Simulation training method, system, electronic device, storage medium and program product
By acquiring and parsing standardized system architecture data, generating target scenario data, and conducting simulation training, the problems of scenario misalignment and lack of targeted evaluation in existing simulation training methods are solved, achieving background consistency in the simulation training process and accuracy in the evaluation results.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- AEROSPACE INFORMATION RES INST CAS
- Filing Date
- 2026-03-18
- Publication Date
- 2026-06-09
AI Technical Summary
Existing simulation training methods suffer from poor scenario fit, inconsistent scenarios, and lack of targeted evaluation, resulting in a disconnect between training scenarios and system architecture design, and insufficient accuracy of evaluation results.
Acquire standardized system architecture data, parse it into system interface description view data, system evolution description view data, capability task mapping view data, and global view data. Based on this data, extract architecture constraint rules, generate target scenario data, conduct simulation training in the global background model, collect process data in real time, and finally generate system evaluation results.
By strictly adhering to the top-level architecture specifications, the consistency of the background and the authenticity of the data in the simulation training process are ensured, thereby improving the relevance and accuracy of the evaluation results and reducing the blindness and subjective bias of manual configuration.
Smart Images
Figure CN122175454A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of national defense simulation training technology, and in particular to a simulation training method, system, electronic device, storage medium, and program product. Background Technology
[0002] Simulation training systems are core support tools for defense training and system evaluation. Their basic functions typically include scenario editing, simulation training, and system effectiveness evaluation. In existing simulation training mechanisms, the setting of interaction logic between equipment, the construction of combat scenario rules, and the establishment of final evaluation indicators mainly rely on manual parameter input and subjective configuration. This results in scenario preparation being highly subjective and not aligned with the system, poor consistency between the simulated scenario and the top-level architecture design, and a lack of specificity in the post-simulation system effectiveness evaluation.
[0003] Therefore, how to solve the problems of existing simulation training methods, such as scenario misalignment, poor scenario consistency, and lack of targeted evaluation, has become an urgent technical challenge in this field. Summary of the Invention
[0004] This invention provides a simulation training method, system, electronic device, storage medium, and program product to solve the problems of existing simulation training methods, such as scenario misalignment, poor scenario consistency, and lack of targeted evaluation.
[0005] This invention provides a simulation training method, comprising: Obtain standardized system architecture data, parse the standardized system architecture data to obtain system interface description view data, system evolution description view data, capability task mapping view data and global view data; Based on the system interface description view data and the architecture evolution description view data, architectural constraint rules are extracted, and user scenario editing operations are constrained based on the architectural constraint rules to generate target scenario data; A global background model is generated based on the global view data; The target scenario data is loaded into the global background model for simulation training, and simulation training process data is collected in real time. Based on the capability task mapping view data and the simulation training process data, system evaluation results are generated.
[0006] According to a simulation training method provided by the present invention, the step of extracting architectural constraint rules based on the system interface description view data and the architecture evolution description view data, constraining the user's scenario editing operations based on the architectural constraint rules, and generating target scenario data includes: Based on the system interface description view data, extract the interface constraint rules; In response to a user's equipment interaction configuration request, the equipment interaction configuration options corresponding to the equipment interaction configuration request are adjusted based on the interface constraint rules. Receive inter-equipment interaction scenario data selected by the user based on the adjusted inter-equipment interaction configuration options; Based on the system evolution description view data, the evolution stages and their constraints are extracted; In response to a user's scenario evolution setting request, the scenario evolution configuration parameters corresponding to the scenario evolution setting request are limited based on the evolution stage and its constraints; Receive scenario evolution scenario data input by the user based on the defined scenario evolution configuration parameters; The architecture constraint rules include the interface constraint rules, the evolution stages and their constraints, and the target scenario data includes the equipment interaction scenario data and the scenario evolution scenario data.
[0007] According to a simulation training method provided by the present invention, generating system evaluation results based on the capability task mapping view data and the simulation training process data includes: Based on the capability task mapping view data, obtain the capability task mapping matrix and its weight vector; Based on the capability-task mapping matrix and its weight vector, an evaluation index system is constructed, which includes capability nodes, task nodes, and the supporting weights between the capability nodes and task nodes. Based on the evaluation index system, analyze the simulation training process data to obtain the actual achievement rate of each capability node; Based on the actual achievement rate and the supporting weights, calculate the system effectiveness score and the system contribution rate; The system evaluation results include the system performance score and the system contribution rate.
[0008] According to a simulation training method provided by the present invention, the step of analyzing the simulation training process data based on the evaluation index system to obtain the actual achievement rate of each capability node includes: Extract the operational metrics corresponding to each capability node from the simulated training process data; The basic performance value of the operational indicators is determined by comparing the operational indicators with preset threshold values. The actual achievement rate of each capability node is obtained by normalizing the basic performance value.
[0009] According to a simulation training method provided by the present invention, the step of generating a global background model based on the global view data includes: Extract target background information from the global view data, wherein the target background information includes at least one of combat zone boundary parameters, force composition parameters, and battlefield environment constraint parameters; Using a preset scene modeling engine, the global background model is generated based on the target background information.
