A non-war military operation chess multi-source data real-time mapping deduction method, system, device and medium

Abstract

The application relates to the field of computer simulation and distributed computing technology, and discloses a non-war military action war game multi-source data real-time mapping deduction method, system, equipment and medium, which comprises the following steps: acquiring multi-source heterogeneous data of a non-war military action scene, processing and generating standardized data based on a preset standardization adaptation protocol; real-time mapping the standardized data to a virtual war game deduction environment, updating the element characteristic value increment to the corresponding element model after time stamp alignment; decomposing the deduction task into subtasks according to the element coupling relationship, and dynamically distributing parallel computing according to the computing power demand and the node state; performing hierarchical fault tolerance treatment on the abnormality, and continuing the deduction after recovery based on the incremental snapshot rollback in case of serious abnormality; and updating the deduction situation and generating the deduction result according to the execution result. The application realizes the rapid access and millisecond-level real-time mapping of multi-source heterogeneous data in a non-hot war scene, improves the computing power utilization rate, and guarantees the deduction stability.

Description

Technical Field

[0001] This invention relates to the field of computer simulation and distributed computing technology, specifically to a method, system, device, and medium for real-time mapping and simulation of multi-source data in wargaming for non-war military operations. Background Technology

[0002] The requirements for non-war military operation simulations differ significantly from those for hot war scenarios. The data sources for non-hot war scenario simulations encompass multiple heterogeneous systems, and the data types include text, video, numerical data, and streaming data, with update frequencies ranging from milliseconds to hours.

[0003] Currently, in non-hot war war games, there are two typical technical solutions:

[0004] One approach is a distributed wargaming engine system. This system employs a distributed parallel computing architecture, breaking down the wargaming task into multiple operators based on pre-defined scenarios and fixed elements. These operators are then distributed to different computing nodes for parallel computation, and the computational results are centrally aggregated to update the wargaming situation. This approach is primarily suited for fixed-element, fixed-step wargaming scenarios and cannot support the access and processing of massive, highly dynamic, heterogeneous elements in non-hotspot war scenarios.

[0005] Another approach is a virtual-real integrated wargaming system. This system acquires equipment status and personnel location data from real-world scenarios through a data acquisition module and maps it offline to the corresponding model in the wargaming system. However, this solution collects specific types of real-world equipment data through fixed interfaces, resulting in a low data update frequency. It only supports the access of single-source homogeneous data and cannot support the real-time access and mapping of massive amounts of multi-source heterogeneous data in non-hotspot scenarios.

[0006] The existing technical solutions have the following shortcomings: The simulation engine architecture is adapted to fixed elements of hot war scenarios, but cannot support the access and processing of massive, highly dynamic, heterogeneous elements in non-hot war scenarios; based on offline static mapping, it cannot achieve real-time synchronization between real scenarios and wargame environments. The fixed task distribution and computing power allocation mechanism cannot be adjusted according to dynamic changes in factors. It supports data access in fixed formats and types, but lacks a standardized heterogeneous data adaptation module; custom development is required to access new data sources. Without a dynamic fault tolerance and rollback mechanism in the extrapolation process, the extrapolation process is prone to interruption or output of distorted results when the data source is interrupted or the elements change drastically.

[0007] Therefore, this application provides a method for real-time mapping and simulation of multi-source data in wargames for non-war military operations to solve the above-mentioned technical problems. Summary of the Invention

[0008] The purpose of this invention is to provide a method, system, device, and medium for real-time mapping and simulation of multi-source data in wargaming for non-war military operations, in order to solve the technical problems in the prior art where simulation engines cannot achieve real-time mapping of multi-source heterogeneous data, dynamic scheduling of computing power, and fault-tolerant rollback of the simulation process in non-hot war scenarios.

[0009] To address the aforementioned technical problems, this invention provides a method for real-time mapping and simulation of multi-source data in wargaming for non-war military operations, comprising: Acquire multi-source heterogeneous data from non-war military operation scenarios, process the multi-source heterogeneous data based on a preset data standardization adaptation protocol, and generate standardized data with a unified data structure. The standardized data is mapped to the virtual war game simulation environment in real time. The timestamps of the standardized data from multiple sources are aligned. The feature values ​​of the elements in the aligned standardized data are updated to the corresponding element models according to the preset mapping relationship, so as to update the virtual war game simulation environment. The multi-element linkage simulation task is decomposed into multiple simulation sub-tasks based on the coupling relationship between the elements. The simulation sub-tasks are dynamically distributed to the corresponding computing nodes for parallel computing according to the computing power requirements of each simulation sub-task and the computing power status of each computing node. During the simulation, the status of the data source, computing node, and task execution are monitored. In response to the detection of an anomaly, the corresponding fault-tolerant handling strategy is adopted according to the level of the anomaly, and the execution result of the simulation subtask is returned. Based on the execution results returned by all the simulation subtasks, the simulation situation of the virtual wargame simulation environment is updated, and simulation results are generated.

[0010] In some specific embodiments, acquiring multi-source heterogeneous data from non-war military operation scenarios, processing the multi-source heterogeneous data based on a preset data standardization adaptation protocol, and generating standardized data with a unified data structure further includes: Execute data acquisition logic that matches the data source transmission protocol to interface with the multi-source heterogeneous data from different data sources; For the collected multi-source heterogeneous data, the format conversion rules corresponding to the data source format are invoked to parse the data structure of the multi-source heterogeneous data and extract key information; The extracted key information is subjected to anomaly filtering to remove invalid data that exceeds the preset valid range; The valid information after the anomaly filtering process is assembled into standardized data, which includes a unique data identifier, timestamp, feature type code, feature value, and data confidence level, according to the structure defined by the data standardization adaptation protocol.

[0011] In some specific embodiments, the standardized data is mapped to the virtual wargame simulation environment in real time, the timestamps of the multi-source standardized data are aligned, and the feature values ​​of the elements in the aligned standardized data are updated to the corresponding element models according to a preset mapping relationship to update the virtual wargame simulation environment, further including: Read all the standardized data that has been accessed and obtain the millisecond-level timestamp carried by each piece of standardized data; Set a sliding time window and group all the standardized data whose millisecond timestamps fall within the same sliding time window into a synchronization batch. Based on the preset mapping relationship, determine the target element model corresponding to the feature value of each element in the synchronous batch in the virtual war game simulation environment; Only the feature values ​​of the elements that have changed are incrementally updated to the corresponding target feature model.

