Joint simulation training system based on kylin operating system
By introducing a joint simulation training system based on Kirin operating system into the simulation training system, using artificial intelligence and internal networking linkage, the problem that existing systems cannot flexibly cooperate with functions is solved, and flexible and accurate tactical and technical training is achieved. The solution is generated to improve the effect of simulation training.
Patent Information
- Application Number
- CN202410992055.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-22
AI Technical Summary
The existing simulation training system cannot flexibly cooperate with the coordination between various functions and cannot effectively deal with the various uncertainties that arise in real battles, making it difficult to generate flexible and accurate training plans in simulation training.
Design a joint simulation training system based on Kirin operating system, including instructor module, control module, shooter module and central service module. Through UDP and TCP communication connection, artificial intelligence and internal networking linkage are used to realize data preprocessing and feature selection. , operation instruction analysis and result recording to improve the accuracy and flexibility of simulation training.
Through artificial intelligence and internal networking linkage, the accuracy and flexibility of the simulated training system can be improved, and reasonable training plans can be generated based on real-time data, improved training results, and adapted to complex tactical and technical training needs.
Smart Images

Figure HDA0004959138890000011 
Figure HDA0004959138890000021 
Figure HDA0004959138890000022
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing, and specifically to a joint simulation training system based on the Kylin operating system. Background Art
[0002] Simulation training is a form of training using simulation methods, which is usually divided into two types: tactical simulation training and technical simulation training. Tactical simulation training belongs to combat command training, and its purpose is to improve command strategy by analyzing and judging simulated battlefield conditions; while technical simulation training belongs to operational training, and improves operational skills through operational feedback.
[0003] The simulation training system is a system used to provide simulation training. It can match the operator's ability information so that the operator can quickly match the corresponding training plan according to the ability level. Through the training results, it provides instructors and operators with accurate and timely training evaluation and feedback, thereby improving the tactical training effect and technical training effect at the same time, and can better cope with real combat scenarios.
[0004] With the development of modernization, more uncertainties will appear in the real battle process, and these uncertainties will become the key factors in the victory or defeat of the battle. The current simulation training system cannot flexibly coordinate various functions. There is an urgent need for a domestically produced simulation training system that can meet the requirements of the simulation training system to flexibly and accurately generate training plans for real-time training data. Summary of the invention
[0005] In response to the problems in the prior art, the present application provides a joint simulation training system and device based on the Kylin operating system, which can be installed on the Kylin operating system and improve the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage.
[0006] In order to solve at least one of the above problems, the present application provides the following technical solutions:
[0007] In a first aspect, the present application provides a joint simulation training system based on a Kylin operating system, which is applied to the Kylin operating system. The joint simulation training system includes an instructor module, a control module, a shooter module, and a central service module. The central service module is respectively communicated with the instructor module, the control module, and the shooter module, wherein the communication connection includes at least one of a UDP communication connection and a TCP communication connection:
[0008] The instructor module is used to receive real training data, input the real training data into the input layer of the preset training deployment model to perform data preprocessing operations on the real training data, determine corresponding real training features, input the real training features into the feature selection layer of the preset training deployment model to perform feature selection operations, determine corresponding selected features, perform feature integration operations on the selected features, input the integrated features after the feature integration operations into the output layer of the preset training deployment model, determine the training plan output by the preset training deployment model, and transmit the training plan to the central service module;
[0009] The control module is used to receive the training scheme from the central service module, determine the corresponding operation instruction according to the training scheme and the preset parsing rule, and transmit the operation instruction to the central service module;
[0010] The shooter module is used to receive the operation instruction from the central service module and display the operation instruction on the training hand interface, record the data of the training hand executing the operation instruction, determine the corresponding operation result, and transmit the operation result to the central service module;
[0011] The central service module is used to receive the training plan, the operation instruction and the operation result, and transmit the training plan, the operation instruction and the operation result to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules.
[0012] Further, the instructor module includes a data input unit, a data processing unit and a data transmission unit;
[0013] The data input unit is used to receive real training data, input the real training data into the input layer of the preset training deployment model, perform feature extraction operation on the real training data, determine the corresponding training features, and determine the corresponding real training features according to the training features and the preset feature balancing algorithm, wherein the real training data includes at least one of the operator information and the operation result information transmitted from the central service module;
[0014] The data processing unit is used to input the real training features into the decision tree feature selection layer and the regression tree feature selection layer of the preset training deployment model respectively to perform feature selection operations, determine corresponding decision tree selection features and regression tree selection features, perform feature integration operations on the decision tree selection features and the regression tree selection features, and determine corresponding integrated features;
[0015] The data transmission unit is used to input the integrated features after the feature integration operation into the output layer of the preset training deployment model, determine the training plan output by the preset training deployment model, and transmit the training plan to the central service module.
[0016] Furthermore, the data input unit comprises:
[0017] A nearest neighbor feature determination subunit is used to perform a minority class recognition operation on the training feature according to a preset minority class recognition rule, and determine a corresponding nearest neighbor training feature according to the minority class training feature obtained after the minority class recognition operation and a preset K nearest neighbor algorithm;
[0018] The real training feature determination subunit is used to perform a distance calculation operation on the minority class training feature and the nearest neighbor training feature to determine the corresponding training feature distance; determine the corresponding synthetic training feature according to the training feature distance and a preset ratio rule, and perform a feature addition operation on the training feature according to the synthetic training feature to determine the corresponding real training feature.
[0019] Furthermore, the data processing unit comprises:
[0020] A decision tree selection feature determination subunit, used for inputting the real training feature into the decision tree feature selection layer of the preset training deployment model to determine the corresponding decision tree selection feature according to the preset Gini impurity;
[0021] A regression tree selection feature determination subunit, used for inputting the real training feature into the regression tree feature selection layer of the preset training deployment model to determine the corresponding regression tree selection feature according to a preset mean square error algorithm;
[0022] The feature integration subunit is used to perform feature integration operations on the decision tree selection features and the regression tree selection features to determine corresponding integrated features.
[0023] Furthermore, the feature integration subunit includes:
[0024] A decision tree prediction feature determination subunit, used to perform a recursive splitting operation on the decision tree selection feature to determine a corresponding decision tree prediction feature, wherein the decision tree prediction feature is used to predict a category label;
[0025] A regression tree prediction feature determination subunit, used to perform a recursive splitting operation on the regression tree selection feature to determine a corresponding regression tree prediction feature, wherein the regression tree prediction feature is used to predict a continuous value;
[0026] The integrated feature determination subunit is used to input the decision tree prediction feature and the regression tree prediction feature into a preset neural network for feature integration operation to determine the corresponding integrated feature.
[0027] Furthermore, the data transmission unit includes:
[0028] A data activation subunit, used to input the integrated features after the feature integration operation into the output layer of the preset training deployment model, perform a feature output operation on the integrated features according to a preset activation function, and determine a training scheme output by the preset training deployment model;
[0029] The data transmission subunit is used to transmit the training plan to the central service module according to a preset communication rule.
[0030] Further, the control module includes a self-checking unit, a communication unit and a parsing unit;
[0031] The self-checking unit is used to perform a self-checking operation on the control module according to a preset self-checking rule, and determine whether there is a problem with the self-checking result. If not, the communication unit is activated;
[0032] The communication unit is used to perform a registration operation on the central service module according to a preset communication rule, so that the control module can receive the training program from the central service module;
[0033] The analysis unit is used to determine the corresponding training objectives and training steps according to the training plan and preset analysis rules, determine the corresponding operation instructions according to the training objectives, the training steps and preset process rules, and transmit the operation instructions to the central service module.
[0034] Further, the shooter module includes a self-checking unit, a communication unit and a recording unit;
[0035] The self-checking unit is used to perform a self-checking operation on the shooter module according to a preset self-checking rule, and determine whether there is a problem with the self-checking result. If not, the communication unit is activated;
[0036] The communication unit is used to perform a registration operation on the central service module according to a preset communication rule, so that the shooter module can receive the operation instruction from the central service module and display the operation instruction on the training hand interface;
[0037] The recording unit is used to record the data of the operation instruction executed by the training hand according to the preset event-driven rules, determine the corresponding operation result, and transmit the operation result to the central service module.
[0038] Further, the central service module includes a first central service unit, a second central service unit and a third central service unit;
[0039] The first central service unit is used to connect the instructor module according to a preset communication rule so that the central service module can receive the training program output by the instructor module;
[0040] The second central service unit is used to connect the control module according to a preset communication rule, so that the central service module can send the received training program to the control module, and receive corresponding operation instructions, and send the operation instructions to the instructor module and the shooter module, wherein the operation instructions are output by the control module after receiving the training program;
[0041] The third central service unit is used to connect the shooter module according to preset communication rules, so that the central service module can send the received operation instruction to the shooter module, receive the corresponding operation result, and send the operation result to the instructor module and the control module, wherein the operation result is output by the shooter module after receiving the operation instruction.
[0042] Furthermore, the central service module also includes:
[0043] The encryption unit is used to determine the corresponding encryption subclass interface according to the preset encryption algorithm;
[0044] The startup unit is used to perform inheritance operation on the preset parent class interface and to start the central service module according to the encrypted subclass interface and the predefined protocol.
