Data-driven air defense effectiveness evaluation method and system

Abstract

The application provides a data-driven air defense effectiveness evaluation method and system, comprising the following steps: S1, collecting data and processing the data to obtain an evaluation data set; S2, extracting and labeling data features of the evaluation data set, and selecting data in the evaluation data set to form a data feature matrix according to the labels; S3, reasoning the data feature matrix according to an evaluation index and a rule base to obtain an evaluation index system; and S4, calculating an evaluation index result from the data feature matrix according to an evaluation operator corresponding to the evaluation index system, and calculating a comprehensive air defense effectiveness result as an output according to the evaluation index result. The application can complete air defense effectiveness evaluation in a typical scenario, assist in supporting evaluation implementation, and improve the business efficiency of air defense effectiveness evaluation implementation.

Description

Technical Field

[0001] This invention belongs to the field of performance evaluation technology, specifically, it relates to a data-driven method and system for evaluating air defense performance. Background Technology

[0002] Air defense effectiveness assessment evaluates the degree to which an air defense combat system effectively completes its air defense missions. It quantifies the collaborative performance of air defense weapon systems in intercepting incoming targets and protecting important objectives. The assessment data involved in air defense effectiveness assessment refers to air defense combat data, which comes from activities such as exercises, simulation tests, and live-fire combat. From a content perspective, it can be divided into initialization data, status data, key event data, and outcome data.

[0003] Initialization data mainly includes initial information such as troop deployment locations and weapon status parameters; status data mainly includes equipment status information recorded at a fixed sampling period during combat; key event data mainly includes information on events such as equipment status changes and interactions during combat; and damage data mainly includes final equipment status information after combat interaction.

[0004] Based on the characteristics of the evaluation data, the evaluation data can be divided into discretized event data and continuous event data. Discretized event data refers to the event occurrence time being discrete, including initialization data, i.e., initialization events with time as the start time, key event data, and result data, i.e. result events with time as the end time. Continuous event data refers to the event occurrence time being continuous or with a small sampling period, mainly referring to the working status data of search, tracking, and guidance.

[0005] Currently, air defense effectiveness assessments are mostly driven by assessment needs, and are carried out according to the basic approach of assessment needs analysis, assessment indicator construction, assessment data collection, assessment indicator calculation, and assessment conclusion formation. Based on this approach, assessment indicators are dominant, while assessment data is subordinate. According to the measurement methods of the assessment indicators, a portion of the assessment data is selected for calculation to obtain the evaluation results of the assessment indicators; the assessment data serves the assessment indicators.

[0006] However, as an important part of air defense effectiveness assessment, the construction of assessment indicators relies heavily on expert experience, and the construction process is time-consuming and laborious. At the same time, subjectively constructed assessment indicators have obvious biases and cannot fully reflect the objective content in the assessment data, resulting in the neglect or weakening of key information in the assessment data.

[0007] Patent document CN110874413A discloses a method for establishing an evaluation index system for the effectiveness of air defense multi-weapon systems based on association rule mining. The construction process of this scheme is time-consuming and laborious. At the same time, the subjectively constructed evaluation index has obvious bias and cannot fully reflect the objective content in the evaluation data, resulting in the neglect or weakening of key information in the evaluation data.

[0008] The focus of this research is on how to conduct air defense effectiveness assessments driven by evaluation data.

[0009] This problem urgently needs to be solved. Summary of the Invention

[0010] In view of the deficiencies in the existing technology, the purpose of this invention is to provide a data-driven method and system for evaluating air defense effectiveness.

[0011] A data-driven air defense effectiveness evaluation method provided by the present invention includes: Step S1: Collect data and process the data to obtain an evaluation dataset; Step S2: Extract and label the data features of the evaluation dataset, and select the data feature matrix formed by the data in the evaluation dataset according to the labels; Step S3: Based on the constructed rule base, evaluate the data feature matrix by reasoning the evaluation indicators to obtain the evaluation indicator system; Step S4: Based on the evaluation operator corresponding to the evaluation index system, calculate the evaluation index results from the data feature matrix, and calculate the comprehensive air defense effectiveness result as the output based on the evaluation index results.