[0010] According to a simulation training method provided by the present invention, the step of acquiring standardized architecture data and parsing the standardized architecture data to obtain system interface description view data, architecture evolution description view data, capability task mapping view data, and global view data includes: The standardized architecture file is read through a preset data exchange interface and converted into the standardized architecture data. The standardized system architecture data is validated, and the validation includes at least one of the following: core field non-empty validation, format validation, and mapping relationship logical consistency validation. When the verification passes, the standardized architecture data is parsed to obtain the system interface description view data, the architecture evolution description view data, the capability task mapping view data, and the global view data.
[0011] The present invention also provides a simulation training system, comprising: The data access module is used to acquire standardized system architecture data, parse the standardized system architecture data, and obtain system interface description view data, system evolution description view data, capability task mapping view data, and global view data. The scenario editing module is used to extract architectural constraint rules based on the system interface description view data and the architecture evolution description view data, constrain the user's scenario editing operation based on the architectural constraint rules, and generate target scenario data. The scene management module is used to generate a global background model based on the global view data; The simulation training module is used to load the target scenario data into the global background model for simulation training and to collect simulation training process data in real time. The system evaluation module is used to generate system evaluation results based on the capability task mapping view data and the simulation training process data.
[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the simulation training method as described above.
[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the simulation training method as described above.
[0014] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the simulation training method as described above.
[0015] The simulation training method, system, electronic device, storage medium, and program product provided by this invention first acquires and parses standardized system architecture data to obtain system interface description view data, system evolution description view data, capability task mapping view data, and global view data. Then, based on the system interface description view data and system evolution description view data, architectural constraint rules are extracted. These rules constrain user scenario editing operations, generating target scenario data. This method eliminates the blindness and subjective bias of manual scenario configuration, ensuring from the source that the interaction logic and evolution process strictly adhere to the top-level architecture specifications. Next, a global background model is generated based on the global view data, and the target scenario data is loaded into the global background model for simulation training, with real-time acquisition of simulation training process data. Because the global background model directly inherits from the macro-definition of the top-level architecture, the target scenario data can run under a unified global background model, solving the problem of poor background consistency in different training scenarios in existing technologies and ensuring the authenticity and effectiveness of the simulation training process data. Finally, based on the capability task mapping view data and the simulation training process data, system evaluation results are generated. By integrating capability task mapping view data, objective and accurate system-level data support is provided for system evaluation, improving the relevance and accuracy of system evaluation results. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1 This is one of the flowcharts of the simulation training method provided by the present invention.
[0018] Figure 2 This is the second flowchart of the simulation training method provided by the present invention.
[0019] Figure 3 This is the third flowchart of the simulation training method provided by the present invention.
[0020] Figure 4 This is the fourth flowchart of the simulation training method provided by the present invention.
[0021] Figure 5 This is a schematic diagram of the structure of the simulation training system provided by the present invention.
[0022] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation
[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0024] Simulation training systems are core support tools for defense training and system evaluation. Their basic functions typically include scenario editing, simulation training, and system effectiveness evaluation. In existing simulation training mechanisms, the setting of interaction logic between equipment, the construction of combat scenario rules, and the establishment of final evaluation indicators mainly rely on manual parameter input and subjective configuration. This results in scenario preparation being highly subjective and not aligned with the system, poor consistency between the simulated scenario and the top-level architecture design, and a lack of specificity in the post-simulation system effectiveness evaluation.
[0025] Therefore, how to solve the problems of existing simulation training methods, such as scenario misalignment, poor scenario consistency, and lack of targeted evaluation, has become an urgent technical challenge in this field.
[0026] Analysis revealed that existing simulation training systems do not fully utilize standardized architecture data, treating it merely as a reference for independent architecture design documents. This lack of deep integration between the architecture data and the training system's functions results in a lack of direct support from standardized architecture data for core system functionalities. Consequently, training scenarios become disconnected from the system architecture design, evaluation results lack accuracy, and scenario consistency is poor, failing to meet the defense sector's needs for systematic simulation training.
[0027] Taking a typical military simulation training system as an example, its scenario editing module constructs training scenarios by manually inputting equipment models, interaction logic, and scenario evolution rules. It does not associate the system evolution constraints in the system evolution description view data and the interface standards in the system interface description view data, which may cause the scenario to be out of touch with the actual system architecture design. The system evaluation module evaluates based on preset general indicators (such as completion time and mission success rate) without introducing the capability-task mapping relationship in the capability-task mapping view data, which makes the evaluation results unable to accurately reflect the system capability's support effectiveness for the mission. During the scenario construction process, background information (such as combat area and force deployment range) is set separately by the user without using unified panoramic view data, resulting in poor background consistency for different training scenarios.
[0028] Therefore, in this invention, based on the original simulation training system, four types of key view data from the standardized system architecture data are embedded into the core processes of scenario editing, system evaluation, and scenario construction of the simulation training system. By directly supporting the core functions of simulation training through these four types of key view data, the pain points of traditional simulation training systems are solved, and the synergistic linkage between simulation training and system architecture design is realized.
[0029] This invention proposes a simulation training method, system, electronic device, storage medium, and program product, which are described below in conjunction with... Figures 1-6 Describe it.
[0030] Figure 1 This is one of the flowcharts illustrating the simulation training method provided by the present invention, such as... Figure 1 As shown, the simulation training method includes steps S110, S120, S130, S140, and S150.
[0031] Step S110: Obtain standardized system architecture data, parse the standardized system architecture data to obtain system interface description view data, system evolution description view data, capability task mapping view data, and global view data.
