An efficient and intelligent battlefield scenario editing method

Abstract

The present application belongs to the field of simulation technology and military information technology, and provides a kind of efficient intelligent battlefield scenario editing method, comprising: obtaining the characteristic data of historical unqualified scenario scheme, constructing scenario scheme analysis library, and dividing the risk degree of scenario scheme in scenario scheme analysis library, and identifying high-risk scenario scheme;According to the high-risk scenario scheme, the high-risk scenario scheme is clustered and analyzed according to the failure link, and the frequency analysis is carried out on each type of failure link to determine the high-frequency failure link;Combining the response measures of high-frequency failure link, update the response measures of high-frequency failure link in subsequent battlefield scenario editing process, the present application automatically triggers critical value update when unqualified scheme proportion exceeds limit, promotes the evolution of detection standard with combat environment, significantly reduces the failure rate of scenario scheme in deduction, and provides reliable scheme support for military training.

Description

Technical Field

[0001] The invention belongs to the fields of simulation technology and military information technology, and specifically relates to an efficient and intelligent battlefield scenario editing method. Background Art

[0002] In modern military training and combat preparation, the scientific nature and reliability of battlefield scenario plans directly affect the quality of military exercises and the improvement of actual combat capabilities.

[0003] Existing technologies have many shortcomings. On the one hand, there is a lack of systematic data management of historical unqualified hypothetical scenarios, and a multidimensional analysis library containing basic information, defect information and scenario information has not been built. Risk assessment relies too much on the subjective experience of experts, resulting in low accuracy in identifying high-risk scenarios and prone to missed or misjudgment. On the other hand, the analysis of failure links remains at the qualitative description level, and no quantitative clustering is performed in combination with the weights of combat elements, making it impossible to accurately locate high-frequency failure links. In addition, the detection standards are static and have not been dynamically adjusted according to actual combat conditions such as combat type and environment. There is a hidden risk of "theoretical qualification but actual failure", which leads to a high failure rate of hypothetical scenarios in simulations, seriously restricting the effectiveness of actual combat training.

[0004] To this end, the present invention provides an efficient and intelligent battlefield scenario editing method. Summary of the Invention

[0005] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0006] The technical solution adopted by the present invention to solve its technical problem is:

[0007] Obtain characteristic data of historically unqualified scenarios, build a scenario analysis library, and classify the scenarios in the scenario analysis library into risk levels to identify high-risk scenarios;

[0008] Based on the high-risk scenarios, cluster analysis is performed on the high-risk scenarios according to the failure links, and frequency analysis is performed on each type of failure link to determine the high-frequency failure links;

[0009] In combination with the countermeasures for high-frequency failure links, the failure response intensity threshold for high-frequency failure links is updated during the subsequent battlefield scenario editing process. The updated failure response intensity threshold is implemented and the results are judged. The clustering frequency of high-frequency failure links is positively correlated with the updated failure response intensity threshold.

[0010] The specific process of implementing the updated failure response strength threshold and determining the result is as follows:

[0011] For each high-frequency failure link, conduct effectiveness testing based on the updated failure response intensity threshold. Conduct mission qualification tests on the high-frequency failure links of each scenario, obtain the actual force loss rate, intelligence misjudgment rate, and mission completion rate in real time, determine the mission completion coefficient and failure avoidance performance, and if the failure avoidance performance is less than 1, calculate the qualification judgment coefficient in combination with the mission completion coefficient.

[0012] If the qualified judgment coefficient is greater than the qualified judgment threshold, the corresponding scenario is judged to be qualified in the high-frequency failure link, and it also indicates that the measures are effective;

[0013] The process of obtaining the task completion coefficient is as follows:

[0014] The ratio of the task completion degree in the actual simulation to the preset target completion degree is used as the task completion coefficient.

[0015] The process of obtaining the failure avoidance performance is as follows:

[0016] Analyze the actual troop loss rate and intelligence misjudgment rate to determine the deviation of the troop loss rate and intelligence misjudgment rate;

[0017] The failure avoidance performance is obtained by weighted summation of the deviation of troop loss rate and the deviation of intelligence misjudgment rate;

[0018] The process of determining the deviation of the troop loss rate and the deviation of the intelligence misjudgment rate is as follows:

[0019] The actual troop loss rate is compared with the preset troop loss rate to obtain the troop loss rate deviation;

[0020] The intelligence misjudgment rate is compared with the preset intelligence misjudgment rate to obtain the intelligence misjudgment rate deviation;

[0021] Based on the judgment results, the scenarios that have passed the validity test are determined for simulation operation, and whether there are still scenarios with high-frequency failure links is identified. If so, the proportion of unqualified scenarios is counted and compared to adaptively determine whether the failure response strength critical value of the high-frequency failure link should be iteratively updated.

