An environmental simulation system for training exercises

Abstract

The present invention relates to the technical field of teaching and training. The present invention discloses an environment simulation system for training exercises; it includes extracting request features from comprehensive input data, identifying the feature attributes of the request features, dividing the request features into environmental features and personality features, simulating a personalized exercise environment with the environmental features and personality features, calculating an environment simulation index, comparing the environment simulation index with an environment simulation safety value, and identifying abnormal points from the personalized exercise environment; compared with the prior art, the present invention can eliminate a large amount of useless data, narrow the scope of use of simulation data, meet the personalized special training exercise needs of the user side through the constructed personalized exercise environment, thereby improving the matching degree between the personalized exercise environment and the user side needs, achieving the effect of environmental simulation analysis and evaluation of the environment simulation system, and tracking and positioning the points with abnormalities according to the evaluation results.

Description

Technical Field

[0001] The present invention relates to the technical field of teaching and training, and more specifically, to an environment simulation system for training exercises. Background Art

[0002] As the requirements for training exercises by troops become increasingly strict, how to effectively improve the combat capabilities of troops and their abilities to respond to emergencies has become an urgent problem to be solved. At the same time, in order to reduce the input costs of training exercises and improve the convenience of training exercises, currently, an environment simulation system is usually used to simulate different environments of training exercises to meet the usage requirements of training exercises, thereby facilitating the training exercises of troops.

[0003] The patent application with the publication number CN116110266A discloses a training system and method based on multi-mode disaster environment linkage simulation, including a disaster scene simulation module for according to real coal mine data; a disaster setting module for calling the pre-stored environmental parameters of different disaster types; a disaster type judgment module for judging the current multiple disaster situations; a trigger module for according to the judged disaster type and the corresponding environmental parameters; a best rescue operation generation module for according to the final environmental parameters; and an exercise personnel operation module for, after receiving an alarm signal, the exercise personnel performing corresponding rescue operations.

[0004] When the existing environment simulation system simulates the training exercise environment, it usually analyzes all the requirements of the user's training exercises one by one and performs an overall simulation of all the user's requirements in an overall environment. For example, in the above patent application, it uses real coal mine data to perform a real simulation of the scene and the corresponding environmental parameters, so as to achieve a real overall simulation effect of the underground coal mine. Although the above method can achieve a real simulation effect of the training environment, the method of performing an overall unified simulation of all the training exercise requirements will result in the lack of pertinence of the simulated training exercise environment and cannot accurately simulate the special and personalized training exercise requirements of the user, thereby reducing the simulation effect of the training exercise environment.

[0005] In view of this, the present invention proposes an environment simulation system for training exercises to solve the above problems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above object, the present invention provides the following technical solution: An environment simulation system for training exercises, applied to an environment simulator, includes:

[0007] A feature extraction module for receiving the comprehensive input data from the user terminal and extracting the requested features from the comprehensive input data;

[0008] A feature classification module is used to identify the characteristic attributes of the request features, which include basic attributes and optimized attributes, and classify the request features into environmental features and individual features based on feature differentiation criteria;

[0009] The environment simulation module is used to simulate the basic exercise environment based on environmental characteristics, and optimize the basic exercise environment into a personalized exercise environment based on individual characteristics;

[0010] The data calculation module is used to collect comprehensive simulation data of the individual exercise environment under effective simulation conditions. The comprehensive simulation data includes the explosion point trigger delay value, the eruption rate difference, and the sound intensity difference, and calculate the environment simulation index;

[0011] A comparison and determination module is used to compare the environmental simulation index with the environmental simulation safety value and determine whether to perform an environmental anomaly tracking operation;

[0012] The point recognition module is used to identify optimized data from comprehensive simulation data and identify abnormal points from personalized exercise environments.

[0013] Furthermore, the method for extracting request features includes:

[0014] Identify the data semantics of the comprehensive input data one by one through natural language processing technology, and split the data semantics into text phrases and numeric phrases according to the different semantic types;

[0015] Record the data semantics that do not contain both text phrases and numeric phrases as useless semantics, and remove the comprehensive input data corresponding to the useless semantics;

[0016] Combining the text phrases and numeric phrases in the remaining comprehensive input data in sequence to generate comprehensive features;

[0017] The status values of the comprehensive features are queried one by one, and the comprehensive features with status values of 001, 010 or 100 are recorded as request features, thereby obtaining A request features.