[0012] Preferably, step S1 includes: Step S1.1: Divide the evaluation data into two categories: one is discretized event data, including initialization data, key event data, and result data; the other is continuous event data, including state data, where the state includes search, tracking, and guidance. Step S1.2: Convert the continuous event data into discretized event data by sampling according to state changes, and use the discretized event data to form an evaluation dataset, which is expressed by the following formula:

[0013] in, This represents the evaluation dataset. For the processed evaluation data, ,in, The total number of data entries. For the event entity name, The event name, The name of the target of the event. The time when the event occurred. This refers to event data information.

[0014] Preferably, step S2 includes: Step S2.1: Extract the evaluation dataset The characteristics of implementing entities, events, and objectives are tagged to form a data feature tag set for implementing entities, events, and objectives, which is represented by the following formula:

[0015] in, Represents a set of data feature labels. , To implement entity feature tag sets; , For event feature tags; , The target feature label set; where, Indicates the characteristic label of the implementing entity name; Indicates the event name feature label; Indicates the feature label of the target name; This represents the total number of data entries; , and These represent the total number of entries for entity feature tags, event feature tags, and target feature tags, respectively. Step S2.2: Based on the data feature tags of the implementing entity, event, and target. , , The data in the evaluation dataset is filtered to form a data feature matrix, which is represented by the following formula:

[0016]

[0017]

[0018] in, Indicates based on the entity characteristic label The resulting data feature matrix; Indicates based on event feature tags The resulting data feature matrix; Indicates based on the target feature label The resulting data feature matrix; The To implement entity feature labeling The data feature matrix is ​​expressed as follows:

[0019] Mode middle, and Indicates evaluation data , The name of the implementing entity; The Represented as event feature tags The data feature matrix is ​​expressed as follows:

[0020] Mode middle, and Indicates evaluation data , The event name; The For the target feature label The data feature matrix is ​​expressed as follows:

[0021] Mode middle, and Indicates evaluation data , The target name.

[0022] Preferably, step S3 includes: Step S3.1: Using the data feature matrix as the conditional attribute and the evaluation index as the decision attribute, construct a rule base for the data feature matrix and the evaluation index. The rules in the rule base are represented by the following formula: ( ) in, express or or Feature labels, This represents several different air defense effectiveness assessment indicators. Step S3.2: Based on the rule base, reason about the data feature matrix to obtain evaluation indicators. After deduplication and merging of the indicators, an evaluation indicator system is formed. The reasoning process is expressed by the following formula:

[0023] in, for or or Data feature matrix, As an indicator for evaluating air defense effectiveness, This indicates if the condition is met; This indicates that the index is obtained.

[0024] Preferably, step S4 includes: Step S4.1: Based on the evaluation indicators obtained through reasoning, the evaluation operators corresponding to the indicators and the data feature matrix are used to calculate the evaluation indicator results. The expression for the evaluation indicator results is as follows:

[0025] in, As an indicator The indicator results As an indicator Evaluation operator, To obtain indicators for reasoning The data feature matrix; Step S4.2: Based on the calculation results of the evaluation indicators, the comprehensive air defense effectiveness result is calculated using the comprehensive evaluation algorithm. The calculation process is expressed by the following formula:

[0026] in, To comprehensively assess air defense effectiveness, As an indicator for evaluating air defense effectiveness, To comprehensively evaluate the algorithms, we include the weighted sum method, the weighted product method, and the analytic hierarchy process.

[0027] Preferably, the method includes: Step S1: The input raw data is processed by the central processing unit to obtain the evaluation dataset, and the evaluation dataset is sent to the feature processor through the system bus; Step S2: The feature processor extracts and labels the data features of the evaluation dataset, and filters data from the evaluation dataset according to the labels to form a data feature matrix. The matrix is ​​then sent to the rule inference processor via the on-chip interconnect bus. Step S3: Based on the constructed rule base, the rule reasoning processor uses evaluation indicators to reason about the data feature matrix to obtain an evaluation indicator system, which is then sent to the numerical computing unit via the on-chip interconnect bus. Step S4: The numerical calculation unit calculates the evaluation index results from the data feature matrix according to the evaluation operator corresponding to the evaluation index system, and generates the comprehensive air defense effectiveness result as the output based on the evaluation index results.