[0045] In a second aspect, the present application provides a joint simulation training device based on the Kylin operating system, comprising:
[0046] The instructor module is used to receive real training data, input the real training data into the input layer of the preset training deployment model to perform data preprocessing operations on the real training data, determine corresponding real training features, input the real training features into the feature selection layer of the preset training deployment model to perform feature selection operations, determine corresponding selected features, perform feature integration operations on the selected features, input the integrated features after the feature integration operations into the output layer of the preset training deployment model, determine the training scheme output by the preset training deployment model, and transmit the training scheme to the central service module;
[0047] A control module, configured to receive the training scheme from the central service module, determine corresponding operation instructions according to the training scheme and preset parsing rules, and transmit the operation instructions to the central service module;
[0048] The shooter module is used to receive the operation instruction from the central service module and display the operation instruction on the training hand interface, record the data of the training hand executing the operation instruction, determine the corresponding operation result, and transmit the operation result to the central service module;
[0049] The central service module is used to receive the training plan, the operation instruction and the operation result, and transmit the training plan, the operation instruction and the operation result to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules.
[0050] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the joint simulation training system based on the Kylin operating system when executing the program.
[0051] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the joint simulation training system based on the Kylin operating system.
[0052] In a fifth aspect, the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the joint simulation training system based on the Kylin operating system.
[0053] It can be seen from the above technical solution that the present application provides a joint simulation training system and device based on the Kylin operating system, through the instructor module, which is used to receive real training data, input the real training data into a preset training deployment model, and determine the training plan output by the preset training deployment model; the control module is used to receive the training plan, determine the corresponding operation instructions according to the training plan and preset parsing rules, the shooter module is used to receive the operation instructions and display the operation instructions on the training hand interface, record the data of the training hand executing the operation instructions, and determine the corresponding operation results; the central service module is used to receive the training plan, the operation instructions and the operation results, and transmit the training plan, the operation instructions and the operation results to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules, thereby improving the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0055] Figure 1 This is one of the flow charts of the joint simulation training system based on the Kylin operating system in the embodiment of the present application;
[0056] Figure 2 This is the second flow chart of the joint simulation training system based on the Kylin operating system in the embodiment of the present application;
[0057] Figure 3 This is the third flow chart of the joint simulation training system based on the Kylin operating system in the embodiment of the present application;
[0058] Figure 4 This is a fourth flowchart of a joint simulation training system based on the Kylin operating system in an embodiment of the present application;
[0059] Figure 5 This is the fifth flow chart of the joint simulation training system based on the Kylin operating system in the embodiment of the present application;
[0060] Figure 6 This is the sixth flow chart of the joint simulation training system based on the Kylin operating system in the embodiment of the present application;
[0061] Figure 7 This is the seventh flow chart of the joint simulation training system based on the Kylin operating system in the embodiment of the present application;
[0062] Figure 8 This is the eighth flow chart of the joint simulation training system based on the Kylin operating system in the embodiment of the present application;
[0063] Fig. 9 This is a ninth flowchart of a joint simulation training system based on the Kylin operating system in an embodiment of the present application;
[0064] Fig.10 This is the tenth flowchart of the joint simulation training system based on the Kylin operating system in the embodiment of the present application;
[0065] Fig.11 This is a structural diagram of a joint simulation training device based on the Kylin operating system in an embodiment of the present application;
[0066] Fig.12 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application.
[0067] Reference numerals:
[0068] Electronic device 9600, central processing unit 9100, memory 9140, communication module 9110, input unit 9120, audio processor 9130, display 9160, power supply 9170, buffer memory 9141, application / function storage unit 9142, data storage unit 9143, driver program storage unit 9144, antenna 9111, speaker 9131, microphone 9132. DETAILED DESCRIPTION
[0069] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0070] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.
[0071] Taking into account the development of the modernization process, more uncertain factors will appear in the real battle process, and these uncertain factors will become the key factors for the victory or defeat of the battle. The current simulation training system cannot flexibly coordinate between various functions. There is an urgent need for a domestically produced simulation training system that can meet the problem of the simulation training system flexibly and accurately generating training plans for real-time training data. The present application provides a joint simulation training system and device based on the Kylin operating system, through an instructor module, for receiving real training data, inputting the real training data into a preset training deployment model, and determining the training plan output by the preset training deployment model, a control module, for receiving the training plan, determining the corresponding operation instructions according to the training plan and the preset parsing rules, a shooter module, for receiving the operation instructions and displaying the operation instructions on the training hand interface, recording the data of the training hand executing the operation instructions, and determining the corresponding operation results, a central service module, for receiving the training plan, the operation instructions and the operation results, and transmitting the training plan, the operation instructions and the operation results to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules, thereby improving the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage.
[0072] In order to improve the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage, this application provides an embodiment of a joint simulation training system based on the Kylin operating system, see Figure 1The joint simulation training system based on Kylin operating system specifically includes the following contents:
[0073] The minimum system of the joint simulation training system framework includes an instructor module, a control module, a shooter module and a central server module. The instructor module implements the selection of training plans; the control module implements the management of the training process and sends operation instructions to the shooter; the shooter module completes the instruction operation and displays the operation results to the control module and the instructor module, and realizes joint training of multiple training positions through multi-screen linkage. Each trainer is built on the Kylin operating system, using the domestic Feiteng processor with independent intellectual property rights, and the communication method uses UDP and TCP communication to realize the message linkage through internal networking.
[0074] The instructor module is used to execute step S101: receiving real training data, inputting the real training data into the input layer of the preset training deployment model to perform data preprocessing operations on the real training data, determining corresponding real training features, inputting the real training features into the feature selection layer of the preset training deployment model to perform feature selection operations, determining corresponding selected features, performing feature integration operations on the selected features, inputting the integrated features after the feature integration operations into the output layer of the preset training deployment model, determining the training scheme output by the preset training deployment model, and transmitting the training scheme to the central service module;
[0075] Optionally, in this embodiment, the role of the instructor module is to score and guide the operator's training operations based on real training data and preset rules, and generate a reasonable training plan in real time based on the score, so that the instructor and trainer can conduct effective simulation training.
[0076] Optionally, in this embodiment, the technical means adopted by the instructor module is to use model integration technology to train a training deployment model, which can predict classification problems and regression problems respectively. The real training data is input into the trained model, and the model will perform model prediction based on the training parameters and output the final prediction result, that is, the score and training plan for the training operation. Among them, the model decision tree part is used to classify the skill level and tactical decision type of the trainer, and provide strategic guidance to the instructor according to the skill level and tactical decision type of the trainer; the model regression tree part is used to predict the performance of the trainer in a specific task and provide tactical guidance to the trainer.
[0077] Optionally, in this embodiment, for example, it is assumed that a special operations team needs to undergo tactical training to improve its combat capability in a complex battlefield environment.
[0078] During the training process, the trainee's operation data is collected in real time and fed back to the training deployment model. The training deployment model can perform difference evaluation based on the trainee's actual training status and the training status predicted by the model, and generate analysis results in real time, where the analysis results include the trainee's operation score and training plan.
[0079] The decision tree part of the model is used to classify the skill level and tactical decision type of the trainer, and provide strategic guidance to the instructor based on the skill level and tactical decision type of the trainer. If the decision tree model identifies that a trainer performs poorly in the "direct attack decision" type, the training plan can be adjusted to add related simulation training tasks. The instructor can intuitively see the performance of the trainer and the training plan, and can manually adjust the plan based on the model-generated plan.
[0080] The regression tree part of the model is used to predict the trainer's performance in a specific task and provide tactical guidance to the trainer. If the regression tree model predicts that a trainer's speed in the "quick response" task is not up to standard, the training plan can be adjusted to add relevant "quick response" training tasks. After seeing the training evaluation, the trainer can strengthen his attention in the quick response exercise, conduct self-reflection and improvement.
[0081] In summary, instructors can adjust training content and methods in real time based on the analysis results of the model, and trainers can adjust their tactical actions based on the analysis results to improve task completion.
[0082] It is understandable that the coach can manually change the training plan generated by the model, such as injecting questions into the training process, triggering questions after starting the process, and requiring the designated operator to give answers to the questions before the process can continue. The changed training plan will be used as the iterative update data of the model to continuously tune the model so that the model can more flexibly adapt to the simulation training process. Through continuous iteration, flexible and intelligent inspections, dynamic question insertion, and customized inspection plan generation can be achieved.
[0083] Optionally, in this embodiment, the implementation step of the instructor module, that is, the step of the model receiving real data and performing prediction to obtain a prediction result, includes:
[0084] Specifically, A) the instructor module includes (a) a data input unit, (b) a data processing unit, and (c) a data transmission unit.
[0085] First, (a) a data input unit, including (1) a nearest neighbor feature determination subunit and (2) a true training feature determination subunit;
[0086] Optionally, in this embodiment, (a) a data input unit is used to receive real training data and extract data features in the real training data that can be used for model prediction for data preprocessing, so that the model can recognize the data features and make predictions and continuously update the prediction results.
[0087] Optionally, in this embodiment, after the training deployment model automatically extracts the corresponding training features;
[0088] (1) a nearest neighbor feature determination subunit, performing a minority class recognition operation on the training feature according to a preset minority class recognition rule, and determining a corresponding nearest neighbor training feature according to the minority class training feature obtained after the minority class recognition operation and a preset K nearest neighbor algorithm;
[0089] The preset minority class identification rule uses the SMOTE algorithm to analyze the category distribution in the training features, confirm whether there is category imbalance, and generate minority class training features.
[0090] The preset K nearest neighbor algorithm is to find the nearest neighbor point of the sample point through the K nearest neighbor algorithm.