[0022] As a further solution of the present invention: the specific process of identifying high-risk scenarios is as follows:

[0023] The analytic hierarchy process is used to determine the weight of characteristic data, and the safety impact coefficient is introduced to comprehensively calculate the campaign risk assessment index;

[0024] If the campaign risk assessment index is greater than the campaign risk assessment index threshold, the corresponding scenario will be classified as high risk.

[0025] As a further solution of the present invention, the specific process of clustering the high-risk scenarios according to the failure links is as follows:

[0026] Scenarios classified as high risk are recorded as high-risk scenarios. High-risk scenarios are broken down into several key elements according to the corresponding operational process and integrated into a set of operational elements:

[0027] For each high-risk scenario, count the number of occurrences of each failure link in different combat elements; preset the original frequency of a failure link in the combat element;

[0028] According to the weighted frequency formula, the original frequency is multiplied by the combat element weight to obtain the weighted frequency value of the failure link, and then integrated into the weighted frequency vector of the failure link;

[0029] Use K-Means algorithm for clustering and output failure link clusters.

[0030] As a further solution of the present invention: the process of determining the high-frequency failure link is:

[0031] After the iteration, the number of high-risk scenarios in each type of failure link cluster is counted, the frequency of occurrence of each type of failure link cluster in all high-risk scenarios is calculated, and the failure link clusters with an occurrence frequency greater than the occurrence frequency threshold are screened. The failure link corresponding to the failure link cluster is the high-frequency failure link.

[0032] As a further solution of the present invention: the process of obtaining the updated critical value of failure response strength is as follows:

[0033] For high-frequency failure links, the updated critical value of failure response strength is calculated based on the clustering frequency of the high-frequency failure links.

[0034] As a further solution of the present invention, the specific process of determining whether the failure response strength critical value of the high-frequency failure link needs to be updated again is as follows:

[0035] Extract scenarios that have passed the validity test and run simulations to test whether the scenarios are qualified for high-frequency failure links.

[0036] The unqualified scenarios are recorded as unqualified scenarios; the proportion of unqualified scenarios among the extracted scenarios that passed the validity test is calculated;

[0037] If the proportion of unqualified scenarios is less than or equal to the limit of the proportion of unqualified scenarios, no further update is required;

[0038] If the proportion of unqualified assumptions is greater than the limit of the proportion of unqualified assumptions, it is necessary to enter the failure response strength critical value update again.

[0039] The beneficial effects of the present invention are as follows: obtaining characteristic data of historical unqualified hypothetical scenarios, constructing a hypothetical scenario analysis library, and classifying the hypothetical scenarios in the hypothetical scenario analysis library into risk levels to identify high-risk hypothetical scenarios; clustering the high-risk hypothetical scenarios according to the failure links according to the high-risk hypothetical scenarios, and performing frequency analysis on each type of failure link to determine the high-frequency failure links; combining the response measures for the high-frequency failure links, updating the failure response intensity critical value for the high-frequency failure links in the subsequent battlefield scenario editing process, implementing the updated failure response intensity critical value and making result judgments; obtaining hypothetical scenarios that have passed the validity test, identifying whether there are hypothetical scenarios with high-frequency failure links, and if so, statistically analyzing the number of them and comparing them to determine whether the failure response intensity critical value of the high-frequency failure links needs to be updated again, and if so, updating them again; the present invention accurately identifies high-risk scenarios by constructing a multidimensional analysis library and quantifying the risk index, combining the hierarchical analysis method with the safety impact coefficient, and using K-Means The algorithm clusters failed links, determines high-frequency failure points based on combat element weights, focuses detection resources on key weak links, improves identification efficiency, dynamically updates the response intensity critical value based on failure frequency and risk factor, forms a closed-loop iteration through simulation operation, and automatically triggers the critical value update when the proportion of unqualified solutions exceeds the limit, promotes the evolution of detection standards with the combat environment, significantly reduces the failure rate of hypothetical solutions in simulations, and provides reliable solution support for military training. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention will be further described below with reference to the accompanying drawings.

