[0003] In related technologies, patent application CN117991201A discloses a dynamic assessment method for multi-target threats in the air based on an improved TOPSIS. This method can dynamically assess the threat level of multiple targets in the air according to changes in the electromagnetic environment. It takes into account the correlation between threats from air targets and the advantages of reasonably classifying each target according to its threat level.

[0004] However, the types of targets that need to be dealt with in reality are diverse (land, surface / underwater, etc., not limited to air), and this method is difficult to apply to non-air targets; moreover, the ranking conclusions based only on target threat-related indicators tend to overlook high-value targets that are not currently a significant threat, or targets that are easy to strike and can produce significant effects, thus causing a certain degree of decision-making bias and limitations.

[0005] Furthermore, the evaluation system inevitably involves qualitative indicators such as "objective importance." Existing methods typically quantify this by having experts score the data directly or by assigning levels (e.g., 5 levels). However, the specific values ​​assigned to each objective during the calculation introduce a degree of subjective uncertainty, making the evaluation results susceptible to the influence of personnel experience and their state of mind, thus reducing the stability and repeatability of the ranking results. Summary of the Invention

[0006] This invention provides a target attack priority ranking method, apparatus, equipment, and medium based on intelligent assessment, which solves the problem of how to improve the scientificity, objectivity, and reliability of target ranking results.

[0007] To achieve the above objectives, this application adopts the following technical solution: Firstly, a target engagement priority ranking method based on intelligent assessment is provided, including: Construct a target strike priority ranking evaluation index system; the evaluation index system includes a first-level index and a second-level index; the first-level index includes at least categorical indexes, and the second-level index is used to predict and evaluate the categorical indexes in the first-level index. A target evaluation decision matrix is ​​constructed based on the first-level indicators. In the target evaluation decision matrix, the numerical indicators in the first-level indicators are the actual values ​​corresponding to each target, and the values ​​of the categorical indicators in the first-level indicators are calculated using a neural network-based intelligent evaluation method based on the values ​​of the second-level indicators. The entropy weight method is used to calculate the weights of each first-level indicator based on the target evaluation decision matrix; The TOPSIS method is used to calculate the proximity of each target based on the weights of each first-level indicator. The grey relational analysis method is used to calculate the comprehensive correlation degree of each objective based on the weights of each first-level indicator. Based on the proximity and the comprehensive correlation, a weighted comprehensive evaluation value for each objective is calculated. The objectives are ranked according to the comprehensive evaluation values.

[0008] Secondly, a target engagement priority ranking device based on intelligent assessment is provided, comprising: The evaluation index system construction module is used to construct a target strike priority ranking evaluation index system; the evaluation index system includes a first-level index and a second-level index; the first-level index includes at least categorical indexes, and the second-level indexes are used to predict and evaluate the categorical indexes in the first-level index. The target evaluation decision matrix construction module is used to construct a target evaluation decision matrix based on the first-level indicators. The values ​​of the categorical indicators in the first-level indicators are calculated using a neural network-based intelligent evaluation method based on the values ​​of the second-level indicators. The first-level indicator weight calculation module is used to calculate the weight of each first-level indicator based on the target evaluation decision matrix using the entropy weight method. The proximity calculation module is used to calculate the proximity of each target based on the weights of each first-level indicator obtained by using the TOPSIS method. The comprehensive correlation calculation module is used to calculate the comprehensive correlation of each target based on the weights of each first-level indicator obtained by grey relational analysis. The comprehensive evaluation value calculation module is used to calculate the comprehensive evaluation value of each target based on the proximity and the comprehensive correlation. The target ranking module is used to rank the targets according to the comprehensive evaluation value.

[0009] Thirdly, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, performs the steps of the method as described in the first aspect.

[0010] Fourthly, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method as described in the first aspect. Attached Figure Description

[0011] Figure 1 A schematic flowchart illustrating a target strike priority ranking method based on intelligent evaluation, provided for embodiments of this application; Figure 2 This is a schematic diagram of a target strike priority ranking evaluation index system provided in an embodiment of this application. Detailed Implementation

[0012] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the technical solutions in the embodiments of this application are clearly described. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art are within the scope of protection of this application.

[0013] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0014] The steps described in this application and the flowcharts in the accompanying drawings are not necessarily strictly executed according to the step numbers; the execution order of the steps can be changed. Furthermore, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be broken down into multiple steps.