[0032] Standardized architecture data refers to top-level architecture model data built based on the model systems engineering concept, such as data generated by standards like DODAF 2.0 (Department of Defense Architecture Framework Version 2.0), MODAF (Ministry of Defence Architecture Framework), and UAF (Unified Architecture Framework).
[0033] Currently, DODAF 2.0 is widely used in the defense field as the standard for system architecture design. Therefore, in this embodiment, DODAF 2.0 is used as an example for illustration.
[0034] System interface description view data defines the interaction standards between systems within the architecture, specifically including interface types, parameters, and interaction protocols. In DODAF 2.0, system interface description view data corresponds to SV2 (System View2). Figure 2 ).
[0035] System evolution description view data is used to record the development stages, evolution rules, and constraints of the system. In DODAF 2.0, the system evolution description view data corresponds to SV7 (System View 7).
[0036] Capability-task mapping view data is used to clarify the correspondence between core system capabilities and specific tasks, as well as the strength of their support. In DODAF 2.0, capability-task mapping view data corresponds to CV6 (Capability View 6). Figure 6 ).
[0037] Global view data provides metadata about the overall system context, including operational area boundary parameters, force composition parameters, and battlefield environment constraints. In DODAF 2.0, global view data corresponds to AV1 (All View 1, panoramic view). Figure 1 ).
[0038] Step S120: Based on the system interface description view data and the architecture evolution description view data, extract architecture constraint rules, constrain the user's scenario editing operations based on the architecture constraint rules, and generate target scenario data.
[0039] Based on system interface description view data and architecture evolution description view data, architectural constraint rules are extracted, and these architectural constraint rules are used to strictly constrain the user's scenario editing operations, thereby generating scenario data that conforms to objective military laws, denoted as target scenario data.
[0040] In one embodiment, interface constraint rules are extracted based on system interface description view data; in response to a user's inter-equipment interaction configuration request, the inter-equipment interaction configuration options corresponding to the inter-equipment interaction configuration request are adjusted based on the interface constraint rules; the inter-equipment interaction scenario data selected by the user based on the adjusted inter-equipment interaction configuration options is received; evolution stages and their constraints are extracted based on system evolution description view data; in response to a user's scenario evolution setting request, the scenario evolution configuration parameters corresponding to the scenario evolution setting request are limited based on the evolution stages and their constraints; and scenario evolution scenario data input by the user based on the limited scenario evolution configuration parameters is received. The architecture constraint rules include interface constraint rules, evolution stages and their constraints, and the target scenario data includes inter-equipment interaction scenario data and scenario evolution scenario data. The specific execution process can be referred to in the following embodiments, which will not be elaborated here.
[0041] Step S130: Generate a global background model based on the global view data.
[0042] Step S140: Load the target scenario data into the global background model for simulation training, and collect simulation training process data in real time.
[0043] Generate a global background model based on global view data.
[0044] In one embodiment, target background information is extracted from the global view data. This target background information includes at least one of operational area boundary parameters, force composition parameters, and battlefield environment constraint parameters. Then, a global background model is generated based on the target background information using a preset scene modeling engine. The specific execution process can be found in the following embodiments, and will not be elaborated upon here.
[0045] Load the global background model and load the target scenario data into the global background model to integrate the scenario equipment and mission flow with the area and force deployment in the background model to generate a complete training scenario. For example, deploy the scenario strike mission equipment to the combat area defined by the global view data.
[0046] Users initiate simulation training through the user interface. In response, the system receives the model training instructions and then runs the simulation training according to the intended evolution process and the global background model. The system collects simulation training data in real time, such as equipment interaction logs, task completion progress, and capability performance.
[0047] Step S150: Generate system evaluation results based on the capability task mapping view data and the simulation training process data.
[0048] Finally, based on the capability task mapping view data and the simulation training process data, the system evaluation results are generated.
[0049] In one embodiment, a capability-task mapping matrix and its weight vector are obtained based on capability-task mapping view data. An evaluation index system is constructed based on the capability-task mapping matrix and its weight vector. The evaluation index system includes capability nodes, task nodes, and supporting weights between capability nodes and task nodes. Based on the evaluation index system, simulated training process data is analyzed to obtain the actual achievement rate of each capability node. Based on the actual achievement rate and supporting weights, the system performance score and system contribution rate are calculated. The system evaluation results include the system performance score and the system contribution rate. The specific execution process can be found in the following embodiments, which will not be elaborated here.
[0050] Furthermore, after calculating the system performance score and system contribution rate, a visual evaluation report can be generated based on the system performance score and system contribution rate, and stored in the system database. This visual evaluation report can sort the system contribution rates and display the system performance score in chart form.
[0051] The simulation training method provided in this invention first acquires and parses standardized system architecture data to obtain system interface description view data, system evolution description view data, capability task mapping view data, and global view data. Then, based on the system interface description view data and system evolution description view data, architectural constraint rules are extracted. These rules constrain the user's scenario editing operations, generating target scenario data. This eliminates the blindness and subjective bias of manual scenario configuration, ensuring from the source that the interaction logic and evolution process strictly adhere to the top-level architecture specifications. Next, a global background model is generated based on the global view data, and the target scenario data is loaded into the global background model for simulation training, with real-time acquisition of simulation training process data. Since the global background model directly inherits from the macro-definition of the top-level architecture, the target scenario data can run under a unified global background model, solving the problem of poor background consistency in different training scenarios in existing technologies and ensuring the authenticity and effectiveness of the simulation training process data. Finally, based on the capability task mapping view data and the simulation training process data, system evaluation results are generated. By integrating capability task mapping view data, objective and accurate system-level data support is provided for system evaluation, improving the relevance and accuracy of system evaluation results.
