Method, device, medium and product for dynamic management and control of training resources and preplan generation based on multi-domain mapping

Abstract

This application discloses a method, device, medium, and product for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping, relating to the field of intelligent management and control technology for trial training tasks. The method includes: acquiring multi-domain trial training data; pre-standardizing and aggregating the multi-domain trial training data, and constructing a three-layer mapping model to form a knowledge graph of trial training resources and requirements; then performing dynamic resource matching to obtain the optimal resource scheduling scheme; subsequently generating structured trial training contingency plans and performing verification and optimization processing to obtain contingency plan logical instructions; performing protocol conversion based on the contingency plan logical instructions to obtain industrial protocol messages; collecting execution data from the industrial protocol messages in real time, performing verification, and making corrections based on the verification results; and optimizing the trial training resource-requirement related knowledge graph based on historical execution data and the correction results. This application can improve the utilization rate of trial training resources and the efficiency of contingency plan generation.

Description

Technical Field

[0001] This application relates to the field of intelligent management and control technology for trial training tasks, and in particular to a method, equipment, medium and product for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping. Background Technology

[0002] Currently, various test and training activities are developing towards large-scale, complex, and intelligent directions, involving physical resources such as equipment, personnel, and venues, logical resources such as spectrum, airspace, and time domain, as well as multiple types of test and training tasks. The resource elements are complicated and the time and space constraints are strict.

[0003] The current management of trial training resources and the generation of contingency plans rely heavily on human experience to complete resource allocation and contingency plan writing, which has many technical drawbacks: 1. Multi-domain data resources are fragmented and cannot be mapped to a unified model, resulting in fragmented resource scheduling and low efficiency in supply and demand matching.

[0004] 2. It is difficult for manual methods to fully detect spatiotemporal conflicts of resources, which can easily lead to scheduling errors and affect the conduct of trial training.

[0005] 3. The contingency plans have a long preparation cycle and poor flexibility, making them unable to adapt to the actual needs of dynamic trial training. Moreover, they are mostly in text form and difficult to implement directly.

[0006] 4. Without a complete execution feedback loop, the control process cannot be traced, and it is impossible to achieve strategy iteration and optimization. Summary of the Invention

[0007] The purpose of this application is to provide a method, equipment, medium, and product for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping, which can improve the utilization rate of trial training resources and the efficiency of contingency plan generation.

[0008] To achieve the above objectives, this application provides the following solution: In a first aspect, this application provides a method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping, which is implemented using a system for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping; the system for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping includes: a fusion control platform and an external interaction and resource layer connected via a communication link; The method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping includes: Acquire multi-domain training data; the multi-domain training data is obtained by the data access module contained in the fusion control platform through connection with the multi-source training system; the multi-domain training data includes physical resources, logical resources, and task requirements. The multi-domain trial training data is pre-standardized and collected, and a three-layer mapping model is constructed based on the multi-domain mapping engine contained in the fusion control platform to form a trial training resource-demand association knowledge graph; Based on the knowledge graph of the trial training resources-demand association, the intelligent planning engine contained in the fusion control platform performs dynamic resource matching to obtain the optimal resource scheduling scheme; the optimal resource scheduling scheme is obtained by matching and selecting with the optimization objectives of maximizing resource utilization and minimizing task priority weighted conflict rate; Based on the optimal resource scheduling scheme, historical cases, and real-time training situation, the contingency plan generation engine included in the fusion control platform generates a structured training contingency plan and performs verification and optimization processing to obtain the contingency plan logic instructions. Based on the linkage control engine contained in the fusion control platform, the protocol is converted according to the pre-planned logic instructions to obtain industrial protocol messages, which are then sent to the external interaction and resource layer. The feed data acquisition module included in the fusion control platform collects the execution data fed back by the external interaction and the device terminals included in the resource layer according to the industrial protocol message in real time, performs verification, and makes corrections based on the verification results; wherein, a retry or compensation mechanism is initiated for abnormal items that do not meet the preset requirements in the verification. The knowledge graph relating trial training resources and requirements is optimized based on historical execution data and the correction results obtained through correction; the historical execution data includes historical cases and the execution data itself.

[0009] Secondly, this application provides a computer 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 above-described method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping.

[0010] Thirdly, this application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping.

[0011] Fourthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping.