[0018] Furthermore, the feature differentiation criteria are as follows: the text phrases of the environmental features must contain the standard phrases, and the numerical phrases must be less than or equal to the standard value;

[0019] Methods for dividing environmental characteristics and personality characteristics include:

[0020] Compare the text phrases in the A request features one by one with the standard phrases pre-stored in the database;

[0021] Record the request feature containing any standard phrase in the text phrase as the feature to be verified, and record the numeric phrase in the feature to be verified as the feature value, and obtain B feature values;

[0022] Mark out the literal parts of the standard values pre-stored in the database one by one, and record the standard values whose literal parts are consistent with the literal phrases in the feature to be verified as comparison values, obtaining B comparison values;

[0023] Record the features to be verified with feature values less than or equal to the comparison values as environmental features, obtaining C environmental features, and record the remaining request features and features to be verified as personality features, obtaining D personality features.

[0024] Furthermore, the simulation method of the basic exercise environment includes:

[0025] Identify the environmental semantics of the C environmental features one by one through natural language processing technology, and record the environmental features with environmental semantics of blast points, smoke, sound, and light as the first exercise element, the second exercise element, the third exercise element, and the fourth exercise element respectively;

[0026] Mark the simulation positions corresponding to blast points, smoke, sound, and light on the environmental simulator respectively, denoted as the first simulation position, the second simulation position, the third simulation position, and the fourth simulation position;

[0027] Adjust the simulation values of the first simulation position, the second simulation position, the third simulation position, and the fourth simulation position to be the same as the magnitudes of the feature values in the first exercise element, the second exercise element, the third exercise element, and the fourth exercise element respectively, obtaining the basic exercise environment.

[0028] Furthermore, the optimization method of the personality exercise environment includes:

[0029] Mark D independent optimization positions in the basic exercise environment, and sequentially number the D optimization positions in ascending order according to the marking sequence;

[0030] Establish two cells in each of the D optimization positions, denoted as the first cell and the second cell;

[0031] According to the order of numbers from small to large, note the same literal words as those in the literal phrases of the D personality features in the first cell of the D optimization positions, and note the same numerical phrases as those in the numerical phrases of the D personality features in the second cell of the D optimization positions, obtaining the D optimized optimization positions;

[0032] Establish interaction channels between adjacent optimized optimization positions, obtaining D - 1 interaction channels, and set simulation periods with the same duration on the D - 1 interaction channels to generate the personality exercise environment.

[0033] Furthermore, the method for obtaining the blast point trigger delay value includes:

[0034] Mark out E explosion points in the personalized exercise environment one by one, and record the moment when the human infrared sensor configured at the explosion point first receives the human infrared signal as the starting moment, obtaining E starting moments;

[0035] Query the moments when the E explosion points execute explosion operations one by one through the data concentrator, obtaining E explosion moments. Record the duration between the E starting moments and the E explosion moments as the trigger duration, obtaining E trigger durations;

[0036] After subtracting the E trigger durations from the preset standard duration respectively, obtain E sub-delay values. After removing the maximum and minimum values of the sub-delay values, accumulate and average the remaining E - 2 sub-delay values to obtain the explosion point trigger delay value;

[0037] The expression for the explosion point trigger delay value is:

[0038]

[0039] In the formula, ZD ys is the explosion point trigger delay value, CF sce is the e-th sub-delay value, BZ sc is the preset standard duration.

[0040] Furthermore, the method for obtaining the difference in eruption rate includes:

[0041] Mark out F smoke points in the personalized exercise environment one by one, and record the smoke ejectors configured at the smoke points as the target ejectors, obtaining F target ejectors;

[0042] In the order of marking, query the initial rates of the F target ejectors ejecting smoke one by one through the data concentrator, obtaining F real-time rates;

[0043] After subtracting the preset standard rate from the F real-time rates in sequence, obtain F sub-rate differences, and accumulate and average the F sub-rate differences to obtain the difference in eruption rate;

[0044] The expression for the difference in eruption rate is:

[0045]

[0046] In the formula, PF sl is the difference in eruption rate, BZ sl is the preset standard rate, SS slf is the f-th real-time rate.

