Service-oriented multi-core parallel simulation training engine system and simulation processing method thereof

Abstract

The present invention provides a service-oriented multi-core parallel simulation training engine system and a simulation processing method thereof, which relates to the field of military simulation technology. The service-oriented multi-core parallel simulation training engine system includes: a front-end simulation operation control environment engine; a back-end cloud simulation computing service environment engine, including: a resource scheduling node deployed to the cloud, multiple artificial intelligence nodes, and multiple simulation computing nodes; wherein the simulation computing node is used to perform resource scheduling and multi-core parallel simulation computing on the confrontation process between the red party's intelligent agent and the blue party's intelligent agent based on the simulation engine instance, and provide simulation sample data for the training of each intelligent agent based on the multi-core parallel simulation computing results. The present invention is capable of large-scale complex simulation computing tasks, has strong simulation support capabilities, high simulation operation efficiency, can achieve ultra-real-time simulation with high simulation acceleration ratio, and meet the large sample collection requirements required for intelligent agent training.

Description

Technical Field

[0001] The present invention relates to the field of military simulation technology, and in particular to a service-oriented multi-core parallel simulation training engine system and a simulation processing method thereof. Background Art

[0002] In recent years, with the development and application of technologies in the field of artificial intelligence, applying artificial intelligence technology to military system confrontation simulation and conducting intelligent game simulation has become one of the hot research directions in the field of military simulation. Therefore, service-oriented simulation training engine technology is also particularly important.

[0003] At present, most simulation engines used in the field of military simulation adopt a single-process monolithic software model with sequential scheduling, or simply deploy traditional monolithic software on the cloud. There is a lack of cloud service simulation training engines that are truly capable of large-scale and complex simulation computing tasks, resulting in insufficient simulation support capabilities and low simulation operation efficiency. It is impossible to achieve ultra-real-time simulation with a high simulation acceleration ratio, and it is impossible to meet the large sample collection requirements required for intelligent agent training. Summary of the invention

[0004] The present invention provides a service-oriented multi-core parallel simulation training engine system and a simulation processing method thereof, so as to solve the problems that most simulation engines used in the field of military simulation in the prior art adopt a single-process monolithic software mode with sequential scheduling, or simply deploy traditional monolithic software on the cloud, and lack a cloud service simulation training engine that can truly handle large-scale and complex simulation computing tasks, resulting in insufficient simulation support capabilities, low simulation operation efficiency, inability to achieve ultra-real-time simulation with a high simulation acceleration ratio, and inability to meet the large sample collection requirements required for intelligent body training. The present invention achieves the purpose of being able to handle large-scale and complex simulation computing tasks, having strong simulation support capabilities, high simulation operation efficiency, being able to achieve ultra-real-time simulation with a high simulation acceleration ratio, and meeting the large sample collection requirements required for intelligent body training.

[0005] The present invention provides a service-oriented multi-core parallel simulation training engine system, comprising:

[0006] A front-end simulation operation control environment engine is used to create a military simulation task through a browser and generate a task simulation request carrying the military simulation task;

[0007] The backend cloud simulation computing service environment engine includes: resource scheduling nodes deployed to the cloud, multiple artificial intelligence nodes, and multiple simulation computing nodes; among them,

[0008] The resource scheduling node is used to receive and respond to the task simulation request, create and start the multiple artificial intelligence nodes and multiple simulation computing nodes based on the resource pool in the cloud, dynamically deploy the military simulation task to the multiple simulation computing nodes, and create and control the simulation engine instances in the simulation computing nodes;

[0009] The artificial intelligence node is used to manage and control at least one intelligent agent;

[0010] The simulation computing node is used to perform resource scheduling and multi-core parallel simulation computing on the confrontation process between at least one of the red agents and at least one of the blue agents based on the simulation engine instance, and provide simulation sample data for the training of each of the agents based on the multi-core parallel simulation computing results.

[0011] According to a service-oriented multi-core parallel simulation training engine system provided by the present invention, an artificial intelligence scheduler and a first artificial intelligence interface service are deployed and run in the artificial intelligence node; wherein,

[0012] The artificial intelligence scheduler is used to manage the registration, operation, suspension, resumption and exit of at least one intelligent agent;

[0013] The first artificial intelligence interface service is used to call at least one of the simulation control interface, micro-operation instruction interface and action-level instruction interface required for the training and operation of the intelligent body.