[0041] Figure 1 This is a flowchart of the steps of an efficient and intelligent battlefield scenario editing method according to an embodiment of the present invention;

[0042] Figure 2 This is a system block diagram of an efficient and intelligent battlefield scenario editing system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0044] Example 1

[0045] See also Figure 1 As shown, an efficient and intelligent battlefield scenario editing method according to an embodiment of the present invention includes the following steps:

[0046] Step 1: Obtain characteristic data of historically unsatisfactory scenarios, build a scenario analysis library, and classify the scenarios in the library into risk levels to identify high-risk scenarios.

[0047] Unsatisfactory scenarios from the past year can be collected from historical simulation logs in wargames.

[0048] Enter unqualified scenario information through the unified scenario defect collection form. The fields include:

[0049] Basic information: plan number, exercise name, operation type (offensive / defensive / special operations), directorate rating.

[0050] Defect information: type of non-conformity (such as strategic misjudgment, tactical loopholes), expert review opinions, and key failure nodes in simulation and deduction.

[0051] Scenario information: combat environment (mountain / city / desert), enemy force size, and our equipment types;

[0052] Based on historical scenarios, obtain characteristic data for each scenario;

[0053] Specifically, characteristic data include but are not limited to: enemy situation misjudgment rate, deviation from the main attack direction, and number of delays in arms coordination;

[0054] Data features were preprocessed, including: missing and outlier handling and data standardization, removal of confidential information, replacement with numbers, and unified military measurement standards: force density: refer to the standard values ​​in the "Combined Forces Campaign Tactics Calculation Manual"; fire damage probability: calculated based on weapon equipment performance parameter models (such as the hit rate of a certain type of artillery);

[0055] Use a relational database (such as PostgreSQL) to design the table structure:

[0056] Plan basic information table: stores plan ID, operation type, rating, and timestamp;

[0057] Feature details table: Associated with the solution ID, stores quantitative features such as "enemy misjudgment rate" and "cooperative conflict number";

[0058] Review opinion table: stores expert text opinions and automatically extracted keyword tags, and builds an analysis library for unqualified scenarios;

[0059] Combined with the characteristic data of the scenario, the safety impact coefficient is introduced to comprehensively calculate the campaign risk assessment index;

[0060] Specifically, the calculation process of the campaign risk assessment index is as follows:

[0061] The analytic hierarchy process is used to determine the weights and construct a linear weighted formula: ,in, is the safety impact factor, is the weight of the jth feature parameter. The weight distribution is determined by those skilled in the art based on industry experience. is the standardized value of the j-th feature parameter;

[0062] The analytic hierarchy process is a method well known to those skilled in the art;

[0063] The safety impact coefficient is set as 1 if the scenario does not result in campaign failure. If the scenario does result in campaign failure, the safety impact coefficient can be set to a value greater than 1, generally 1.2 or 1.5, and is determined by those skilled in the art based on the characteristics of actual campaign failure.

[0064] In some embodiments, the campaign risk assessment index is compared with the level classification threshold, and the specific comparison process is as follows:

[0065] If the campaign risk assessment index is less than or equal to the campaign risk assessment index threshold, the corresponding scenario is classified as low risk;

[0066] If the campaign risk assessment index is greater than the campaign risk assessment index threshold, the corresponding scenario is classified as high risk;

[0067] Step 2: Based on the high-risk scenarios, cluster the high-risk scenarios according to the failure links, and perform frequency analysis on each failure link to determine the high-frequency failure links;

[0068] Scenarios classified as high risk are recorded as high risk scenarios;

[0069] Decompose high-risk scenarios into several key elements (such as reconnaissance, command and control, communications, strike, and support) according to the corresponding operational processes and integrate them into a set of operational elements:

[0070] For each high-risk scenario, count the number of occurrences of each failure link in different combat elements; preset the original frequency of a failure link in the combat element;

[0071] According to the weighted frequency formula, the original frequency is multiplied by the factor weight to obtain the weighted frequency value of the failure link, and then integrated into the weighted frequency vector of the failure link;

[0072] It is understandable that if the original frequency dimensions of each combat element are different, the vector needs to be normalized using the Z-score to eliminate the dimension difference. The element weights are set by those skilled in the art based on historical experience;

[0073] Use K-Means algorithm to cluster and determine the number of clusters K;

[0074] The method to determine the number of clusters K is as follows: by using the elbow method, the sum of squared errors (SSE) under different K values ​​is calculated; where is the kth cluster, and is the coordinate of the cluster center;

[0075] Select the K value that slows down the SSE decline trend as the optimal number of clusters.

