Integrated simulation system, simulation system, integrated simulation method, and integrated simulation program

Abstract

To implement integrated simulation while reducing communication between sets of simulation.SOLUTION: A simulation device 200 obtains a result of its own simulation by implementing simulation by using simulation data. The simulation device 200 implements a target process by using the result of its own simulation and another result of simulation obtained by another simulation system 101, so as to obtain a target result. An inference device 400 implements an inference process by using a learned model and information contained in the simulation data being updated by the simulation, and obtains an inference result corresponding to the target result. The inference process is implemented each time a period has elapsed, and the target process is implemented each time a certain period longer than the period has elapsed.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to integrated simulation. [Background technology]

[0002] In conventional technology, in order to synchronize execution control and ensure data consistency between linked simulations, objects (setting values) communicated between simulations are manually defined in advance. During execution, constant communication occurs between all objects, which places a load on the network. In the technology disclosed in Patent Document 1, simulation systems in remote locations are connected to each other, but in this case, bandwidth limitations become an obstacle.

[0003] The detection process is carried out based on the position of each object and information from the onboard sensors. The detection process is performed in a brute force manner for each object that performs the detection action and all objects that are the target of the detection action (detected objects). A large number of objects appear in the integrated simulation. In an integrated simulation, an increase in the number of objects leads to an increase in the amount of data sent and received between simulations, and an increase in the network load leads to a delay in the processing of the entire integrated simulation. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 5159300 Summary of the Invention [Problem to be solved by the invention]

[0005] The present disclosure aims to enable integrated simulations to be performed with reduced communication between the simulations. [Means for solving the problem]

[0006] The integrated simulation system of the present disclosure includes multiple simulation systems. Each of the plurality of simulation systems a simulation unit that executes a simulation using the simulation data and obtains its own simulation results; an integration unit that executes a target process using the simulation result of the simulation system itself and other simulation results obtained by other simulation systems among the plurality of simulation systems to obtain a target result; an inference unit that performs an inference process using a trained model and information included in the simulation data updated by the simulation to obtain an inference result corresponding to the target result; Equipped with. the inference unit executes the inference process every time one cycle elapses, the integration unit executes the target process at each time a fixed period longer than one period elapses, The simulation unit executes the simulation using the simulation data in which the inference result is reflected at each elapse of one cycle, and executes the simulation using the simulation data in which the target result is reflected at each elapse of the fixed cycle. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to perform an integrated simulation by reducing communication between simulations. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a configuration diagram of an integrated simulation system 100 according to a first embodiment. [Figure 2] FIG. 1 is a configuration diagram of a simulation device 200 according to a first embodiment. [Figure 3]FIG. 2 is a configuration diagram of a learning device 300 according to the first embodiment. [Figure 4] FIG. 1 is a configuration diagram of an inference device 400 according to the first embodiment. [Figure 5] FIG. 2 is a functional configuration diagram of a simulation device 200 according to the first embodiment. [Figure 6] FIG. 2 is a functional configuration diagram of a learning device 300 according to the first embodiment. [Figure 7] FIG. 2 is a functional configuration diagram of an inference device 400 according to the first embodiment. [Figure 8] FIG. 2 is a functional configuration diagram of a simulation device 200 according to the first embodiment. [Figure 9] 3 is a flowchart of a simulation method [learning phase] according to the first embodiment. [Figure 10] 3 is a flowchart of a simulation method [utilization phase] according to the first embodiment. [Figure 11] FIG. 2 is a diagram showing an example of a neural network according to the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] In the embodiments and drawings, the same or corresponding elements are denoted by the same reference numerals. The description of elements denoted by the same reference numerals as those already described will be omitted or simplified as appropriate. Arrows in the drawings primarily indicate the flow of data or the flow of processing.

[0010] Embodiment 1 The integrated simulation system 100 will be described with reference to FIGS.