[0012] In some specific embodiments, the multi-element linkage inference task is decomposed into multiple inference sub-tasks based on the coupling relationship between the elements, and the inference sub-tasks are dynamically distributed to the corresponding computing nodes for parallel computing according to the computing power requirements of each inference sub-task and the computing power status of each computing node, further including: The decomposition rules of multi-element inference tasks are represented by directed graphs. Based on the causal and influence logic between each element, the overall inference task is decomposed into multiple inference sub-tasks with sequential or independent parallel relationships, and a priority is set for each inference sub-task. Based on historical simulation data, the computational load required for each simulation subtask is estimated in real time, and the computational power requirement of the simulation subtask is generated. A multi-objective scheduling function is constructed with minimizing simulation latency, maximizing the average utilization of computing resources, and minimizing the latency of high-priority tasks as optimization objectives. Based on the solution results of the multi-objective scheduling function, a set of available computing power nodes that meet the computing power requirements of the simulation subtask is determined, and the computing power node with the lowest load is selected from the set of available computing power nodes. The simulation subtask is then distributed to the selected computing power node for execution.

[0013] In some specific embodiments, during the simulation process, the status of the data source, the status of the computing node, and the task execution status are detected. In response to the detection of an anomaly, a corresponding fault-tolerant handling strategy is adopted according to the level of the anomaly, and the execution result of the simulation subtask is returned. This further includes: The connection status of the data source, the resource utilization rate of the computing power node, and the execution timeout information of the inference subtask are collected in real time. If any monitoring item exceeds the preset threshold range, it is determined that an anomaly has occurred. The identified anomalies are classified into at least three levels, where minor anomalies are brief fluctuations in data, moderate anomalies are failures of a single computing node, and severe anomalies are computing logic conflicts or data interruptions. For the aforementioned minor anomalies, perform data completion or parameter smoothing processing; For the aforementioned moderate anomaly, the inference subtask that caused the moderate anomaly will be redistributed to other healthy nodes. In response to the severe anomaly, a state rollback mechanism is activated to restore the virtual wargame simulation environment to its most recent normal state before the severe anomaly occurred, and then the simulation is re-executed.

[0014] In some specific embodiments, in response to the severe anomaly, a state rollback mechanism is activated to restore the virtual wargame simulation environment to its most recent normal state before the severe anomaly occurred, and the simulation is then re-executed. This further includes: During the simulation, incremental snapshots of the full state of the virtual wargame simulation environment are periodically generated and stored, with the simulation step size as the period. In response to the detection of the severe anomaly, determine the most recently generated complete full state increment snapshot before the time point of the severe anomaly occurrence; Restore the state of all elements in the virtual wargame simulation environment to the state recorded by the found full state incremental snapshot; Based on the recovered state, the standardized data after the anomaly recovery is reacquired, and the deduction is continued based on the recovered state.

[0015] In some specific embodiments, a scenario-based adaptation step is included before acquiring multi-source heterogeneous data from non-war military operation scenarios: Receive scenario deployment instructions, which indicate the type of non-war military operation scenario to be deployed; Based on the scenario type, determine the configuration template set corresponding to the scenario type, and load the configuration template set; Complete the loading and initialization of the element system, data source adaptation logic, inference rules and computing power configuration parameters defined in the configuration template set.

[0016] Based on the same concept, the present invention also provides a real-time mapping and simulation system for multi-source data in non-war military operations wargaming, comprising: The multi-source heterogeneous data standardization processing module is configured to acquire multi-source heterogeneous data in non-war military operation scenarios, process the multi-source heterogeneous data based on a preset data standardization adaptation protocol, and generate standardized data with a unified data structure. The virtual-real data real-time mapping and synchronization module is configured to map the standardized data to the virtual war game simulation environment in real time, align the timestamps of the standardized data from multiple sources, and update the feature values ​​of the elements in the aligned standardized data to the corresponding element model according to the preset mapping relationship, so as to update the virtual war game simulation environment. The parallel scheduling and distribution module for simulation tasks is configured to decompose multi-element linkage simulation tasks into multiple simulation sub-tasks based on the coupling relationship between the elements, and dynamically distribute the simulation sub-tasks to the corresponding computing nodes for parallel computing according to the computing power requirements of each simulation sub-task and the computing power status of each computing node. The anomaly detection and hierarchical fault tolerance module is configured to detect the data source status, computing node status and task execution status during the simulation process. In response to the detection of an anomaly, it adopts the corresponding fault tolerance strategy according to the level of the anomaly and returns the execution result of the simulation subtask. The simulation situation update and result generation module is configured to update the simulation situation of the virtual wargame simulation environment and generate simulation results based on the execution results returned by all the simulation sub-tasks.

[0017] Based on the same concept, the present invention also provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a method for real-time mapping and simulation of multi-source data in non-war military operations wargaming.

[0018] Based on the same concept, the present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a method for real-time mapping and simulation of multi-source data in a non-war military operations wargaming.

[0019] Compared with existing technologies, its advantages are as follows: This invention discloses a method, system, device, and medium for real-time mapping and simulation of multi-source data in wargaming for non-war military operations. By constructing a standardized multi-source heterogeneous data adaptation and processing flow, it supports all types of data formats and mainstream transmission protocols, enabling rapid access and unified standardized processing of multi-source heterogeneous data in non-hot war scenarios. This solves the problems of high cost and the need for customized development for heterogeneous data access in existing technologies.

[0020] By using a timestamp-aligned multi-source data synchronization mechanism and an incremental update mechanism, real-time mapping and synchronization between real-world scenario data and the virtual simulation environment are achieved. The end-to-end mapping latency can be controlled within milliseconds, solving the problem that existing technologies only support offline static mapping and the disconnect between the virtual and real worlds leads to the simulation results losing their decision-making reference value.

[0021] By adopting a parallel scheduling mechanism based on task decomposition and multi-objective scheduling functions, the simulation subtasks are dynamically distributed to the computing nodes with the lowest load according to the computing power requirements of each simulation subtask and the real-time status of each computing node. This improves the utilization rate of computing power resources, ensures the real-time performance of the simulation, and solves the problems of resource waste and insufficient real-time performance caused by fixed computing power allocation in existing technologies.

[0022] By constructing a multi-dimensional anomaly monitoring system and a hierarchical fault-tolerant processing mechanism, corresponding fault-tolerant strategies such as data completion, task redistribution, and state rollback are adopted for different levels of anomalies such as data fluctuations, node failures, and logical conflicts. This ensures the continuity of the simulation process and the accuracy of the results, and solves the problems of insufficient fault tolerance of existing technologies and the easy interruption or distortion of simulation results under abnormal conditions.