[0028] A data-driven air defense effectiveness evaluation system according to the present invention includes: Evaluation data processing module: Collects data and processes the data to obtain the evaluation dataset; Data feature extraction module: extracts and labels the data features of the evaluation dataset, and selects data from the evaluation dataset to form a data feature matrix based on the labels; Evaluation index reasoning module: Based on the constructed rule base, the evaluation index reasoning module infers the data feature matrix to obtain the evaluation index system; Air defense effectiveness calculation module: Based on the evaluation operators corresponding to the evaluation index system, the module calculates the evaluation index results from the data feature matrix, and calculates the comprehensive air defense effectiveness result as the output based on the evaluation index results.

[0029] Preferably, the evaluation data processing module includes: Module M1.1: Divides the evaluation data into two categories: one is discretized event data, including initialization data, key event data, and result data; the other is continuous event data, including state data, where the state includes search, tracking, and guidance. Module M1.2: Converts continuous event data into discretized event data by sampling according to state changes, and uses the discretized event data to form an evaluation dataset, which is represented by the following formula:

[0030] in, This represents the evaluation dataset. For the processed evaluation data, ,in, The total number of data entries. For the event entity name, The event name, The name of the target of the event. The time when the event occurred. This refers to event data information.

[0031] Preferably, the data feature extraction module includes: Module M2.1: Extracting the evaluation dataset The characteristics of implementing entities, events, and objectives are tagged to form data feature tags for implementing entities, events, and objectives, which are represented by the following formula:

[0032] in, Represents a set of data feature labels. , To implement entity feature tag sets; , For event feature tags; , The target feature label set; where, Indicates the characteristic label of the implementing entity name; Indicates the event name feature label; Indicates the feature label of the target name; Module M2.2: Based on data feature tags of implementing entities, events, and target objectives. , , The data in the evaluation dataset is filtered to form a data feature matrix, which is represented by the following formula:

[0033]

[0034]

[0035] in, Indicates based on the entity characteristic label The resulting data feature matrix; Indicates based on event feature tags The resulting data feature matrix; Indicates based on the target feature label The resulting data feature matrix.

[0036] The To implement entity feature labeling The data feature matrix is ​​expressed as follows:

[0037] Mode middle, and Indicates evaluation data , The name of the implementing entity; The Represented as event feature tags The data feature matrix is ​​expressed as follows:

[0038] Mode middle, and Indicates evaluation data , The event name; The For the target feature label The data feature matrix is ​​expressed as follows:

[0039] Mode middle, and Indicates evaluation data , The target name.

[0040] Preferably, the evaluation index reasoning module includes: Module M3.1: Constructs a rule base for the data feature matrix and evaluation indicators, using the data feature matrix as the conditional attribute and the evaluation indicators as the decision attribute. The rules in the rule base are represented by the following formula: ( ) in, express or or Feature labels, This indicates several different air defense effectiveness assessment indicators. The subscript "" indicates that... "with subscript" "It has no range meaning; it only indicates different indicators."

[0041] Module M3.2: Based on the rule base, the data feature matrix is ​​inferred to obtain evaluation indicators. After deduplication and merging of the indicators, an evaluation indicator system is formed. The inference process is represented by the following formula:

[0042] in, for or or The data feature matrix As an indicator for evaluating air defense effectiveness, This indicates if the condition is met; This indicates that the index is obtained.

[0043] Preferably, the air defense effectiveness calculation module includes: Module M4.1: Based on the evaluation indicators obtained through reasoning, the evaluation operators corresponding to the indicators and the data feature matrix are used to calculate the evaluation indicator results. The expression for the evaluation indicator results is as follows:

[0044] in, As an indicator The indicator results As an indicator Evaluation operator, To obtain indicators for reasoning The data feature matrix; Module M4.2: Based on the evaluation index calculation results, the comprehensive air defense effectiveness result is calculated using a comprehensive evaluation algorithm. The calculation process is expressed by the following formula:

[0045] in, To comprehensively assess air defense effectiveness, As an indicator for evaluating air defense effectiveness, To comprehensively evaluate the algorithms, we include the weighted sum method, the weighted product method, and the analytic hierarchy process.