[0012] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a method, device, medium, and product for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping. It acquires multi-domain trial training data; standardizes and aggregates this data in advance; and constructs a three-layer mapping model to form a knowledge graph linking trial training resources and needs, achieving unified description and association of multi-domain elements. Then, it performs dynamic resource matching to obtain the optimal resource scheduling scheme; subsequently, it generates structured trial training contingency plans, verifies and optimizes them to obtain contingency plan logical instructions; it performs protocol conversion based on the contingency plan logical instructions to obtain industrial protocol messages; it collects execution data based on the industrial protocol messages in real time, forming a scheduling-execution-feedback closed loop, and performs verification and correction based on the verification results; based on historical execution data and the correction results, it optimizes the trial training resource-needs association knowledge graph, achieving integrated intelligent management and control of the entire process from task input to resource management, contingency plan generation, instruction execution, and iterative optimization, significantly improving the efficiency of trial training organization and resource utilization. Therefore, this application can improve the utilization rate of trial training resources and the efficiency of contingency plan generation. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 The flowchart shows a method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping. Figure 2 This is a schematic diagram of the overall architecture of a trial training resource dynamic management and contingency plan generation system based on multi-domain mapping; Figure 3 A flowchart for processing business scenarios in the application; Figure 4 This is a schematic diagram illustrating the operational steps of a method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping in practical applications. Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0015] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] To address the aforementioned industry pain points and technical shortcomings, this application proposes a dynamic management and control scheme for trial training resources and an automatic contingency plan generation scheme based on multi-domain mapping. This scheme enables integrated management and control of multi-domain resources, intelligent scheduling, automatic generation of contingency plans, and closed-loop execution, thus solving the core problems of current technologies.

[0017] This application utilizes a unified control platform to access multi-domain training data across three categories: physical resources, logical resources, and task requirements. It constructs a three-layer "physical-logical-task" mapping knowledge graph, enabling standardized modeling and fusion of multi-domain elements. Leveraging an intelligent planning engine, it achieves dynamic resource matching and global optimization scheduling. Combining historical cases and real-time situational awareness, it automatically generates executable training plans and distributes these plans to device terminals for execution via protocol conversion. Simultaneously, it collects feedback to form a closed-loop management system, continuously iterating and optimizing based on historical data.

[0018] This application can significantly improve the utilization rate of training resources and the efficiency of contingency plan generation. It is applicable to complex training scenarios such as exercises, equipment tests, and emergency training, and solves problems such as low efficiency of traditional manual scheduling, rigid contingency plans, and insufficient execution loop.

[0019] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] In an exemplary embodiment, a method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping is provided, which is implemented using a system for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping. The system for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping includes: a fusion control platform and an external interaction and resource layer connected via a communication link.

[0021] The overall architecture of the trial training resource dynamic management and contingency plan generation system based on multi-domain mapping is as follows: Figure 2 As shown: Figure 2 The multi-domain mapping-based dynamic management and contingency plan generation system for trial training resources is divided into two layers. The upper layer is the core module layer of the fusion control platform, which includes a data access module, a multi-domain mapping engine, an intelligent planning engine, a contingency plan generation engine, a linkage control engine, a protocol conversion gateway, a feedback acquisition module, and an optimization module. Each module interacts through an internal data bus. All of the above structural modules are integrated within the fusion control platform and achieve bidirectional data interaction through a unified data bus to collaboratively complete the corresponding methods and steps, forming a complete closed-loop system for the management and contingency plan generation of trial training resources.

[0022] The lower layer is the external interaction and resource layer, which includes equipment terminals, command systems and physical / logical / task resources. The core module interacts bidirectionally with the external layer through communication links, forming a complete closed-loop architecture of data access, modeling, scheduling, contingency plan generation, instruction issuance, feedback collection and optimization iteration.

[0023] like Figure 1 As shown, the method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping includes: Step 100: Acquire multi-domain training data. Multi-domain training data is obtained by connecting the data access module in the integrated control platform to the multi-source training system; multi-domain training data includes physical resources, logical resources, and task requirements.

[0024] Step 200: Standardize and collect multi-domain trial training data in advance, and build a three-layer mapping model based on the multi-domain mapping engine contained in the fusion control platform to form a knowledge graph of trial training resources-requirements.

[0025] This involves pre-standardizing and aggregating multi-domain trial training data, and constructing a three-layer mapping model based on the multi-domain mapping engine within the fusion control platform to form a knowledge graph linking trial training resources and requirements, including: Step 201: Perform unified processing on the multi-domain trial training data in terms of data format, timestamp, and resource number to eliminate heterogeneous data barriers and obtain standardized multi-domain data.

[0026] Step 202: Based on the multi-domain mapping engine contained in the fusion control platform, construct a three-layer mapping model according to standardized multi-domain data to form a knowledge graph of trial training resources-requirements.

[0027] In one embodiment, based on the multi-domain mapping engine included in the fusion control platform, a three-layer mapping model is constructed according to standardized multi-domain data to form a knowledge graph relating training resources and requirements, including: Based on the multi-domain mapping engine contained in the fusion control platform, a three-layer ontology model of physical resources, logical resources, and task requirements is constructed according to standardized multi-domain data, resulting in a three-layer mapping model.