[0023] By periodically generating and storing full state incremental snapshots of the simulation environment during the simulation process, in the event of a serious anomaly, the simulation environment can be restored to the most recent normal state before the anomaly occurred and the simulation can continue to be executed. This achieves continuous and stable operation of the simulation and solves the problems of existing technologies having no state rollback capability and needing to start the simulation from scratch after a serious anomaly causes the simulation to be interrupted. Attached Figure Description

[0024] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating some specific embodiments of the present invention, which describes a method for real-time mapping and simulation of multi-source data in wargaming for non-war military operations. Figure 2 This is a schematic diagram of the real-time mapping and synchronization process of virtual and real data in another embodiment of the non-war military operations wargaming multi-source data real-time mapping and simulation method of the present invention; Figure 3This is a schematic diagram of the distributed parallel simulation computing power intelligent scheduling process in another embodiment of the non-war military operations wargaming multi-source data real-time mapping and simulation method of the present invention. Figure 4 This is a schematic diagram of the structure of a non-war military operations wargaming multi-source data real-time mapping and simulation system in some specific embodiments of the present invention; Figure 5 This is a schematic diagram of the structure of an electronic device according to some specific embodiments of the present invention; In the diagram, 710 is the processor; 720 is the memory; 730 is the input device; and 740 is the output device. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail 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 in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms "a," "the," and "the" as used in the embodiments of this application are also intended to include the plural forms, unless the context clearly indicates otherwise, and "multiple" generally includes at least two.

[0027] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0028] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0029] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0030] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0031] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0032] Reference Figure 1 A method for real-time mapping and simulation of multi-source data in non-war military operations wargaming, comprising: S101, acquire multi-source heterogeneous data in non-war military operation scenarios, process the multi-source heterogeneous data based on a preset data standardization adaptation protocol, and generate standardized data with a unified data structure. S101 further includes: Execute data acquisition logic that matches the data source transmission protocol to interface with the multi-source heterogeneous data from different data sources; For the collected multi-source heterogeneous data, the format conversion rules corresponding to the data source format are invoked to parse the data structure of the multi-source heterogeneous data and extract key information; The extracted key information is subjected to anomaly filtering to remove invalid data that exceeds the preset valid range; The valid information after the anomaly filtering process is assembled into standardized data, which includes a unique data identifier, timestamp, feature type code, feature value, and data confidence level, according to the structure defined by the data standardization adaptation protocol.

[0033] Prior to S101, it also includes: Context-specific adaptation steps: Receive scenario deployment instructions, which indicate the type of non-war military operation scenario to be deployed; Based on the scenario type, determine the configuration template set corresponding to the scenario type, and load the configuration template set; Complete the loading and initialization of the element system, data source adaptation logic, inference rules and computing power configuration parameters defined in the configuration template set.

[0034] Specifically, in this embodiment of the invention, multi-source heterogeneous data in non-war military operation scenarios are acquired, and the multi-source heterogeneous data is processed based on a preset data standardization adaptation protocol to generate standardized data with a unified data structure.

[0035] Before acquiring multi-source heterogeneous data, a scenario deployment instruction is received. This instruction specifies the type of non-war military operation scenario to be deployed, including scenarios such as emergency response and security for major events. Based on the scenario type, a set of configuration templates corresponding to the scenario type is determined from a pre-built scenario template library. This set of configuration templates is then loaded, completing the loading and initialization of the element system, data source adaptation logic, inference rules, and computing power configuration parameters defined within it. The element system defines the types of elements participating in the inference within the scenario and their encodings. The data source adaptation logic defines the transmission protocol adaptation rules and format conversion rules corresponding to each data source. The inference rules define the coupling relationships and inference logic between the elements. The computing power configuration parameters define the number of computing power nodes, the computing power threshold, and scheduling strategy parameters.

[0036] After completing the scenario adaptation, data acquisition logic matching the data source transmission protocol is executed to interface with the multi-source heterogeneous data from different data sources. The sources of this multi-source heterogeneous data include public opinion platforms, traffic control systems, city operation platforms, emergency command systems, and video surveillance systems, and the data types cover text, numerical values, video, images, and streaming data. For different data sources, data acquisition logic corresponding to the data source transmission protocol is executed. For example, HTTP / HTTPS protocol data retrieval logic is executed for public opinion platform data, RTSP protocol streaming media retrieval logic is executed for video surveillance system data, MQTT protocol topic subscription logic is executed for sensor data, and FTP protocol file retrieval logic is executed for batch file data.

[0037] After collecting the multi-source heterogeneous data, the system invokes format conversion rules corresponding to the data source format to parse the data structure and extract key information. Different data sources output data in various formats, including JSON, XML, CSV, and binary streams. The format conversion rules define the parsing logic for each data format. For text data, text segmentation and vectorization are performed; for video and image data, object detection and feature extraction are performed; for numerical data, normalization is performed; and for streaming data, temporal segmentation and feature aggregation are performed.

[0038] The extracted key information undergoes anomaly filtering to remove invalid data that exceeds a preset valid range. This anomaly filtering includes: for numerical features, detecting whether they fall within a preset valid numerical range; data exceeding this range is marked as invalid and removed. For text features, detecting their length and semantic consistency; text exceeding a preset upper limit or with semantic consistency below a preset threshold is marked as invalid and removed. For video / image features, detecting their clarity and completeness; image frames with clarity below a preset threshold or incomplete data are marked as invalid and removed.

[0039] The valid information after the anomaly filtering process is assembled according to the structure defined by the data standardization adaptation protocol to generate standardized data containing a unique data identifier, timestamp, feature type code, feature value, and data confidence score. The unique data identifier is a globally unique string used to uniquely identify the standardized data throughout the entire simulation period. The timestamp is a Unix timestamp with millisecond precision, recording the actual acquisition time of the data. The feature type code is a code corresponding to the feature system in the scene template, used to identify the simulation feature type corresponding to the data. The feature values ​​are standardized numerical values ​​or vectors; numerical features are normalized to the [0,1] interval, and textual features are converted into vector representations of a preset dimension. The data confidence score characterizes the credibility of the data, determined comprehensively based on the stability of the data source, the integrity of the data acquisition chain, and the results of the anomaly filtering process.

[0040] S102, the standardized data is mapped to the virtual war game simulation environment in real time, the timestamps of the standardized data from multiple sources are aligned, and the feature values ​​of the elements in the aligned standardized data are updated to the corresponding element models according to the preset mapping relationship, so as to update the virtual war game simulation environment. S102 further includes: Read all the standardized data that has been accessed and obtain the millisecond-level timestamp carried by each piece of standardized data; Set a sliding time window and group all the standardized data whose millisecond timestamps fall within the same sliding time window into a synchronization batch. Based on the preset mapping relationship, determine the target element model corresponding to the feature value of each element in the synchronous batch in the virtual war game simulation environment; Only the feature values ​​of the elements that have changed are incrementally updated to the corresponding target feature model.