[0091] (2) A subunit for determining real training features, performing a distance calculation operation on the minority class training features and the nearest neighbor training features to determine a corresponding training feature distance; determining a corresponding synthetic training feature based on the training feature distance and a preset ratio rule; performing a feature addition operation on the training feature based on the synthetic training feature to determine a corresponding real training feature.
[0092] Distance calculation operation, choose an appropriate distance metric method, such as Euclidean distance.
[0093] The ratio rule is preset, which is the basis for determining the number of new sample points to be generated. For example, if the distance is less than 1 (or other threshold), a new sample point is generated on the line between the minority class sample point and its nearest neighbor. The generation of these new sample points can increase the number of minority class samples, thereby reducing class imbalance.
[0094] The feature addition operation adds the generated new sample points to the original data set to obtain a more balanced real training data feature, that is, the real training feature.
[0095] It can be understood that the feature balancing operation in this step increases the number of samples in the minority category, making the category distribution in the training data more balanced, so that the model can improve its ability to make targeted predictions for the minority category.
[0096] Secondly, (b) a data processing unit, including (1) a decision tree selection feature determination subunit, (2) a regression tree selection feature determination subunit, and (3) a feature integration subunit, wherein the (3) feature integration subunit includes 1) a decision tree prediction feature determination subunit, 2) a regression tree prediction feature determination subunit, and 3) an integration feature determination subunit;
[0097] Optionally, in this embodiment, (b) the data processing unit receives the above-mentioned real training features, and inputs the real training features into the decision tree model and the regression tree model respectively for feature selection, and integrates the selected features.
[0098] Specifically, (1) a decision tree selection feature determination subunit inputs the real training feature into the decision tree feature selection layer of the preset training deployment model to determine the corresponding decision tree selection feature according to the preset Gini impurity;
[0099] Gini impurity is a method used in decision tree algorithms to measure the purity of a data set for feature selection. It is based on probability and calculates the uneven distribution of labels for each category in the data set.
[0100] The Gini impurity algorithm calculates the Gini impurity of the data set for each possible split point of each feature, and selects the split point that reduces the Gini impurity the most. This split point divides the data set into two parts, so that the sum of the Gini impurities of the two parts is minimized.
[0101] The balanced training features are divided into two selection features according to the position of the split point on the balanced training features. The selection feature determines how the current node of the decision tree will be split. This feature will define a rule of the decision tree, for example: "If feature A is greater than a certain threshold, then go to the left branch; otherwise, go to the right branch."
[0102] (2) a regression tree selection feature determination subunit, which inputs the real training feature into the regression tree feature selection layer of the preset training deployment model to determine the corresponding regression tree selection feature according to a preset mean square error algorithm;
[0103] The preset mean square error algorithm, the mean square error (MSE) algorithm is a regression analysis method that aims to find the optimal model parameters so that the sum of the squares of the differences (i.e., errors) between the model prediction values and the actual values is minimized.
[0104] Calculate the mean square error based on the predicted value and the actual value. Use gradient descent or other optimization algorithms to update the model parameters to reduce the mean square error. By minimizing the mean square error, determine the corresponding regression tree selection features.
[0105] (3) A feature integration subunit performs a feature integration operation on the decision tree selection features and the regression tree selection features to determine corresponding integrated features.
[0106] Specifically, the feature integration subunit receives the above-mentioned decision tree selection features and regression tree selection features, and performs feature integration, which is achieved through three subunits, including: 1) a decision tree prediction feature determination subunit, 2) a regression tree prediction feature determination subunit, and 3) an integrated feature determination subunit.
[0107] 1) a decision tree prediction feature determination subunit, which performs a recursive splitting operation on the decision tree selection feature to determine a corresponding decision tree prediction feature, wherein the decision tree prediction feature is used to predict a category label;
[0108] The recursive splitting operation is to input the selected selection features into the splitting layer. According to the feature selection and splitting point, the data is divided into two or more subsets, and each subset enters the next layer of the tree. The feature selection and splitting process is repeated recursively for each subset. Each split will divide the data set into two parts according to the selected features, and then the splitting process is repeated on these two parts of the data. New recursive features are determined for each split. These features are the optimal features of the current splitting node and are used to further split the data set until the stopping condition is met. In this process, the nodes except the root node represent a series of decisions that have been made. The end node of the tree, without further splitting, will contain a category label, which is the prediction feature of the decision tree.
[0109] Among them, the stopping condition is the maximum tree depth condition, that is, a maximum tree depth is preset, and when the decision tree model splits to the preset depth, the splitting stops. It can be understood that the maximum tree depth is a hyperparameter of a model set according to specific business and training needs. Setting the maximum tree depth helps the model to better predict features.
[0110] 2) a regression tree prediction feature determination subunit, which performs a recursive splitting operation on the regression tree selection feature to determine a corresponding regression tree prediction feature, wherein the regression tree prediction feature is used to predict a continuous value;
[0111] The regression tree prediction feature predicts the output of the regression tree model. The preset regression tree model is also a decision tree. Unlike the decision tree model, it is used to predict continuous numerical data instead of discrete labels in classification problems. The leaf nodes of the decision tree contain category labels, indicating the predicted category. The leaf nodes of the regression tree contain numerical values, indicating the continuous output of the prediction.
[0112] Recursive splitting operation, according to the selected features and splitting points, the data is divided into two or more subsets, each subset enters the next layer of the tree. For each subset, the feature selection and splitting process is repeated until the stopping condition is met. The stopping condition here is also the maximum tree depth. After the regression tree model stops splitting, the regression tree recursive features will be obtained.
[0113] 3) An integrated feature determination subunit inputs the decision tree prediction feature and the regression tree prediction feature into a preset neural network for feature integration operation to determine the corresponding integrated feature.
[0114] Feature integration operation,Feature integration is a technique that combines the prediction results of multiple models to improve the prediction accuracy.,Decision trees and regression trees are two prediction models, and the features they generate are input into,neural networks for further integration and learning.
[0115] Specifically, first, use the decision tree model to predict the training data and generate decision paths or decision rules as features; then, use the regression tree model to predict the training data and generate predicted values or prediction paths as features; then, combine the features generated by the decision tree and the regression tree into an integrated feature set; finally, design a neural network model with the number of nodes in the input layer equal to the number of integrated features, use the standardized integrated features as input data, and train the neural network.
[0116] It can be understood that this integrated operation improves the predictive ability of the model and is suitable for scenarios that require the advantages of multiple predictive models.
[0117] The function of (3) feature integration subunit is realized by 1) decision tree prediction feature determination subunit, 2) regression tree prediction feature determination subunit and 3) integration feature determination subunit.
[0118] Finally, (c) a data transmission unit, including (1) a data activation subunit and (2) a data transmission subunit;
[0119] Optionally, in this embodiment, (c) the data transmission unit inputs the above-mentioned integrated features into the model output layer for data conversion, determines the corresponding training scheme, and outputs the training scheme.
[0120] Specifically, (1) a data activation subunit inputs the integrated features after the feature integration operation into the output layer of a preset training deployment model, performs a feature output operation on the integrated features according to a preset activation function, and determines a training scheme output by the preset training deployment model.
[0121] Preset activation function,feature conversion to the output of the training scheme involves the design of the output layer of the model and the selection of activation function.
[0122] The activation function of the output layer is crucial to determining the format of the model output. For multi-class classification problems, the softmax activation function is used to output the probability distribution.
[0123] Design the number of neurons in the output layer based on the number and type of training scenarios. For example, if there are N possible training scenarios, the output layer will have N neurons.
[0124] (2) A data transmission subunit, which transmits the training plan to the central service module according to a preset communication rule.
[0125] Preset communication rules, use UDP and TCP communication to achieve internal networking to complete message linkage.
[0126] The control module is used to execute step S102: receiving the training scheme from the central service module, determining corresponding operation instructions according to the training scheme and preset parsing rules, and transmitting the operation instructions to the central service module;
[0127] Optionally, in this embodiment, the function of the control module is to complete the overall training process control, from the start process, according to the training steps, to output instructions for each training operation, and the operator receives the operation instructions, performs actual operation actions, completes the training steps, and displays the training results to the control position and instructor position.
[0128] Optionally, in this embodiment, the control module includes a self-checking unit, a communication unit and a parsing unit;
[0129] Specifically, the self-checking unit performs a self-checking operation on the control module according to a preset self-checking rule, and determines whether there is a problem with the self-checking result. If not, the communication unit is activated;
[0130] Self-check unit, the preset self-check rules are pre-programmed self-check operation procedures. According to the operation procedures, the control bit self-check can be completed. The self-check rules are set according to the specific needs of the business. It can be to check whether the control bit is operating normally or whether the control bit confidentiality function is intact. After the self-check is completed, the communication module is triggered to activate if the self-check rules are met.
[0131] It is understood that the self-check function includes hardware detection (such as processor, memory, etc.) and software detection (such as operating system version, key service status, etc.). When the system starts, these detections are automatically performed and any potential problems are reported.
[0132] a communication unit, performing a registration operation on the central service module according to a preset communication rule, so that the control module can receive the training program from the central service module;
[0133] The message registration to the central server is completed through the communication rules, and the control unit is connected to the network. The communication rules are the rules for completing the message linkage of the internal network. After the communication unit is connected to the network, the control module can receive messages from the instructor module and the shooter module from the central service module through the internal networking message linkage, so that the control module can receive the training plan of the instructor module and send the operation instructions to the shooter module.