[0076] For example, if the initial setting K=6, traverse K=1 to K=6, and calculate the sum of squared errors corresponding to each K, the calculation results are that SEE is 120000, 60000, 25000, 20000, 23000, and 17000 corresponding to K values ​​1-6 respectively; draw the K-SSE curve, and observe that the slope of the curve becomes significantly slower when K=4, so K=4 is selected as the optimal number of clusters;

[0077] According to the determined K value, the K-Means++ algorithm is used to initialize the cluster center;

[0078] The initial cluster center includes: randomly selecting the weighted frequency vector of any failed link as the center;

[0079] The distance from the weighted frequency vector of each failure link to the nearest selected cluster center is calculated using the Euclidean distance formula;

[0080] Recalculate the cluster centers of each cluster and iterate until the centers no longer change significantly or the maximum number of iterations is reached. The maximum number of iterations is set to 50 and the failure link clusters are output. Each cluster corresponds to a type of failure link.

[0081] For example, in link A: "Reconnaissance Misjudgment", the weighted frequency vector is [1.2, 0.2, 0.1, 0.1] (the reconnaissance factor has a high weight, and the other factors have a low impact);

[0082] Link B: “Command delay”, with a weighted frequency vector of [0.3, 1.6, 0.2, 0.1] (command factor has a high weight, and other factors have a low influence);

[0083] The Euclidean distance between the two is:

[0084] Since the weighted frequencies of the two in the core elements (reconnaissance / command) are significantly different and far apart, they will be assigned to different categories when clustering;

[0085] After the iteration, the number of high-risk scenarios in each failure link cluster is counted, and the frequency of occurrence of each failure link cluster in all high-risk scenarios is calculated. The frequency calculation formula is: frequency of a cluster = number of high-risk scenarios in the cluster / total number of high-risk scenarios;

[0086] Set a frequency threshold to filter out clusters with frequencies greater than the frequency threshold. The failure link corresponding to the cluster is the high-frequency failure link.

[0087] Step 3: Based on the countermeasures for high-frequency failure links, update the failure response intensity threshold for high-frequency failure links during subsequent battlefield scenario editing, implement the updated failure response intensity threshold, and conduct result judgment;

[0088] Extract all scenarios belonging to the high-frequency failure link cluster and associate the following data:

[0089] Combat element parameters: historical weights of combat elements corresponding to failure links (such as reconnaissance and command and control), and scenario adaptability (for example, communications elements have a higher weight in urban warfare);

[0090] Failure impact parameters: troop loss rate, intelligence misjudgment rate;

[0091] Historical data on countermeasures: preventive measures designed for this link in previous scenarios (such as backup communication links) and their effectiveness in simulations (number of successful avoidances / total number of applications);

[0092] For high-frequency failure links, the updated critical value of failure response strength is calculated based on the clustering frequency of high-frequency failure links. The calculation formula is: ;in, Updated failure response strength threshold; is the original critical value; f is the cluster frequency corresponding to the high-frequency failure link, which is the normalized value; is the risk factor, which is set by those skilled in the art based on experience;

[0093] Implement the effectiveness detection and determination of the critical value of failure response strength after the update;

[0094] For each high-frequency failure link, effectiveness testing is conducted based on the updated failure response intensity threshold. Mission eligibility testing is conducted on the high-frequency failure links of each scenario, and actual troop loss rate, intelligence misjudgment rate, and mission completion rate are obtained in real time.

[0095] Based on the task completion coefficient and failure avoidance performance, determine whether the corresponding scenario is qualified in the high-frequency failure link;

[0096] The failure avoidance performance is obtained by weighted summing the deviation of the force loss rate and the deviation of the intelligence misjudgment rate. The weights are set by technical personnel based on the importance of combat elements.