[0041] Specifically, in this embodiment of the invention, all accessed standardized data is read, and the millisecond-level timestamp carried by each piece of standardized data is obtained. The standardized data is generated by the aforementioned steps and includes five core fields: unique data identifier, timestamp, feature type code, feature feature value, and data confidence level. The timestamp is a Unix timestamp with millisecond precision, recording the actual collection time of the data.

[0042] A sliding time window is defined, with a preset window size and sliding step. The window size determines the time span covered by each synchronization batch, and the sliding step determines the time interval between two adjacent windows. The sliding time window starts from the beginning of the simulation and advances forward according to the sliding step, dividing the simulation timeline into continuous window intervals. All standardized data with millisecond-level timestamps falling within the same sliding time window are grouped into one synchronization batch. For data whose timestamps are exactly at the window boundary, they are assigned to a specific window according to a preset allocation rule to ensure that each piece of data belongs to only one synchronization batch.

[0043] Based on a pre-defined mapping relationship, the target element model corresponding to each element feature value within a synchronous batch in the virtual wargame simulation environment is determined. This pre-defined mapping relationship is defined in the configuration template loaded during the scenario adaptation phase, establishing a correspondence between element type codes and element models in the virtual wargame simulation environment. Based on the element type code of each standardized data entry, the mapping relationship table is consulted to determine the target element model that needs to be updated for that element feature value. When multiple standardized data entries corresponding to the same target element model exist within the same synchronous batch, the updates to the target element model for each data entry are processed sequentially according to the timestamp order.

[0044] Only the changed feature values ​​are incrementally updated to the corresponding target feature model. For each target feature model, the feature values ​​in the standardized data within the current synchronization batch are compared with the feature values ​​already stored in the current state of the target feature model. If the difference exceeds a preset change threshold, the feature values ​​in the target feature model are updated to the new feature values; if the difference does not exceed the preset change threshold, the current feature values ​​of the target feature model remain unchanged, and no update operation is performed. The preset change threshold is used to filter out invalid updates caused by minor data fluctuations, reducing mapping computation overhead. After completing the incremental updates of all target feature models within the sliding time window, the state of the virtual wargame simulation environment is updated, and the sliding time window advances by one step to process the next synchronization batch.

[0045] S103, the multi-element linkage inference task is decomposed into multiple inference sub-tasks based on the coupling relationship between the elements, and the inference sub-tasks are dynamically distributed to the corresponding computing nodes for parallel computing according to the computing power requirements of each inference sub-task and the computing power status of each computing node. S103 further includes: The decomposition rules of multi-element inference tasks are represented by directed graphs. Based on the causal and influence logic between each element, the overall inference task is decomposed into multiple inference sub-tasks with sequential or independent parallel relationships, and a priority is set for each inference sub-task. Based on historical simulation data, the computational load required for each simulation subtask is estimated in real time, and the computational power requirement of the simulation subtask is generated. A multi-objective scheduling function is constructed with minimizing simulation latency, maximizing the average utilization of computing resources, and minimizing the latency of high-priority tasks as optimization objectives. Based on the solution results of the multi-objective scheduling function, a set of available computing power nodes that meet the computing power requirements of the simulation subtask is determined, and the computing power node with the lowest load is selected from the set of available computing power nodes. The simulation subtask is then distributed to the selected computing power node for execution.

[0046] Specifically, in this embodiment of the invention, a directed graph is used to represent the decomposition rules of the multi-element inference task. Based on the causal and influence logic between the elements, the overall inference task is decomposed into multiple inference subtasks with sequential dependencies or independent parallel relationships, and a priority is assigned to each inference subtask. Nodes in the directed graph represent inference subtasks, directed edges represent the dependencies between inference subtasks, the direction of the edges indicates the execution order, and nodes with an in-degree of zero represent inference subtasks that can be executed independently in parallel. The causal and influence logic between the elements is defined in the inference rules loaded during the scenario adaptation stage, including the triggering relationship between public behavior and public opinion trends, the influence relationship between traffic flow and the urban environment, and the effect relationship between the distribution of emergency resources and public behavior. Based on these relationships, a directed graph is constructed to decompose the overall simulation task into multiple simulation subtasks, such as traffic situation simulation, public opinion situation simulation, public behavior simulation, urban environment simulation, and emergency resource simulation. These subtasks are interdependent; for example, the public behavior simulation subtask depends on the outputs of the public opinion situation simulation and traffic situation simulation subtasks. The priority of each simulation subtask is set according to its criticality in the simulation, with a priority value ranging from [1, 10]. Higher values ​​indicate higher priority. The emergency resource simulation subtask is set to the highest priority in emergency response scenarios.

[0047] Based on historical simulation data, the computational load required for each simulation subtask is estimated in real time, generating the computational power requirement for each subtask. Historical simulation data includes the actual computation time, input data size, and feature dimensions of each subtask during the historical simulation period. The input data size and feature dimensions of the current simulation subtask are matched with the historical simulation data, and the computational load required for the current subtask is estimated based on the matching results. This computational load is expressed as a computational power requirement, with the unit being a unified computational resource measurement standard, representing the amount of computational resources required to complete the simulation subtask.

[0048] A multi-objective scheduling function is constructed with the optimization objectives of minimizing simulation latency, maximizing average utilization of computing resources, and minimizing latency of high-priority tasks. The objective of minimizing simulation latency is achieved by minimizing the execution latency of the maximum task among all simulation subtasks. The objective of maximizing average utilization of computing resources is achieved by maximizing the arithmetic mean of the utilization rates of all computing nodes. The objective of minimizing latency of high-priority tasks is achieved by minimizing the sum of the weighted execution latencies of the differences between the priorities of all simulation subtasks and the highest priority task. The constraints of the multi-objective scheduling function are that the available computing power of each computing node is not less than the computing power requirement of the simulation subtasks allocated to that node, and the utilization rate of each computing node does not exceed a preset maximum utilization threshold.

[0049] Based on the solution results of the multi-objective scheduling function, a set of available computing power nodes that meet the computing power requirements of the simulation subtasks is determined. The computing power node with the lowest load is selected from this set, and the simulation subtasks are distributed to the selected node for execution. The set of available computing power nodes consists of all nodes whose available computing power is not less than the computing power requirement of the simulation subtask and whose current utilization rate does not exceed the maximum utilization rate threshold. The computing power node with the lowest load is the node with the lowest current utilization rate in the set of available computing power nodes. According to the priority order and dependencies of the simulation subtasks, the target computing power nodes for each simulation subtask are determined sequentially and distributed for execution. Simultaneous simulation subtasks without dependencies can be distributed to different computing power nodes for execution.