[0052] Based on any of the above embodiments Figure 2 This is the second flowchart of the simulation training method provided by the present invention, as shown below. Figure 2 As shown, step S120 includes: step S121, step S122, step S123, step S124, step S125 and step S126.
[0053] Step S121: Extract interface constraint rules based on the system interface description view data.
[0054] Step S122: In response to the user's equipment interaction configuration request, adjust the equipment interaction configuration options corresponding to the equipment interaction configuration request based on the interface constraint rules.
[0055] Step S123: Receive the inter-equipment interaction scenario data selected by the user based on the adjusted inter-equipment interaction configuration options.
[0056] The embodiments of the present invention are implemented through the scenario editing module of the simulation training system. Based on the traditional scenario editing functions (including scenario process design, equipment parameter configuration, task objective setting, etc.), system interface description view data and system evolution description view data are integrated to realize scenario construction with system architecture-level data support.
[0057] Using the traditional scenario editing function, users can set basic information about the training scenario through a visual interface, such as training type, task objective, and time range.
[0058] The integration process of system interface description view data is as follows: When a user configures the interaction logic between equipment, the system automatically retrieves the corresponding equipment's system interface description view data from the data access module. Based on the system interface description view data, interface constraint rules are extracted, including but not limited to: interaction protocols, parameter transmission formats, etc. Then, based on the interface constraint rules, the equipment interaction configuration options are adjusted to provide standardized interface options. Users do not need to manually input these options; they can simply select them, ensuring that equipment interaction conforms to the interface standards of the system architecture design. For example, when configuring "data interaction between radar equipment and missile equipment," the system automatically loads the preset radar-missile interface protocol from the system interface description view data, such as UDP (User Datagram Protocol) protocol with a data transmission rate of 10Mbps, and then adjusts the corresponding equipment interaction configuration options to avoid interface incompatibility caused by manual settings.
[0059] After the user makes a selection, the system will receive the inter-equipment interaction scenario data selected by the user based on the adjusted inter-equipment interaction configuration options.
[0060] Step S124: Based on the system evolution description view data, extract the evolution stages and their constraints.
[0061] Step S125: In response to the user's scenario evolution setting request, the scenario evolution configuration parameters corresponding to the scenario evolution setting request are limited based on the evolution stage and its constraints.
[0062] Step S126: Receive scenario evolution scenario data input by the user based on the defined scenario evolution configuration parameters.
[0063] The architecture constraint rules include the interface constraint rules, the evolution stages and their constraints, and the target scenario data includes the equipment interaction scenario data and the scenario evolution scenario data.
[0064] The integration process of system evolution description view data is as follows: In the scenario evolution rule design phase, the system extracts the evolution stages and constraints from the system evolution description view data. Users design scenario flows based on the evolution paths defined in the system evolution description view data (e.g., "reconnaissance phase → strike phase → withdrawal phase"), and the flow constraints (e.g., maximum duration of each stage, equipment deployment quantity limits) are used to limit the scenario evolution configuration parameters, ensuring consistency with the system evolution description view data. For example, if the system evolution description view data specifies that "the strike phase duration shall not exceed 2 hours," then the maximum value of the duration setting box for that stage in the scenario editing interface will automatically be locked at 2 hours, preventing it from exceeding the system constraints.
[0065] After the user inputs the design based on the defined scenario evolution configuration parameters, the system receives the scenario evolution scenario data input by the user based on the defined scenario evolution configuration parameters.
[0066] Correspondingly, the target scenario data includes inter-equipment interaction scenario data and scenario evolution scenario data.
[0067] Furthermore, compliance verification is performed on the target scenario data. The compliance verification includes at least one of the following: (1) Interface standard verification, i.e., checking whether it conforms to the interface standard; (2) Evolution constraint verification, i.e., checking whether it conforms to the evolution constraint conditions.
[0068] Furthermore, after compliance verification is passed, a scenario file that can be called by the simulation training module is generated based on the target scenario data. The file is in JSON (JavaScript Object Notation) format and stored in the system database.
[0069] The simulation training method provided in this invention integrates system interface description view data and system evolution description view data. When users configure equipment interaction logic, the standardized interface data of the system interface description view data is automatically called. When designing scenario evolution rules, the system evolution constraints of the system evolution description view data are followed. This achieves scenario construction supported by standardized system architecture-level data. At the same time, it ensures that the scenario strictly follows the system interface standards and evolution constraints, improving the scenario compliance rate and the fit with the system. It also reduces the workload of manual configuration and improves construction efficiency.
[0070] Based on any of the above embodiments Figure 3 This is the third flowchart of the simulation training method provided by the present invention, as shown below. Figure 3 As shown, step S150 includes: step S151, step S152, step S153 and step S154.
[0071] Step S151: Based on the capability task mapping view data, obtain the capability task mapping matrix and its weight vector.