[0134] The parsing unit determines the corresponding training objectives and training steps according to the training program and the preset parsing rules, determines the corresponding operation instructions according to the training objectives, the training steps and the preset process rules, and transmits the operation instructions to the central service module.
[0135] Preset parsing rules define the overall goals and requirements of training, as well as how to parse and determine specific training goals based on training needs.
[0136] According to the training plan and preset analysis rules, specific training goals are determined. These goals can be skill mastery, tactical application, operational proficiency, etc. The training goals are further refined into specific training steps. Each step may include a series of operations or tasks that the operator needs to complete.
[0137] According to the training objectives and training steps, corresponding operation instructions are generated. These instructions describe in detail the specific actions or tasks that the operator needs to perform.
[0138] The generated operation instructions are transmitted to the central service module, which is responsible for receiving, processing and distributing these instructions.
[0139] The shooter module is used to execute step S103: receive the operation instruction from the central service module and display the operation instruction on the training hand interface, record the data of the training hand executing the operation instruction, determine the corresponding operation result, and transmit the operation result to the central service module.
[0140] Optionally, in this embodiment, the role of the shooter module is to complete the single-step process operation according to the training process and implement the operation completion event interface.
[0141] Optionally, in this embodiment, the shooter module includes a self-checking unit, a communication unit, and a recording unit;
[0142] Specifically, the self-checking unit performs a self-checking operation on the shooter module according to a preset self-checking rule, and determines whether there is a problem with the self-checking result. If not, the communication unit is activated;
[0143] Self-check unit, the preset self-check rules are pre-programmed self-check operation procedures. According to the operation procedures, the shooter position self-check can be completed. The self-check rules are set according to the specific needs of the business. It can be to check whether the shooter position is operating normally or whether the shooter position information receiving and sending functions are intact. After the self-check is completed, if the self-check rules are met, the communication module is triggered to activate.
[0144] It is understood that the self-check function includes hardware detection (such as processor, memory, etc.) and software detection (such as operating system version, key service status, etc.). When the system starts, these detections are automatically performed and any potential problems are reported.
[0145] a communication unit, performing a registration operation on the central service module according to a preset communication rule, so that the shooter module can receive the operation instruction from the central service module, and display the operation instruction on the training hand interface;
[0146] The message registration to the central server can be completed through the communication rules, and the shooter position can be connected to the network. The communication rules are the rules for completing the message linkage of the internal network. After the communication unit is connected to the network, the shooter module can receive messages from the instructor module and the control module from the central service module through the internal networking message linkage, so that the shooter module can receive the operation instructions of the control module and send the operation results to the instructor module and the control module.
[0147] The recording unit records the data of the operation instruction executed by the training hand according to the preset event-driven rules, determines the corresponding operation result, and transmits the operation result to the central service module.
[0148] Event-driven, the operator component needs to trigger an event after completing each step of the operation, which can notify other parts of the system (such as the control bit or the instructor bit) that the operation has been completed. This mechanism is often called event-driven programming, which allows loosely coupled communication between different components of the system.
[0149] Preset event-driven rules to define the event types and conditions that trigger recording operations. These events can be when an operator completes a specific operation, reaches a certain training milestone, or a specific error occurs.
[0150] Recording operations: When the operator performs an operation, the system automatically records the relevant operation data, which may include operation time, operation steps, operation results, etc.
[0151] The operation results are determined by the system automatically or manually by the instructor based on the preset evaluation criteria. This may involve evaluation of the accuracy, efficiency, and effectiveness of the operation.
[0152] The operation results are transmitted to the central service module through the internal network or communication protocol. This involves the formatting, encryption and transmission of data.
[0153] The central service module is used to execute step S104: receive the training plan, the operation instruction and the operation result, and transmit the training plan, the operation instruction and the operation result to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules.
[0154] Optionally, in this embodiment, the role of the central service module is to deploy and install a central service unit for message synchronization and complete the message linkage of each trainer, wherein the instructor module, control module, shooter module and central service module maintain real-time online status through a heartbeat mechanism.
[0155] Optionally, in this embodiment, the central service module includes a first central service unit, a second central service unit and a third central service unit;
[0156] Specifically, the central service module, as the core of the system, establishes connections with all training modules.
[0157] Receive training plans and scoring information from the instructor position, receive training process status from the control position, and receive operation results from the shooter position. The central server is responsible for the synchronization and distribution of messages, and distributes messages according to the registered operation number position to achieve overall linkage training. The instructor position's instructions and scoring information, the control position's training process instructions, the shooter position's operation results and other data are transmitted to the corresponding training position through the internal network message mechanism.
[0158] The data processing flow of the entire system can be summarized as follows:
[0159] In the first central service unit, the instructor formulates the training plan and sends it to the control position through the central server.
[0160] In the second central service unit, the control position generates operation instructions according to the training plan, sends them to the shooter position, and synchronizes them to the instructor position through the central server.
[0161] In the third central service unit, the shooter position receives the operation instructions, executes the operation and feeds back the results to the control position and the instructor position, and the data is transferred through the central server.
[0162] The central server is responsible for coordinating data transmission between training stations to ensure the synchronization and real-time nature of messages.
[0163] It can be understood that in this way, the joint simulation training system achieves efficient collaboration and data sharing among instructors, controllers, and shooters, providing strong support for training.
[0164] This example demonstrates how this embodiment constructs a joint simulation system, and through the linkage between systems and artificial intelligence technology, it is possible to flexibly generate training plans for training data to guide the simulation training of instructors and trainers.
[0165] From the above description, it can be seen that the joint simulation training system based on the Kylin operating system provided in the embodiment of the present application can receive real training data through the instructor module, input the real training data into the preset training deployment model, and determine the training plan output by the preset training deployment model; the control module is used to receive the training plan, determine the corresponding operation instructions according to the training plan and the preset parsing rules, the shooter module is used to receive the operation instructions and display the operation instructions on the training hand interface, record the data of the training hand executing the operation instructions, and determine the corresponding operation results; the central service module is used to receive the training plan, the operation instructions and the operation results, and transmit the training plan, the operation instructions and the operation results to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules, thereby improving the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage.
[0166] In one embodiment of the joint simulation training system based on the Kylin operating system of the present application, see Figure 2 , and can also include the following:
[0167] A data input unit, configured to execute step S201: receiving real training data, inputting the real training data into an input layer of a preset training deployment model, performing a feature extraction operation on the real training data, determining corresponding training features, and determining corresponding real training features according to the training features and a preset feature balancing algorithm, wherein the real training data includes at least one of operator information and operation result information transmitted from the central service module;
[0168] The data processing unit is used to execute step S202: input the real training features into the decision tree feature selection layer and the regression tree feature selection layer of the preset training deployment model respectively to perform feature selection operations, determine corresponding decision tree selection features and regression tree selection features, perform feature integration operations on the decision tree selection features and the regression tree selection features, and determine corresponding integrated features;
[0169] The data transmission unit is used to execute step S203: input the integrated features after the feature integration operation into the output layer of the preset training deployment model, determine the training plan output by the preset training deployment model, and transmit the training plan to the central service module.
[0170] Optionally, in this embodiment, A) the instructor module includes (a) a data input unit, (b) a data processing unit, and (c) a data transmission unit.
[0171] (a) A data input unit, which is used to receive real training data and extract data features from the real training data that can be used for model prediction for data preprocessing, so that the model can recognize data features and make predictions and continuously update the prediction results.
[0172] It is understandable that the data preprocessing in this step includes a feature balancing operation, which increases the number of samples in the minority category and makes the category distribution in the training data more balanced, so that the model can improve its ability to make targeted predictions for the minority category.
[0173] (b) A data processing unit receives the above-mentioned real training features, and inputs the real training features into the decision tree model and the regression tree model for feature selection, and integrates the selected features.
[0174] Among them, Gini impurity is used for decision tree feature selection, and minimum mean square error is used for regression tree feature selection.
[0175] (c) A data transmission unit, which inputs the above integrated features into the model output layer for data conversion, determines the corresponding training plan, and outputs the training plan.
[0176] Through step S203, this embodiment disassembles the functions of the instructor module and implements the functions of the entire instructor module according to three functional units, laying a foundation for constructing the instructor module.
[0177] In one embodiment of the joint simulation training system based on the Kylin operating system of the present application, see Figure 3 , and can also include the following:
[0178] The nearest neighbor feature determination subunit is used to execute step S301: perform a minority class recognition operation on the training feature according to a preset minority class recognition rule, and determine a corresponding nearest neighbor training feature according to the minority class training feature obtained after the minority class recognition operation and a preset K nearest neighbor algorithm;
[0179] The real training feature determination subunit is used to execute step S302: perform a distance calculation operation on the minority class training feature and the nearest neighbor training feature to determine the corresponding training feature distance; determine the corresponding synthetic training feature according to the training feature distance and a preset ratio rule, and perform a feature addition operation on the training feature according to the synthetic training feature to determine the corresponding real training feature.
[0180] Optionally, in this embodiment, the preset minority class identification rule is to use the SMOTE algorithm to analyze the category distribution in the training features, confirm whether there is category imbalance, and generate minority class training features.
[0181] The preset K nearest neighbor algorithm is to find the nearest neighbor point of the sample point through the K nearest neighbor algorithm.
[0182] Optionally, in this embodiment, in the distance calculation operation, an appropriate distance measurement method is selected, such as Euclidean distance.