[0050] S104. During the simulation, the status of the data source, the status of the computing power node, and the status of the task execution are detected. In response to the detection of an anomaly, the corresponding fault-tolerant processing strategy is adopted according to the level of the anomaly, and the execution result of the simulation subtask is returned. S104 further includes: S1041, Real-time collection of the connection status of the data source, the resource occupancy rate of the computing power node, and the execution timeout information of the inference subtask; In response to any monitoring item exceeding the preset threshold range, an anomaly is determined to have occurred. S1042, the identified anomalies are classified into at least three levels, where minor anomalies are short-term data fluctuations, moderate anomalies are single computing node failures, and severe anomalies are computing logic conflicts or data interruptions. S1043, For the aforementioned minor anomalies, perform data completion or parameter smoothing processing; S1044, For the moderate anomaly, perform the process of redistributing the inference subtask that caused the moderate anomaly to other healthy nodes; S1045, In response to the severe anomaly, the state rollback mechanism is activated to restore the virtual wargame simulation environment to the most recent normal state before the severe anomaly occurred, and then the simulation is re-executed.

[0051] S1045 further includes: During the simulation, incremental snapshots of the full state of the virtual wargame simulation environment are periodically generated and stored, with the simulation step size as the period. In response to the detection of the severe anomaly, determine the most recently generated complete full state increment snapshot before the time point of the severe anomaly occurrence; Restore the state of all elements in the virtual wargame simulation environment to the state recorded by the found full state incremental snapshot; Based on the recovered state, the standardized data after the anomaly recovery is reacquired, and the deduction is continued based on the recovered state.

[0052] Specifically, in this embodiment of the invention, during the simulation process, the status of the data source, the status of the computing power nodes, and the status of the task execution are monitored. The monitoring items for the data source status include the connection status of each data source and the continuity of the data flow; the monitoring items for the computing power node status include the resource utilization rate of each computing power node; and the monitoring items for the task execution status include the execution timeout information of each simulation subtask. Data for the above monitoring items is collected in real time, and the current value of each monitoring item is compared with a preset threshold range. If any monitoring item exceeds the preset threshold range, an anomaly is determined to have occurred.

[0053] The identified anomalies are categorized into at least three levels. Minor anomalies are brief data fluctuations, referring to a momentary deviation of individual data points from the normal range. The data source connection remains normal, and the data stream automatically recovers after a preset short period. Moderate anomalies are single computing node failures, referring to a computing node being unresponsive for a preset time or its resource utilization rate continuously exceeding the maximum utilization threshold, while other computing nodes function normally. Severe anomalies are computational logic conflicts or data interruptions. Computational logic conflicts refer to contradictions in the output results of different inference subtasks that cannot be explained by preset rules. Data interruptions refer to multiple data sources simultaneously disconnecting or data stream interruptions lasting longer than the preset maximum tolerable duration.

[0054] For minor anomalies, data completion or parameter smoothing is performed. Data completion refers to using valid data before and after the outlier data point to fill in the missing or outlier data points through interpolation. Parameter smoothing refers to applying smoothing filters to the fluctuating data sequence to reduce the amplitude of data fluctuations and restore the data sequence to stability.

[0055] For moderate anomalies, the inference subtasks experiencing moderate anomalies are redistributed to other healthy nodes. Healthy nodes refer to computing power nodes other than the faulty node, whose available computing power meets the computing power requirements of the inference subtask and whose current utilization rate does not exceed the maximum utilization rate threshold. The inference subtasks currently executing on the faulty computing power node are marked as pending redistribution. A target node is selected from the healthy nodes according to the computing power scheduling rules, and the inference subtask is redistributed to the target node for re-execution.

[0056] In response to severe anomalies, a state rollback mechanism is activated to restore the virtual wargame simulation environment to its most recent normal state before the anomaly occurred, and then the simulation is re-executed. During the simulation, a full-state incremental snapshot of the virtual wargame simulation environment is periodically generated and stored, with the simulation step size as the period. Each full-state incremental snapshot records the complete state data of all elements of the virtual wargame simulation environment at the end of that simulation step size. In response to the detection of a severe anomaly, the most recently generated full-state incremental snapshot before the time of the severe anomaly is determined. The state of all elements of the virtual wargame simulation environment is restored to the state recorded in the found full-state incremental snapshot. Based on the restored state, standardized data after anomaly recovery is reacquired, and the simulation continues based on the restored state.

[0057] After handling the anomaly, the execution result of the simulation subtask is returned. For minor anomalies, the handled data is directly used as the input to the corresponding simulation subtask, and the execution result is returned normally. For moderate anomalies, the redistributed simulation subtask is executed on a healthy node and the execution result is returned. For severe anomalies, the simulation subtask is rolled back and re-executed, and the re-executed result is returned.

[0058] S105, based on the execution results returned by all the simulation sub-tasks, update the simulation situation of the virtual wargame simulation environment and generate simulation results.

[0059] Specifically, in this embodiment of the invention, the simulation situation of the virtual wargame simulation environment is updated based on the execution results returned by all simulation subtasks. The execution results of each simulation subtask are aggregated, including the element state change information output by the simulation subtask after completing calculations on the corresponding computing nodes. The execution results of each simulation subtask are mapped to the element models in the virtual wargame simulation environment according to the element type encoding, and the state parameters of each element model are updated to the latest values ​​in the execution results. For simulation subtasks with dependencies, the execution results of the dependent simulation subtasks are used as inputs to the dependent simulation subtasks, and the states of each element model are updated sequentially according to the dependency order. After the update, the simulation situation of the virtual wargame simulation environment reflects the comprehensive state of all elements in the current simulation step, including the spatial distribution of each element, the temporal change trend, and the coupling effect between elements.

[0060] Generating simulation results. The simulation results include a simulation situation snapshot and a simulation evaluation conclusion. The simulation situation snapshot is a complete state record of all element models in the virtual wargaming simulation environment at the end of the current simulation step, including the element type code, element feature value, and timestamp of each element model. The simulation evaluation conclusion is an evaluation information generated based on the simulation situation snapshot, after analyzing the development trend, risk level, key nodes, and handling suggestions of the current non-war military operation scenario according to preset evaluation rules. The simulation situation snapshot and simulation evaluation conclusion are assembled according to a preset output format to generate the simulation results for the current simulation step. The simulation results can be output to subsequent display stages or used as input for the next simulation step. After all preset simulation steps have been executed, the simulation results of each simulation step are summarized in chronological order to generate a full-cycle simulation result sequence.