[0015] This specification provides a target strike priority ranking method based on intelligent assessment, and also relates to a target strike priority ranking device based on intelligent assessment, an electronic device, and a computer-readable storage medium. The following describes each of these in detail with reference to the accompanying drawings and preferred embodiments.

[0016] Please see Figure 1 This application provides a target strike priority ranking method based on intelligent assessment, including: Step S1: Construct a target strike priority ranking and evaluation index system; The evaluation index system includes a first-level index and a second-level index; the first-level index includes at least categorical indicators, and the second-level index is used to predict and evaluate the categorical indicators in the first-level index.

[0017] Furthermore, the first layer of indicators includes: target speed configured as a positive indicator, target distance configured as a negative indicator, target criticality configured as a positive indicator, and target strike effectiveness configured as a positive indicator; The second-level indicators include: target node importance, target node type, target value, target existence time window, whether it is a key target, mission response time limit, whether the target has the ability to strike, target movement status, and target protection capability; the second-level indicators are used to predict and generate quantitative scores for the target criticality and target strike effectiveness indicators.

[0018] like Figure 2 As shown, in this step, four attributes—target speed, target distance, target criticality, and target strike effectiveness—are selected as evaluation indicators for target strike ranking. Target speed and target distance are numerical indicators, while target criticality and target effectiveness are categorical indicators. Target distance is a negative indicator, and the other three are positive indicators. Considering the requirements for observable and quantifiable data collection, target criticality and target effectiveness are predicted and generated using nine categorical indicators: target node importance, target node type, target value, target existence time window, whether it is a key target, mission response time limit, whether the target has strike capability at this level, target movement status, and target protection capability.

[0019] Step S2: Construct a target evaluation decision matrix by combining the first layer of indicators with a neural network-based intelligent evaluation method.

[0020] This step constructs a target evaluation decision matrix based on the first-level indicators, namely, target distance, target speed, target criticality, and target strike effectiveness, denoted as: ; in, Indicates the first The first goal The values ​​of each evaluation indicator, This indicates the number of targets that need to be sorted. This indicates the number of indicators used to evaluate the target.

[0021] The target evaluation decision matrix contains the actual values ​​corresponding to the target distance and target speed. The values ​​of target criticality and target strike effectiveness are predicted and generated using a neural network-based intelligent evaluation method, combined with the values ​​of the second-layer indicators.

[0022] Furthermore, a neural network-based intelligent assessment method is used to predict and generate quantitative scores for the target criticality and target strike effectiveness indicators, specifically including: Step S21: Construct a fully connected deep neural network based on the idea of ​​ordinal regression; Each input layer neuron of the fully connected deep neural network corresponds one-to-one with each index of the second layer; the output layer neuron of the fully connected deep neural network corresponds to the two categorical indices of target criticality and target strike effectiveness in the first layer, and is processed by transforming the ordinal classification problem of the two categorical indices into a series of binary classification problems; the hidden layer consists of two fully connected layers, the activation function is ReLU, and a Dropout layer is provided.

[0023] Step S22: Optionally, based on historical cases, exercise data, simulation data, etc., domain experts construct a sample dataset to complete the training of the fully connected deep neural network.

[0024] Step S23: Input the second layer index values ​​of each target into the trained fully connected deep neural network, and then decode the values ​​of each neuron in the output layer to obtain the quantitative scores of the target criticality and the target strike effectiveness.

[0025] Specifically, this application's intelligent evaluation method based on neural networks constructs a fully connected deep neural network based on the ordinal regression concept. This network transforms ordinal classification into a series of binary classification problems to predict the quantitative scores of target criticality and target strike effectiveness. The fully connected deep neural network has 9 neurons in its input layer (corresponding to 9 categorical features: target node importance, target node type, target value, target existence time window, whether it is a key target, task response time limit, whether the target has strike capability, target movement status, and target defense capability). For example, the corresponding feature values ​​are shown in the table below: Table 1 Input Layer Feature Quantization Table The neurons in the output layer of the fully connected deep neural network correspond to the two categorical indicators, target criticality and target strike effectiveness, in the first layer, and the ordinal classification problem of these two categorical indicators is transformed into a series of binary classification problems for processing.

[0026] For example, the criticality and effectiveness of the objectives are quantified and scored according to the following table: Table 2. Quantitative Scoring Table for Objective Criticality and Objective Effectiveness The fully connected deep neural network has 12 neurons in the output layer (6 neurons each for the two evaluation indicators of target criticality and strike effectiveness), and each neuron uses the Sigmoid activation function. The hidden layer consists of two fully connected layers with the ReLU activation function, and a Dropout layer is added to prevent overfitting.