[0011] ***Configuration Description*** The configuration of the integrated simulation system 100 will be described with reference to FIG. The integrated simulation system 100 includes a plurality of simulation systems 101 . Each simulation system 101 communicates with other simulation systems 101 via a network.

[0012] The simulation system 101 includes a simulation device 200, a learning device 300, and an inference device 400.

[0013] The configuration of the simulation device 200 will be described with reference to FIG. The simulation device 200 is a computer that includes hardware such as a processor 201, a memory 202, an auxiliary storage device 203, a communication device 204, and an input / output interface 205. These pieces of hardware are connected to one another via signal lines.

[0014] The processor 201 is a processor of the simulation device 200 . A processor is an integrated circuit that performs computations and controls other hardware. For example, a processor can be a CPU, a DSP, or a GPU. IC is an abbreviation for Integrated Circuit. CPU is an abbreviation for Central Processing Unit. DSP is an abbreviation for Digital Signal Processor. GPU is an abbreviation for Graphics Processing Unit.

[0015] The memory 202 is a memory of the simulation device 200 . Memory is a volatile or non-volatile storage device. Memory is also called primary or main memory. For example, memory is RAM. Data stored in memory is saved to secondary storage as needed. RAM is an abbreviation for Random Access Memory.

[0016] The auxiliary storage device 203 is an auxiliary storage device for the simulation device 200 . The secondary storage device is a non-volatile storage device. For example, the secondary storage device may be a ROM, a HDD, a flash memory, or a combination of these. Data stored in the secondary storage device is loaded into the memory as needed. ROM is an abbreviation for Read Only Memory. HDD is an abbreviation for Hard Disk Drive.

[0017] The communication device 204 is a communication device of the simulation device 200. The communication device 204 is used for communication of the simulation device 200. The communication device is a receiver and a transmitter, for example, the communication device is a communication chip or a NIC. NIC is an abbreviation for Network Interface Card.

[0018] The input / output interface 205 is an input / output interface for the simulation device 200. The input / output interface 205 is used for input and output of the simulation device 200. An input / output interface is a port to which an input device and an output device are connected. For example, an input / output interface is a USB terminal, and the input devices are a keyboard and a mouse, and the output device is a display. USB is an abbreviation for Universal Serial Bus.

[0019] The simulation device 200 includes elements such as a reception unit 210, a simulation unit 220, an integration unit 230, and a management unit 240. These elements are realized by software.

[0020] The auxiliary storage device 203 stores a simulation device program for causing a computer to function as a reception unit 210, a simulation unit 220, an integration unit 230, and a management unit 240. The simulation device program is loaded into the memory 202 and executed by the processor 201. The auxiliary storage device 203 also stores an OS. At least a part of the OS is loaded into the memory 202 and executed by the processor 201. The processor 201 executes the simulation device program while running the OS. OS is an abbreviation for Operating System.

[0021] Input and output data of the simulation device program are stored in the storage unit 290 . The auxiliary storage device 203 functions as the storage unit 290. However, a storage device such as the memory 202, a register in the processor 201, or a cache memory in the processor 201 may function as the storage unit 290 instead of the auxiliary storage device 203 or together with the memory 202. The simulation data 291 is an example of data stored in the storage unit 290. The simulation data 291 is managed by the management unit 240 .

[0022] The simulation device 200 may include a plurality of processors that replace the processor 201 .

[0023] The configuration of the learning device 300 will be described with reference to FIG. The learning device 300 is a computer that includes hardware such as a processor 301, a memory 302, an auxiliary storage device 303, a communication device 304, and an input / output interface 305. These pieces of hardware are connected to each other via signal lines.

[0024] The processor 301 is the processor of the learning device 300 . The memory 302 is the memory of the learning device 300 . The auxiliary storage device 303 is an auxiliary storage device for the learning device 300 . The communication device 304 is a communication device for the learning device 300. The communication device 304 is used for communication of the learning device 300. The input / output interface 305 is an input / output interface for the learning device 300. The input / output of the learning device 300 is performed using the input / output interface 305.