[0061] The following is combined Figure 2 and Figure 3 This invention describes another embodiment of a real-time mapping and simulation method for multi-source data in wargaming for non-war military operations: like Figure 2 and Figure 3 As shown, in this embodiment, distributed computing and microservice architecture are introduced to build a real-time mapping and distributed simulation engine for multiple elements of wargames in non-war military operations.

[0062] Overall architecture of cloud-native microservice engine: We employ cloud-native microservices technology to build a wargaming engine architecture capable of supporting non-hotspot scenarios. The architecture is divided into six independent microservice modules, each supporting independent scaling and deployment. Modules communicate with each other via standardized RPC interfaces. The specific architecture is as follows: Multi-source heterogeneous data adaptation microservice: responsible for the access, preprocessing and standardization transformation of various heterogeneous data sources; Real-time mapping microservice between virtual and real data: responsible for the real-time mapping, timestamp alignment and synchronous update of real data and wargame environment model; Distributed parallel scheduling microservice: responsible for the decomposition and distribution of inference tasks and the intelligent scheduling of computing resources; Multi-factor extrapolation calculation kernel microservice: responsible for executing the calculation of the extrapolation model involving multiple factors; Dynamic fault-tolerant and rollback microservice: responsible for anomaly monitoring, fault tolerance handling, and state rollback during the simulation process; Scenario-based adaptation and interface microservices: responsible for rapid adaptation to different non-hotspot scenarios, providing standardized external interfaces.

[0063] Multi-source heterogeneous data standardization adaptation module: Build a standardized data adaptation protocol to enable rapid and standardized access to heterogeneous data.

[0064] Build a standardized adaptation protocol for data sources in non-hotspot war scenarios, supporting mainstream data transmission protocols such as HTTP / HTTPS, MQTT, WebSocket, RTSP, and FTP, and covering all types of data formats including text, numerical, video, image, and streaming data; Configure pluggable data source adaptation plugins. Develop corresponding adaptation plugins for different types of data sources. The plugins include four core functions: data acquisition, format conversion, feature extraction, and anomaly filtering. When a new data source is connected, only the corresponding adaptation plugin needs to be developed / imported, without modifying the core engine code. Establish data standardization and transformation rules to uniformly convert various heterogeneous data into a standardized data format that the engine can recognize. This includes five core fields: unique data identifier, timestamp, feature type, feature value, and confidence level, as well as expandable personalized attributes, ensuring that all accessed data has a unified format.

[0065] This embodiment establishes a data standard mapping formula for the standardized conversion of heterogeneous data sources, ensuring that all data formats in the access engine are consistent and improving the delivery efficiency of heterogeneous data access: ; in, The output data is standardized and consists of quintuples with a fixed structure. This is the original heterogeneous input data; To standardize the transformation function, a rule-based implementation based on the adapter plugin is used; Adaptation rules for the transmission protocol corresponding to the data source; Conversion rules corresponding to the data format; It serves as a unique identifier for the data, and is globally unique. This is the data timestamp, in Unix timestamp format, with millisecond precision. This is a unique code for the feature type, corresponding to the engine's standardized feature system. These are feature values, standardized to numerical values ​​in the range [0,1] or standardized text vectors. This represents the data confidence level, with a value range of [0,1], and is used for filtering outlier data.

[0066] Low-latency virtual-real real-time mapping and synchronization mechanism: A low-latency virtual-real real-time mapping and synchronization mechanism is used to achieve low-latency real-time synchronization between the real scene and the wargame environment.

[0067] Configure a multi-source data synchronization mechanism based on timestamp alignment, set millisecond-level timestamps for all accessed standardized data, and realize timestamp alignment of multi-source data based on sliding time windows to ensure that all data within the same time window are synchronously mapped to the wargaming environment; Construct a real-time mapping model of wargaming environment elements, and bind standardized data with the corresponding element models in the wargaming environment; Configure an incremental data update mechanism to update only the parameters of elements that have changed, without having to refresh the entire wargame environment, thus reducing mapping overhead; Configure a closed-loop optimization mechanism for mapping latency, monitor data access latency, mapping calculation latency, and environment update latency in real time, and dynamically adjust the time window size and update frequency based on latency monitoring results to ensure that end-to-end mapping latency is controlled within the target range.

[0068] This embodiment uses an end-to-end mapping delay calculation and optimization formula for real-time calculation and closed-loop optimization of mapping delay, ensuring that the total end-to-end virtual-to-real mapping delay is stably controlled within 500ms, meeting the requirements of real-time simulation. ; in, The total end-to-end virtual-to-physical mapping delay is expressed in milliseconds. Data access delay; Delay for timestamp alignment; Calculate the delay for the mapping; The wargaming environment update was delayed; This is the size of the sliding time window; These are the upper and lower limits of the window size; For environmental update frequency; These are the upper and lower limits for the update frequency; These are the constraints that need to be satisfied.

[0069] Intelligent computing power scheduling model for multi-factor parallel extrapolation: In this embodiment, a multi-factor parallel simulation intelligent scheduling model for computing power is configured to realize the dynamic allocation of computing power resources.

[0070] Using directed graphs, we construct decomposition rules for inference tasks, decompose multi-element linkage inference tasks into multiple independent sub-tasks, each sub-task corresponds to the calculation of one or a group of related elements, and clarify the priority, calculation volume estimate, and computing power requirements of the sub-tasks. The deep learning-based computational load prediction model, based on historical extrapolation data, predicts the computational load and computing power requirements of each sub-task in real time, providing a basis for computing power allocation. A multi-objective intelligent computing power scheduling model is established, with the optimization objectives of minimizing latency, maximizing computing power utilization, and ensuring the priority of core tasks. The decomposed sub-tasks are dynamically distributed to the corresponding computing power nodes to achieve dynamic allocation and optimal utilization of computing power resources.

[0071] The distributed parallel simulation computing power intelligent scheduling adopts a multi-objective optimization function for intelligent computing power scheduling, which is used for dynamic distribution of simulation tasks and intelligent scheduling of computing resources. It can improve the utilization rate of computing resources from 40% to over 85%, and the real-time simulation frame rate is stable at over 30 frames per second. Even in scenarios where the amount of computation surges due to sudden events, the real-time performance of the simulation can be guaranteed. ; in, The primary optimization objective is to minimize the maximum task execution latency and ensure a high real-time simulation frame rate. The second optimization objective is to maximize the average utilization rate of computing resources and avoid resource waste. The third optimization objective is to minimize the total latency of high-priority tasks and ensure that core tasks are executed first. For the first Execution delay of individual subtasks, This represents the total number of subtasks. For the first Utilization rate of each computing node; This represents the total number of computing nodes. The threshold for maximum node utilization; For the first The priority of each subtask, with a value range of [1, 10], where the larger the value, the higher the priority; It has the highest priority. For the first Available computing power of each computing node; For the first The computing power requirements of each sub-task; These are the constraints that need to be satisfied.