[0097] The actual troop loss rate is compared with the preset troop loss rate to obtain the troop loss rate deviation;

[0098] The intelligence misjudgment rate is compared with the preset intelligence misjudgment rate to obtain the intelligence misjudgment rate deviation;

[0099] If the failure avoidance performance is greater than 1, the corresponding scenario is judged to be unqualified in the high-frequency failure link;

[0100] If the failure avoidance performance is less than 1, the task completion coefficient is combined to determine the pass judgment coefficient. The calculation formula is: ; Among them, HP is the qualification judgment coefficient, RW is the task completion coefficient, and SG is the failure avoidance performance;

[0101] The ratio of the actual task completion degree in the simulation to the preset target completion degree is used as the task completion coefficient;

[0102] If the qualification coefficient is less than or equal to the qualification threshold, the corresponding scenario is judged to be unqualified in the high-frequency failure link, indicating that the countermeasures are ineffective;

[0103] If the qualified judgment coefficient is greater than the qualified judgment threshold, the corresponding scenario is judged to be qualified in the high-frequency failure link, indicating that the countermeasures are effective;

[0104] Step 4: Obtain scenarios that have passed the effectiveness test and identify whether there are still scenarios with high-frequency failure links. If so, determine whether the failure response strength threshold of the high-frequency failure link needs to be updated based on the proportion of unqualified scenarios. If necessary, update it again.

[0105] Extract scenarios that have passed the validity test and run simulations to test whether the scenarios are qualified for high-frequency failure links.

[0106] Record unqualified scenarios as unqualified scenarios; count the number of unqualified scenarios among the scenarios, and calculate the proportion of unqualified scenarios among the scenarios;

[0107] Compare the proportion of unqualified scenarios with the limit of the proportion of unqualified scenarios. If the proportion of unqualified scenarios is less than or equal to the limit of the proportion of unqualified scenarios, it means that the current failure response strength critical value is valid and does not need to be updated again.

[0108] If the proportion of unqualified scenarios exceeds the limit, it means that the current failure response strength threshold still has insufficient response risk and needs to be updated again.

[0109] The technical solution of this embodiment is: obtain the characteristic data of historical unqualified hypothetical scenarios, build a hypothetical scenario analysis library, and classify the hypothetical scenarios in the hypothetical scenario analysis library into risk levels to identify hypothetical scenarios with high risk levels; based on the hypothetical scenarios with high risk levels, cluster the hypothetical scenarios with high risk levels according to the failure links, and perform frequency analysis on each type of failure link to determine the high-frequency failure links; in combination with the response measures for the high-frequency failure links, update the failure response intensity critical value for the high-frequency failure links in the subsequent battlefield scenario editing process, implement the updated failure response intensity critical value and make result judgments; obtain hypothetical scenarios that have passed the validity test, identify whether there are hypothetical scenarios with high-frequency failure links, and if so, count the number of percentages and compare them to determine whether the failure response intensity critical value of the high-frequency failure links needs to be updated again, and if so, update it again; the present invention accurately identifies high-risk scenarios by building a multidimensional analysis library and quantifying the risk index, combining the hierarchical analysis method with the safety impact coefficient, and using K-Means The algorithm clusters failed links, determines high-frequency failure points based on combat element weights, focuses detection resources on key weak links, improves identification efficiency, dynamically updates the response intensity critical value based on failure frequency and risk factor, forms a closed-loop iteration through simulation operation, and automatically triggers the critical value update when the proportion of unqualified solutions exceeds the limit, promotes the evolution of detection standards with the combat environment, significantly reduces the failure rate of hypothetical solutions in simulations, and provides reliable solution support for military training.

[0110] Example 2

[0111] See also Figure 2 As shown, an efficient and intelligent battlefield scenario compilation system according to an embodiment of the present invention includes the following modules:

[0112] Data acquisition module: This module obtains characteristic data of historically unqualified scenarios, builds a scenario analysis library, and classifies the scenarios in the library into risk levels, identifying high-risk scenarios.

[0113] Failure link analysis module: Based on high-risk scenarios, cluster high-risk scenarios according to failure links, and perform frequency analysis on each type of failure link to identify high-frequency failure links;

[0114] Effectiveness judgment module: Combined with the response measures for high-frequency failure links, it updates the failure response intensity threshold for high-frequency failure links during the subsequent battlefield scenario editing process, implements the updated failure response intensity threshold, and conducts result judgment;

[0115] Detection and update module: obtains the assumptions that have passed the effectiveness test, identifies whether there are assumptions with high-frequency failure links, and if so, counts and compares the proportions of the assumptions to determine whether the failure response strength critical value of the high-frequency failure link needs to be updated again. If necessary, it is updated again.