[0072] The embodiments of the present invention are implemented through the system evaluation module of the simulation training system. On the basis of traditional evaluation functions, capability task mapping view data is integrated to realize the system effectiveness and contribution rate evaluation guided by the system capability-task framework.
[0073] After obtaining the capability-task mapping view data, the capability-task mapping matrix and its weight vector are obtained based on the capability-task mapping view data.
[0074] Step S152: Based on the capability-task mapping matrix and its weight vector, construct an evaluation index system. The evaluation index system includes capability nodes, task nodes, and the support weights between the capability nodes and task nodes.
[0075] Based on the capability-task mapping matrix and its weight vector, an evaluation index system is constructed. The evaluation index system includes capability nodes, task nodes, and the supporting weights between capability nodes and task nodes.
[0076] For example, for a "joint air defense mission," the dependencies are identified as "area reconnaissance capability" and "precision strike capability." Simultaneously, the weight vectors of these two capabilities for the mission are extracted, such as [0.4, 0.6]. Correspondingly, the evaluation index system can use "joint air defense mission" as the root node (i.e., the mission node), "area reconnaissance capability" and "precision strike capability" as leaf nodes (i.e., capability nodes), and use 0.4 and 0.6 as directed edge attributes (i.e., support weights) connecting the capability nodes and the mission nodes.
[0077] Step S153: Based on the evaluation index system, analyze the simulation training process data to obtain the actual achievement rate of each capability node.
[0078] Based on this evaluation index system, we analyze the data from the simulated training process to obtain the actual achievement rate for each capability node.
[0079] Actual achievement rate measures the extent to which a certain ability is demonstrated in actual simulation. The calculation method can be set according to the specific ability and the simulation training data; no specific limitations are specified here.
[0080] Step S154: Calculate the system performance score and system contribution rate based on the actual achievement rate and the support weight.
[0081] The system evaluation results include the system performance score and the system contribution rate.
[0082] Finally, based on the actual achievement rate and supporting weights, the system effectiveness score and system contribution rate are calculated.
[0083] In one embodiment, the formula for calculating the system performance score is as follows: System effectiveness score = Σ (achievement rate of a certain capability × weight of the capability in supporting the task) × 100%.
[0084] In one embodiment, the formula for calculating the system contribution rate is as follows: The system contribution rate of a certain capability = (actual achievement rate of the capability × support weight) / Σ (actual achievement rate of each capability × support weight) × 100%.
[0085] For example, in the above example, assuming the actual achievement rate of regional reconnaissance capability is 85% and the actual achievement rate of precision strike capability is 90%, then the system effectiveness score = (85% × 0.4) + (90% × 0.6) = 88%. Among them, the system contribution rate of precision strike capability = (90% × 0.6) / 88% × 100% = 61.36%.
[0086] The simulation training method provided in this invention constructs an evaluation index system based on capability-task mapping view data, analyzes the simulation training process data based on the evaluation index system, obtains the actual achievement rate of each capability, and then calculates the system effectiveness and capability contribution rate. This quantifies the contribution rate of different capabilities to specific tasks, improves the fit between the system evaluation results and the actual system, and also improves the accuracy of the system evaluation results.
[0087] Based on any of the above embodiments, step S153 includes: step S1531, step S1532 and step S1533.
[0088] Step S1531: Extract the operational indicators corresponding to each capability node from the simulation training process data.
[0089] Taking the aforementioned "area reconnaissance capability" as an example, after collecting data from the simulation training process (such as radar detection logs and target trajectory logs), the system extracts two core operational indicators through a sliding window algorithm and an event filtering mechanism: target continuous tracking time and false alarm rate.
[0090] Step S1532: Compare the operating indicators with the preset threshold values to determine the basic performance value of the operating indicators.
[0091] The operational indicators are compared with preset compliance thresholds to determine the basic performance value of each operational indicator. These preset compliance thresholds can be derived from constraints in the system evolution description view data.
[0092] For example, suppose the system evolution description view data specifies that: the target continuous tracking time must reach 120 seconds for a perfect score, and the minimum must not be less than 60 seconds; the false alarm rate must be less than 5%.
[0093] Regarding the target tracking time, assuming the measured value is 100 seconds, the system uses a linear utility function to calculate its basic performance value: (100-60) / (120-60)=0.66.
[0094] Regarding the false alarm rate, assuming the measured value is 2%, the system judges it to be far below the threshold limit of 5%. After calculation using the dimensionality reduction utility function, it is assigned a basic performance value of 0.95.
[0095] Step S1533: Normalize the basic performance value to obtain the actual achievement rate of each capability node.
[0096] After obtaining the basic performance values of the above-mentioned multiple operational indicators, the system performs intra-group normalized weighted fusion according to the preset internal weights, and uses the fusion result as the actual achievement rate of the corresponding capability node.
[0097] For example, assuming the target tracking time metric has a weight of 60% and the false alarm rate metric has a weight of 40%, the actual achievement rate can be calculated as: (0.66 × 0.6) + (0.95 × 0.4) × 100% = 77.6%. Ultimately, this 77.6% is taken as the actual achievement rate of "area reconnaissance capability".