[0027] The training of the fully connected neural network is based on historical cases, exercise data, and simulation data. The sample dataset is constructed by domain experts and implemented using the Adam algorithm, with weighted binary cross-entropy loss selected as the loss function.

[0028] The nine feature values ​​of the input layer of the neural network corresponding to each target are input into the trained neural network to obtain the values ​​of the 12 neurons in the output layer. After decoding the values ​​of the output layer neurons, the quantitative scores of the target's criticality and the effectiveness of the target strike are obtained.

[0029] For example, for the target criticality (or strike effectiveness) indicator, the sigmoid output values ​​of the corresponding 6 neurons are compared with a threshold of 0.5. The quantification score of this indicator is 1 + [the number of (output values ​​> 0.5)].

[0030] Traditional methods rely on expert scoring to determine target criticality and effectiveness. To avoid the influence of personnel experience and state of mind on expert scoring in practical applications, this invention employs a neural network-based intelligent evaluation method to replace subjective expert scoring, generating quantitative scores for target criticality and effectiveness, thus reducing the adverse effects of subjective factors. Furthermore, based on historical cases, exercise data, and simulation data, domain experts construct a sample dataset beforehand and train a fully connected deep neural network. During evaluation, inputting the values ​​of each indicator into the trained neural network quickly yields quantitative scores for target criticality and target strike effectiveness, thereby improving the timeliness of the evaluation process.

[0031] Step S3: Using the entropy weight method, calculate the weights of each first-level indicator based on the target evaluation decision matrix. Specifically, this includes: S31: Standardize the target evaluation decision matrix to obtain a standardized matrix; in, , For positive indicators, ; For negative indicators, ; S32: Calculate the information entropy of each indicator based on the standardized matrix: ; S33: Calculate the weights of each indicator based on information entropy: .

[0032] Step S4: Using the TOPSIS method, calculate the proximity of each target based on the calculated weights of each first-level indicator. Specifically, this includes: S41: Based on the standardized matrix Determine the ideal solution With negative ideal solution ; Standardized matrix All medium-sized data is converted to extremely large-scale data, therefore: ; S42: Based on the weights of each first-level indicator Calculate the weighted distance between each objective and the positive and negative ideal solutions. and : ; S43: Calculate the proximity of each target based on the weighted distance. : ; The higher the relevance score, the better the solution.

[0033] Step S5: Using grey relational analysis, calculate the comprehensive correlation degree of each objective based on the calculated weights of each first-level indicator. Specifically, this includes: S51: Adopt the aforementioned positive ideal solution and negative ideal solution These are used as the optimal and worst reference sequences, respectively. S52: Calculate the correlation coefficients between each target and the best and worst reference sequences, respectively. For the optimal reference sequence Calculate the correlation coefficient: , in, , is the resolution coefficient. ; For the worst reference sequence Calculate the correlation coefficient: , in, , is the resolution coefficient. ; S53: Based on the weights of each first-level indicator Calculate the correlation between each target and the optimal reference sequence, and the correlation between each target and the worst reference sequence: ; S54: Calculate the comprehensive correlation degree of each target based on the aforementioned correlation degree. : .

[0034] Step S6: Based on the proximity and the comprehensive correlation, calculate the comprehensive evaluation value of each target using a weighted average.

[0035] Overall evaluation value : .

[0036] Step S7: Sort the targets according to the comprehensive evaluation value.

[0037] Based on the calculated comprehensive evaluation value The system provides a comprehensive ranking of target strikes, with higher comprehensive evaluation values ​​indicating higher target strike priority.

[0038] Based on the above technical solution, this application has the following beneficial effects: 1. In the process of constructing the target strike ranking evaluation index system, a hierarchical index system was constructed. Considering the requirements for observable and quantifiable data collection, four attributes were selected as evaluation indicators for target strike ranking: target speed, target distance, target criticality, and target strike effectiveness. Among them, target criticality and target effectiveness are predicted and generated through nine categorical indicators, including target node importance, target node type, target value, target existence time window, whether it is a key target, mission response time limit, whether the target has strike capability at this level, target movement status, and target protection capability.

[0039] This invention comprehensively considers the target's threat, capability, and value-related influencing factors, and can objectively and comprehensively reflect the target's overall characteristics. This makes the evaluation indicators more comprehensive and more universal, and can be applied not only to the calculation of air targets, but also to the calculation of land and water targets.