[0116] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. An efficient and intelligent battlefield scenario editing method, characterized by: include: Obtain characteristic data of historically unqualified scenarios, build a scenario analysis library, and classify the scenarios in the scenario analysis library into risk levels to identify high-risk scenarios; Based on the high-risk scenarios, cluster analysis is performed on the high-risk scenarios according to the failure links, and frequency analysis is performed on each type of failure link to determine the high-frequency failure links; In combination with the countermeasures for high-frequency failure links, the failure response intensity critical value for high-frequency failure links in the subsequent battlefield scenario editing process is updated, the updated failure response intensity critical value is implemented and the results are judged. The clustering frequency of high-frequency failure links is positively correlated with the updated failure response intensity critical value; The specific process of implementing the updated failure response strength threshold and determining the result is as follows: For each high-frequency failure link, conduct effectiveness testing based on the updated failure response intensity threshold. Conduct mission qualification tests on the high-frequency failure links of each scenario, obtain the actual force loss rate, intelligence misjudgment rate, and mission completion rate in real time, determine the mission completion coefficient and failure avoidance performance, and if the failure avoidance performance is less than 1, calculate the qualification judgment coefficient in combination with the mission completion coefficient. If the qualified judgment coefficient is greater than the qualified judgment threshold, the corresponding scenario is judged to be qualified in the high-frequency failure link, and it also indicates that the measures are effective; The process of obtaining the task completion coefficient is as follows: The ratio of the actual task completion degree in the simulation to the preset target completion degree is used as the task completion coefficient; The process of obtaining the failure avoidance performance is as follows: Analyze the actual troop loss rate and intelligence misjudgment rate to determine the deviation of the troop loss rate and intelligence misjudgment rate; The failure avoidance performance is obtained by weighted summation of the deviation of troop loss rate and the deviation of intelligence misjudgment rate; The process of determining the deviation of the troop loss rate and the deviation of the intelligence misjudgment rate is as follows: The actual troop loss rate is compared with the preset troop loss rate to obtain the troop loss rate deviation; The intelligence misjudgment rate is compared with the preset intelligence misjudgment rate to obtain the intelligence misjudgment rate deviation; Based on the judgment results, the scenarios that have passed the validity test are determined for simulation operation, and whether there are still scenarios with high-frequency failure links is identified. If so, the proportion of unqualified scenarios is counted and compared to adaptively determine whether the failure response strength critical value of the high-frequency failure link should be iteratively updated.

2. The efficient and intelligent battlefield scenario editing method according to claim 1, characterized in that: The specific process of identifying high-risk scenarios is as follows: The analytic hierarchy process is used to determine the weight of characteristic data, and the safety impact coefficient is introduced to comprehensively calculate the campaign risk assessment index; If the campaign risk assessment index is greater than the campaign risk assessment index threshold, the corresponding scenario will be classified as high risk.

3. The efficient and intelligent battlefield scenario editing method according to claim 1, characterized in that: The specific process of clustering the high-risk scenarios according to the failure links is as follows: Scenarios classified as high risk are recorded as high-risk scenarios. High-risk scenarios are broken down into several key elements according to the corresponding operational process and integrated into a set of operational elements: For each high-risk scenario, count the number of times each failure link occurs in different combat elements; Preset the original frequency of a certain failure link on the combat element; According to the weighted frequency formula, the original frequency is multiplied by the combat element weight to obtain the weighted frequency value of the failure link, and then integrated into the weighted frequency vector of the failure link; Use K-Means algorithm for clustering and output failure link clusters.

4. The efficient and intelligent battlefield scenario editing method according to claim 3, characterized in that: The process of determining the high-frequency failure link is as follows: After the iteration, the number of high-risk scenarios in each type of failure link cluster is counted, the frequency of occurrence of each type of failure link cluster in all high-risk scenarios is calculated, and the failure link clusters with an occurrence frequency greater than the occurrence frequency threshold are screened. The failure link corresponding to the failure link cluster is the high-frequency failure link.

5. The efficient and intelligent battlefield scenario editing method according to claim 1, characterized in that: The specific process of determining whether the critical value of the failure response strength of the high-frequency failure link needs to be updated again is as follows: Extract scenarios that have passed the validity test, run simulations, and record unqualified scenarios as unqualified scenarios; calculate the proportion of unqualified scenarios among the extracted scenarios that have passed the validity test; If the proportion of unqualified assumptions is greater than the limit of the proportion of unqualified assumptions, it is necessary to enter the failure response strength critical value update again.

Images