[0047] Furthermore, the method for obtaining the difference in sound intensity includes:

[0048] Query the maximum decibel of the sound at E explosion points at E explosion times one by one through the data concentrator to obtain E real-time decibels;

[0049] Subtract the E real-time decibels from the preset standard decibel in sequence and take the absolute value to obtain E sub-intensity differences, and then accumulate and average the E sub-intensity differences to obtain the sound intensity difference;

[0050] The expression of the sound intensity difference is:

[0051]

[0052] In the formula, ST qd is the sound intensity difference, SS qde is the e-th real-time decibel, and BZ qd is the preset standard decibel.

[0053] Furthermore, the expression of the environment simulation index is:

[0054]

[0055] In the formula, MN zs is the environment simulation index, and ρ1, ρ2, and ρ3 are all proportionality coefficients greater than 0;

[0056] The determination method for whether to perform the environmental anomaly tracing operation includes:

[0057] Compare the environment simulation index MN zs with the environment simulation safety value MN aq ;

[0058] When MN zs is greater than or equal to MN aq , it is determined to perform the environmental anomaly tracing operation;

[0059] When MN zs is less than MN aq , it is determined not to perform the environmental anomaly tracing operation.

[0060] Furthermore, the method for identifying optimized data includes:

[0061] In the personalized exercise environment, record the trigger duration longer than the preset standard duration as the first abnormal data, and count the number of the first abnormal data to obtain the first abnormal value;

[0062] Record half of the number of trigger durations as the first safety value. When the first abnormal value is greater than the first safety value, record the blast point trigger delay value as the optimized data;

[0063] Record the real-time rate less than the preset standard rate as the second abnormal data, and count the number of the second abnormal data to obtain the second abnormal value;

[0064] Record half of the real-time rate quantity as the second safety value. When the second outlier is greater than the second safety value, record the eruption rate difference as the optimized data;

[0065] Record the real-time decibels less than or greater than the preset standard decibels as the third abnormal data, count the quantity of the third abnormal data, and obtain the third outlier;

[0066] Record half of the real-time decibel quantity as the third safety value. When the third outlier is greater than the third safety value, record the sound intensity difference as the optimized data.

[0067] The technical effects and advantages of an environment simulation system for training exercises of the present invention:

[0068] By receiving the comprehensive input data from the user terminal and extracting the request features from the comprehensive input data, the present invention can not only simplify and represent the complex and lengthy comprehensive input data, but also eliminate a large amount of useless data, narrow the scope of use of the simulation data. By identifying the feature attributes of the request features and based on the feature discrimination criteria, the request features are divided into environmental features and personality features. Taking the environmental features as the simulation standard, a basic exercise environment is simulated, and taking the personality features as the optimization standard, the basic exercise environment is optimized into a personalized exercise environment, so that the environmental features and personality features can respectively represent the conventional and personalized needs of training exercises, and the personalized special training exercise needs of the user terminal are met through the constructed personalized exercise environment, thereby improving the matching degree between the personalized exercise environment and the user terminal needs. Under the effective simulation state, the comprehensive simulation data of the personalized exercise environment is collected, and the environment simulation index is calculated. The environment simulation index is compared with the environment simulation safety value, and it is determined whether to perform the environment anomaly tracing operation. The optimized data is identified from the comprehensive simulation data, and the abnormal points are identified from the personalized exercise environment. Through the collection and calculation of the comprehensive simulation data, the stability and reliability of the personalized exercise environment can be accurately calculated, the effect of environmental simulation analysis and evaluation of the environment simulation system can be achieved, and the abnormal points are traced and located according to the evaluation results, thereby providing a basis for subsequent optimization and adjustment to improve the stability and reliability of the environment simulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 It is a schematic diagram of an environment simulation system for training exercises provided by Embodiment 1 of the present invention;

[0070] Figure 2 It is a schematic diagram of an environment simulation method for training exercises provided by Embodiment 2 of the present invention;

[0071] Figure 3A schematic structural diagram of an electronic device provided in a third embodiment of the present invention;

[0072] Figure 4 A schematic structural diagram of a computer-readable storage medium provided in accordance with a fourth embodiment of the present invention. DETAILED DESCRIPTION

[0073] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0074] Example 1: Please refer to Figure 1 As shown, the environmental simulation system for training exercises described in this embodiment is applied to an environmental simulator, including:

[0075] The feature extraction module receives the comprehensive input data from the user end and extracts the request features from the comprehensive input data;

[0076] The user end refers to the user who uses the environmental simulation system to conduct training exercises and can input raw user data into the environmental simulator. The raw user data at this time is recorded as comprehensive input data, which can be used to comprehensively represent all the training exercise data input by the user end to the environmental simulator. This also allows the comprehensive input data to serve as the data basis for subsequent simulations.