[0014] According to a service-oriented multi-core parallel simulation training engine system provided by the present invention, the simulation computing node deploys and runs a second artificial intelligence interface service, multiple application domain models corresponding to the target business, a CGF top-level model framework and at least one simulation engine; wherein,

[0015] The second artificial intelligence interface service is used to respond to the simulation control interface, micro-operation instruction interface and action-level instruction interface required for the training and operation of the intelligent agent;

[0016] The CGF top-level model framework is used to develop the multiple application domain models;

[0017] The simulation engine instance corresponding to the simulation engine is used to call the application domain model to simulate scene objects in a military confrontation scenario, and to perform resource scheduling and multi-core parallel simulation calculations on the confrontation process between at least one of the red agents and at least one of the blue agents in the military confrontation scenario, and to provide simulation sample data for the training of each of the agents based on the multi-core parallel simulation calculation results.

[0018] According to a service-oriented multi-core parallel simulation training engine system provided by the present invention, the simulation engine comprises:

[0019] A simulation manager, configured to perform at least one simulation management of the simulation engine including system management, communication management, component management, object management, event management, time management, scene management and resource management;

[0020] A multi-core parallel scheduler is used to control and manage each of the application domain models and the simulation time of the application domain models, call the application domain models to simulate the scene objects in the military confrontation scene, allocate computing resources, storage resources and communication resources to each of the application domain models involved in the confrontation process between at least one of the red agents and at least one of the blue agents in the military confrontation scene under the constraint of consistent time and space, adopt a fork-convergence parallel computing mode to fork the main thread at a given synchronization point to generate several sub-threads, allocate the same type of the application domain model to each of the sub-threads, converge to the main thread after the multi-core parallel simulation calculations are completed by the several sub-threads, and provide simulation sample data for the training of each of the agents based on the multi-core parallel simulation calculation results;

[0021] The simulation engine kernel is used to provide a reflective object system kernel framework and is the core base of the simulation engine.

[0022] According to a service-oriented multi-core parallel simulation training engine system provided by the present invention, an engine instance manager is deployed in the resource scheduling node, and the engine instance manager is used to receive and respond to the task simulation request, create and start the multiple artificial intelligence nodes and multiple simulation computing nodes based on the resource pool in the cloud, create simulation engine instances in the multiple simulation computing nodes respectively based on the military simulation task, and control the operation, stop, recovery and end of the simulation engine instance.

[0023] According to a service-oriented multi-core parallel simulation training engine system provided by the present invention, the front-end simulation operation control environment includes: a simulation control node, in which a simulation operation controller is deployed;

[0024] The simulation operation controller is used to display the human-computer interaction interface of the browser, receive task creation operation information based on the human-computer interaction interface, create a military simulation task based on the task creation operation information, generate a task simulation request carrying the military simulation task, and send the task simulation request to the resource scheduling node.

[0025] According to a service-oriented multi-core parallel simulation training engine system provided by the present invention, the simulation operation controller is also used to receive instruction issuance operation information based on the human-computer interaction interface, and issue simulation interaction instructions to the resource scheduling node based on the instruction issuance operation information, and the simulation interaction instructions are used to control the simulation engine instance.

[0026] According to a service-oriented multi-core parallel simulation training engine system provided by the present invention, the simulation manager is also used to: access at least one external resource among real soldier resources, virtual resources and construction test resources to the simulation engine.

[0027] The present invention also provides a simulation processing method for a service-oriented multi-core parallel simulation training engine system, the method being applied to a background cloud simulation computing service environment engine, the method comprising:

[0028] The resource scheduling node receives and responds to the task simulation request carrying the military simulation task sent by the front-end simulation operation control environment engine, creates and starts multiple artificial intelligence nodes and multiple simulation computing nodes based on the cloud resource pool, dynamically deploys the military simulation task to the multiple simulation computing nodes, and creates and controls the simulation engine instances in the simulation computing nodes;

[0029] The artificial intelligence node manages and controls at least one intelligent agent;

[0030] The simulation computing node performs resource scheduling and multi-core parallel simulation computing on the confrontation process between at least one of the red agents and at least one of the blue agents based on the simulation engine instance, and provides simulation sample data for the training of each of the agents based on the multi-core parallel simulation computing results.

[0031] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the simulation processing method of the service-oriented multi-core parallel simulation training engine system as described above are implemented.

[0032] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the simulation processing method of the service-oriented multi-core parallel simulation training engine system as described above are implemented.