[0098] The simulation training method provided in this invention successfully solves the mathematical problem that different physical dimensions cannot be directly added by introducing threshold-based normalization. Simultaneously, by deeply binding preset compliance thresholds with system evolution description view data, a true closed loop of "evolutionary constraints - simulation operation - capability assessment" is achieved. This enables the assessment system not only to know the equipment's effectiveness but also to accurately determine whether the equipment meets the performance baseline requirements of the top-level architecture design, thereby enhancing the engineering guidance value of the system assessment results.
[0099] Based on any of the above embodiments Figure 4 This is the fourth flowchart of the simulation training method provided by the present invention, as shown below. Figure 4 As shown, step S130 includes steps S131 and S132.
[0100] Step S131: Extract target background information from the global view data. The target background information includes at least one of the following: combat area boundary parameters, force composition parameters, and battlefield environment constraint parameters.
[0101] This invention is implemented through the scene management module of the simulation training system, which constructs a unified global background model for simulation training based on global view data.
[0102] After acquiring the global view data, the background information in the global view data is extracted and recorded as target background information. Target background information includes at least one of the following: operational area boundary parameters, force composition parameters, and battlefield environment constraint parameters. Among them, the operational area boundary parameters can be the latitude and longitude range of the operational area; the force composition parameters can include the quantity and deployment location of equipment of each service branch; and the battlefield environment constraint parameters can include terrain type, weather conditions, etc.
[0103] Step S132: Using a preset scene modeling engine, generate the global background model based on the target background information.
[0104] Import the target background information into global view data (such as Unity3D) to generate a 3D visualized global background model. This global background model serves as the global background of the training scene, clearly marking the combat area boundaries, force deployment locations, and battlefield environment parameters defined by the global view data.
[0105] The default scene modeling engine can be Unity 3D, Unreal Engine 5, etc.
[0106] The simulation training method provided in this invention extracts target background information from global view data to generate a unified global background model. This target background information covers the entire system, avoiding training logic breaks caused by missing local backgrounds; at the same time, the global background model serves as the global background for simulation training, ensuring background consistency and integrity across multiple training scenarios.
[0107] Based on any of the above embodiments, step S110 includes: step S111, step S112 and step S113.
[0108] Step S111: Read the standardized architecture file through a preset data exchange interface and convert the standardized architecture file into the standardized architecture data.
[0109] Considering that the raw data exported by external architecture design tools (such as IBM Rational System Architect) is often in complex formats and may contain human input errors, the system first reads standardized architecture files (such as XML format) from the external architecture design tools through a preset data exchange interface and converts them into standardized architecture data in the target format.
[0110] In one implementation, the target format can be the JSON format required for system operation.
[0111] In another implementation, the target format can be CSV (Comma-Separated Values), which is suitable for training scenarios with a small amount of data.
[0112] Furthermore, the preset data exchange interface can be the DODAF data exchange interface based on XML (Extensible Markup Language).
[0113] Furthermore, core fields must be retained during the conversion process. For example, the interface ID, interaction protocol, and parameter type of SV2; the evolution stage and constraints of SV7; the capability ID, mission ID, and support weight of CV6; and the operational area boundary parameters and force composition parameters of AV1.
[0114] Step S112: Verify the standardized system architecture data. The verification includes at least one of the following: core field non-empty verification, format verification, and mapping relationship logical consistency verification.
[0115] The standardized architecture data of the target format obtained by the rule engine is validated. The validation includes, but is not limited to: (1) core field non-empty validation, that is, checking whether the core field is empty; (2) format validation, that is, checking whether the field format is compliant, such as whether the protocol type conforms to the TCP / IP (Transmission Control Protocol / IP: Internet Protocol) standard; (3) mapping relationship logical consistency validation, that is, checking whether there is a circular dependency in the mapping relationship between capabilities and tasks in the capability-task mapping view data.
[0116] Step S113: When the verification passes, the standardized architecture data is parsed to obtain the system interface description view data, the architecture evolution description view data, the capability task mapping view data, and the global view data.
[0117] When the verification passes, the standardized architecture data is parsed to obtain system interface description view data, architecture evolution description view data, capability task mapping view data, and global view data.
[0118] When validation fails, the failed data is returned to an external architecture design tool for correction.
[0119] Furthermore, in this embodiment of the invention, the data acquisition, conversion, and verification of the aforementioned data are achieved through the data access module of the simulation training system. After obtaining system interface description view data, system evolution description view data, capability task mapping view data, and global view data, the system interface description view data and system evolution description view data are distributed to the scenario editing module, the capability task mapping view data is distributed to the system evaluation module, and the global view data is distributed to the scenario management module. Simultaneously, all four types of data are stored in the system database.
[0120] The simulation training method provided in this invention acquires standardized architecture files and converts and parses them to obtain system interface description view data, architecture evolution description view data, capability task mapping view data, and global view data. These data are then integrated with the core functions of simulation training, solving the core problem of traditional systems lacking architectural support. During data acquisition, validation effectively isolates invalid, erroneous, or misformatted architectural data from the simulation training system, ensuring the stability of the entire simulation training system and the reliability of the system evaluation results.
[0121] The simulation training system provided by the present invention is described below. The simulation training system described below can be referred to in correspondence with the simulation training method described above.