[0025] The learning device 300 includes elements such as an input acquisition unit 310 and a model generation unit 320. These elements are realized by software.

[0026] The auxiliary storage device 303 stores a learning device program for causing the computer to function as an input acquisition unit 310 and a model generation unit 320. The learning device program is loaded into the memory 302 and executed by the processor 301. The auxiliary storage device 303 also stores an OS. At least a part of the OS is loaded into the memory 302 and executed by the processor 301. The processor 301 executes the learning device program while running the OS.

[0027] Input and output data of the learning device program are stored in the storage unit 390 . The memory 302 functions as the storage unit 390. However, a storage device such as the auxiliary storage device 303, a register in the processor 301, or a cache memory in the processor 301 may function as the storage unit 390 instead of the memory 302 or together with the memory 302.

[0028] The learning device 300 may include multiple processors replacing the processor 301.

[0029] The configuration of the inference device 400 will be described with reference to FIG. The inference device 400 is a computer that includes hardware such as a processor 401, a memory 402, an auxiliary storage device 403, a communication device 404, and an input / output interface 405. These pieces of hardware are connected to one another via signal lines.

[0030] Processor 401 is the processor of inference device 400 . Memory 402 is the memory of reasoning device 400 . Auxiliary storage device 403 is an auxiliary storage device for inference device 400 . Communication device 404 is a communication device for inference device 400. Communication for inference device 400 is performed using communication device 404. Input / output interface 405 is an input / output interface for inference device 400. Input / output to / from inference device 400 is performed using input / output interface 405.

[0031] The inference device 400 comprises elements such as an input acquisition unit 410 and an inference unit 420. These elements are realized by software.

[0032] The auxiliary storage device 403 stores an inference device program for causing the computer to function as an input acquisition unit 410 and an inference unit 420. The inference device program is loaded into the memory 402 and executed by the processor 401. The auxiliary storage device 403 also stores an OS. At least a part of the OS is loaded into the memory 402 and executed by the processor 401. The processor 401 executes the inference device program while running the OS.

[0033] Input and output data of the inference device program are stored in memory unit 490. The auxiliary storage device 403 functions as the storage unit 490. However, a storage device such as the memory 402, a register in the processor 401, or a cache memory in the processor 401 may function as the storage unit 490 instead of the auxiliary storage device 403 or together with the auxiliary storage device 403. The trained model 491 is an example of data stored in the storage unit 490.

[0034] Reasoning apparatus 400 may include multiple processors replacing processor 401 .

[0035] 5 to 8 show the functional configuration of each device in the simulation system 101. FIG. 5 shows a part of the functional configuration of the simulation device 200. FIG. 6 shows the functional configuration of the learning device 300. FIG. 7 shows the functional configuration of inference device 400. FIG. 8 shows a part of the functional configuration of the simulation device 200.

[0036] ***Explanation of Operation*** The operation procedures of the integrated simulation system 100 and the simulation system 101 correspond to an integrated simulation method. The operation procedure of the simulation system 101 corresponds to an integrated simulation system program. The integrated simulation program includes a simulation device program, a learning device program, and an inference device program. The program can be recorded (stored) in a computer-readable manner on a non-volatile recording medium such as an optical disk or flash memory.

[0037] The integrated simulation method is divided into a learning phase and an application phase. The learning phase and utilization phase will be explained using a simulation method for "object detection" as an example. The object is a moving object such as an aircraft. An object that detects another object is called a "detecting object," and an object that is detected by a detecting object is called a "detected object." The plurality of simulation systems 101 perform simulations on different objects.

[0038] The learning phase is a phase for generating a trained model 491. In the learning phase, preliminary simulations such as plan verification and rehearsal are performed. The utilization phase is a phase in which the trained model 491 is utilized. In the utilization phase, simulations are conducted for training and exercises.