[0033] The service-oriented multi-core parallel simulation training engine system and the simulation processing method thereof provided by the present invention include: a front-end simulation operation control environment engine and a back-end cloud simulation computing service environment engine; the front-end simulation operation control environment engine can create military simulation tasks through a browser, and generate task simulation requests carrying military simulation tasks; the back-end cloud simulation computing service environment engine includes: a resource scheduling node deployed to the cloud, multiple artificial intelligence nodes and multiple simulation computing nodes, the resource scheduling node can receive and respond to task simulation requests, create and start multiple artificial intelligence nodes and multiple simulation computing nodes based on a resource pool in the cloud, dynamically deploy military simulation tasks to multiple simulation computing nodes, and perform simulation The simulation engine instance in the computing node is created and controlled, that is, a large number of resources in the cloud resource pool can be called through the browser, supporting dynamic scheduling and parallel operation of large-scale simulation engine instances; the artificial intelligence node can manage and control at least one intelligent agent; the simulation computing node can perform resource scheduling and multi-core parallel simulation calculations on the confrontation process between at least one intelligent agent on the red side and at least one intelligent agent on the blue side based on the simulation engine instance, and provide simulation sample data for the training of each intelligent agent based on the multi-core parallel simulation calculation results. It is capable of large-scale and complex simulation calculation tasks, has strong simulation support capabilities, high simulation operation efficiency, can achieve ultra-real-time simulation with high simulation acceleration ratio, and meet the large sample collection requirements required for intelligent agent training. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 It is a schematic diagram of the architecture of a service-oriented multi-core parallel simulation training engine system provided by an embodiment of the present invention;

[0036] Figure 2 is a schematic diagram of an engine instance manager provided by an embodiment of the present invention;

[0037] Figure 3 is a schematic diagram of an artificial intelligence node provided by an embodiment of the present invention;

[0038] Figure 4 It is a schematic diagram of a model system of a CGF model framework provided by an embodiment of the present invention;

[0039] Figure 5 is a schematic diagram of resource scheduling of a multi-core parallel scheduler provided by an embodiment of the present invention;

[0040] Figure 6 It is a flowchart of a simulation processing method of a service-oriented multi-core parallel simulation training engine system provided by an embodiment of the present invention;

[0041] Figure 7 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Combine the following Figures 1 to 5 The service-oriented multi-core parallel simulation training engine system of the present invention is described.

[0044] Please refer to Figure 1 , Figure 1 Schematic diagram of the architecture of a service-oriented multi-core parallel simulation training engine system provided by an embodiment of the present invention. Figure 1 As shown, the service-oriented multi-core parallel simulation training engine system may include: a front-end simulation operation control environment engine 1 and a back-end cloud simulation computing service environment engine 2, and the front-end simulation operation control environment engine 1 and the back-end cloud simulation computing service environment engine 2 are separate architectures.

[0045] The front-end simulation operation control environment engine 1 is used to create military simulation tasks through a browser and generate task simulation requests carrying military simulation tasks.

[0046] The backend cloud simulation computing service environment engine 2 includes multiple simulation nodes, and the multiple simulation nodes may include physical simulation nodes and / or virtual simulation nodes. Specifically, the backend cloud simulation computing service environment engine 2 includes: a resource scheduling node 21 deployed to the cloud, multiple artificial intelligence nodes 22, and multiple simulation computing nodes 23. The artificial intelligence node and the simulation computing node can be used as separate simulation nodes, or they can be merged into the same simulation node as needed. Among them, the front-end simulation operation control environment engine 1 is connected to the resource scheduling node 21 in communication, and the resource scheduling node 21 is connected to the artificial intelligence node 22 and the simulation computing node 23 in communication, and the artificial intelligence node 22 is connected to the simulation computing node 23 in communication. In addition, the resource scheduling node 21 can realize the control of all artificial intelligence nodes 22 and simulation computing nodes 23. Each artificial intelligence node 22 is usually connected to a simulation computing node 23 for intelligent decision-making and control. A simulation computing node 23 can also access multiple artificial intelligence nodes 22.

[0047] Specifically, the resource scheduling node 21 is used to receive and respond to task simulation requests, create and start multiple artificial intelligence nodes 22 and multiple simulation computing nodes 23 based on the cloud resource pool, dynamically deploy military simulation tasks to multiple simulation computing nodes 23, and create and control simulation engine instances in the simulation computing nodes 23. In other words, a large number of resources in the cloud resource pool can be called through the browser, supporting dynamic scheduling and parallel operation of large-scale simulation engine instances.