[0183] The ratio rule is preset, which is the basis for determining the number of new sample points to be generated. For example, if the distance is less than 1 (or other threshold), a new sample point is generated on the line between the minority class sample point and its nearest neighbor. The generation of these new sample points can increase the number of minority class samples, thereby reducing class imbalance.
[0184] The feature addition operation adds the generated new sample points to the original data set to obtain a more balanced real training data feature, that is, the real training feature.
[0185] It can be understood that the feature balancing operation in this step increases the number of samples in the minority category, making the category distribution in the training data more balanced, so that the model can improve its ability to make targeted predictions for the minority category.
[0186] Through step S302, this embodiment disassembles the function of the data input unit in the instructor module, and implements the function of the data input unit through two functional sub-units, laying a foundation for the construction of the instructor module.
[0187] In one embodiment of the joint simulation training system based on the Kylin operating system of the present application, see Figure 4 , and can also include the following:
[0188] The decision tree selection feature determination subunit is used to execute step S401: input the real training feature into the decision tree feature selection layer of the preset training deployment model to determine the corresponding decision tree selection feature according to the preset Gini impurity;
[0189] The regression tree selection feature determination subunit is used to execute step S402: input the real training feature into the regression tree feature selection layer of the preset training deployment model to determine the corresponding regression tree selection feature according to the preset mean square error algorithm;
[0190] The feature integration subunit is used to execute step S403: perform feature integration operation on the decision tree selected features and the regression tree selected features to determine corresponding integrated features.
[0191] Optionally, in this embodiment, (1) a decision tree selection feature determination subunit inputs the real training feature into the decision tree feature selection layer of the preset training deployment model to determine the corresponding decision tree selection feature according to the preset Gini impurity;
[0192] Gini impurity is a method used in decision tree algorithms to measure the purity of a data set for feature selection. It is based on probability and calculates the uneven distribution of labels for each category in the data set.
[0193] The Gini impurity algorithm calculates the Gini impurity of the data set for each possible split point of each feature, and selects the split point that reduces the Gini impurity the most. This split point divides the data set into two parts, so that the sum of the Gini impurities of the two parts is minimized.
[0194] The balanced training features are divided into two selection features according to the position of the split point on the balanced training features. The selection feature determines how the current node of the decision tree will be split. This feature will define a rule of the decision tree, for example: "If feature A is greater than a certain threshold, then go to the left branch; otherwise, go to the right branch."
[0195] (2) a regression tree selection feature determination subunit, which inputs the real training feature into the regression tree feature selection layer of the preset training deployment model to determine the corresponding regression tree selection feature according to a preset mean square error algorithm;
[0196] The preset mean square error algorithm, the mean square error (MSE) algorithm is a regression analysis method that aims to find the optimal model parameters so that the sum of the squares of the differences (i.e., errors) between the model prediction values and the actual values is minimized.
[0197] Calculate the mean square error based on the predicted value and the actual value. Use gradient descent or other optimization algorithms to update the model parameters to reduce the mean square error. By minimizing the mean square error, determine the corresponding regression tree selection features.
[0198] (3) A feature integration subunit performs a feature integration operation on the decision tree selection features and the regression tree selection features to determine corresponding integrated features.
[0199] Through step S403, this embodiment disassembles the function of the data processing unit in the instructor module, and implements the function of the data input unit through three functional sub-units, laying a foundation for the construction of the instructor module.
[0200] In one embodiment of the joint simulation training system based on the Kylin operating system of the present application, see Figure 5 , and can also include the following:
[0201] The decision tree prediction feature determination subunit is used to execute step S501: recursively split the decision tree selection feature to determine the corresponding decision tree prediction feature, wherein the decision tree prediction feature is used to predict the category label;
[0202] The regression tree prediction feature determination subunit is used to execute step S502: recursively split the regression tree selection feature to determine the corresponding regression tree prediction feature, wherein the regression tree prediction feature is used to predict continuous values.
[0203] The integrated feature determination subunit is used to execute step S503: input the decision tree prediction feature and the regression tree prediction feature into a preset neural network to perform a feature integration operation to determine the corresponding integrated feature.
[0204] Optionally, in this embodiment, the feature integration subunit receives the above-mentioned decision tree selection features and regression tree selection features, and performs feature integration, which is achieved through three subunits, including: 1) a decision tree prediction feature determination subunit, 2) a regression tree prediction feature determination subunit, and 3) an integrated feature determination subunit.
[0205] 1) a decision tree prediction feature determination subunit, which performs a recursive splitting operation on the decision tree selection feature to determine a corresponding decision tree prediction feature, wherein the decision tree prediction feature is used to predict a category label;
[0206] The recursive splitting operation is to input the selected selection features into the splitting layer. According to the feature selection and splitting point, the data is divided into two or more subsets, and each subset enters the next layer of the tree. The feature selection and splitting process is repeated recursively for each subset. Each split will divide the data set into two parts according to the selected features, and then the splitting process is repeated on these two parts of the data. New recursive features are determined for each split. These features are the optimal features of the current splitting node and are used to further split the data set until the stopping condition is met. In this process, the nodes except the root node represent a series of decisions that have been made. The end node of the tree, without further splitting, will contain a category label, which is the prediction feature of the decision tree.
[0207] Among them, the stopping condition is the maximum tree depth condition, that is, a maximum tree depth is preset, and when the decision tree model splits to the preset depth, the splitting stops. It can be understood that the maximum tree depth is a hyperparameter of a model set according to specific business and training needs. Setting the maximum tree depth helps the model to better predict features.
[0208] 2) a regression tree prediction feature determination subunit, which performs a recursive splitting operation on the regression tree selection feature to determine a corresponding regression tree prediction feature, wherein the regression tree prediction feature is used to predict a continuous value;
[0209] The regression tree prediction feature predicts the output of the regression tree model. The preset regression tree model is also a decision tree. Unlike the decision tree model, it is used to predict continuous numerical data instead of discrete labels in classification problems. The leaf nodes of the decision tree contain category labels, indicating the predicted category. The leaf nodes of the regression tree contain numerical values, indicating the continuous output of the prediction.
[0210] Recursive splitting operation, according to the selected features and splitting points, the data is divided into two or more subsets, each subset enters the next layer of the tree. For each subset, the feature selection and splitting process is repeated until the stopping condition is met. The stopping condition here is also the maximum tree depth. After the regression tree model stops splitting, the regression tree recursive features will be obtained.
[0211] 3) An integrated feature determination subunit inputs the decision tree prediction feature and the regression tree prediction feature into a preset neural network for feature integration operation to determine the corresponding integrated feature.
[0212] Feature integration operation,Feature integration is a technique that combines the prediction results of multiple models to improve the prediction accuracy.,Decision trees and regression trees are two prediction models, and the features they generate are input into,neural networks for further integration and learning.
[0213] Specifically, first, use the decision tree model to predict the training data and generate decision paths or decision rules as features; then, use the regression tree model to predict the training data and generate predicted values or prediction paths as features; then, combine the features generated by the decision tree and the regression tree into an integrated feature set; finally, design a neural network model with the number of nodes in the input layer equal to the number of integrated features, use the standardized integrated features as input data, and train the neural network.
[0214] It can be understood that this integrated operation improves the predictive ability of the model and is suitable for scenarios that require the advantages of multiple predictive models.
[0215] The function of (3) feature integration subunit is realized by 1) decision tree prediction feature determination subunit, 2) regression tree prediction feature determination subunit and 3) integration feature determination subunit.
[0216] Through step S503, this embodiment successfully disassembles the function of the feature integration subunit of the data processing unit in the instructor module, and implements the function of the feature integration subunit through three functional subunits, laying a foundation for the construction of the instructor module.
[0217] In one embodiment of the joint simulation training system based on the Kylin operating system of the present application, see Figure 6 , and can also include the following:
[0218] The data activation subunit is used to execute step S601: input the integrated features after the feature integration operation into the output layer of the preset training deployment model, perform feature output operation on the integrated features according to a preset activation function, and determine the training scheme output by the preset training deployment model;
[0219] The data transmission subunit is used to execute step S602: transmitting the training plan to the central service module according to a preset communication rule.
[0220] Optionally, in this embodiment, (1) the data activation subunit inputs the integrated features after the feature integration operation into the output layer of the preset training deployment model, performs a feature output operation on the integrated features according to a preset activation function, and determines the training scheme output by the preset training deployment model.
[0221] Preset activation function,feature conversion to the output of the training scheme involves the design of the output layer of the model and the selection of activation function.
[0222] The activation function of the output layer is crucial to determining the format of the model output. For multi-class classification problems, the softmax activation function is used to output the probability distribution.
[0223] Design the number of neurons in the output layer based on the number and type of training scenarios. For example, if there are N possible training scenarios, the output layer will have N neurons.
[0224] (2) A data transmission subunit, which transmits the training plan to the central service module according to a preset communication rule.
[0225] Preset communication rules, use UDP and TCP communication to achieve internal networking to complete message linkage.
[0226] Through step S602, this embodiment successfully disassembles the function of the data transmission unit in the instructor module, and implements the function of the data transmission unit through two functional sub-units, laying a foundation for the construction of the instructor module.