[0028] Based on the entities, attributes, and associated mapping relationships corresponding to standardized multi-domain data, nodes and cross-layer associated edges are established to form a test training resource-demand association knowledge graph that supports bidirectional traceability and has spatiotemporal constraint verification.

[0029] The nodes are determined based on a three-layer mapping model; the nodes include: physical layer nodes of hardware entities, logical layer nodes of virtual resources, and task layer nodes of task requirements.

[0030] Cross-layer association edges are determined based on preset association mapping standard rules; the preset association mapping standard rules include: physical-logical rules for mapping by device capability-resource type and logical-task rules for matching by resource parameters-task indicators.

[0031] Step 300: Based on the knowledge graph of the relationship between trial training resources and requirements, the intelligent planning engine included in the fusion control platform performs dynamic resource matching to obtain the optimal resource scheduling scheme. The optimal resource scheduling scheme is obtained by matching and selecting with the optimization objectives of maximizing resource utilization and minimizing the task priority-weighted conflict rate.

[0032] Among them, the intelligent planning engine included in the fusion control platform dynamically matches resources based on the knowledge graph of trial training resources and requirements to obtain the optimal resource scheduling scheme, including: Based on the intelligent planning engine included in the fusion control platform, the knowledge graph of the association between trial and training resources and requirements is traversed to complete the dynamic matching of task requirements and trial and training resources, and the initial screening results are obtained. Trial and training resources include physical resources and logical resources. Among them, when the performance parameters, spatiotemporal attributes, and status permissions of the logical resources simultaneously meet the preset thresholds corresponding to the task requirements, the dynamic matching is determined to be successful.

[0033] Spatiotemporal conflict detection is performed on the initial screening results to eliminate conflicting resources and obtain candidate resource combinations.

[0034] With the optimization objectives of maximizing resource utilization and minimizing task priority-weighted conflict rate, a heuristic algorithm is used to iteratively optimize candidate resource combinations to obtain the optimal resource scheduling scheme.

[0035] As an optional implementation, with the optimization objectives of maximizing resource utilization and minimizing task priority-weighted conflict rate, a heuristic algorithm is used to iteratively optimize candidate resource combinations to obtain the optimal resource scheduling scheme, including: A heuristic algorithm is used to iterate on candidate resource combinations, generating new solutions through crossover, mutation, and neighborhood search. The optimization objectives are to maximize resource utilization and minimize task priority weighted conflict rate, and the iteration is carried out until convergence.

[0036] After the iteration is completed, the optimal resource allocation and timing plan corresponding to the function value of the optimization objective are output, thus obtaining the optimal resource scheduling scheme.

[0037] Step 400: Based on the optimal resource scheduling scheme, historical cases, and real-time training situation, the contingency plan generation engine included in the fusion control platform generates a structured training contingency plan and performs verification and optimization to obtain the contingency plan logic instructions.

[0038] During the verification process, the verification standards are time sequence non-conflict, resource matching degree, and process integrity. The optimization process aims to reduce the execution conflict rate, improve the task success rate, and shorten the execution cycle of the plan. For structured training plans that do not meet the preset verification threshold, the timing window is automatically adjusted, spare resources are reallocated, and process branches are supplemented to generate multiple sets of structured training plans that meet all verification standards, so as to determine the logical instructions of the plan.

[0039] Step 500: Based on the linkage control engine included in the integrated control platform, perform protocol conversion according to the pre-planned logic instructions to obtain industrial protocol messages, and send them to the external interaction and resource layer.

[0040] Step 600: Based on the feedback acquisition module included in the fusion control platform, real-time acquisition of execution data from external interactions and device terminals in the resource layer, based on industrial protocol messages, is performed, and corrections are made based on the verification results. Specifically, a retry or compensation mechanism is initiated for any anomalies found during verification that do not meet preset requirements.

[0041] In one embodiment, a retry or compensation mechanism is initiated for anomalies that do not meet preset requirements during verification, including: For contingency logic instructions that fail to execute in a single instance, reissue them according to the preset number of times and time intervals.

[0042] When the target device fails at the terminal, the system matches similar backup resources based on the knowledge graph of the trial training resources-demand association, adjusts the scheduling sequence, and then switches to execution.

[0043] For scenarios where the deviation of the execution data results exceeds the standard, the instruction parameters are automatically corrected and reissued; the instruction parameters include: power, bandwidth, and time window.

[0044] The execution path is adjusted according to the preset rules of the contingency plan's logical instructions, prioritizing the completion of preset core tasks.

[0045] Step 700: Optimize the knowledge graph of the relationship between training resources and requirements based on historical execution data and the resulting corrections. Historical execution data includes historical cases and execution data.