[0048] The artificial intelligence node 22 is used to manage and control at least one intelligent agent. The red team or the blue team can set up several intelligent agents, for example: one intelligent agent simulates the leader and one intelligent agent simulates the pilot.

[0049] The simulation computing node 23 is used to perform resource scheduling and multi-core parallel simulation computing on the confrontation process between at least one agent of the red team and at least one agent of the blue team based on the simulation engine instance, and provide simulation sample data for the training of each agent based on the multi-core parallel simulation computing results. The simulation computing node 23 supports dynamic scheduling and parallel operation of large-scale simulation engine instances, can realize parallel computing of simulation tasks, and effectively support agent training and confrontation.

[0050] The service-oriented multi-core parallel simulation training engine system provided in this embodiment includes: a front-end simulation operation control environment engine and a back-end cloud simulation computing service environment engine; the front-end simulation operation control environment engine can create military simulation tasks through a browser and generate task simulation requests carrying military simulation tasks; the back-end cloud simulation computing service environment engine includes: a resource scheduling node deployed to the cloud, multiple artificial intelligence nodes and multiple simulation computing nodes, the resource scheduling node can receive and respond to task simulation requests, create and start multiple artificial intelligence nodes and multiple simulation computing nodes based on a resource pool in the cloud, dynamically deploy military simulation tasks to multiple simulation computing nodes, and perform simulation engine instance operations on the simulation computing nodes. Create and control, that is, a large number of resources in the cloud resource pool can be called through the browser, supporting dynamic scheduling and parallel operation of large-scale simulation engine instances; artificial intelligence nodes can manage and control at least one intelligent agent; simulation computing nodes can perform resource scheduling and multi-core parallel simulation calculations on the confrontation process between at least one intelligent agent on the red side and at least one intelligent agent on the blue side based on the simulation engine instance, and provide simulation sample data for the training of each intelligent agent based on the multi-core parallel simulation calculation results. It is capable of large-scale and complex simulation computing tasks, has strong simulation support capabilities, high simulation operation efficiency, can achieve ultra-real-time simulation with high simulation acceleration ratio, and meet the large sample collection requirements required for intelligent agent training.

[0051] In one embodiment, the front-end simulation operation control environment 1 includes: a simulation control node 11, in which a simulation operation controller 12 is deployed; the simulation operation controller 12 is used to display the human-computer interaction interface of the browser, receive task creation operation information based on the human-computer interaction interface, create a military simulation task based on the task creation operation information, generate a task simulation request carrying the military simulation task, and send the task simulation request to the resource scheduling node 21. The resource scheduling node 21 can be requested through the browser to call a large number of resources in the resource pool in the cloud, supporting dynamic scheduling and parallel operation of large-scale simulation engine instances.

[0052] In one embodiment, a runtime engine instance manager 211 is deployed in the resource scheduling node 21. Figure 2 As shown, the engine instance manager 211 is used to receive and respond to task simulation requests, create and start multiple artificial intelligence nodes 22 and multiple simulation computing nodes 23 based on the cloud resource pool, create simulation engine instances in multiple simulation computing nodes 23 based on military simulation tasks, and control the operation, stop, recovery and end of the simulation engine instances. The resource scheduling node 21 can create and control all artificial intelligence nodes 22 and simulation computing nodes 23, as well as the creation and control of simulation engine instances.

[0053] In one embodiment, if Figure 3As shown, an artificial intelligence scheduler 221 and a first artificial intelligence interface service 222 are deployed and run in the artificial intelligence node 22; wherein the artificial intelligence scheduler 221 is used to manage the registration, operation, suspension, resumption and exit of at least one intelligent agent; the first artificial intelligence interface service 222 is used to call at least one of the simulation control interface, micro-operation instruction interface and action-level instruction interface required for the training and operation of the intelligent agent.

[0054] Specifically, the first artificial intelligence interface service 222 is a cloud service interface type, which provides a series of simulation control interfaces, micro-operation instruction interfaces and action-level instruction interfaces required for calling the training and operation of the intelligent body.

[0055] Among them, the simulation control interface is used to realize the control of the simulation process, for example: the simulation start interface void simulationStart(), the simulation pause interface void simulationPause(), the simulation acceleration interface void simulationFast(), etc.