[0122] Figure 5 This is a schematic diagram of the simulation training system provided by the present invention, as shown below. Figure 5 As shown, the simulation training system includes a data access module 510, a scenario editing module 520, a scenario management module 530, a simulation training module 540, and a system evaluation module 550; wherein: The data access module 510 is used to acquire standardized architecture data, parse the standardized architecture data, and obtain system interface description view data, architecture evolution description view data, capability task mapping view data, and global view data. The scenario editing module 520 is used to extract architectural constraint rules based on the system interface description view data and the architecture evolution description view data, constrain the user's scenario editing operation based on the architectural constraint rules, and generate target scenario data. Scene management module 530 is used to generate a global background model based on the global view data; The simulation training module 540 is used to load the target scenario data into the global background model for simulation training and to collect simulation training process data in real time. The system evaluation module 550 is used to generate system evaluation results based on the capability task mapping view data and the simulation training process data.
[0123] The simulation training system provided in this invention first acquires and parses standardized architecture data through a data access module, obtaining system interface description view data, architecture evolution description view data, capability task mapping view data, and global view data. Then, the scenario editing module extracts architecture constraint rules based on the system interface description view data and architecture evolution description view data, and constrains the user's scenario editing operations based on these rules to generate target scenario data. This eliminates the blind spots and subjective biases inherent in manual scenario configuration, ensuring from the source that the interaction logic and evolution process strictly adhere to the top-level architecture specifications. Next, the scenario management module generates a global background model based on the global view data, and the simulation training module loads the target scenario data into the global background model for simulation training, collecting simulation training process data in real time. Since the global background model directly inherits from the macro-level definition of the top-level architecture, the target scenario data can run under a unified global background model, solving the problem of poor background consistency in different training scenarios in existing technologies, and ensuring the authenticity and effectiveness of the simulation training process data. Finally, the system evaluation module generates system evaluation results based on the capability task mapping view data and the simulation training process data. By integrating capability task mapping view data, objective and accurate system-level data support is provided for system evaluation, improving the relevance and accuracy of system evaluation results.
[0124] According to a simulation training system provided by the present invention, the scenario editing module 520 is specifically used for: Based on the system interface description view data, extract the interface constraint rules; In response to a user's equipment interaction configuration request, the equipment interaction configuration options corresponding to the equipment interaction configuration request are adjusted based on the interface constraint rules. Receive inter-equipment interaction scenario data selected by the user based on the adjusted inter-equipment interaction configuration options; Based on the system evolution description view data, the evolution stages and their constraints are extracted; In response to a user's scenario evolution setting request, the scenario evolution configuration parameters corresponding to the scenario evolution setting request are limited based on the evolution stage and its constraints; Receive scenario evolution scenario data input by the user based on the defined scenario evolution configuration parameters; The architecture constraint rules include the interface constraint rules, the evolution stages and their constraints, and the target scenario data includes the equipment interaction scenario data and the scenario evolution scenario data.
[0125] According to a simulation training system provided by the present invention, the system evaluation module 550 includes: The acquisition unit is used to acquire the capability task mapping matrix and its weight vector based on the capability task mapping view data. The construction unit is used to construct an evaluation index system based on the capability-task mapping matrix and its weight vector. The evaluation index system includes capability nodes, task nodes, and support weights between the capability nodes and task nodes. The analysis unit is used to analyze the simulated training process data based on the evaluation index system to obtain the actual achievement rate of each capability node. The calculation unit is used to calculate the system performance score and system contribution rate based on the actual achievement rate and the support weight; The system evaluation results include the system performance score and the system contribution rate.
[0126] According to a simulation training system provided by the present invention, the analysis unit is specifically used for: Extract the operational metrics corresponding to each capability node from the simulated training process data; The basic performance value of the operational indicators is determined by comparing the operational indicators with preset threshold values. The actual achievement rate of each capability node is obtained by normalizing the basic performance value.
[0127] According to a simulation training system provided by the present invention, the scene management module 530 is specifically used for: Extract target background information from the global view data, wherein the target background information includes at least one of combat zone boundary parameters, force composition parameters, and battlefield environment constraint parameters; Using a preset scene modeling engine, the global background model is generated based on the target background information.
[0128] According to a simulation training system provided by the present invention, the data access module 510 is specifically used for: The standardized architecture file is read through a preset data exchange interface and converted into the standardized architecture data. The standardized system architecture data is validated, and the validation includes at least one of the following: core field non-empty validation, format validation, and mapping relationship logical consistency validation. When the verification passes, the standardized architecture data is parsed to obtain the system interface description view data, the architecture evolution description view data, the capability task mapping view data, and the global view data.
[0129] It should be noted that the simulation training system provided in this embodiment of the invention can implement all the method steps implemented in the above simulation training method embodiment and can achieve the same technical effect. Here, the parts that are the same as those in the method embodiment and the beneficial effects will not be described in detail.
[0130] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6 As shown, the electronic device may include: a processor 610, a communications interface 620, a memory 630, and a communication bus 640, wherein the processor 610, the communications interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute a method, which includes: acquiring standardized architecture data; parsing the standardized architecture data to obtain system interface description view data, system evolution description view data, capability task mapping view data, and global view data; extracting architecture constraint rules based on the system interface description view data and the system evolution description view data; constraining the user's scenario editing operations based on the architecture constraint rules to generate target scenario data; generating a global background model based on the global view data; loading the target scenario data into the global background model for simulation training and collecting simulation training process data in real time; and generating system evaluation results based on the capability task mapping view data and the simulation training process data.