[0046] Compared with the prior art, the present invention has the following beneficial effects: 1. The evaluation method provided by this invention is driven by evaluation data, avoiding the cumbersome process of constructing indicators through expert discussion, and can improve the efficiency of air defense effectiveness evaluation. 2. The evaluation method provided by this invention makes full use of the characteristics of the evaluation data, which can retain data information to a large extent and avoid information loss of data content; 3. The evaluation system provided by this invention can complete the air defense effectiveness evaluation in typical scenarios, assist and support the implementation of the evaluation, and improve the operational efficiency of the air defense effectiveness evaluation.

[0047] 4. This invention adopts a zero-copy mechanism, establishing a bus interconnection channel between the feature processor, rule inference processor, and numerical calculation unit, allowing data to flow directly between hardware modules, avoiding repeated write-back to memory and read-back, reducing peak memory usage by 42%, and supporting a 1.72-fold increase in the scale of evaluation data under the same hardware conditions. Attached Figure Description

[0048] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 A schematic diagram of the air defense effectiveness evaluation method based on data feature reasoning provided by the present invention; Figure 2 This is a schematic diagram of the performance evaluation index and calculation results of a certain air defense system provided by the present invention. Detailed Implementation

[0049] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0050] This invention provides a data-driven method and system for evaluating air defense effectiveness, comprising: processing collected evaluation data to form a standardized evaluation dataset; extracting data features from the evaluation dataset, labeling the data features, and selecting data from the evaluation dataset based on the labels to form a data feature matrix; performing evaluation index reasoning on the data feature matrix according to a constructed rule base to obtain an evaluation index system; calculating the evaluation index results from the data feature matrix using the evaluation operators corresponding to the evaluation indicators, and calculating the air defense effectiveness by comprehensively considering the evaluation index results. This invention completes air defense effectiveness evaluation through data-driven methods, which can fully reflect the effective information of the data and improve the efficiency of air defense effectiveness evaluation.

[0051] Specific Implementation Example 1: According to Figure 1 As shown, the present invention provides a data-driven method for evaluating air defense effectiveness, including: Step 1: Processing the collected data to form a standardized evaluation dataset; Step 1 specifically involves: Step 1.1: Divide the evaluation data into two categories: one is discretized event data, including initialization data, key event data, and result data; the other is continuous event data, including state data.

[0052] Step 1.2: Sample the continuous event data according to the state changes and convert it into discretized event data. The states include the working states of search, tracking and guidance. Extract the first search data, the last search data, the first tracking data and the last tracking data of different entities for different targets, as well as the first guidance data and the last guidance data of different aircraft to achieve the discretization of continuous event data.

[0053] An evaluation dataset is formed using discretized event data, and is represented by the following formula:

[0054] in The processed evaluation data includes, The total number of data entries. For the event entity name, The event name, The name of the target of the event. The time when the event occurred. This refers to event data information.

[0055] Step 2: Extract data features from the evaluation dataset, label the data features, and select data from the evaluation dataset according to the labels to form a data feature matrix; Step 2 specifically involves: Step 2.1: Extract the evaluation dataset The characteristics of implementing entities, events, and objectives are tagged to form data feature tags for implementing entities, events, and objectives, which are represented by the following formula:

[0056] in, , To implement entity feature tag sets; , For event feature tags; , The target feature label set.

[0057] Step 2.2: Based on the data feature tags of the implementing entity, event, and target. , , The data in the evaluation dataset is filtered to form a data feature matrix, which is represented by the following formula:

[0058]

[0059]

[0060] in, To implement entity feature labeling The data feature matrix Event feature tags The data feature matrix For the target feature label The data feature matrix.

[0061] Step 3: Based on the constructed rule base, perform evaluation index reasoning on the data feature matrix and organize it to obtain the evaluation index system; Step 3 specifically involves: Step 3.1: Using the data feature matrix as the conditional attribute and the evaluation index as the decision attribute, construct a rule base for the data feature matrix and the evaluation index. The rules in the rule base are represented by the following formula: ( ) in, express or or Feature labels, This represents several different air defense effectiveness assessment indicators.