[0056] The micro-operation instruction interface is used to control the simulation entity to carry out micro-operation actions, such as: moving along the specified route void sendMoveAlongTsk (MoveAlongTsk task, char*taskN ame), aircraft takeoff void sendTakeOffTsk (TakeOffTsk task, char*task Name) and returning void sendReturnBaseTsk (ReturnBaseTsk task, char*tas kName), etc.

[0057] The action-level command interface is used to trigger the simulation entity to carry out a specific action, such as patrol reconnaissance combat mission void sendPatrolOperationTsk(PatrolScoutOperationTsk task,char*taskName), air interception combat mission void sendAirInterceptOp erationTsk(AirInterceptOperationTsk task,char*taskName), etc.

[0058] In this embodiment, an artificial intelligence scheduler and a first artificial intelligence interface service are deployed and run in the artificial intelligence node. The artificial intelligence scheduler can manage the registration, operation, suspension, resumption and exit of at least one intelligent agent. The intelligent agent can call the simulation control interface, micro-operation instruction interface and action-level instruction interface through the first artificial intelligence interface service to realize the training and operation of the intelligent agent.

[0059] like Figure 3 As shown, the artificial intelligence scheduler 221 is also used to: call the initialization interface Init() to start the simulation engine, load the script, load the artificial intelligence algorithm, and perform a series of initialization actions; control entry into the main loop function Loop(), obtain the simulation status in each loop process, call the external artificial intelligence algorithm for decision-making calculations, control the simulation process, and issue simulation interaction instructions.

[0060] The simulation operation controller 12 is also used to receive instruction issuance operation information based on the human-computer interaction interface, and issue simulation interaction instructions to the resource scheduling node 21 based on the instruction issuance operation information. The simulation interaction instructions are used to control the simulation engine instance. The simulation interaction instructions can be issued through the browser, and the parallel management of the military simulation tasks can be realized through the control of the simulation instance. That is, the simulation control instructions can be dynamically input through the browser to control the simulation process.

[0061] In one embodiment, the simulation computing node 23 deploys and runs a second artificial intelligence interface service 231, multiple application domain models 232 corresponding to the target business, a computer generated forces (CGF) top-level model framework 233, and at least one simulation engine; wherein,

[0062] The second artificial intelligence interface service 231 is used to respond to the simulation control interface, micro-operation instruction interface and action-level instruction interface required for the training and operation of the intelligent body;

[0063] The CGF top-level model framework 233 is used to develop models for multiple application areas;

[0064] The simulation engine instance corresponding to the simulation engine is used to call the application domain model to simulate the scene objects in the military confrontation scenario, and perform resource scheduling and multi-core parallel simulation calculations on the confrontation process between at least one intelligent agent of the red side and at least one intelligent agent of the blue side in the military confrontation scenario, and provide simulation sample data for the training of each intelligent agent based on the multi-core parallel simulation calculation results.

[0065] Specifically, the CGF model framework 233 provides a complete set of general top-level model framework supports for model developers. Based on the CGF model framework, model developers can quickly develop application domain models through inheritance and generalization mechanisms.

[0066] like Figure 4As shown, the CGF model framework 233 includes the top-level model node CNode, the target data class JSTargetDataRep, the model state data class JSModelSR, the formation description class JSFormation, the participant class JSSide, the radiation data class JSEmitter, the entity state pool class JSEntitySR, the simulation task description class JSSimTask, the communication network class JSComNe twork, the model class JSModel, the scenario description class JSScnProfile and the environment class JSEnvi ronment.

[0067] Among them, the model status data class JSModelSR includes JSSensorModelSR for recording sensor status parameters, JSWeaponSysModelSR for recording the working status and some working parameters of the weapon system, and JSFacilityModelSR for recording the status and some parameters of aircraft / dock facilities.

[0068] The entity status pool JSEntitySR mainly includes the satellite status pool JSSatelliteESR, the aircraft status pool JSAircraftESR, the ship status pool JSShipESR, the submersible status pool JSSubmarineESR, the facility status pool JSFacilityESR, the land vehicle status pool JSGroundVehicleESR and the weapon status pool JSWeaponESR.

[0069] The model state data class JSModelSR includes the equipment class capability model JSEquipment and the task class capability model JSMission.

[0070] In general, the model system is a tree structure, and each category follows a certain traceability and inheritance relationship. The simulation engine organizes, manages and schedules the application domain model according to the model type to realize the simulation model calculation control.