[0077] Request features refer to key information in the comprehensive input data that can affect the success of the training and exercise environment simulation. They can also accurately simplify the complex and lengthy comprehensive input data and serve as a reference for subsequent training and exercise environment simulation.

[0078] Methods for extracting request features include:

[0079] The data semantics of the comprehensive input data are identified one by one through natural language processing technology, and the data semantics are divided into text phrases and numeric phrases according to the different semantic types. Data semantics are used to concisely express the true meaning expressed in the comprehensive input data. Data semantics include but are not limited to multiple types of data such as text, numbers, and graphics. Text phrases and numeric phrases are the basic units of data semantics and are used to represent the text and numbers in the comprehensive input data.

[0080] Record the data semantics that do not contain both text phrases and numeric phrases as useless semantics, and remove the comprehensive input data corresponding to the useless semantics;

[0081] After sequentially combining the text phrases and numerical phrases in the remaining comprehensive input data, comprehensive features are generated.

[0082] The status values of the comprehensive features are queried one by one, and the comprehensive features with status values of 001, 010, or 100 are recorded as requested features, obtaining A requested features. The status value is a numerical representation of whether the comprehensive feature is of the requested type. Specifically, the status values include 001, 010, 100, 110, 101, and 011. Among them, when the status value is 110, 101, and 011, it indicates that the comprehensive feature is not a requested feature.

[0083] It should be noted that the obtained requested features are used to represent the direct features regarding the simulation of the training exercise environment in the comprehensive input data, enabling it to directly determine whether the training exercise environment can be successfully simulated. Therefore, the requested features at this time will include multi-dimensional and diverse data for simulating the training exercise environment, making the number of requested features not unique either.

[0084] The feature division module identifies the feature attributes of the requested features and, based on the feature discrimination criterion, divides the requested features into environmental features and individual features.

[0085] The feature attribute is a representation of the specific meaning that the requested feature represents in the simulation of the training exercise environment, which can effectively and accurately distinguish requested features with different meanings, so as to effectively distinguish the mixed requested features and facilitate the subsequent efficient and accurate simulation operation of the training exercise environment.

[0086] The feature attributes include basic attributes and optimization attributes; specifically, the basic attribute refers to the basic data for environmental simulation in the simulation of the training exercise environment by the requested feature, which is used to ensure that the framework of the training exercise environment can be initialized and simulated, and provides a basis for subsequent optimization and supplementation. The optimization attribute refers to the optimization data for environmental simulation in the simulation of the training exercise environment by the requested feature, which is used to ensure that the training exercise environment better meets the training exercise usage requirements of the user side and improves the pertinence of the training exercise environment.

[0087] After identifying the basic attributes and optimization attributes, it is necessary to distinguish the requested features according to different feature attributes, so that the requested features can be divided into environmental features and individual features. At this time, the environmental features are used to represent the basic framework of the training exercise environment, and the individual features are used to represent the user requirements of the training exercise environment.

[0088] To improve the accuracy of the division of environmental features and individual features, it is necessary to divide the requested features under the limitation of the feature discrimination criterion.

[0089] The feature differentiation criterion is as follows: the literal phrase of the environmental feature should contain the standard phrase, and the numerical phrase should be less than or equal to the standard value; this can ensure that the divided environmental features can meet the simulation requirements of the general and conventional training exercise environment, and thus ensure that the initial training exercise environment framework can be quickly simulated.

[0090] The methods for dividing environmental features and personality features include:

[0091] Compare each literal phrase in the A request features with the standard phrases pre-stored in the database one by one; the pre-stored standard phrases refer to the literal phrases corresponding to the environmental features pre-stored in the database, which serve as the basis for subsequent comparison of literal phrases.

[0092] Mark the request features whose literal phrases contain any one of the standard phrases as the features to be verified, and record the numerical phrases in the features to be verified as the feature values to obtain B feature values.

[0093] Mark the literal parts of the standard values pre-stored in the database one by one, and record the standard values whose literal parts are the same as the literal phrases in the features to be verified as the comparison values to obtain B comparison values; the pre-stored standard values refer to the numerical phrases corresponding to the environmental features pre-stored in the database, which serve as the basis for subsequent comparison of numerical phrases.