[0039] The simulation method [learning phase] will be explained based on FIG. In step S101, the simulation device 200 executes a simulation.

[0040] The simulation is carried out as follows. The receiving unit 210 receives the operation information 111 . The operation information 111 indicates an operation of an object by a user. For example, the operation information 111 indicates the movement of an object and the control of a sensor mounted on the object. The simulation unit 220 executes a simulation using the simulation data 291 in accordance with the operation information 111. Specifically, a simulation is performed for an event (movement, occurrence of detection, etc.) that occurs due to an operation indicated in the operation information 111. The simulation data 291 indicates the position (coordinate values) of an object, a sensor mounted on the object, a pair of a detecting object and a detected object, etc. The simulation data 291 is updated by a simulation. Execution of the simulation produces a simulation result 119. The simulation result 119 indicates the positions of objects, pairs of detecting objects and detected objects, sensors used for detection, and the like.

[0041] In step S102, the simulation device 200 executes a detection process. The detection process is a process for detecting an object. However, the detection process is an example of a process that is the objective of a simulation (objective process).

[0042] The detection process is carried out as follows. The integration unit 230 distributes the simulation results 119 to other simulation systems 101 . The simulation result 119 is the simulation result obtained by the own simulation system 101 . The integration unit 230 receives the simulation results 121 from the other simulation systems 101 . The simulation result 121 is a simulation result obtained by another simulation system 101. The simulation result 121 is reflected in the simulation data 291, and the simulation data 291 is updated. The integration unit 230 performs detection determination using the simulation results 119 and 121 . The detection determination determines which object is detected among the multiple objects to be simulated by the multiple simulation systems 101, and the detection result 129 is obtained. The detection determination is performed in a brute force manner on one or more objects that are the subject of simulation in the own simulation system 101 and one or more objects that are the subject of simulation in the other simulation systems 101. The detection result 129 indicates a pair of a detected object and a detected object, and is an example of data (target result) obtained by target processing. The detection result 129 is reflected in the simulation data 291, and the simulation data 291 is updated.

[0043] Steps S101 and S102 are executed every time one cycle elapses. One period is a predetermined length of time.

[0044] In step S103, the learning device 300 determines whether there is a predetermined amount of learning data.

[0045] The determination is performed as follows: The input acquisition unit 310 acquires the object information 131 and the detection result 129. The object information 131 is acquired from the simulation data 291. The object information 131 includes the object's position information and the object's sensor information. The position information indicates the position of the object. The sensor information indicates information about a sensor mounted on an object, such as the performance specifications, coverage area, and operational status of the sensor.

[0046] The object information 131 and the detection result 129 are saved as input data (learning data) for generating a trained model 491.

[0047] The model generation unit 320 determines whether a predetermined amount of learning data (object information 131 and detection results 129) has been saved. The predetermined amount is a predetermined amount of data.

[0048] If there is a predetermined amount of learning data, the process proceeds to step S104. If there is not the predetermined amount of learning data, the process proceeds to step S101.

[0049] In step S104, the learning device 300 generates a trained model 491.

[0050] The trained model 491 is generated as follows: The model generation unit 320 learns the object information 131 and the detection result 129 to generate a trained model 491. The details of the learning will be described later.

[0051] The simulation method [utilization phase] will be explained based on FIG. In step S111, the simulation device 200 executes a simulation. The simulation method is the same as the method in step S101.

[0052] In step S112, inference device 400 executes inference processing. The inference process is a process of inferring the results of the detection process using the trained model 491.

[0053] The inference process is carried out as follows. The input acquisition unit 410 acquires the object information 141 and the detection information 142. The object information 141 and the detection information 142 are acquired from the simulation data 291. The object information 141 includes the position information of the object and the sensor information of the object. The object information 141 corresponds to the object information 131. The detection information 142 is information that identifies a detected object. For example, the detection information 142 indicates an identifier of the detected object. The inference unit 420 receives the object information 141 and the detection information 142 as input and calculates the trained model 491. As a result, the inference result 149 is obtained. The inference result 149 indicates a pair of a detected object and a detected object. The inference result 149 corresponds to the detection result 129. The inference result 149 is reflected in the simulation data 291, and the simulation data 291 is updated.