[0071] According to actual business needs, multiple application domain models 232 corresponding to the target business can be developed based on the CGF model framework 233, for example: a certain type of aircraft model, ship model, warship model, rocket model, etc.

[0072] The simulation computing environment is composed of several simulation engines running in parallel. Multiple simulation engines can be distributed and networked to run in parallel. The process of the simulation engine running is the simulation engine instance. The simulation engine instance can call the application domain model to simulate the scene objects in the military confrontation scene. For example, the simulation engine instance calls a certain type of aircraft model to simulate the aircraft scene object in the military confrontation scene.

[0073] The simulation engine instance performs resource scheduling and multi-core parallel simulation calculations on the confrontation process between at least one intelligent agent of the red side and at least one intelligent agent of the blue side in a military confrontation scenario, and provides simulation sample data for the training of each intelligent agent based on the multi-core parallel simulation calculation results.

[0074] In this embodiment, multiple application domain models corresponding to the target business can be developed based on the CGF model framework according to actual business needs, and the simulation engine instance can call each application domain model to simulate each scene object in the military confrontation scene.

[0075] In one embodiment, the simulation engine includes:

[0076] A simulation manager 31, used for performing at least one simulation management of the simulation engine including system management, communication management, component management, object management, event management, time management, scene management and resource management;

[0077] The multi-core parallel scheduler 32 is used to accurately control and manage each application domain model 232 and the simulation time of the application domain model 232, call the application domain model 232 to simulate the scene objects in the military confrontation scenario, and allocate computing resources, storage resources and communication resources to each application domain model 232 involved in the confrontation process between at least one intelligent agent of the red side and at least one intelligent agent of the blue side in the military confrontation scenario under the constraints of consistent time and space.

[0078] Among them, the allocation of computing resources is the most critical, such as Figure 5 As shown, a fork-join parallel computing mode is adopted to fork (Fork) the main thread at a given synchronization point to generate several sub-threads, and each sub-thread is assigned an application domain model 232 of the same type. After the several sub-threads complete the multi-core parallel simulation calculation, they are converged (Join) to the main thread, and simulation sample data is provided for the training of each intelligent agent based on the multi-core parallel simulation calculation results.

[0079] The simulation engine kernel 33 is used to provide a reflective object system kernel framework, high-performance service retrieval and scheduling capabilities, and is the core base of the simulation engine. The simulation manager 31, multi-core parallel scheduler 32, CGF model framework 233, first AI interface service 222 and second AI interface service 231 are built on the simulation engine kernel 33 and are designed and developed in a component-based manner.

[0080] In this embodiment, the simulation manager performs simulation management at the granularity of the simulation engine, and the multi-core parallel scheduler accurately controls and manages each application domain model and simulation time, and allocates computing resources, storage resources and communication resources to each application domain model in a timely manner under the constraints of consistent time and space. It also uses a fork-convergence mode based on the thread pool to perform multi-core parallel simulation calculations, which can achieve parallelism at the entity object level and ensure load balancing for each thread.

[0081] In one embodiment, the simulation manager is also used to: access at least one external resource among real-life resources, virtual resources, and construction test resources to the simulation engine, and these external resources can be combined to perform simulations to achieve purposes such as tactical deduction and tactics research.

[0082] The simulation processing method of the service-oriented multi-core parallel simulation training engine system provided by the present invention is described below. The simulation processing method of the service-oriented multi-core parallel simulation training engine system described below and the service-oriented multi-core parallel simulation training engine system described above can be referenced to each other.

[0083] Please refer to Figure 6 , Figure 6 1 is a flow chart of a simulation processing method of a service-oriented multi-core parallel simulation training engine system provided by an embodiment of the present invention. The method is applied to a background cloud simulation computing service environment engine, such as Figure 6 As shown, the method may include the following steps:

[0084] Step 601: The resource scheduling node receives and responds to a task simulation request carrying a military simulation task sent by the front-end simulation operation control environment engine, creates and starts multiple artificial intelligence nodes and multiple simulation computing nodes based on a cloud resource pool, dynamically deploys the military simulation task to the multiple simulation computing nodes, and creates and controls simulation engine instances in the simulation computing nodes;

[0085] Step 602: The artificial intelligence node manages and controls at least one intelligent agent;

[0086] Step 603: The simulation computing node performs resource scheduling and multi-core parallel simulation computing on the confrontation process between at least one of the red agents and at least one of the blue agents based on the simulation engine instance, and provides simulation sample data for the training of each of the agents based on the multi-core parallel simulation computing results.