[0094] Mark the features to be verified whose feature values are less than or equal to the comparison values as environmental features to obtain C environmental features, and mark the remaining request features and features to be verified as personality features to obtain D personality features.

[0095] It should be noted that the sum of the numbers of environmental features and personality features is the number of request features, and the number of environmental features is usually greater than the number of personality features, which can not only ensure that the request features can be completely divided, but also ensure that there are sufficient environmental features to simulate the initial training exercise environment.

[0096] The environment simulation module, taking the environmental features as the simulation standard, simulates the basic exercise environment, and taking the personality features as the optimization standard, optimizes the basic exercise environment into a personalized exercise environment.

[0097] The basic exercise environment is a training exercise environment simulated according to the environmental features, so that the basic exercise environment can meet the other training exercise requirements of the user side except for personalized needs, and provide a good basis for the accurate simulation of the subsequent personalized exercise environment.

[0098] When simulating the basic exercise environment, it is necessary to be based on the environmental features so that the simulated basic exercise environment can match and adapt to the environmental features.

[0099] The simulation methods of the basic exercise environment include:

[0100] Use natural language processing technology to identify the environmental semantics of C environmental features one by one, and record the environmental features with environmental semantics of explosion points, smoke, sound, and light as the first exercise element, the second exercise element, the third exercise element, and the fourth exercise element respectively;

[0101] Mark the simulation positions corresponding to explosion points, smoke, sound, and light on the environmental simulator respectively, denoted as the first simulation position, the second simulation position, the third simulation position, and the fourth simulation position; the simulation position refers to the import position in the environmental simulator for the environmental features corresponding to the conventional training exercise requirements of the user side, which can ensure that the conventional training exercise requirements of the user side can be effectively simulated;

[0102] Adjust the simulation values of the first simulation position, the second simulation position, the third simulation position, and the fourth simulation position to be the same as the characteristic values in the first exercise element, the second exercise element, the third exercise element, and the fourth exercise element respectively, to obtain the basic exercise environment. The simulation value is used to represent the specific numerical size on the simulation position, which can represent the size and quantity of explosion points, smoke, sound, and light corresponding to the conventional training exercise requirements of the user side.

[0103] When the basic exercise environment is simulated, the current basic exercise environment can only represent the basic training exercise requirements of the user side and cannot meet the personalized training exercise requirements of the user side. Therefore, on the basis of the basic exercise environment, taking the personality characteristics as the optimization standard, the basic exercise environment needs to be optimized into a personalized exercise environment so that the personalized exercise environment can more accurately fit the real training exercise requirements of the user side;

[0104] The optimization method of the personalized exercise environment includes:

[0105] Mark D independent optimization positions in the basic exercise environment, and sequentially number the D optimization positions in ascending order according to the marking sequence; the optimization position refers to the import position in the environmental simulator for the personality characteristics corresponding to the personalized training exercise requirements of the user side, which can ensure that the personalized training exercise requirements of the user side can be effectively simulated;

[0106] Establish two cells in each of the D optimization positions, denoted as the first cell and the second cell;

[0107] In the first cell of the D optimization positions, note the same text phrases as those in the D personality characteristics in ascending order of the numbers, and in the second cell of the D optimization positions, note the same numerical phrases as those in the D personality characteristics, to obtain the optimized D optimization positions;

[0108] An interaction channel is established between two adjacent optimized positions to obtain D - 1 interaction channels, and simulation periods with the same duration are set on the D - 1 interaction channels to generate a personalized exercise environment. The interaction channel is used for data transmission between two adjacent optimized positions, which can ensure that the simulation data in the personalized exercise environment can flow mutually. The simulation period refers to the duration of data acquisition and analysis of the simulation data within the interaction channel, which can ensure that the personalized exercise environment can effectively simulate and operate and achieve the effect of timed data acquisition.

[0109] It should be noted that when the basic exercise environment is optimized into a personalized optimization environment, the personalized exercise environment at this time can meet the personalized training exercise requirements of the user side, ensuring that the user side can perform real and effective training exercise operations in the simulated personalized exercise environment.

[0110] The data calculation module, in the effective simulation state, collects the comprehensive simulation data of the personalized exercise environment and calculates the environmental simulation index; the comprehensive simulation data includes the blast point trigger delay value, the eruption rate difference, and the sound intensity difference.