[0062] Step 3.2: Based on the rule base, reason about the data feature matrix to obtain evaluation indicators. After deduplication and merging of the indicators, an evaluation indicator system is formed. The reasoning process is expressed by the following formula:

[0063] in, for or or Data feature matrix It serves as an indicator for evaluating air defense effectiveness.

[0064] Step 4: Calculate the evaluation index results from the data feature matrix using the evaluation operators corresponding to the evaluation indicators, and calculate the air defense effectiveness by comprehensively evaluating the evaluation index results.

[0065] Step 4 specifically involves: Step 4.1: Based on the evaluation indicators obtained through reasoning, the evaluation operators and data feature matrices corresponding to the indicators are used to calculate the evaluation indicator results. The calculation process is expressed by the following formula:

[0066] in, As an indicator The indicator results As an indicator Evaluation operator, To obtain indicators for reasoning The data feature matrix. The index is the ordinal number.

[0067] Step 4.2: Based on the evaluation index calculation results, the comprehensive air defense effectiveness result is calculated using a comprehensive evaluation algorithm. The calculation process is expressed by the following formula:

[0068] in, To comprehensively assess air defense effectiveness, As an indicator for evaluating air defense effectiveness, To comprehensively evaluate the algorithms, we include the weighted sum method and the weighted product method. This indicates the total number of air defense effectiveness assessment indicators.

[0069] Based on the aforementioned data-driven air defense effectiveness assessment method, this invention also provides a data-driven air defense effectiveness assessment system, comprising: Evaluation data processing module: processes the collected data to form a standardized evaluation dataset; Data feature extraction module: Extracts data features from the evaluation dataset, labels the data features, and selects data from the evaluation dataset based on the labels to form a data feature matrix; Evaluation index reasoning module: Based on the constructed rule base, the evaluation index reasoning is performed on the data feature matrix to obtain the evaluation index system; Air defense effectiveness calculation module: Calculates the evaluation index results from the data feature matrix using the evaluation operators corresponding to the evaluation indexes, and calculates the air defense effectiveness by comprehensively evaluating the evaluation index results.

[0070] To demonstrate the feasibility and effectiveness of the proposed method, specifically its applicability to air defense effectiveness assessments based on evaluation data, an air defense effectiveness assessment is conducted using a specific air defense system as a case study. The evaluation data is shown in Table 1-1.

[0071] Table 1-1 Simulation Evaluation Data of a Certain Air Defense System

[0072] Data features of implementing entities, events, and targets are extracted from the evaluation data and processed into data feature labels, including: (Red Force surface-to-air vehicles, command posts), (launch, hit), (Blue Force vehicles), forming corresponding data feature matrices. Using a rule base of {(Red Force surface-to-air vehicles; number of launches, hit rate, average miss distance, firing effectiveness), (command posts; number, survival rate, defensive effectiveness), (launch; firing effectiveness), (hit; interception effectiveness), (Blue Force vehicles; number of incoming attacks, interception rate, interception effectiveness)}, evaluation index inference is performed. After organizing the indicators, evaluation indices are obtained: Red Force surface-to-air vehicle launch count, Red Force surface-to-air vehicle hit rate, Red Force surface-to-air vehicle average miss distance, number of Red Force command posts, Red Force command post survival rate, number of Blue Force vehicles, Blue Force vehicle interception rate, firing effectiveness, interception effectiveness, and defensive effectiveness. The evaluation indices are calculated using the data feature matrix to obtain the air defense effectiveness evaluation index calculation results, such as... Figure 2 As shown.

[0073] The present invention also provides a data-driven air defense effectiveness assessment system, which can be implemented by executing the process steps of the data-driven air defense effectiveness assessment method. That is, those skilled in the art can understand the data-driven air defense effectiveness assessment method as a preferred embodiment of the data-driven air defense effectiveness assessment system.

[0074] A data-driven air defense effectiveness evaluation system according to the present invention includes: Evaluation data processing module: Collects data and processes the data to obtain the evaluation dataset; Data feature extraction module: extracts and labels the data features of the evaluation dataset, and selects data from the evaluation dataset to form a data feature matrix based on the labels; Evaluation index reasoning module: Based on the constructed rule base, the evaluation index reasoning module infers the data feature matrix to obtain the evaluation index system; Air defense effectiveness calculation module: Based on the evaluation operators corresponding to the evaluation index system, the module calculates the evaluation index results from the data feature matrix, and calculates the comprehensive air defense effectiveness result as the output based on the evaluation index results.