[0087] The specific implementation process and technical effects of the method of this embodiment are similar to those of the aforementioned embodiments. For details, please refer to the detailed introduction in the service-oriented multi-core parallel simulation training engine system embodiment, which will not be repeated here.

[0088] Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the simulation processing method of the service-oriented multi-core parallel simulation training engine system, and the method includes:

[0089] The resource scheduling node receives and responds to the task simulation request carrying the military simulation task sent by the front-end simulation operation control environment engine, creates and starts multiple artificial intelligence nodes and multiple simulation computing nodes based on the cloud resource pool, dynamically deploys the military simulation task to the multiple simulation computing nodes, and creates and controls the simulation engine instances in the simulation computing nodes;

[0090] The artificial intelligence node manages and controls at least one intelligent agent;

[0091] The simulation computing node performs resource scheduling and multi-core parallel simulation computing on the confrontation process between at least one of the red agents and at least one of the blue agents based on the simulation engine instance, and provides simulation sample data for the training of each of the agents based on the multi-core parallel simulation computing results.

[0092] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0093] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer, the computer can execute the simulation processing method of the service-oriented multi-core parallel simulation training engine system provided by the above methods, the method comprising:

[0094] The resource scheduling node receives and responds to the task simulation request carrying the military simulation task sent by the front-end simulation operation control environment engine, creates and starts multiple artificial intelligence nodes and multiple simulation computing nodes based on the cloud resource pool, dynamically deploys the military simulation task to the multiple simulation computing nodes, and creates and controls the simulation engine instances in the simulation computing nodes;

[0095] The artificial intelligence node manages and controls at least one intelligent agent;

[0096] The simulation computing node performs resource scheduling and multi-core parallel simulation computing on the confrontation process between at least one of the red agents and at least one of the blue agents based on the simulation engine instance, and provides simulation sample data for the training of each of the agents based on the multi-core parallel simulation computing results.

[0097] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the simulation processing method of the service-oriented multi-core parallel simulation training engine system provided above, the method comprising:

[0098] The resource scheduling node receives and responds to the task simulation request carrying the military simulation task sent by the front-end simulation operation control environment engine, creates and starts multiple artificial intelligence nodes and multiple simulation computing nodes based on the cloud resource pool, dynamically deploys the military simulation task to the multiple simulation computing nodes, and creates and controls the simulation engine instances in the simulation computing nodes;

[0099] The artificial intelligence node manages and controls at least one intelligent agent;

[0100] The simulation computing node performs resource scheduling and multi-core parallel simulation computing on the confrontation process between at least one of the red agents and at least one of the blue agents based on the simulation engine instance, and provides simulation sample data for the training of each of the agents based on the multi-core parallel simulation computing results.

[0101] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0102] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A service-oriented multi-core parallel simulation training engine system, characterized in that: include: A front-end simulation operation control environment engine is used to create a military simulation task through a browser and generate a task simulation request carrying the military simulation task; The backend cloud simulation computing service environment engine includes: resource scheduling nodes deployed to the cloud, multiple artificial intelligence nodes, and multiple simulation computing nodes; among them, The resource scheduling node is used to receive and respond to the task simulation request, create and start the multiple artificial intelligence nodes and multiple simulation computing nodes based on the resource pool in the cloud, dynamically deploy the military simulation task to the multiple simulation computing nodes, and create and control the simulation engine instances in the simulation computing nodes; The artificial intelligence node is used to manage and control at least one intelligent agent; The simulation computing node is used to perform resource scheduling and multi-core parallel simulation computing on the confrontation process between at least one of the red agents and at least one of the blue agents based on the simulation engine instance, and provide simulation sample data for the training of each of the agents based on the multi-core parallel simulation computing results.

2. The service-oriented multi-core parallel simulation training engine system according to claim 1, characterized in that: The artificial intelligence node deploys and runs an artificial intelligence scheduler and a first artificial intelligence interface service; wherein, The artificial intelligence scheduler is used to manage the registration, operation, suspension, resumption and exit of at least one intelligent agent; The first artificial intelligence interface service is used to call at least one of the simulation control interface, micro-operation instruction interface and action-level instruction interface required for the training and operation of the intelligent body.