[0072] Dynamic fault tolerance and rollback mechanism during the simulation process: Configure a dynamic fault tolerance and rollback mechanism for the simulation process to achieve fault tolerance and accurate rollback during the simulation process, ensuring continuous and stable real-time simulation.

[0073] Construct a multi-dimensional anomaly monitoring system to monitor the status of data sources, computing nodes, task execution, and element computing logic in real time, and identify anomaly types such as data source interruption, node failure, task timeout, and logic conflict. Configure a tiered fault tolerance mechanism and adopt corresponding fault tolerance strategies for different levels of anomalies: minor anomalies are handled with data completion and parameter smoothing; moderate anomalies are handled with task redistribution and node switching; and severe anomalies are handled with a state rollback mechanism. An incremental snapshot mechanism for the simulation state is constructed. An incremental snapshot of the state is generated at each simulation step to record the full state data of the wargame environment. When an anomaly occurs, the simulation can be rolled back to the most recent normal state based on the snapshot and the simulation can be re-executed to ensure the continuity of the simulation and the accuracy of the results.

[0074] Extended adaptation and interface modules: Based on the plug-in-play architecture, the system implements scenario-based adaptation modules. For different non-hot war scenarios such as national defense mobilization, emergency response, urban stability maintenance, and security for major events, it pre-creates corresponding element systems, adaptation plugins, simulation rules, and computing power configuration templates. By importing the corresponding scenario templates, the scenario can be quickly adapted and deployed in the simulation engine.

[0075] For the purpose of simplicity, the method steps disclosed in the above embodiments are described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0076] like Figure 4 As shown, the present invention also provides a real-time mapping and simulation system for multi-source data in non-war military operations wargaming, comprising: The multi-source heterogeneous data standardization processing module 201 is configured to acquire multi-source heterogeneous data in non-war military operation scenarios, process the multi-source heterogeneous data based on a preset data standardization adaptation protocol, and generate standardized data with a unified data structure. The virtual-real data real-time mapping and synchronization module 202 is configured to map the standardized data to the virtual war game simulation environment in real time, align the timestamps of the standardized data from multiple sources, and update the feature values ​​of the elements in the aligned standardized data to the corresponding element model according to the preset mapping relationship, so as to update the virtual war game simulation environment. The parallel scheduling and distribution module 203 for simulation tasks is configured to decompose multi-element linkage simulation tasks into multiple simulation sub-tasks based on the coupling relationship between the elements, and dynamically distribute the simulation sub-tasks to the corresponding computing nodes for parallel computing according to the computing power requirements of each simulation sub-task and the computing power status of each computing node. The anomaly detection and graded fault tolerance handling module 204 is configured to detect the data source status, computing node status and task execution status during the simulation process. In response to the detection of an anomaly, it adopts the corresponding fault tolerance handling strategy according to the level of the anomaly and returns the execution result of the simulation subtask. The simulation situation update and result generation module 205 is configured to update the simulation situation of the virtual wargame simulation environment and generate simulation results based on the execution results returned by all the simulation sub-tasks.

[0077] It is worth noting that although only some basic functional modules are disclosed in the embodiments of this invention, it does not mean that the composition of this system is limited to the above-mentioned basic functional modules. On the contrary, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with existing technology to form an infinite number of embodiments or technical solutions. That is to say, this system is open rather than closed. The fact that this embodiment only discloses a few basic functional modules should not be considered as the scope of protection of this invention being limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above devices are described separately according to their functions as various units and modules. Of course, in implementing this invention, the functions of each unit and module can be implemented in one or more software and / or hardware.

[0078] like Figure 5 As shown, the present invention also provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the steps of a method for real-time mapping and simulation of multi-source data in non-war military operations wargaming.

[0079] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. For example... Figure 5 The structure shown in this embodiment of the invention includes an electronic device comprising one or more processors 710 and a memory 720; the processors 710 in this electronic device may be one or more. Figure 5 Taking a processor 710 as an example; a memory 720 is used to store one or more programs; the one or more programs are executed by the one or more processors 710, so that the one or more processors 710 implement a real-time mapping and simulation method for multi-source data of non-war military operations wargaming as described in any one of the embodiments of the present invention.

[0080] The electronic device may also include an input device 730 and an output device 740.

[0081] The processor 710, memory 720, input device 730, and output device 740 in this electronic device can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0082] The memory 720 in this electronic device serves as a computer-readable storage medium, capable of storing one or more programs. These programs can be software programs, computer-executable programs, or modules, such as the program instructions / modules corresponding to the real-time mapping and deduction method for multi-source data in a non-war military operations wargaming provided in this embodiment of the invention. The processor 710 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 720, thereby realizing the real-time mapping and deduction method for multi-source data in a non-war military operations wargaming as described in the above method embodiment.

[0083] The memory 720 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device. Furthermore, the memory 720 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 720 may further include memory remotely located relative to the processor 710, which can be connected to the device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0084] Input device 730 can be used to receive input digital or character information, and to generate key signal inputs related to user settings and function control of the electronic device. Output device 740 may include display devices such as a display screen.

[0085] The present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of a method for real-time mapping and simulation of multi-source data in a non-war military operations wargaming.

[0086] Specifically, the computer storage medium in this embodiment of the invention can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be—but is not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0087] 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 or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for real-time mapping and simulation of multi-source data in wargaming for non-war military operations, characterized in that, include: Acquire multi-source heterogeneous data from non-war military operation scenarios, process the multi-source heterogeneous data based on a preset data standardization adaptation protocol, and generate standardized data with a unified data structure. The standardized data is mapped to the virtual war game simulation environment in real time. The timestamps of the standardized data from multiple sources are aligned. The feature values ​​of the elements in the aligned standardized data are updated to the corresponding element models according to the preset mapping relationship, so as to update the virtual war game simulation environment. The multi-element linkage simulation task is decomposed into multiple simulation sub-tasks based on the coupling relationship between the elements. The simulation sub-tasks are dynamically distributed to the corresponding computing nodes for parallel computing according to the computing power requirements of each simulation sub-task and the computing power status of each computing node. During the simulation, the status of the data source, computing node, and task execution are monitored. In response to the detection of an anomaly, the corresponding fault-tolerant handling strategy is adopted according to the level of the anomaly, and the execution result of the simulation subtask is returned. Based on the execution results returned by all the simulation subtasks, the simulation situation of the virtual wargame simulation environment is updated, and simulation results are generated.