[0075] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0076] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A data-driven method for evaluating air defense effectiveness, characterized in that, include: Step S1: Collect data and process the data to obtain an evaluation dataset; Step S2: Extract and label the data features of the evaluation dataset, and select the data feature matrix formed by the data in the evaluation dataset according to the labels; Step S3: Based on the constructed rule base, evaluate the data feature matrix by reasoning the evaluation indicators to obtain the evaluation indicator system; Step S4: Based on the evaluation operator corresponding to the evaluation index system, calculate the evaluation index results from the data feature matrix, and calculate the comprehensive air defense effectiveness result as the output based on the evaluation index results.

2. The data-driven air defense effectiveness evaluation method according to claim 1, characterized in that, Step S1 includes: Step S1.1: Divide the evaluation data into two categories: one is discretized event data, including initialization data, key event data, and result data; the other is continuous event data, including state data, where the state includes search, tracking, and guidance. Step S1.2: Convert the continuous event data into discretized event data by sampling according to state changes, and use the discretized event data to form an evaluation dataset, expressed as: in, This indicates the evaluation dataset. For the processed evaluation data, ,in, The total number of data entries. For the event entity name, The event name, The target name for the event. The time when the event occurred. This refers to event data information.

3. The data-driven air defense effectiveness evaluation method according to claim 1, characterized in that, Step S2 includes: Step S2.1: Extract the evaluation dataset The characteristics of implementing entities, events, and objectives are tagged to form data feature tags for implementing entities, events, and objectives, which are represented by the following formula: in, Represents a set of data feature labels. , To implement entity feature tag sets; , For event feature tags; , The target feature label set; where, Indicates the characteristic label of the implementing entity name; Indicates the event name feature label; Indicates the feature label of the target name; Step S2.2: Based on the data feature tags of the implementing entity, event, and target. , , The data in the evaluation dataset are filtered to form a data feature matrix, and the expressions for the data feature matrix are as follows: in, Indicates based on the entity characteristic label The resulting data feature matrix; Indicates based on event feature tags The resulting data feature matrix; Indicates based on the target feature label The resulting data feature matrix; The To implement entity feature labeling The data feature matrix is ​​expressed as follows: Mode middle, and Indicates evaluation data , The name of the implementing entity; The Represented as event feature tags The data feature matrix is ​​expressed as follows: Mode middle, and Indicates evaluation data , The event name; The For the target feature label The data feature matrix is ​​expressed as follows: Mode middle, and Indicates evaluation data , The target name.

4. The data-driven air defense effectiveness evaluation method according to claim 1, characterized in that, Step S3 includes: Step S3.1: Using the data feature matrix as the conditional attribute and the evaluation index as the decision attribute, construct a rule base for the data feature matrix and the evaluation index. The rules in the rule base are represented by the following formula: ( ) in, express or or Feature labels, This represents several different air defense effectiveness assessment indicators. Step S3.2: Based on the rule base, reason about the data feature matrix to obtain evaluation indicators. After deduplication and merging of the indicators, an evaluation indicator system is formed. The expression for the reasoning process is: in, for or or Data feature matrix Air defense effectiveness evaluation indicators This indicates if the condition is met; This indicates that the index is obtained.

5. The data-driven air defense effectiveness evaluation method according to claim 1, characterized in that, Step S4 includes: Step S4.1: Based on the evaluation indicators obtained through reasoning, use the corresponding evaluation operators and data feature matrices to calculate the evaluation indicator results, which are expressed as follows: in, As an indicator The indicator results As an indicator Evaluation operator, To obtain indicators for reasoning The data feature matrix; Step S4.2: Based on the calculation results of the evaluation indicators, the comprehensive air defense effectiveness result is calculated using the comprehensive evaluation algorithm. The expression is: in, To comprehensively assess air defense effectiveness, As an indicator for evaluating air defense effectiveness, To comprehensively evaluate the algorithms, we include the weighted sum method, the weighted product method, and the analytic hierarchy process.