[0111] The effective simulation state refers to the simulation state of the personalized exercise environment within the simulation period, ensuring that the relevant data in the personalized exercise environment at this time can be effectively collected and analyzed, avoiding phenomena such as omission and loss of relevant data, and ensuring the accuracy of the subsequent analysis of the simulation effect of the personalized exercise environment. On the contrary, when the personalized exercise environment is not within the simulation period, the relevant data in the personalized exercise environment at this time cannot be effectively and accurately collected.

[0112] The comprehensive simulation data is the relevant change data when the personalized exercise environment conducts training exercises in the effective simulation state, which can provide a basis for analyzing and evaluating the actual simulation stability and reliability of the personalized exercise environment, and thus is used to evaluate the simulation effect of the personalized exercise environment.

[0113] The comprehensive simulation data includes the blast point trigger delay value, the eruption rate difference, and the sound intensity difference.

[0114] The blast point trigger delay value refers to the difference between the duration from when the explosion point in the personalized exercise environment receives the trigger signal to when the explosion point executes the explosion operation and the standard duration, which can represent the blast point trigger time in the personalized exercise environment. When the blast point trigger delay value is larger, it indicates that the simulation stability of the personalized exercise environment is worse, and the environmental simulation index is larger.

[0115] The methods for obtaining the blast point trigger delay value include:

[0116] Mark out E explosion points in the personalized drill environment one by one, and record the moment when the human infrared sensor configured at the explosion point first receives the human infrared signal as the starting moment, obtaining E starting moments;

[0117] Query the moments of explosion operations for the E explosion points one by one through the data concentrator, obtaining E explosion moments. Record the duration between the E starting moments and the E explosion moments as the trigger duration, obtaining E trigger durations;

[0118] After subtracting the E trigger durations from the preset standard duration respectively, obtain E sub-delay values. After removing the maximum and minimum values of the sub-delay values, accumulate and average the remaining E - 2 sub-delay values to obtain the explosion point trigger delay value. The preset standard duration refers to the maximum value of the trigger duration in the personalized drill environment under high stability and high reliability conditions, so as to accurately determine the actual trigger duration size and improve the calculation accuracy of the explosion point trigger delay value;

[0119] The expression of the explosion point trigger delay value is:

[0120]

[0121] In the formula, ZD ys is the explosion point trigger delay value, CF sce is the e-th sub-delay value, BZ sc is the preset standard duration.

[0122] The difference in eruption rate refers to the difference between the rate of smoke eruption at the smoke point in the personalized drill environment and the standard rate, which can represent the eruption rate of the smoke point in the personalized drill environment. The larger the difference in eruption rate, the worse the simulation stability of the personalized drill environment, and the larger the environment simulation index;

[0123] The method for obtaining the difference in eruption rate includes:

[0124] Mark out F smoke points in the personalized drill environment one by one, and record the smoke ejectors configured at the smoke points as the target ejectors, obtaining F target ejectors;

[0125] In the marked order, query the initial rates of smoke eruption of the F target ejectors in sequence through the data concentrator, obtaining F real-time rates;

[0126] After subtracting the preset standard rate from the F real-time rates in sequence, obtain F sub-rate differences, and accumulate and average the F sub-rate differences to obtain the difference in eruption rate. The preset standard rate refers to the minimum value of the real-time rate in the personalized drill environment under high stability and high reliability conditions, so as to accurately determine the actual real-time rate size and improve the calculation accuracy of the difference in eruption rate;

[0127] The expression for the difference in eruption rate is:

[0128]

[0129] In the formula, PF sl is the difference in eruption rate, BZ sl is the preset standard rate, and SS slf is the f-th real-time rate.

[0130] The difference in sound intensity refers to the magnitude of the difference between the sound decibels emitted at the sonic boom point in the personalized drill environment and the standard decibels, which can represent the sound intensity in the personalized drill environment. The larger the difference in sound intensity, the worse the simulation stability of the personalized drill environment, and the larger the environmental simulation index;

[0131] The methods for obtaining the difference in sound intensity include:

[0132] Query the maximum sound decibels at E explosion points at E explosion times one by one through the data concentrator to obtain E real-time decibels;

[0133] Subtract the preset standard decibels from the E real-time decibels in sequence and take the absolute value to obtain E sub-intensity differences, and then accumulate and average the E sub-intensity differences to obtain the difference in sound intensity; the preset standard decibels refer to the constant value of the real-time decibels in the personalized drill environment under high stability and high reliability conditions, so as to accurately determine the actual real-time decibel magnitude and improve the calculation accuracy of the difference in sound intensity;

[0134] The expression for the difference in sound intensity is:

[0135]

[0136] In the formula, SY qd is the difference in sound intensity, SS qde is the e-th real-time decibel, and BZ qd is the preset standard decibel.