2. The method for real-time mapping and simulation of multi-source data in non-war military operations wargaming according to claim 1, characterized in that, Acquiring multi-source heterogeneous data from non-war military operation scenarios, processing the multi-source heterogeneous data based on a preset data standardization adaptation protocol to generate standardized data with a unified data structure, further including: Execute data acquisition logic that matches the data source transmission protocol to interface with the multi-source heterogeneous data from different data sources; For the collected multi-source heterogeneous data, the format conversion rules corresponding to the data source format are invoked to parse the data structure of the multi-source heterogeneous data and extract key information; The extracted key information is subjected to anomaly filtering to remove invalid data that exceeds the preset valid range; The valid information after the anomaly filtering process is assembled into standardized data, which includes a unique data identifier, timestamp, feature type code, feature value, and data confidence level, according to the structure defined by the data standardization adaptation protocol.

3. The method for real-time mapping and simulation of multi-source data in non-war military operations wargaming according to claim 1, characterized in that, The process of mapping the standardized data to a virtual wargame simulation environment in real time, aligning the timestamps of the multi-source standardized data, and updating the feature values ​​of the aligned standardized data to the corresponding feature models according to a preset mapping relationship to update the virtual wargame simulation environment further includes: Read all the standardized data that has been accessed and obtain the millisecond-level timestamp carried by each piece of standardized data; Set a sliding time window and group all the standardized data whose millisecond timestamps fall within the same sliding time window into a synchronization batch. Based on the preset mapping relationship, determine the target element model corresponding to the feature value of each element in the synchronous batch in the virtual war game simulation environment; Only the feature values ​​of the elements that have changed are incrementally updated to the corresponding target feature model.

4. The method for real-time mapping and simulation of multi-source data in non-war military operations wargaming according to claim 1, characterized in that, Disassemble the deduction task with multi-factor linkage into multiple deduction subtasks based on the coupling relationship between various factors, and dynamically distribute the deduction subtasks to the corresponding computing power nodes for parallel computing according to the computing power requirements of each deduction subtask and the computing power status of each computing power node, further including: Characterize the disassembly rules of the multi-factor deduction task with a directed graph, and disassemble the overall deduction task into multiple deduction subtasks with sequential dependencies or independent parallel relationships based on the causal and impact logic between various factors, and set priorities for each deduction subtask; Based on historical deduction data, estimate in real time the current required computing volume of each deduction subtask, and generate the computing power requirements of the deduction subtask; Take minimizing deduction latency, maximizing the average utilization rate of computing power resources, and minimizing the latency of high-priority tasks as optimization objectives, and construct a multi-objective scheduling function; According to the solution result of the multi-objective scheduling function, determine the set of available computing power nodes that meet the computing power requirements of the deduction subtask, and select the computing power node with the lowest load from the set of available computing power nodes, and distribute the deduction subtask to the selected computing power node for execution.

5. The method for real-time mapping and simulation of multi-source data in non-war military operations wargaming according to claim 1, characterized in that, During the deduction process, detect the data source status, the computing power node status, and the task execution status. In response to detecting an abnormality, adopt a corresponding fault tolerance handling strategy according to the level of the abnormality for disposal, and return the execution result of the deduction subtask, further including: Real-time collect the connection status of the data source, the resource occupancy rate of the computing power node, and the execution timeout information of the deduction subtask. In response to any monitoring item exceeding the preset threshold range, it is determined that an abnormality has occurred; Classify the identified abnormality into at least three levels. Among them, a minor abnormality is a short-term data fluctuation, a moderate abnormality is a single computing power node failure, and a severe abnormality is a computing logic conflict or data interruption; For the minor abnormality, perform data completion or parameter smoothing processing; For the moderate abnormality, perform the process of redistributing the deduction subtask with the moderate abnormality to other healthy nodes; For the severe abnormality, start a state rollback mechanism, restore the virtual wargame deduction environment to the nearest normal state before the severe abnormality occurs, and then re-execute the deduction.

6. The method for real-time mapping and simulation of multi-source data in non-war military operations wargaming according to claim 5, characterized in that, For the severe abnormality, start a state rollback mechanism, restore the virtual wargame deduction environment to the nearest normal state before the severe abnormality occurs, and then re-execute the deduction, further including: During the deduction process, generate and store a full-scale state increment snapshot of the virtual wargame deduction environment periodically with the deduction step length as the period; In response to detecting the severe abnormality, determine the last complete full-scale state increment snapshot generated before the time point of the severe abnormality; Restore the state of all elements of the virtual wargame deduction environment to the state recorded in the found full-scale state increment snapshot; Based on the restored state, re-obtain the standardized data after the abnormality is restored, and continue to execute the deduction based on the restored state.

7. The method for real-time mapping and simulation of multi-source data in non-war military operations wargaming according to claim 1, characterized in that, Before obtaining multi-source heterogeneous data in the non-war military operation scenario, it also includes a scenario adaptation step: Receive scenario deployment instructions, which indicate the type of non-war military operation scenario to be deployed; Based on the scenario type, determine the configuration template set corresponding to the scenario type, and load the configuration template set; Complete the loading and initialization of the element system, data source adaptation logic, inference rules and computing power configuration parameters defined in the configuration template set.

8. A real-time mapping and simulation system for multi-source data in non-war military operations wargaming, characterized in that, include: The multi-source heterogeneous data standardization processing module is configured to acquire multi-source heterogeneous data in non-war military operation scenarios, process the multi-source heterogeneous data based on a preset data standardization adaptation protocol, and generate standardized data with a unified data structure. The virtual-real data real-time mapping and synchronization module is configured to map the standardized data to the virtual war game simulation environment in real time, align the timestamps of the standardized data from multiple sources, and update the feature values ​​of the elements in the aligned standardized data to the corresponding element model according to the preset mapping relationship, so as to update the virtual war game simulation environment. The parallel scheduling and distribution module for simulation tasks is configured to decompose multi-element linkage simulation tasks into multiple simulation sub-tasks based on the coupling relationship between the elements, and dynamically distribute the simulation sub-tasks to the corresponding computing nodes for parallel computing according to the computing power requirements of each simulation sub-task and the computing power status of each computing node. The anomaly detection and hierarchical fault tolerance module is configured to detect the data source status, computing node status and task execution status during the simulation process. In response to the detection of an anomaly, it adopts the corresponding fault tolerance strategy according to the level of the anomaly and returns the execution result of the simulation subtask. The simulation situation update and result generation module is configured to update the simulation situation of the virtual wargame simulation environment and generate simulation results based on the execution results returned by all the simulation sub-tasks.

9. An electronic device, characterized in that, include: The system includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program executable by an electronic device, which, when run on the electronic device, causes the electronic device to perform the steps of the method according to any one of claims 1 to 7.

Images