[0227] In one embodiment of the joint simulation training system based on the Kylin operating system of the present application, see Figure 7 , and can also include the following:
[0228] A self-checking unit, configured to execute step S701: performing a self-checking operation on the control module according to a preset self-checking rule, and determining whether there is a problem with the self-checking result, and if not, activating the communication unit;
[0229] A communication unit, configured to execute step S702: performing a registration operation on the central service module according to a preset communication rule, so that the control module can receive the training program from the central service module;
[0230] The parsing unit is used to execute step S703: determine the corresponding training objectives and training steps according to the training plan and preset parsing rules, determine the corresponding operation instructions according to the training objectives, the training steps and preset process rules, and transmit the operation instructions to the central service module.
[0231] Optionally, in this embodiment, the control module includes a self-checking unit, a communication unit and a parsing unit;
[0232] Specifically, the self-checking unit performs a self-checking operation on the control module according to a preset self-checking rule, and determines whether there is a problem with the self-checking result. If not, the communication unit is activated;
[0233] Self-check unit, the preset self-check rules are pre-programmed self-check operation procedures. According to the operation procedures, the control bit self-check can be completed. The self-check rules are set according to the specific needs of the business. It can be to check whether the control bit is operating normally or whether the control bit confidentiality function is intact. After the self-check is completed, the communication module is triggered to activate if the self-check rules are met.
[0234] It is understood that the self-check function includes hardware detection (such as processor, memory, etc.) and software detection (such as operating system version, key service status, etc.). When the system starts, these detections are automatically performed and any potential problems are reported.
[0235] a communication unit, performing a registration operation on the central service module according to a preset communication rule, so that the control module can receive the training program from the central service module;
[0236] The message registration to the central server is completed through the communication rules, and the control unit is connected to the network. The communication rules are the rules for completing the message linkage of the internal network. After the communication unit is connected to the network, the control module can receive messages from the instructor module and the shooter module from the central service module through the internal networking message linkage, so that the control module can receive the training plan of the instructor module and send the operation instructions to the shooter module.
[0237] The parsing unit determines the corresponding training objectives and training steps according to the training plan and the preset parsing rules, determines the corresponding operation instructions according to the training objectives, the training steps and the preset process rules, and transmits the operation instructions to the central service module.
[0238] Preset parsing rules define the overall goals and requirements of training, as well as how to parse and determine specific training goals based on training needs.
[0239] According to the training plan and preset analysis rules, specific training goals are determined. These goals can be skill mastery, tactical application, operational proficiency, etc. The training goals are further refined into specific training steps. Each step may include a series of operations or tasks that the operator needs to complete.
[0240] According to the training objectives and training steps, corresponding operation instructions are generated. These instructions describe in detail the specific actions or tasks that the operator needs to perform.
[0241] The generated operation instructions are transmitted to the central service module, which is responsible for receiving, processing and distributing these instructions.
[0242] Through step S703, this embodiment successfully disassembles the functions of the control module, implements the functions of the overall control module according to three functional units, and lays a foundation for constructing the control module.
[0243] In one embodiment of the joint simulation training system based on the Kylin operating system of the present application, see Figure 8 , and can also include the following:
[0244] A self-checking unit, configured to execute step S801: performing a self-checking operation on the shooter module according to a preset self-checking rule, and determining whether there is a problem with the self-checking result, and if not, activating the communication unit;
[0245] The communication unit is used to execute step S802: perform a registration operation on the central service module according to a preset communication rule, so that the shooter module can receive the operation instruction from the central service module and display the operation instruction on the training hand interface;
[0246] The recording unit is used to execute step S803: record the data of the training hand executing the operation instruction according to the preset event-driven rule, determine the corresponding operation result, and transmit the operation result to the central service module.
[0247] Optionally, in this embodiment, the role of the shooter module is to complete the single-step process operation according to the training process and implement the operation completion event interface.
[0248] Optionally, in this embodiment, the shooter module includes a self-checking unit, a communication unit, and a recording unit;
[0249] Specifically, the self-checking unit performs a self-checking operation on the shooter module according to a preset self-checking rule, and determines whether there is a problem with the self-checking result. If not, the communication unit is activated;
[0250] Self-check unit, the preset self-check rules are pre-programmed self-check operation procedures. According to the operation procedures, the shooter position self-check can be completed. The self-check rules are set according to the specific needs of the business. It can be to check whether the shooter position is operating normally or whether the shooter position information receiving and sending functions are intact. After the self-check is completed, if the self-check rules are met, the communication module is triggered to activate.
[0251] It is understood that the self-check function includes hardware detection (such as processor, memory, etc.) and software detection (such as operating system version, key service status, etc.). When the system starts, these detections are automatically performed and any potential problems are reported.
[0252] a communication unit, performing a registration operation on the central service module according to a preset communication rule, so that the shooter module can receive the operation instruction from the central service module, and display the operation instruction on the training hand interface;
[0253] The message registration to the central server can be completed through the communication rules, and the shooter position can be connected to the network. The communication rules are the rules for completing the message linkage of the internal network. After the communication unit is connected to the network, the shooter module can receive messages from the instructor module and the control module from the central service module through the internal networking message linkage, so that the shooter module can receive the operation instructions of the control module and send the operation results to the instructor module and the control module.
[0254] The recording unit records the data of the operation instruction executed by the training hand according to the preset event-driven rules, determines the corresponding operation result, and transmits the operation result to the central service module.
[0255] Event-driven, the operator component needs to trigger an event after completing each step of the operation, which can notify other parts of the system (such as the control bit or the instructor bit) that the operation has been completed. This mechanism is often called event-driven programming, which allows loosely coupled communication between different components of the system.
[0256] Preset event-driven rules to define the event types and conditions that trigger recording operations. These events can be when an operator completes a specific operation, reaches a certain training milestone, or a specific error occurs.
[0257] Recording operations: When the operator performs an operation, the system automatically records the relevant operation data, which may include operation time, operation steps, operation results, etc.
[0258] The operation results are determined by the system automatically or manually by the instructor based on the preset evaluation criteria. This may involve evaluation of the accuracy, efficiency, and effectiveness of the operation.
[0259] The operation results are transmitted to the central service module through the internal network or communication protocol. This involves the formatting, encryption and transmission of data.
[0260] Through step S803, this embodiment successfully disassembles the functions of the shooter module, implements the functions of the overall shooter module according to three functional units, and lays a foundation for constructing the shooter module.
[0261] In one embodiment of the joint simulation training system based on the Kylin operating system of the present application, see Fig. 9 , and can also include the following:
[0262] The first central service unit is used to execute step S901: connect the instructor module according to a preset communication rule so that the central service module can receive the training program output by the instructor module;
[0263] The second central service unit is used to execute step S902: connect the control module according to the preset communication rule, so that the central service module can send the received training program to the control module, receive the corresponding operation instruction, and send the operation instruction to the instructor module and the shooter module, wherein the operation instruction is output by the control module after receiving the training program;
[0264] The third central service unit is used to execute step S903: connect the shooter module according to the preset communication rules, so that the central service module can send the received operation instruction to the shooter module, receive the corresponding operation result, and send the operation result to the instructor module and the control module, wherein the operation result is output by the shooter module after receiving the operation instruction.
[0265] Optionally, in this embodiment, the role of the central service module is to deploy and install the central service unit for message synchronization and complete the message linkage of each trainer, wherein the instructor module, control module, shooter module and central service module maintain real-time online status through the heartbeat mechanism. According to the operability of the operator, the operator can be added dynamically, and after the operation, the ranking sequence is automatically generated according to the system, and a unique operator network identifier is assigned. All command messages are sent to the central server first, and the central server distributes the messages according to the registered operation number to realize the overall linkage training.
[0266] Optionally, in this embodiment, the central service module includes a first central service unit, a second central service unit and a third central service unit;
[0267] Specifically, the central service module, as the core of the system, establishes connections with all training modules.
[0268] Receive training plans and scoring information from the instructor position, receive training process status from the control position, and receive operation results from the shooter position. The central server is responsible for the synchronization and distribution of messages, and distributes messages according to the registered operation number position to achieve overall linkage training. The instructor position's instructions and scoring information, the control position's training process instructions, the shooter position's operation results and other data are transmitted to the corresponding training position through the internal network message mechanism.
[0269] The data processing flow of the entire system can be summarized as follows:
[0270] In the first central service unit, the instructor formulates the training plan and sends it to the control position through the central server.
[0271] In the second central service unit, the control position generates operation instructions according to the training plan, sends them to the shooter position, and synchronizes them to the instructor position through the central server.
[0272] In the third central service unit, the shooter position receives the operation instructions, executes the operation and feeds back the results to the control position and the instructor position, and the data is transferred through the central server.
[0273] The central server is responsible for coordinating data transmission between training stations to ensure the synchronization and real-time nature of messages.
[0274] It can be understood that in this way, the joint simulation training system achieves efficient collaboration and data sharing among instructors, controllers, and shooters, providing strong support for training.
[0275] Through step S903, this embodiment successfully decomposes the functions of the central service module, implements the functions of the entire central service module according to three functional units, and lays a foundation for constructing the central service module.
[0276] In one embodiment of the joint simulation training system based on the Kylin operating system of the present application, see Fig.10 , and can also include the following:
[0277] The encryption unit is used to execute step S1001: determine the corresponding encryption subclass interface according to a preset encryption algorithm;
[0278] The startup unit is used to execute step S1002: perform an inheritance operation on a preset parent class interface, and start the central service module according to the encryption subclass interface and a predefined protocol.