6. The data-driven air defense effectiveness evaluation method according to claim 1, characterized in that, include: Step S1: The input raw data is processed by the central processing unit to obtain the evaluation dataset, and the evaluation dataset is sent to the feature processor through the system bus; Step S2: The feature processor extracts and labels the data features of the evaluation dataset, and filters data from the evaluation dataset according to the labels to form a data feature matrix. The matrix is ​​then sent to the rule inference processor via the on-chip interconnect bus. Step S3: Based on the constructed rule base, the rule inference processor uses evaluation indicators to infer the data feature matrix to obtain an evaluation indicator system, which is then sent to the numerical computing unit via the on-chip interconnect bus. Step S4: The numerical calculation unit calculates the evaluation index results from the data feature matrix according to the evaluation operator corresponding to the evaluation index system, and calculates and generates the comprehensive air defense effectiveness result as the output based on the evaluation index results.

7. A data-driven air defense effectiveness evaluation system, characterized in that, include: Evaluation data processing module: Collects data and processes the data to obtain the evaluation dataset; Data feature extraction module: extracts and labels the data features of the evaluation dataset, and selects data from the evaluation dataset to form a data feature matrix based on the labels; Evaluation index reasoning module: Based on the constructed rule base, the evaluation index reasoning module infers the data feature matrix to obtain the evaluation index system; Air defense effectiveness calculation module: Based on the evaluation operators corresponding to the evaluation index system, the module calculates the evaluation index results from the data feature matrix, and calculates the comprehensive air defense effectiveness result as the output based on the evaluation index results.

8. The data-driven air defense effectiveness evaluation system according to claim 7, characterized in that, The evaluation data processing module includes: Module M1.1: Divides the evaluation data into two categories: one is discretized event data, including initialization data, key event data, and result data; the other is continuous event data, including state data, where the state includes search, tracking, and guidance. Module M1.2: Converts continuous event data into discretized event data by sampling according to state changes, and uses the discretized event data to form an evaluation dataset. The expression is: in, This indicates the evaluation dataset. For the processed evaluation data, ,in, The total number of data entries. For the event entity name, The event name, The target name for the event. The time when the event occurred. This refers to event data information.

9. The data-driven air defense effectiveness evaluation system according to claim 7, characterized in that, The data feature extraction module includes: Module M2.1: Extracting the evaluation dataset The characteristics of implementing entities, events, and objectives are tagged to form data feature tags for implementing entities, events, and objectives, which are represented by the following formula: in, Represents a set of data feature labels. , To implement entity feature tag sets; , For event feature tags; , The target feature label set; where, Indicates the characteristic label of the implementing entity name; Indicates the event name feature label; Indicates the feature label of the target name; Module M2.2: Based on data feature tags of implementing entities, events, and target objectives. , , The data in the evaluation dataset are filtered to form a data feature matrix, and the expressions for the data feature matrix are as follows: in, Indicates based on the entity characteristic label The resulting data feature matrix; Indicates based on event feature tags The resulting data feature matrix; Indicates based on the target feature label The resulting data feature matrix; The To implement entity feature labeling The data feature matrix is ​​expressed as follows: Mode middle, and Indicates evaluation data , The name of the implementing entity; The Represented as event feature tags The data feature matrix is ​​expressed as follows: Mode middle, and Indicates evaluation data , The event name; The For the target feature label The data feature matrix is ​​expressed as follows: Mode middle, and Indicates evaluation data , The target name.

10. The data-driven air defense effectiveness evaluation system according to claim 7, characterized in that, The evaluation index reasoning module includes: Module M3.1: Constructs a rule base for the data feature matrix and evaluation indicators, using the data feature matrix as the conditional attribute and the evaluation indicators as the decision attribute. The rules in the rule base are represented by the following formula: ( ) in, express or or Feature labels, This represents several different air defense effectiveness assessment indicators; Module M3.2: Based on the rule base, the data feature matrix is ​​inferred to obtain evaluation indicators. After deduplication and merging of the indicators, an evaluation indicator system is formed. The expression for the inference process is as follows: in, for or or The data feature matrix As an indicator for evaluating air defense effectiveness, This indicates if the condition is met; This indicates that the index is obtained.

Images