[0046] This application utilizes a unified control platform to access multi-domain training data across three categories: physical resources, logical resources, and task requirements. It constructs a three-layer mapping model and knowledge graph to achieve unified description and association of multi-domain elements. An intelligent planning engine is used to dynamically match and globally optimize resource scheduling, forming the optimal resource allocation scheme. Based on the scheduling results and real-time situation, a structured training plan is automatically generated and distributed to the equipment terminal for execution after protocol conversion. The feedback acquisition module obtains the equipment execution status, forming a scheduling-execution-feedback closed loop. Historical execution data is used to optimize model parameters, scheduling rules, and plan templates, achieving integrated intelligent control throughout the entire process from task input to resource management, plan generation, command execution, and iterative optimization. This significantly improves the efficiency of training organization and resource utilization.

[0047] The technical approach of this application mainly includes: The system includes: construction of a multi-domain mapping knowledge graph for trial training based on a three-layer mapping of physical, logical, and task aspects; dynamic matching and global optimization scheduling of trial training resources based on the knowledge graph; automatic generation and iterative optimization of trial training plans combining historical cases and real-time situations; and closed-loop management of trial training scheduling instruction protocol conversion, issuance, execution, and feedback.

[0048] Specifically, in practical applications, such as Figure 4 As shown, it includes the following steps: S1: Multi-domain trial training data access and unified data aggregation: The data access module in the fusion control platform connects to the multi-source trial training system to complete the collection and access of three types of data: physical resources, logical resources, and task requirements. It unifies the data format, timestamp, and resource number to achieve standardized aggregation of multi-domain data.

[0049] The entity responsible for executing this step is the data access module in the fusion control platform.

[0050] Function: To connect with multi-source training systems, complete the collection and access of three types of data: physical resources, logical resources, and task requirements, unify data formats, timestamps and resource numbers, eliminate heterogeneous data barriers, and achieve standardized aggregation of multi-domain data.

[0051] Known quantities: physical resources, logical resources, access information for task requirements, communication parameters, and numbering mapping rules.

[0052] Unknown quantities: standardized multi-domain fusion datasets and unified time-series resource data streams.

[0053] S2: Multi-domain ontology model construction and knowledge graph building: The multi-domain mapping engine in the fusion control platform constructs a three-layer ontology model of "physical resources - logical resources - task requirements", defines the entities, attributes and relationships of each domain, and builds a knowledge graph of trial training resources and requirements.

[0054] The main entity responsible for executing this step is the multi-domain mapping engine in the fusion control platform.

[0055] Function: To construct a three-layer ontology model of physical resources, logical resources, and task requirements, define entities, attributes, and relationships in each domain, build a knowledge graph of trial training resources and requirements, realize bidirectional association mapping of multi-domain elements, and provide data support for subsequent resource scheduling.

[0056] Specifically, the node construction strategy is based on a three-layer structure of physical resources, logical resources, and task requirements, and generates three types of entity nodes according to standardized data: (1) Physical layer: hardware entities such as equipment and site.

[0057] (2) Logical layer: virtual resources such as spectrum, computing power, and channels.

[0058] (3) Task layer: Task requirements such as exercise subjects and test cases.

[0059] Association mapping standard: Establish cross-layer association edges based on preset rules: (1) Physical → Logical: Mapping by device capability-resource type, such as server → computing service, communication link → data channel.

[0060] (2) Logic → Task: Matching by resource parameters and task indicators, such as bandwidth / computing power / time window to meet task requirement thresholds.

[0061] Final graph form: A resource-demand association knowledge graph that supports bidirectional traceability and has spatiotemporal constraint verification is formed, providing data support for subsequent scheduling.

[0062] Known quantities: standardized multi-domain data output by S1, entity attribute rules within the domain, and spatiotemporal constraints.

[0063] Unknown quantities: multi-domain ontology model, knowledge graph relating trial and training resources and requirements.

[0064] S3: Dynamic resource matching based on the knowledge graph of trial training resources and requirements: The intelligent planning engine in the fusion control platform traverses the knowledge graph to accurately match task requirements with trial training resources, detects spatiotemporal conflicts, and generates a globally optimal resource scheduling scheme through heuristic algorithms.

[0065] The main entity responsible for executing this step is the intelligent planning engine of the integrated control platform.

[0066] Function: Traverse the knowledge graph to accurately match task requirements with training resources, detect resource usage conflicts (spatiotemporal conflicts), select available resources through heuristic algorithms, and generate a globally optimal resource scheduling scheme to resolve spatiotemporal conflicts, resource usage conflicts, and temporal conflicts.

[0067] Known quantities: multi-domain resource knowledge graph, task requirement template, and optimization scheduling objective.

[0068] Unknowns: optimal resource allocation scheme, resource scheduling timing plan.