[0279] Optionally, in this embodiment, a symmetric encryption algorithm and library are selected to implement the encryption and decryption process of the message to ensure the security of data transmission. The encryption algorithm is integrated into the subclass interface to obtain an encryption subclass interface.
[0280] Optionally, in this embodiment, the central server uses the encryption subclass interface to inherit the already defined parent class interface to meet specific encryption requirements.
[0281] Through step S1002, this embodiment successfully encrypts the information transmission of the central server, thereby ensuring the data security of the entire system.
[0282] It can be understood that the minimum system of the joint simulation training system framework of this system includes an instructor position, a control position, a shooter position and a central server. Users can inherit the above components according to actual training needs, and add their own extended functions and processes to achieve personalized customization of each component.
[0283] In order to improve the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage, the present application provides an embodiment of a joint simulation training device based on the Kylin operating system for implementing all or part of the contents of the joint simulation training system based on the Kylin operating system, see Fig.11 The joint simulation training device based on Kylin operating system specifically includes the following contents:
[0284] The instructor module 10 is used to receive real training data, input the real training data into the input layer of the preset training deployment model to perform data preprocessing operations on the real training data, determine corresponding real training features, input the real training features into the feature selection layer of the preset training deployment model to perform feature selection operations, determine corresponding selected features, perform feature integration operations on the selected features, input the integrated features after the feature integration operations into the output layer of the preset training deployment model, determine the training scheme output by the preset training deployment model, and transmit the training scheme to the central service module;
[0285] The control module 20 is used to receive the training scheme from the central service module, determine the corresponding operation instruction according to the training scheme and the preset analysis rules, and transmit the operation instruction to the central service module;
[0286] The shooter module 30 is used to receive the operation instruction from the central service module and display the operation instruction on the training hand interface, record the data of the training hand executing the operation instruction, determine the corresponding operation result, and transmit the operation result to the central service module.
[0287] The central service module 40 is used to receive the training plan, the operation instruction and the operation result, and transmit the training plan, the operation instruction and the operation result to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules.
[0288] From the above description, it can be seen that the joint simulation training device based on the Kylin operating system provided in the embodiment of the present application can receive real training data through the instructor module, input the real training data into the preset training deployment model, and determine the training plan output by the preset training deployment model; the control module is used to receive the training plan, determine the corresponding operation instructions according to the training plan and the preset parsing rules, the shooter module is used to receive the operation instructions and display the operation instructions on the training hand interface, record the data of the training hand executing the operation instructions, and determine the corresponding operation results; the central service module is used to receive the training plan, the operation instructions and the operation results, and transmit the training plan, the operation instructions and the operation results to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules, thereby improving the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage.
[0289] From the hardware level, in order to improve the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage, the present application provides an embodiment of an electronic device for implementing all or part of the contents of the joint simulation training system based on the Kylin operating system, and the electronic device specifically includes the following contents:
[0290] Processor, memory, communication interface and bus; wherein the processor, memory and communication interface communicate with each other through the bus; the communication interface is used to realize information transmission between the joint simulation training system based on the Kylin operating system and the core business system, user terminal and related databases and other related devices; the logic controller can be a desktop computer, a tablet computer and a mobile terminal, etc., but the present embodiment is not limited thereto. In the present embodiment, the logic controller can be implemented with reference to the embodiment of the joint simulation training system based on the Kylin operating system and the embodiment of the joint simulation training system based on the Kylin operating system in the embodiment, and the contents thereof are incorporated herein, and the repeated parts are not repeated.
[0291] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.
[0292] In practical applications, part of the joint simulation training system based on the Kylin operating system can be executed on the electronic device side as described above, or all operations can be completed in the client device. The specific selection can be based on the processing capability of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device may also include a processor.
[0293] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.
[0294] Fig.12 FIG. 9 is a schematic block diagram of the system structure of the electronic device 9600 according to an embodiment of the present application. Fig.12 As shown, the electronic device 9600 may include a central processor 9100 and a memory 9140; the memory 9140 is coupled to the central processor 9100. It is worth noting that Fig.12 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.
[0295] In one embodiment, the joint simulation training system function based on the Kylin operating system can be integrated into the central processing unit 9100. The central processing unit 9100 can be configured to perform the following control:
[0296] Step S101: receiving real training data, inputting the real training data into the input layer of the preset training deployment model to perform data preprocessing operations on the real training data, determining corresponding real training features, inputting the real training features into the feature selection layer of the preset training deployment model to perform feature selection operations, determining corresponding selected features, performing feature integration operations on the selected features, inputting the integrated features after the feature integration operations into the output layer of the preset training deployment model, determining the training scheme output by the preset training deployment model, and transmitting the training scheme to the central service module;
[0297] Step S102: receiving the training scheme from the central service module, determining corresponding operation instructions according to the training scheme and preset parsing rules, and transmitting the operation instructions to the central service module;
[0298] Step S103: receiving the operation instruction from the central service module and displaying the operation instruction on the training hand interface, recording the data of the training hand executing the operation instruction, determining the corresponding operation result, and transmitting the operation result to the central service module.
[0299] Step S104: receiving the training program, the operation instruction and the operation result, and transmitting the training program, the operation instruction and the operation result to the corresponding instructor module, the control module and the shooter module according to a preset linkage rule.
[0300] From the above description, it can be seen that the electronic device provided in the embodiment of the present application, through the instructor module, is used to receive real training data, input the real training data into a preset training deployment model, and determine the training plan output by the preset training deployment model; the control module is used to receive the training plan, determine the corresponding operation instructions according to the training plan and preset parsing rules, the shooter module is used to receive the operation instructions and display the operation instructions on the training hand interface, record the data of the training hand executing the operation instructions, and determine the corresponding operation results; the central service module is used to receive the training plan, the operation instructions and the operation results, and transmit the training plan, the operation instructions and the operation results to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules, thereby improving the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage.
[0301] In another embodiment, the joint simulation training system based on the Kylin operating system can be configured separately from the central processing unit 9100. For example, the joint simulation training system based on the Kylin operating system can be configured as a chip connected to the central processing unit 9100, and the functions of the joint simulation training system based on the Kylin operating system can be realized through the control of the central processing unit.
[0302] like Fig.12 As shown, the electronic device 9600 may also include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily have to include Fig.12 In addition, the electronic device 9600 may also include Fig.12 For components not shown, reference may be made to the prior art.
[0303] like Fig.12 As shown, the central processing unit 9100 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor device and / or logic device, which receives input and controls the operation of various components of the electronic device 9600.
[0304] The memory 9140 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. The above-mentioned information related to the failure may be stored, and a program for executing the relevant information may also be stored. The CPU 9100 may execute the program stored in the memory 9140 to implement information storage or processing, etc.
[0305] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display display objects such as images and texts. The display may be, for example, an LCD display, but is not limited thereto.
[0306] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), a SIM card, etc. It may also be a memory that saves information even when the power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as EPROMs, etc. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142, which is used to store application programs and function programs or processes for executing the operation of the electronic device 9600 through the central processor 9100.
[0307] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various drivers for communication functions of the electronic device and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).
[0308] The communication module 9110 is a transmitter / receiver that sends and receives signals via the antenna 9111. The communication module 9110 (transmitter / receiver) is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.
[0309] Based on different communication technologies, multiple communication modules 9110 may be provided in the same electronic device, such as a cellular network module, a Bluetooth module and / or a wireless LAN module, etc. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide an audio output via the speaker 9131 and receive an audio input from the microphone 9132, thereby realizing a common telecommunication function. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processor 9100, so that recording can be performed on the local machine through the microphone 9132, and the sound stored on the local machine can be played through the speaker 9131.
[0310] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the joint simulation training system based on the Kylin operating system in the above embodiments, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, all the steps in the joint simulation training system based on the Kylin operating system in the above embodiments are implemented. For example, when the processor executes the computer program, the following steps are implemented:
[0311] Step S101: receiving real training data, inputting the real training data into the input layer of the preset training deployment model to perform data preprocessing operations on the real training data, determining corresponding real training features, inputting the real training features into the feature selection layer of the preset training deployment model to perform feature selection operations, determining corresponding selected features, performing feature integration operations on the selected features, inputting the integrated features after the feature integration operations into the output layer of the preset training deployment model, determining the training scheme output by the preset training deployment model, and transmitting the training scheme to the central service module;
[0312] Step S102: receiving the training scheme from the central service module, determining corresponding operation instructions according to the training scheme and preset parsing rules, and transmitting the operation instructions to the central service module;
[0313] Step S103: receiving the operation instruction from the central service module and displaying the operation instruction on the training hand interface, recording the data of the training hand executing the operation instruction, determining the corresponding operation result, and transmitting the operation result to the central service module.
[0314] Step S104: receiving the training program, the operation instruction and the operation result, and transmitting the training program, the operation instruction and the operation result to the corresponding instructor module, the control module and the shooter module according to a preset linkage rule.
[0315] From the above description, it can be seen that the computer-readable storage medium provided in the embodiment of the present application is used to receive real training data through the instructor module, input the real training data into the preset training deployment model, and determine the training plan output by the preset training deployment model; the control module is used to receive the training plan, determine the corresponding operation instructions according to the training plan and the preset parsing rules, the shooter module is used to receive the operation instructions and display the operation instructions on the training hand interface, record the data of the training hand executing the operation instructions, and determine the corresponding operation results; the central service module is used to receive the training plan, the operation instructions and the operation results, and transmit the training plan, the operation instructions and the operation results to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules, thereby improving the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage.