[0040] 2. For the two qualitative indicators, target criticality and target effectiveness, in the evaluation metrics, a neural network-based intelligent evaluation method is constructed. By transforming the ordinal classification of qualitative indicators into a series of binary classification problems, the method better handles the sequential relationship between the categories of qualitative indicators, making the evaluation values ​​of qualitative indicators more objective and reasonable, and reducing the adverse effects of subjective factors. Furthermore, by training the neural network model in advance, the timeliness of the evaluation process can be improved.

[0041] 3. By adopting the entropy weight method and introducing the concept of information entropy, the objective characteristics of the target evaluation matrix data are reasonably utilized to calculate the weights of each evaluation indicator. The calculated weights are then incorporated into the calculations of the TOPSIS method and the grey relational analysis method, making the determination of weights in the TOPSIS method and the grey relational analysis method more objective and reasonable. By combining the TOPSIS method and the grey relational analysis method, the comprehensive evaluation value of each target is calculated, avoiding the limitations of a single evaluation mathematical model and making the evaluation results more scientific and reliable.

[0042] Corresponding to the above-described target strike priority ranking method based on intelligent assessment, this application provides a target strike priority ranking device based on intelligent assessment, comprising: The evaluation index system construction module is used to construct a target strike priority ranking evaluation index system; the evaluation index system includes a first-level index and a second-level index; the first-level index includes at least categorical indexes, and the second-level indexes are used to predict and evaluate the categorical indexes in the first-level index. The target evaluation decision matrix construction module is used to construct a target evaluation decision matrix based on the first-level indicators. The values ​​of the categorical indicators in the first-level indicators are calculated using a neural network-based intelligent evaluation method based on the values ​​of the second-level indicators. The first-level indicator weight calculation module is used to calculate the weight of each first-level indicator based on the target evaluation decision matrix using the entropy weight method. The proximity calculation module is used to calculate the proximity of each target based on the weights of each first-level indicator obtained by using the TOPSIS method. The comprehensive correlation calculation module is used to calculate the comprehensive correlation of each target based on the weights of each first-level indicator obtained by grey relational analysis. The comprehensive evaluation value calculation module is used to calculate the comprehensive evaluation value of each target based on the proximity and the comprehensive correlation. The target ranking module is used to rank the targets according to the comprehensive evaluation value.

[0043] Furthermore, the first layer of indicators includes: target speed configured as a positive indicator, target distance configured as a negative indicator, target criticality configured as a positive indicator, and target strike effectiveness configured as a positive indicator; The second-level indicators include: target node importance, target node type, target value, target existence time window, whether it is a key target, mission response time limit, whether the target has the ability to strike, target movement status, and target protection capability; the second-level indicators are used to predict and generate quantitative scores for the target criticality and target strike effectiveness indicators.

[0044] Furthermore, a neural network-based intelligent assessment method is used to predict and generate quantitative scores for the target criticality and target strike effectiveness indicators, specifically including: A fully connected deep neural network is constructed based on the idea of ​​ordinal regression; The second-layer index values ​​of each target are input into the trained fully connected deep neural network, and then the values ​​of each neuron in the output layer are decoded to obtain the quantitative scores of the target criticality and the target strike effectiveness.

[0045] Furthermore, each input layer neuron of the fully connected deep neural network corresponds one-to-one with each index of the second layer; the output layer neuron of the fully connected deep neural network corresponds to the two categorical indices of target criticality and target strike effectiveness in the first layer, and is processed by transforming the ordinal classification problem of the two categorical indices into a series of binary classification problems, with the activation function being Sigmoid; the hidden layer consists of two fully connected layers, with the activation function being ReLU, and includes a Dropout layer.

[0046] The above-described target strike priority ranking device based on intelligent assessment implements the steps and processes of the above-described target strike priority ranking method based on intelligent assessment, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0047] Corresponding to the above-described embodiment of the target strike priority ranking method based on intelligent assessment, this application provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, it implements the steps and processes of the above-described embodiment of the target strike priority ranking method based on intelligent assessment, and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0048] Corresponding to the above-described embodiment of the target strike priority ranking method based on intelligent assessment, this application embodiment also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the steps and processes of the above-described embodiment of the target strike priority ranking method based on intelligent assessment, and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0049] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0050] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0051] It is understood that the embodiments of this application have been described above in conjunction with the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. As those skilled in the art will know, various changes or equivalent substitutions can be made to these features and embodiments without departing from the spirit and scope of the invention. Furthermore, those skilled in the art, under the guidance or instruction of this application, can modify these features and embodiments to adapt to specific situations and materials without departing from the spirit and scope of the invention. Therefore, this invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the protection scope of this invention.