[0069] Specifically, the matching rules and judgment criteria are as follows: based on the three-layer association of "task-logic-physical" in the knowledge graph, when the performance parameters, spatiotemporal attributes, and state permissions of the logical resource simultaneously meet the task requirement threshold, the matching is considered successful.

[0070] Conflict resolution: The initial screening results are checked for time and space occupancy, resource mutual exclusion, and time sequence dependency, and conflicting resources are marked and excluded.

[0071] Heuristic optimization process: With the goal of maximizing resource utilization and minimizing conflict rate, a heuristic algorithm is used to iteratively optimize candidate resource combinations and output the globally optimal resource allocation scheme and time sequence plan.

[0072] Available resources are selected using a heuristic algorithm to generate a globally optimal resource scheduling scheme, specifically as follows: 1. Initialize candidate set: Based on the knowledge graph matching results, generate a candidate set of all resource-task combinations that meet the hard constraints (performance, spatiotemporal, permissions).

[0073] 2. Objective function setting: With the optimization objectives of maximizing resource utilization and minimizing the task priority weighted conflict rate, a multi-objective evaluation function is constructed.

[0074] 3. Heuristic Iterative Optimization: Heuristic algorithms (such as genetic / simulated annealing) are used to iterate the candidate set, generate new solutions through crossover, mutation / neighborhood search, and select better solutions according to the objective function until convergence.

[0075] 4. Output the optimal solution: After the iteration is completed, the resource allocation and timing plan with the optimal objective function value are output, which is the global optimal scheduling solution.

[0076] S4: Automatic generation and optimization iteration of trial training plans: The plan generation engine in the integrated control platform combines the optimal scheduling scheme, historical cases and real-time trial training situation to automatically generate structured trial training plans and complete feasibility verification and optimization.

[0077] The entity responsible for executing this step is the contingency plan generation engine of the fusion control platform.

[0078] Function: By combining the optimal scheduling scheme, historical cases and real-time trial training situation, it automatically generates task execution sequence and trial training resource scheduling instructions, and completes the feasibility verification and preliminary optimization of the plan.

[0079] Known quantities: resource scheduling scheme, historical case library, real-time environmental and situational data, and contingency plan preparation specifications.

[0080] Unknown quantity: Trial training plan and multiple options for the plan.

[0081] 1. Verification Standards and Thresholds: The core verification standards are time sequence non-conflict (time window crossover rate = 0), resource matching degree (parameter satisfaction rate = 100%), and process integrity (key node coverage rate = 100%). At the same time, the adaptability to the real-time situation is also verified (environmental constraint conflict rate = 0).

[0082] 2. Optimization Objectives: The optimization objectives are to reduce the execution conflict rate, increase the task success rate, and shorten the contingency plan execution cycle.

[0083] 3. Optimize the processing: For contingency plans that do not meet the verification threshold, automatically adjust the timing window, reallocate backup resources, supplement process branches, and generate multiple contingency plan configuration schemes that meet all verification standards.

[0084] S5: Contingency Plan Command Protocol Conversion and Execution: The linkage control engine in the fusion control platform converts the contingency plan logic commands into industrial control protocol messages and sends them to the external interaction and resource layer, namely: equipment terminals and command systems to drive execution.

[0085] The main entity responsible for executing this step is the integrated control platform's linkage control engine.

[0086] Function: Converts pre-planned logical commands into industrial control protocol messages and sends them to equipment terminals, command systems, and other hardware devices in milliseconds, driving the equipment to execute pre-planned actions.

[0087] Known quantities: trial training plan instructions, equipment communication protocols, hardware addresses, and linkage execution rules.

[0088] Unknown quantities: Control messages after protocol conversion, device execution instructions, and issued execution logs.

[0089] S6: Execution Feedback Acquisition and Closed-Loop Handling Management: The feedback acquisition module (feedback acquisition module) in the fusion control platform collects the execution feedback and field status of the equipment in real time, verifies the execution results, and initiates retry or compensation mechanisms for abnormal items to form a closed-loop record.

[0090] The entity responsible for executing this step is the feedback acquisition module of the fusion control platform.

[0091] Function: Real-time collection of hardware device execution feedback and on-site status data, verification of contingency plan execution results, initiation of retry or compensation mechanisms for failed execution items, forming a complete scheduling-execution-feedback closed-loop record.

[0092] Known quantities: issued execution commands, device feedback interfaces, and status determination criteria.

[0093] Unknown quantities: equipment execution results, closed-loop processing records, and execution status ledgers.

[0094] Specifically, retry or compensation mechanisms include: 1. Command retry: For commands that fail to execute in a single attempt, resend them a preset number of times and time intervals.