[0316] The embodiments of the present application also provide a computer program product capable of implementing all the steps in the joint simulation training system based on the Kylin operating system in the above embodiments, where the execution subject is a server or a client. When the computer program / instruction is executed by a processor, the steps of the joint simulation training system based on the Kylin operating system are implemented. For example, the computer program / instruction implements the following steps:
[0317] Step S101: receiving real training data, inputting the real training data into the input layer of the preset training deployment model to perform data preprocessing operations on the real training data, determining corresponding real training features, inputting the real training features into the feature selection layer of the preset training deployment model to perform feature selection operations, determining corresponding selected features, performing feature integration operations on the selected features, inputting the integrated features after the feature integration operations into the output layer of the preset training deployment model, determining the training scheme output by the preset training deployment model, and transmitting the training scheme to the central service module;
[0318] Step S102: receiving the training scheme from the central service module, determining corresponding operation instructions according to the training scheme and preset parsing rules, and transmitting the operation instructions to the central service module;
[0319] Step S103: receiving the operation instruction from the central service module and displaying the operation instruction on the training hand interface, recording the data of the training hand executing the operation instruction, determining the corresponding operation result, and transmitting the operation result to the central service module.
[0320] Step S104: receiving the training program, the operation instruction and the operation result, and transmitting the training program, the operation instruction and the operation result to the corresponding instructor module, the control module and the shooter module according to a preset linkage rule.
[0321] From the above description, it can be seen that the computer program product provided in the embodiment of the present application, through the instructor module, is used to receive real training data, input the real training data into a preset training deployment model, and determine the training plan output by the preset training deployment model; the control module is used to receive the training plan, determine the corresponding operation instructions according to the training plan and preset parsing rules, the shooter module is used to receive the operation instructions and display the operation instructions on the trainer interface, record the data of the trainer executing the operation instructions, and determine the corresponding operation results; the central service module is used to receive the training plan, the operation instructions and the operation results, and transmit the training plan, the operation instructions and the operation results to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules, thereby improving the accuracy and flexibility of the simulation training system based on artificial intelligence and internal networking linkage.
[0322] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0323] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0324] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0325] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0326] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. A joint simulation training system based on Kylin operating system, characterized in that: Applied to the Kylin operating system, the joint simulation training system includes an instructor module, a control module, a shooter module and a central service module, the central service module is respectively connected to the instructor module, the control module and the shooter module in communication, wherein the communication connection includes at least one of a UDP communication connection and a TCP communication connection; The instructor module is used to receive real training data, input the real training data into the input layer of the preset training deployment model to perform data preprocessing operations on the real training data, determine corresponding real training features, input the real training features into the feature selection layer of the preset training deployment model to perform feature selection operations, determine corresponding selected features, perform feature integration operations on the selected features, input the integrated features after the feature integration operations into the output layer of the preset training deployment model, determine the training plan output by the preset training deployment model, and transmit the training plan to the central service module; The control module is used to receive the training scheme from the central service module, determine the corresponding operation instruction according to the training scheme and the preset parsing rule, and transmit the operation instruction to the central service module; The shooter module is used to receive the operation instruction from the central service module and display the operation instruction on the training hand interface, record the data of the training hand executing the operation instruction, determine the corresponding operation result, and transmit the operation result to the central service module; The central service module is used to receive the training plan, the operation instruction and the operation result, and transmit the training plan, the operation instruction and the operation result to the corresponding instructor module, the control module and the shooter module according to the preset linkage rules.
2. The joint simulation training system based on Kylin operating system according to claim 1 is characterized in that: The instructor module includes a data input unit, a data processing unit and a data transmission unit; The data input unit is used to receive the real training data, input the real training data into the input layer of the preset training deployment model, perform feature extraction operation on the real training data, determine the corresponding training features, and determine the corresponding real training features according to the training features and the preset feature balancing algorithm, wherein the real training data includes at least one of the operator information and the operation result information transmitted from the central service module; The data processing unit is used to input the real training features into the decision tree feature selection layer and the regression tree feature selection layer of the preset training deployment model respectively to perform feature selection operations, determine corresponding decision tree selection features and regression tree selection features, perform feature integration operations on the decision tree selection features and the regression tree selection features, and determine corresponding integrated features; The data transmission unit is used to input the integrated features after the feature integration operation into the output layer of the preset training deployment model, determine the training plan output by the preset training deployment model, and transmit the training plan to the central service module.
3. The joint simulation training system based on Kylin operating system according to claim 2 is characterized in that: The data input unit comprises: A nearest neighbor feature determination subunit is used to perform a minority class recognition operation on the training feature according to a preset minority class recognition rule, and determine a corresponding nearest neighbor training feature according to the minority class training feature obtained after the minority class recognition operation and a preset K nearest neighbor algorithm; The real training feature determination subunit is used to perform a distance calculation operation on the minority class training feature and the nearest neighbor training feature to determine the corresponding training feature distance; determine the corresponding synthetic training feature according to the training feature distance and a preset ratio rule, and perform a feature addition operation on the training feature according to the synthetic training feature to determine the corresponding real training feature.
4. The joint simulation training system based on Kylin operating system according to claim 2 is characterized in that: The data processing unit comprises: A decision tree selection feature determination subunit, used for inputting the real training feature into the decision tree feature selection layer of the preset training deployment model to determine the corresponding decision tree selection feature according to the preset Gini impurity; A regression tree selection feature determination subunit, used for inputting the real training feature into the regression tree feature selection layer of the preset training deployment model to determine the corresponding regression tree selection feature according to a preset mean square error algorithm; The feature integration subunit is used to perform feature integration operations on the decision tree selection features and the regression tree selection features to determine corresponding integrated features.
5. The joint simulation training system based on Kylin operating system according to claim 4 is characterized in that: The feature integration subunit comprises: A decision tree prediction feature determination subunit, used to perform a recursive splitting operation on the decision tree selection feature to determine a corresponding decision tree prediction feature, wherein the decision tree prediction feature is used to predict a category label; A regression tree prediction feature determination subunit, used to perform a recursive splitting operation on the regression tree selection feature to determine a corresponding regression tree prediction feature, wherein the regression tree prediction feature is used to predict a continuous value; The integrated feature determination subunit is used to input the decision tree prediction feature and the regression tree prediction feature into a preset neural network for feature integration operation to determine the corresponding integrated feature.
6. The joint simulation training system based on Kylin operating system according to claim 2 is characterized in that: The data transmission unit comprises: A data activation subunit, used to input the integrated features after the feature integration operation into the output layer of the preset training deployment model, perform a feature output operation on the integrated features according to a preset activation function, and determine a training scheme output by the preset training deployment model; The data transmission subunit is used to transmit the training plan to the central service module according to a preset communication rule.
7. The joint simulation training system based on Kylin operating system according to claim 1 is characterized in that: The control module includes a self-checking unit, a communication unit and a parsing unit; The self-checking unit is used to perform a self-checking operation on the control module according to a preset self-checking rule, and determine whether there is a problem with the self-checking result. If not, the communication unit is activated; The communication unit is used to perform a registration operation on the central service module according to a preset communication rule, so that the control module can receive the training program from the central service module; The analysis unit is used to determine the corresponding training objectives and training steps according to the training plan and preset analysis rules, determine the corresponding operation instructions according to the training objectives, the training steps and preset process rules, and transmit the operation instructions to the central service module.
8. The joint simulation training system based on Kylin operating system according to claim 1 is characterized in that: The shooter module includes a self-checking unit, a communication unit and a recording unit; The self-checking unit is used to perform a self-checking operation on the shooter module according to a preset self-checking rule, and determine whether there is a problem with the self-checking result. If not, the communication unit is activated; The communication unit is used to perform a registration operation on the central service module according to a preset communication rule, so that the shooter module can receive the operation instruction from the central service module and display the operation instruction on the training hand interface; The recording unit is used to record the data of the operation instruction executed by the training hand according to the preset event-driven rules, determine the corresponding operation result, and transmit the operation result to the central service module.
9. The joint simulation training system based on Kylin operating system according to claim 1 is characterized in that: The central service module includes a first central service unit, a second central service unit and a third central service unit; The first central service unit is used to connect the instructor module according to a preset communication rule so that the central service module can receive the training program output by the instructor module; The second central service unit is used to connect the control module according to a preset communication rule, so that the central service module can send the received training program to the control module, and receive corresponding operation instructions, and send the operation instructions to the instructor module and the shooter module, wherein the operation instructions are output by the control module after receiving the training program; The third central service unit is used to connect the shooter module according to preset communication rules, so that the central service module can send the received operation instruction to the shooter module, receive the corresponding operation result, and send the operation result to the instructor module and the control module, wherein the operation result is output by the shooter module after receiving the operation instruction.
10. The joint simulation training system based on Kylin operating system according to claim 1 is characterized in that: The central service module also includes: The encryption unit is used to determine the corresponding encryption subclass interface according to the preset encryption algorithm; The startup unit is used to perform inheritance operation on the preset parent class interface and to start the central service module according to the encrypted subclass interface and the predefined protocol.
Citation Information
Patent Citations
Battle plan optimizing method based on military simulator
CN106952014A
Asthma diagnosis system based on decision tree and improved SMOTE algorithm
CN112951413A
Flight simulator intelligent training system, method and device
CN114373360A
Shooting simulation training method and system based on moving carrier
CN116558360A
Training system and control method for CIWS
KR102437045B1