[0054] Steps S111 and S112 are executed every time one cycle elapses.

[0055] In step S113, the integration unit 230 determines whether a fixed period has elapsed. The constant period is a predetermined time length that is longer than one period.

[0056] If the fixed period has elapsed, the process proceeds to step S114. If the fixed period has not elapsed, the process proceeds to step S111.

[0057] In step S114, the simulation device 200 executes a detection process. The detection process is the same as that in step S112. After step S114, the process proceeds to step S111.

[0058] The learning in step S104 will be described in detail below. The model generation unit 320 can use a known algorithm for supervised learning. Supervised learning is a method of using pairs of input and result (label) data as training data, learning the features of the training data, and inferring the result from the input.

[0059] Supervised learning, for example, uses neural networks. A neural network consists of an input layer, an intermediate layer (hidden layer), and an output layer. Each layer consists of multiple neurons. The intermediate layer can be one layer or two or more layers.

[0060] Figure 11 shows an example of a three-layer neural network. When multiple input values ​​are input to the input layer (X1 to X3), the multiple input values ​​are multiplied by weights W1 (w11 to w16) to obtain multiple calculated values, which are then input to the hidden layer (Y1, Y2). When multiple calculated values ​​are input to the intermediate layer (Y1, Y2), the multiple calculated values ​​are multiplied by weights W2 (w21 to w26) to obtain multiple output values. The multiple output values ​​are output from the output layer (Z1 to Z3). The output values ​​vary depending on the respective values ​​of weights W1 and W2.

[0061] The neural network generates a trained model 491 through supervised learning according to the training data. Specifically, the neural network inputs object information 131 to the input layer and adjusts weights W1 and W2 so that the result output from the output layer approaches detection result 129.

[0062] The model generation unit 320 may use deep learning or machine learning as a learning algorithm. Deep learning learns to extract features themselves. Machine learning is carried out according to genetic programs, machine logic programs, or support vector machines, for example.

[0063] ***Description of Example*** The simulation system 101 may have one, two, four or more devices functioning as the simulation device 200, the learning device 300 and the inference device 400. Each of the simulation device 200, the learning device 300, and the inference device 400 may be configured with two or more devices.

[0064] There may be multiple integrated simulation systems 100. Furthermore, a new integrated simulation system 100 may be added, or an existing integrated simulation system 100 may be removed. The training data may be generated by another integrated simulation system 100 . The input acquisition unit 310 may acquire learning data from two or more integrated simulation systems 100 used in the same area as the area in which its own integrated simulation system 100 is used. The input acquisition unit 310 may also acquire learning data from two or more integrated simulation systems 100 used in areas different from the area in which its own integrated simulation system 100 is used. The trained model 491 may be generated in another integrated simulation system 100. The model generation unit 320 may update the trained model 491 generated by another integrated simulation system 100 by re-training.

[0065] ***Effects of the First Embodiment*** The first embodiment discloses a detection processing method in a simulation connection. The first embodiment relates to a method for reducing the amount of data communication on a network while ensuring transmission and reception of data required between simulations in an integrated simulation.

[0066] In an integrated simulation, multiple simulations at different levels are linked together through a wide area network with limited bandwidth. In order to connect multiple simulations without delaying the processing of the entire integrated simulation, the challenge is to reduce the amount of data communication between simulations in the brute force detection process that spans multiple simulations. The first embodiment has the effect of enabling simulations installed in remote locations to be linked together and executed without delay, regardless of network bandwidth limitations.