[0095] 2. Resource substitution: When the target device fails, the system matches similar backup resources based on the knowledge graph, adjusts the scheduling sequence, and then switches to execution.

[0096] 3. Parameter correction: For scenarios where the execution result deviation exceeds the standard, the command parameters (such as power, bandwidth, and time window) are automatically corrected and reissued.

[0097] 4. Process Degradation: Adjust the execution path according to the pre-set rules of the contingency plan, prioritizing the completion of core tasks. All handling processes are recorded in a closed-loop ledger, forming a complete scheduling-execution-feedback record.

[0098] S7: Historical Data Backflow and Model Strategy Optimization: The optimization module in the fusion control platform collects historical execution data and manual correction results to optimize knowledge graph mapping rules, scheduling algorithms, and contingency plan templates, thereby achieving iterative optimization of the system.

[0099] The main entity responsible for executing this step is the fusion control platform optimization module.

[0100] Function: Collect historical execution data and manually corrected results; statistically analyze the scheduling and contingency plan execution effects; optimize knowledge graph mapping rules, resource scheduling algorithms, and contingency plan generation templates to achieve continuous self-optimization of the system; and feed back to the S2 knowledge graph, S3 scheduling algorithm, and S4 contingency plan template.

[0101] Known quantities: closed-loop processing records, historical execution samples, and manual review results.

[0102] Unknowns: optimized modeling parameters, updated scheduling plan, and iterated contingency plan template.

[0103] Figure 3 This document provides a flowchart for processing business scenarios in the application. Taking a joint exercise and training scenario as an example, it describes the method mentioned in this application as follows: Multi-domain data access and standardized processing: Access physical resource data such as participating equipment (radar, communication terminal), venue, and personnel; logical resource data such as spectrum, airspace, and timing; and task requirement data such as exercise subjects, task timing, and priority, and complete the processing of format unification, timestamp alignment, and resource number standardization.

[0104] Three-layer ontology model and knowledge graph construction: A three-layer ontology model of "physical resources - logical resources - task requirements" is constructed, entity attributes and association rules are defined, and a knowledge graph of test training resources and requirements is built to realize bidirectional association mapping between equipment, spectrum and task.

[0105] Dynamic resource matching and global optimization scheduling: The intelligent planning engine traverses the knowledge graph and filters resources according to rules of performance matching, spatiotemporal conflict-free, and priority; it resolves multi-task resource occupation and timing conflicts through heuristic algorithms and generates a globally optimal scheduling scheme.

[0106] Automatic generation and optimization of trial training plans: By combining the optimal scheduling scheme, historical exercise cases, and real-time airspace / electromagnetic situation, structured exercise plans are automatically generated; the rationality of timing, resource matching degree, and process integrity are verified, and multiple sets of plan configurations are optimized and generated.

[0107] Contingency plan instruction protocol conversion and issuance execution: The logical scheduling instructions in the plan are converted into industrial control protocol messages supported by each equipment terminal (device terminal), and then sent to the radar and communication terminals for execution through the linkage control engine.

[0108] Execution feedback collection and closed-loop processing: The feedback module (feedback acquisition module) collects the equipment execution status and field data in real time and verifies the execution results; in case of instruction timeout or execution deviation exceeding the standard, it initiates a compensation mechanism of retry or alternative resource replacement, forming a complete scheduling-execution-feedback closed loop record.

[0109] Historical data backflow and system iterative optimization: After the exercise, the execution data and closed-loop handling records will be fed back into the system to optimize the knowledge graph association rules, heuristic algorithm parameters and contingency plan templates, thereby improving the organizational efficiency and resource utilization of subsequent exercises.

[0110] For the methods mentioned above, the corresponding solutions for the product types are as follows: Multi-source data access and unified aggregation structure: The execution entity is the data access module, unified data bus, and protocol adaptation interface within the fusion control platform. It is responsible for accessing physical resource systems, logical resource systems, and task requirement systems, completing the collection, format adaptation, and standardized aggregation of multi-source heterogeneous data, and providing a unified data source for subsequent processing.

[0111] Multi-domain ontology modeling and knowledge graph construction structure: The execution entity is the multi-domain mapping engine inside the fusion control platform, which is responsible for processing standardized multi-domain data, constructing a three-layer ontology model of "physical resources-logical resources-task requirements", building a knowledge graph of trial training resources-requirements association, and realizing unified description and association mapping of multi-domain elements.

[0112] Dynamic resource matching structure: The execution entity is the intelligent planning engine inside the integrated control platform, which has built-in resource matching and scheduling optimization units. Based on the knowledge graph, it completes the matching of tasks and resources and generates the globally optimal resource scheduling scheme.