Claims

1. A method for target engagement prioritization based on smart assessment, characterized in that, include: Construct a target strike priority ranking evaluation index system; the evaluation index system includes a first-level index and a second-level index; the first-level index includes at least categorical indexes, and the second-level index is used to predict and evaluate the categorical indexes in the first-level index. A target evaluation decision matrix is ​​constructed based on the first-level indicators. The values ​​of the categorical indicators in the first-level indicators are calculated using a neural network-based intelligent evaluation method based on the values ​​of the second-level indicators. The entropy weight method is used to calculate the weights of each first-level indicator based on the target evaluation decision matrix; The TOPSIS method is used to calculate the proximity of each target based on the weights of each first-level indicator. The grey relational analysis method is used to calculate the comprehensive correlation degree of each objective based on the weights of each first-level indicator. Based on the proximity and the comprehensive correlation, a weighted comprehensive evaluation value for each objective is calculated. The objectives are ranked according to the comprehensive evaluation values.

2. The target strike priority ranking method based on intelligent assessment according to claim 1, characterized in that, The first layer of indicators includes: target speed configured as a positive indicator, target distance configured as a negative indicator, target criticality configured as a positive indicator, and target strike effectiveness configured as a positive indicator; The second-level indicators include: target node importance, target node type, target value, target existence time window, whether it is a key target, mission response time limit, whether the target has the ability to strike, target movement status, and target protection capability; the second-level indicators are used to predict and generate quantitative scores for the target criticality and target strike effectiveness indicators.

3. The target strike priority ranking method based on intelligent assessment according to claim 2, characterized in that, The quantitative scores for the target criticality and target strike effectiveness indicators are predicted and generated using a neural network-based intelligent assessment method, specifically including: A fully connected deep neural network is constructed based on the idea of ​​ordinal regression; The second-layer index values ​​of each target are input into the trained fully connected deep neural network, and then the values ​​of each neuron in the output layer are decoded to obtain the quantitative scores of the target criticality and the target strike effectiveness.

4. The target strike priority ranking method based on intelligent assessment according to claim 3, characterized in that, Each input layer neuron of the fully connected deep neural network corresponds one-to-one with each index of the second layer; the output layer neuron of the fully connected deep neural network corresponds to the two categorical indices of target criticality and target strike effectiveness in the first layer, and is processed by transforming the ordinal classification problem of the two categorical indices into a series of binary classification problems; the hidden layer consists of two fully connected layers, the activation function is ReLU, and a Dropout layer is provided.

5. The target strike priority ranking method based on intelligent assessment according to claim 1, characterized in that, The first layer of indicators also includes numerical indicators; In the target evaluation decision matrix, the numerical indicators in the first layer of indicators are taken as the actual values ​​corresponding to each target.

6. An intelligent assessment based target engagement prioritization apparatus, comprising: include: The evaluation index system construction module is used to construct a target strike priority ranking evaluation index system; the evaluation index system includes a first-level index and a second-level index; the first-level index includes at least categorical indexes, and the second-level indexes are used to predict and evaluate the categorical indexes in the first-level index. The target evaluation decision matrix construction module is used to construct a target evaluation decision matrix based on the first-level indicators. The values ​​of the categorical indicators in the first-level indicators are calculated using a neural network-based intelligent evaluation method based on the values ​​of the second-level indicators. The first-level indicator weight calculation module is used to calculate the weight of each first-level indicator based on the target evaluation decision matrix using the entropy weight method. The proximity calculation module is used to calculate the proximity of each target based on the weights of each first-level indicator obtained by using the TOPSIS method. The comprehensive correlation calculation module is used to calculate the comprehensive correlation of each target based on the weights of each first-level indicator obtained by grey relational analysis. The comprehensive evaluation value calculation module is used to calculate the comprehensive evaluation value of each target based on the proximity and the comprehensive correlation. The target ranking module is used to rank the targets according to the comprehensive evaluation value.

7. An electronic device, comprising: The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the target strike priority ranking method based on intelligent assessment as described in any one of claims 1 to 5.

8. A readable storage medium, characterized by, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the target strike priority ranking method based on intelligent assessment as described in any one of claims 1 to 5.

Images