[0067] ***Summary of the first embodiment*** The integrated simulation system 100 includes a learning device 300 and an inference device 400. The integrated simulation system 100 obtains the results of detection processing from inputs such as location information of the detected target and the sensor operation status by utilizing multiple trained models generated using past simulation results as training data. In the learning phase, learning is performed using the results of past detection processes as training data to create a trained model 491. The trained model 491 is a trained model for inferring the results of detection processes according to the location information of the detected target, the sensor operation status, etc. In the utilization phase, the trained model 491 is used to input the location information of the detected object, the sensor operation status, etc., to obtain the results of the detection process. This allows each simulation system 101 to obtain the results of the detection process without performing the conventional detection process that requires communication between systems, thereby reducing the amount of data communication between systems.

[0068] In order to connect multiple simulations without delaying the processing of the entire integrated simulation, the challenge is to reduce the amount of data communication between simulations in the brute force detection process that spans multiple simulations. Using multiple trained models that use past simulation results as training data, the results of the detection process are cached within each simulation, reducing the amount of network traffic caused by detection processes across simulations. By performing conventional detection processing at a fixed interval, differences in the results of detection processing due to user operations are absorbed. A model obtained by learning the results of detection processing according to the location information of the detected object, the sensor operation status, etc. outputs the results of detection processing from inputs such as the location information of the detected object and the sensor operation status. This allows each simulation to obtain the results of the detection process without performing the conventional detection process that requires communication between simulations, thereby reducing the amount of data communication between simulations.

[0069] ***Explanation of the first embodiment*** In order to conduct training and exercises, simplified verification of multiple response plans (scenario situations) is carried out in the preliminary stages (plan verification, rehearsal). During training and exercises, a response plan to be implemented is selected from among the tested response plans.

[0070] In the first embodiment, the learning device 300 models the results of the simulation carried out in the previous stage (plan verification, rehearsal). In training and exercises, each simulation system 101 uses the learned model 491 and the inference device 400 to perform detection processing without communicating with other simulation systems 101. By using the trained model 491, it is no longer necessary to send and receive data with other simulation systems 101, thereby reducing the amount of network communication.

[0071] However, in training and exercises, operations are performed by the user, and therefore, in training and exercises, operations that are similar to operations in the simulation performed in the previous stage may differ in detail. To compensate for this difference, a detection process using the trained model 491 is combined with a conventional detection process that communicates between the simulation systems 101. In normal step progression (every cycle), the trained model 491 is used, and conventional detection processing is performed at regular intervals. This absorbs the difference in the results of the detection processing due to user operations.

[0072] ***Supplement to the first embodiment*** The first embodiment is an example of a preferred embodiment and is not intended to limit the technical scope of the present disclosure. The first embodiment may be implemented in part or in combination with other embodiments. The procedures described using flowcharts and the like may be modified as appropriate.

[0073] Each element of the simulation system 101 may be implemented in software, hardware, firmware, or a combination thereof. The "part" of each element of the simulation system 101 may be read as a "process," a "step," a "circuit," or a "circuitry."

[0074] Various aspects of the present disclosure are described below as appendices. (Appendix 1) It has multiple simulation systems, Each of the plurality of simulation systems a simulation unit that executes a simulation using the simulation data and obtains its own simulation results; an integration unit that executes a target process using the simulation result of the simulation system itself and other simulation results obtained by other simulation systems among the plurality of simulation systems to obtain a target result; an inference unit that performs an inference process using a trained model and information included in the simulation data updated by the simulation to obtain an inference result corresponding to the target result; Equipped with the inference unit executes the inference process every time one cycle elapses, the integration unit executes the target process at each time a fixed period longer than one period elapses, The simulation unit executes the simulation using the simulation data in which the inference result is reflected at each elapse of one period, and executes the simulation using the simulation data in which the target result is reflected at each elapse of the fixed period. Integrated simulation system.