[0113] Automatic generation and optimization of trial training plans: The execution entity is the plan generation engine within the integrated control platform, which includes a historical case retrieval unit, a real-time situation fusion unit, and a plan generation unit. Based on the resource scheduling scheme, it automatically generates and optimizes structured and executable trial training plans.

[0114] Command protocol conversion and execution structure: The execution entity is the linkage control engine and protocol conversion gateway inside the integrated control platform, which converts the pre-planned logical commands into underlying industrial control messages and sends them to the equipment control terminal and command system, realizing the conversion from software commands to hardware execution.

[0115] The execution feedback acquisition and closed-loop management structure is as follows: The execution entity is the feedback acquisition module inside the integrated control platform, which collects hardware device execution feedback and field status data in real time, completes the execution result verification, and forms a complete closed-loop record of scheduling-execution-feedback.

[0116] Historical data feedback and optimization iteration structure: The execution entity is the optimization module within the integrated control platform. Based on historical execution data and manual correction results, it optimizes system model parameters, scheduling rules, and contingency plan templates to achieve continuous iterative optimization of the system.

[0117] The benefits of this application are: 1. More precise multi-domain resource management: Through a three-layer mapping knowledge graph, unified modeling of physical, logical and task-related resources is achieved, solving the problem of fragmented resource data, greatly improving the accuracy of resource matching, and significantly improving the supply and demand mismatch problem.

[0118] 2. Significantly improved scheduling and contingency planning efficiency: Replacing manual scheduling and contingency planning, the work that originally took several days can be completed within hours, eliminating human error and significantly improving the efficiency of trial training preparation.

[0119] 3. Achieve closed-loop execution throughout the entire process: Through protocol conversion, the contingency plan instructions are directly executed to hardware devices. Combined with real-time feedback collection, a closed loop of control, execution, and verification is formed, solving the problem that traditional contingency plans only remain on text and cannot be implemented.

[0120] 4. The system has continuous optimization capabilities: relying on historical data feedback to iteratively optimize models and rules, adapt to different training scenarios, significantly improve resource utilization, and continuously optimize the feasibility and adaptability of contingency plans.

[0121] 5. Strong versatility: It can be adapted to various complex training scenarios such as military exercises, equipment testing, and emergency training. It can be implemented without major adjustments, and its scalability and practicality far exceed those of existing single-scenario management and control systems.

[0122] Currently known methods using manual table scheduling and simple rule engines can only complete basic resource allocation and cannot achieve global optimization. Relying on manual preparation of plans, they cannot achieve automated and structured generation. A single data acquisition system cannot complete protocol conversion and hardware closed-loop execution.

[0123] Currently, a single technical approach can only achieve partial functionality and cannot cover the full-process technical effects of multi-domain mapping modeling, global intelligent scheduling, automatic contingency plan generation, hardware closed-loop execution, and continuous iterative optimization. Therefore, there is no complete alternative solution.

[0124] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data for dynamic management and contingency plan generation based on multi-domain mapping of training resources. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the method for dynamic management and contingency plan generation based on multi-domain mapping of training resources.

[0125] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0126] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0127] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0128] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0129] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0130] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0131] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logic devices, etc., and are not limited to these.

[0132] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0133] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping, characterized in that, The system employs a dynamic management and contingency plan generation system for trial training resources based on multi-domain mapping. This system includes a fusion control platform and an external interaction and resource layer connected via a communication link. The method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping includes: Acquire multi-domain training data; the multi-domain training data is obtained by the data access module contained in the fusion control platform through connection with the multi-source training system; the multi-domain training data includes physical resources, logical resources, and task requirements. The multi-domain trial training data is pre-standardized and collected, and a three-layer mapping model is constructed based on the multi-domain mapping engine contained in the fusion control platform to form a trial training resource-demand association knowledge graph; Based on the knowledge graph of the trial training resources-demand association, the intelligent planning engine contained in the fusion control platform performs dynamic resource matching to obtain the optimal resource scheduling scheme; the optimal resource scheduling scheme is obtained by matching and selecting with the optimization objectives of maximizing resource utilization and minimizing task priority weighted conflict rate; Based on the optimal resource scheduling scheme, historical cases, and real-time training situation, the contingency plan generation engine included in the fusion control platform generates a structured training contingency plan and performs verification and optimization processing to obtain the contingency plan logic instructions. Based on the linkage control engine contained in the fusion control platform, the protocol is converted according to the pre-planned logic instructions to obtain industrial protocol messages, which are then sent to the external interaction and resource layer. The feed data acquisition module included in the fusion control platform collects the execution data fed back by the external interaction and the device terminals included in the resource layer according to the industrial protocol message in real time, performs verification, and makes corrections based on the verification results; wherein, a retry or compensation mechanism is initiated for abnormal items that do not meet the preset requirements in the verification. The knowledge graph relating trial training resources and requirements is optimized based on historical execution data and the correction results obtained through correction; the historical execution data includes historical cases and the execution data itself.