[0131] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0132] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the simulation training method provided in the above embodiments. The method includes: acquiring standardized system architecture data; parsing the standardized system architecture data to obtain system interface description view data, system evolution description view data, capability task mapping view data, and global view data; extracting architecture constraint rules based on the system interface description view data and the system evolution description view data; constraining the user's scenario editing operations based on the architecture constraint rules to generate target scenario data; generating a global background model based on the global view data; loading the target scenario data into the global background model for simulation training and collecting simulation training process data in real time; and generating system evaluation results based on the capability task mapping view data and the simulation training process data.
[0133] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the simulation training method provided in the above embodiments. The method includes: acquiring standardized architecture data; parsing the standardized architecture data to obtain system interface description view data, system evolution description view data, capability-task mapping view data, and global view data; extracting architecture constraint rules based on the system interface description view data and the system evolution description view data; constraining the user's scenario editing operations based on the architecture constraint rules to generate target scenario data; generating a global background model based on the global view data; loading the target scenario data into the global background model for simulation training and collecting simulation training process data in real time; and generating system evaluation results based on the capability-task mapping view data and the simulation training process data.
[0134] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0135] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A simulation training method, characterized in that, include: Obtain standardized system architecture data, parse the standardized system architecture data to obtain system interface description view data, system evolution description view data, capability task mapping view data and global view data; Based on the system interface description view data and the architecture evolution description view data, architectural constraint rules are extracted, and user scenario editing operations are constrained based on the architectural constraint rules to generate target scenario data; A global background model is generated based on the global view data; The target scenario data is loaded into the global background model for simulation training, and simulation training process data is collected in real time. Based on the capability task mapping view data and the simulation training process data, system evaluation results are generated.
2. The simulation training method according to claim 1, characterized in that, Based on the system interface description view data and the architecture evolution description view data, architectural constraint rules are extracted, and user scenario editing operations are constrained based on the architectural constraint rules to generate target scenario data, including: Based on the system interface description view data, extract the interface constraint rules; In response to a user's equipment interaction configuration request, the equipment interaction configuration options corresponding to the equipment interaction configuration request are adjusted based on the interface constraint rules. Receive inter-equipment interaction scenario data selected by the user based on the adjusted inter-equipment interaction configuration options; Based on the system evolution description view data, the evolution stages and their constraints are extracted; In response to a user's scenario evolution setting request, the scenario evolution configuration parameters corresponding to the scenario evolution setting request are limited based on the evolution stage and its constraints; Receive scenario evolution scenario data input by the user based on the defined scenario evolution configuration parameters; The architecture constraint rules include the interface constraint rules, the evolution stages and their constraints, and the target scenario data includes the equipment interaction scenario data and the scenario evolution scenario data.
3. The simulation training method according to claim 1, characterized in that, The generation of system evaluation results based on the capability task mapping view data and the simulation training process data includes: Based on the capability task mapping view data, obtain the capability task mapping matrix and its weight vector; Based on the capability-task mapping matrix and its weight vector, an evaluation index system is constructed, which includes capability nodes, task nodes, and the supporting weights between the capability nodes and task nodes. Based on the evaluation index system, analyze the simulation training process data to obtain the actual achievement rate of each capability node; Based on the actual achievement rate and the supporting weights, calculate the system effectiveness score and the system contribution rate; The system evaluation results include the system performance score and the system contribution rate.
4. The simulation training method according to claim 3, characterized in that, The step of analyzing the simulated training process data based on the evaluation index system to obtain the actual achievement rate of each capability node includes: Extract the operational metrics corresponding to each capability node from the simulated training process data; The basic performance value of the operational indicators is determined by comparing the operational indicators with preset threshold values. The actual achievement rate of each capability node is obtained by normalizing the basic performance value.
5. The simulation training method according to claim 1, characterized in that, The generation of the global background model based on the global view data includes: Extract target background information from the global view data, wherein the target background information includes at least one of combat zone boundary parameters, force composition parameters, and battlefield environment constraint parameters; Using a preset scene modeling engine, the global background model is generated based on the target background information.
6. The simulation training method according to any one of claims 1 to 5, characterized in that, The process of acquiring standardized architecture data, parsing the standardized architecture data, and obtaining system interface description view data, architecture evolution description view data, capability task mapping view data, and global view data includes: The standardized architecture file is read through a preset data exchange interface and converted into the standardized architecture data. The standardized system architecture data is validated, and the validation includes at least one of the following: core field non-empty validation, format validation, and mapping relationship logical consistency validation. When the verification passes, the standardized architecture data is parsed to obtain the system interface description view data, the architecture evolution description view data, the capability task mapping view data, and the global view data.
7. A simulation training system, characterized in that, include: The data access module is used to acquire standardized system architecture data, parse the standardized system architecture data, and obtain system interface description view data, system evolution description view data, capability task mapping view data, and global view data. The scenario editing module is used to extract architectural constraint rules based on the system interface description view data and the architecture evolution description view data, and based on the... The architectural constraint rules constrain the user's intended editing operations and generate target intended data; The scene management module is used to generate a global background model based on the global view data; The simulation training module is used to load the target scenario data into the global background model for simulation training and to collect simulation training process data in real time. The system evaluation module is used to generate system evaluation results based on the capability task mapping view data and the simulation training process data.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the simulation training method as described in any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the simulation training method as described in any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the simulation training method as described in any one of claims 1 to 6.