[0075] (Appendix 2) the integration unit distributes the simulation results of the own to the other simulation systems, receives the simulation results of the other simulation systems from the other simulation systems, and executes the target processing; The inference unit executes the inference process without communication with the other simulation system. 10. The integrated simulation system of claim 1.

[0076] (Appendix 3) In each of the plurality of simulation systems, the simulation unit executes the simulation in accordance with a user's operation. 10. The integrated simulation system of claim 1 or 2.

[0077] (Appendix 4) each of the plurality of simulation systems includes a model generation unit; The simulation unit executes the simulation for each cycle before the trained model is generated, The integration unit executes the target processing for each cycle before the trained model is generated, The model generation unit learns the target result and information included in the simulation data updated by the simulation to generate the trained model. 4. The integrated simulation system of claim 1.

[0078] (Appendix 5) the simulation unit executes the simulation on one or more objects that are different from the one or more objects that are the target of the simulation in the other simulation system; The integration unit executes, as the target process, a detection process for determining which object detects which other object among a plurality of objects that are the targets of the simulation in the plurality of simulation systems. 5. The integrated simulation system of any one of appendices 1 to 4.

[0079] (Appendix 6) a simulation unit that executes a simulation using the simulation data and obtains its own simulation results; an integration unit that executes a target process using the simulation result of the simulation system itself and other simulation results obtained by other simulation systems to obtain a target result; an inference unit that performs an inference process using a trained model and information included in the simulation data updated by the simulation to obtain an inference result corresponding to the target result; Equipped with the inference unit executes the inference process every time one cycle elapses, the integration unit executes the target process at each time a fixed period longer than one period elapses, The simulation unit executes the simulation using the simulation data in which the inference result is reflected at each elapse of one period, and executes the simulation using the simulation data in which the target result is reflected at each elapse of the fixed period. Simulation system.

[0080] (Appendix 7) Run a simulation using the simulation data to obtain your own simulation results, Executing a target process using the result of the simulation performed by the computer and the result of another simulation performed by another simulation system to obtain a target result; an integrated simulation method that performs an inference process using a trained model and information included in the simulation data updated by the simulation to obtain an inference result corresponding to the target result, Execute the inference process every time one cycle elapses, executes the target process at each time a fixed period longer than one period elapses; The simulation is executed using the simulation data in which the inference result is reflected at each elapse of one period, and the simulation is executed using the simulation data in which the target result is reflected at each elapse of the fixed period. Integrated simulation method.

[0081] (Appendix 8) a simulation unit that executes a simulation using the simulation data and obtains its own simulation results; an integration unit that executes a target process using the simulation result of the simulation system itself and other simulation results obtained by other simulation systems to obtain a target result; An inference unit that performs inference processing using a trained model and information included in the simulation data updated by the simulation to obtain an inference result corresponding to the target result, It is an integrated simulation program for making computers function. the inference unit executes the inference process every time one cycle elapses, the integration unit executes the target process at each time a fixed period longer than one period elapses, The simulation unit executes the simulation using the simulation data in which the inference result is reflected at each elapse of one period, and executes the simulation using the simulation data in which the target result is reflected at each elapse of the fixed period. Integrated simulation program. [Explanation of symbols]

[0082] 100 Integrated simulation system, 101 Simulation system, 111 Operation information, 119 Simulation result, 121 Simulation result, 129 Detection result, 131 Object information, 141 Object information, 142 Detection information, 149 Inference result, 200 Simulation device, 201 Processor, 202 Memory, 203 Auxiliary storage device, 204 Communication device, 205 Input / output interface, 210 Reception unit, 220 Simulation unit, 230 Integration unit, 240 Management unit, 290 Storage unit, 291 Simulation data, 300 Learning device, 301 Processor, 302 Memory, 303 Auxiliary storage device, 304 Communication device, 305 Input / output interface, 310 Input acquisition unit, 320 Model generation unit, 390 Storage unit, 400 Inference device, 401 Processor, 402 Memory, 403 Auxiliary storage device, 404 Communication device, 405 input / output interface, 410 input acquisition unit, 420 inference unit, 490 memory unit, 491 trained model.