3. The service-oriented multi-core parallel simulation training engine system according to claim 1, characterized in that: The simulation computing node deploys and runs a second artificial intelligence interface service, multiple application domain models corresponding to the target business, a CGF top-level model framework, and at least one simulation engine; wherein, The second artificial intelligence interface service is used to respond to the simulation control interface, micro-operation instruction interface and action-level instruction interface required for the training and operation of the intelligent agent; The CGF top-level model framework is used to develop the multiple application domain models; The simulation engine instance corresponding to the simulation engine is used to call the application domain model to simulate scene objects in a military confrontation scenario, and to perform resource scheduling and multi-core parallel simulation calculations on the confrontation process between at least one of the red agents and at least one of the blue agents in the military confrontation scenario, and to provide simulation sample data for the training of each of the agents based on the multi-core parallel simulation calculation results.

4. The service-oriented multi-core parallel simulation training engine system according to claim 3, characterized in that: The simulation engine comprises: A simulation manager, configured to perform at least one simulation management of the simulation engine including system management, communication management, component management, object management, event management, time management, scene management and resource management; A multi-core parallel scheduler is used to control and manage each of the application domain models and the simulation time of the application domain models, call the application domain models to simulate the scene objects in the military confrontation scene, allocate computing resources, storage resources and communication resources to each of the application domain models involved in the confrontation process between at least one of the red agents and at least one of the blue agents in the military confrontation scene under the constraint of consistent time and space, adopt a fork-convergence parallel computing mode to fork the main thread at a given synchronization point to generate several sub-threads, allocate the same type of the application domain model to each of the sub-threads, converge to the main thread after the multi-core parallel simulation calculations are completed by the several sub-threads, and provide simulation sample data for the training of each of the agents based on the multi-core parallel simulation calculation results; The simulation engine kernel is used to provide a reflective object system kernel framework and is the core base of the simulation engine.

5. The service-oriented multi-core parallel simulation training engine system according to any one of claims 1 to 4, characterized in that: An engine instance manager is deployed in the resource scheduling node. The engine instance manager is used to receive and respond to the task simulation request, create and start the multiple artificial intelligence nodes and multiple simulation computing nodes based on the resource pool in the cloud, create simulation engine instances in the multiple simulation computing nodes respectively based on the military simulation task, and control the operation, stop, recovery and end of the simulation engine instance.

6. The service-oriented multi-core parallel simulation training engine system according to any one of claims 1 to 4, characterized in that: The front-end simulation operation control environment includes: a simulation control node, in which a simulation operation controller is deployed; The simulation operation controller is used to display the human-computer interaction interface of the browser, receive task creation operation information based on the human-computer interaction interface, create a military simulation task based on the task creation operation information, generate a task simulation request carrying the military simulation task, and send the task simulation request to the resource scheduling node.

7. The service-oriented multi-core parallel simulation training engine system according to claim 6, characterized in that: The simulation operation controller is also used to receive instruction issuance operation information based on the human-computer interaction interface, and issue simulation interaction instructions to the resource scheduling node based on the instruction issuance operation information, and the simulation interaction instructions are used to control the simulation engine instance.

8. The service-oriented multi-core parallel simulation training engine system according to claim 4, characterized in that: The simulation manager is also used to: access at least one external resource among real soldier resources, virtual resources and construction test resources to the simulation engine.

9. A simulation processing method for a service-oriented multi-core parallel simulation training engine system as claimed in any one of claims 1 to 8, characterized in that: The method is applied to a background cloud simulation computing service environment engine, and the method comprises: The resource scheduling node receives and responds to the task simulation request carrying the military simulation task sent by the front-end simulation operation control environment engine, creates and starts multiple artificial intelligence nodes and multiple simulation computing nodes based on the cloud resource pool, dynamically deploys the military simulation task to the multiple simulation computing nodes, and creates and controls the simulation engine instances in the simulation computing nodes; The artificial intelligence node manages and controls at least one intelligent agent; The simulation computing node performs resource scheduling and multi-core parallel simulation computing on the confrontation process between at least one of the red agents and at least one of the blue agents based on the simulation engine instance, and provides simulation sample data for the training of each of the agents based on the multi-core parallel simulation computing results.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the simulation processing method of the service-oriented multi-core parallel simulation training engine system as described in claim 9 are implemented.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the simulation processing method of the service-oriented multi-core parallel simulation training engine system as described in claim 9 are implemented.

Images