2. The method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping according to claim 1, characterized in that, The multi-domain training data is pre-standardized and aggregated, and a three-layer mapping model is constructed based on the multi-domain mapping engine included in the fusion control platform to form a knowledge graph of training resources and requirements, including: The multi-domain training data is processed to unify the data format, timestamp, and resource number to eliminate heterogeneous data barriers and obtain standardized multi-domain data. Based on the multi-domain mapping engine contained in the fusion control platform, a three-layer mapping model is constructed according to the standardized multi-domain data to form a knowledge graph of trial training resources and requirements.

3. The method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping according to claim 2, characterized in that, Based on the multi-domain mapping engine included in the fusion control platform, a three-layer mapping model is constructed according to the standardized multi-domain data to form a knowledge graph relating training resources and requirements, including: Based on the multi-domain mapping engine contained in the fusion control platform, a three-layer ontology model of physical resources, logical resources, and task requirements is constructed according to the standardized multi-domain data to obtain the three-layer mapping model. Based on the entities, attributes, and associated mapping relationships corresponding to the standardized multi-domain data, nodes and cross-layer associated edges are established to form a test training resource-demand association knowledge graph that supports bidirectional traceability and has spatiotemporal constraint verification. The nodes are determined based on the three-layer mapping model; the nodes include: physical layer nodes of hardware entities, logical layer nodes of virtual resources, and task layer nodes of task requirements. The cross-layer association edges are determined based on preset association mapping standard rules; the preset association mapping standard rules include: physical-logical rules for mapping by device capability-resource type and logical-task rules for matching by resource parameters-task indicators.

4. The method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping according to claim 1, characterized in that, Based on the aforementioned knowledge graph relating training resources and requirements, the intelligent planning engine within the fusion control platform performs dynamic resource matching to obtain the optimal resource scheduling scheme, including: Based on the intelligent planning engine contained in the fusion control platform, the system traverses the knowledge graph of the association between the training resources and the requirements to complete the dynamic matching of the task requirements and the training resources, and obtains the initial screening results. The training resources include physical resources and logical resources. When the performance parameters, spatiotemporal attributes, and status permissions of the logical resources simultaneously meet the preset thresholds corresponding to the task requirements, the dynamic matching is determined to be successful. Spatiotemporal conflict detection is performed on the initial screening results to eliminate conflicting resources and obtain candidate resource combinations; With the optimization objectives of maximizing resource utilization and minimizing task priority-weighted conflict rate, a heuristic algorithm is used to iteratively optimize the candidate resource combinations to obtain the optimal resource scheduling scheme.

5. The method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping according to claim 4, characterized in that, With the optimization objectives of maximizing resource utilization and minimizing task priority-weighted conflict rate, a heuristic algorithm is used to iteratively optimize the candidate resource combinations to obtain the optimal resource scheduling scheme, including: The candidate resource combinations are iterated using a heuristic algorithm. New solutions are generated through crossover, mutation, and neighborhood search. The optimization objectives are to maximize resource utilization and minimize task priority weighted conflict rate. The iteration continues until convergence. After the iteration is completed, the optimal resource allocation and timing plan corresponding to the function value of the optimization objective are output, thus obtaining the optimal resource scheduling scheme.

6. The method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping according to claim 1, characterized in that, When performing verification, the verification standards are no timing conflicts, resource matching degree, and process integrity. The optimization process aims to reduce the execution conflict rate, improve the task success rate, and shorten the execution cycle of the contingency plan. For structured trial training contingency plans that do not meet the preset verification threshold, the timing window is automatically adjusted, spare resources are reallocated, and process branches are supplemented to generate multiple sets of structured trial training contingency plans that meet all verification standards, so as to determine the logical instructions of the contingency plan.

7. The method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping according to claim 1, characterized in that, For exceptions found during verification that do not meet preset requirements, a retry or compensation mechanism is initiated, including: For contingency logic instructions that fail to execute in a single instance, reissue them according to the preset number of times and time intervals; When the target device fails at the device terminal, the same type of backup resource is matched based on the knowledge graph of the trial training resource-demand association, and the scheduling sequence is adjusted before switching to execution. For scenarios where the deviation of the execution data results exceeds the standard, the instruction parameters are automatically corrected and reissued; the instruction parameters include: power, bandwidth, and time window; The execution path is adjusted according to the preset rules of the contingency plan's logical instructions, prioritizing the completion of preset core tasks.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping as described in any one of claims 1-7.

9. A 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 method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping as described in any one of claims 1-7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for dynamic management and contingency plan generation of trial training resources based on multi-domain mapping as described in any one of claims 1-7.

Images