Claims

1. It has multiple simulation systems, Each of the plurality of simulation systems a simulation unit that executes a simulation using the simulation data and obtains its own simulation results; an integration unit that executes a target process using the simulation result of the simulation system itself and other simulation results obtained by other simulation systems among the plurality of simulation systems to obtain a target result; an inference unit that performs an inference process using a trained model and information included in the simulation data updated by the simulation to obtain an inference result corresponding to the target result; Equipped with the inference unit executes the inference process every time one cycle elapses, the integration unit executes the target process at each time a fixed period longer than one period elapses, The simulation unit executes the simulation using the simulation data in which the inference result is reflected at each elapse of one period, and executes the simulation using the simulation data in which the target result is reflected at each elapse of the fixed period. Integrated simulation system.

2. the integration unit distributes the simulation results of the own to the other simulation systems, receives the simulation results of the other simulation systems from the other simulation systems, and executes the target processing; The inference unit executes the inference process without communication with the other simulation system. The integrated simulation system according to claim 1 .

3. In each of the plurality of simulation systems, the simulation unit executes the simulation in accordance with a user's operation. The integrated simulation system according to claim 1 .

4. each of the plurality of simulation systems includes a model generation unit; The simulation unit executes the simulation for each cycle before the trained model is generated, The integration unit executes the target processing for each cycle before the trained model is generated, The model generation unit learns the target result and information included in the simulation data updated by the simulation to generate the trained model. The integrated simulation system according to claim 1 .

5. the simulation unit executes the simulation on one or more objects that are different from the one or more objects that are the targets of the simulation in the other simulation system; The integration unit executes, as the target process, a detection process for determining which object detects which other object among a plurality of objects that are the targets of the simulation in the plurality of simulation systems. The integrated simulation system according to claim 1 .

6. a simulation unit that executes a simulation using the simulation data and obtains its own simulation results; an integration unit that executes a target process using the simulation result of the simulation system itself and other simulation results obtained by other simulation systems to obtain a target result; an inference unit that performs an inference process using a trained model and information included in the simulation data updated by the simulation to obtain an inference result corresponding to the target result; Equipped with the inference unit executes the inference process every time one cycle elapses, the integration unit executes the target process at each time a fixed period longer than one period elapses, The simulation unit executes the simulation using the simulation data in which the inference result is reflected at each elapse of one period, and executes the simulation using the simulation data in which the target result is reflected at each elapse of the fixed period. Simulation system.

7. Run a simulation using the simulation data to obtain your own simulation results, Executing a target process using the result of the simulation performed by the computer and the result of another simulation performed by another simulation system to obtain a target result; an integrated simulation method that performs an inference process using a trained model and information included in the simulation data updated by the simulation to obtain an inference result corresponding to the target result, Execute the inference process every time one cycle elapses, executes the target process at each time a fixed period longer than one period elapses; The simulation is executed using the simulation data in which the inference result is reflected at each elapse of one period, and the simulation is executed using the simulation data in which the target result is reflected at each elapse of the fixed period. Integrated simulation method.

8. a simulation unit that executes a simulation using the simulation data and obtains its own simulation results; an integration unit that executes a target process using the simulation result of the simulation system itself and other simulation results obtained by other simulation systems to obtain a target result; An inference unit that performs inference processing using a trained model and information included in the simulation data updated by the simulation to obtain an inference result corresponding to the target result, It is an integrated simulation program for making computers function. the inference unit executes the inference process every time one cycle elapses, the integration unit executes the target process at each time a fixed period longer than one period elapses, The simulation unit executes the simulation using the simulation data in which the inference result is reflected at each elapse of one period, and executes the simulation using the simulation data in which the target result is reflected at each elapse of the fixed period. Integrated simulation program.

Images