[0137] When the blast point trigger delay value, the difference in eruption rate, and the difference in sound intensity are obtained, the environmental simulation index can be calculated based on the blast point trigger delay value, the difference in eruption rate, and the difference in sound intensity at this time, so that the environmental simulation index can numerically represent the simulation stability and reliability of the personalized drill environment and be used as a basis for judging whether the personalized drill environment can meet the user's requirements for high stability and high reliability in training drills;

[0138] The expression for the environmental simulation index is:

[0139]

[0140] In the formula, MN zs is the environmental simulation index, and ρ1, ρ2, and ρ3 are all proportionality coefficients greater than 0;

[0141] Among them, ρ1 + ρ2 + ρ3 = 1. The settings of ρ1, ρ2, and ρ3 are to adjust the proportion of the blast point trigger delay value, the eruption rate difference, and the sound intensity difference in the environmental simulation index, so as to ensure that when the blast point trigger delay value, the eruption rate difference, and the sound intensity difference change, they can cause corresponding changes in the environmental simulation index, thereby improving the calculation accuracy of the environmental simulation index.

[0142] The comparison and determination module compares the environmental simulation index with the environmental simulation safety value and determines whether to perform the environmental anomaly tracing operation;

[0143] After calculating the environmental simulation index, the environmental simulation index can be compared with the preset environmental simulation safety value, and according to the comparison result, it is decided whether to perform the environmental anomaly tracing operation. The environmental anomaly tracing operation refers to the tracing operation of the data and factors that cause low stability and reliability in the case of poor stability and reliability in the personalized exercise environment, so as to achieve the abnormal tracking effect of the environmental simulation system;

[0144] The determination method of whether to perform the environmental anomaly tracing operation includes:

[0145] Compare the environmental simulation index MN zs with the environmental simulation safety value MN aq The environmental simulation safety value refers to the maximum value of the environmental simulation index in the personalized exercise environment under high stability and high reliability, which can provide a basis for comparing whether the real-time environmental simulation index is within the normal range, so as to accurately determine whether to perform the environmental anomaly tracing operation;

[0146] When MN zs is greater than or equal to MN aq it indicates that the environmental simulation index of the personalized exercise environment exceeds the maximum value of the environmental simulation index under high stability and high reliability. At this time, the stability and reliability of the personalized exercise environment have abnormal phenomena, and it is determined to perform the environmental anomaly tracing operation;

[0147] When MN zs is less than MN aq it indicates that the environmental simulation index of the personalized exercise environment does not exceed the maximum value of the environmental simulation index under high stability and high reliability. At this time, the stability and reliability of the personalized exercise environment do not have abnormal phenomena, and it is determined not to perform the environmental anomaly tracing operation.

[0148] The point location recognition module identifies optimized data from the comprehensive simulation data, and based on the optimized data, identifies abnormal point locations from the personalized exercise environment;

[0149] Optimized data refers to specific comprehensive simulation data that can have a negative impact on the high stability and high reliability of the personalized exercise environment, and serves as the basis for subsequent optimization and adjustment of the environment simulation system, thereby improving the simulation stability and reliability of the environment simulation system for the training exercise environment;

[0150] The methods for identifying optimized data include:

[0151] In the personalized exercise environment, the trigger duration greater than the preset standard duration is recorded as the first abnormal data, and the number of the first abnormal data is counted to obtain the first abnormal value;

[0152] Half of the number of trigger durations is recorded as the first safety value. When the first abnormal value is greater than the first safety value, it indicates that the number of trigger durations exceeding the preset standard duration is relatively large, and the blast point trigger delay value is recorded as optimized data;

[0153] The real-time rate less than the preset standard rate is recorded as the second abnormal data, and the number of the second abnormal data is counted to obtain the second abnormal value;

[0154] Half of the number of real-time rates is recorded as the second safety value. When the second abnormal value is greater than the second safety value, it indicates that the number of real-time rates lower than the preset standard rate is relatively large, and the eruption rate difference is recorded as optimized data;

[0155] The real-time decibel less than or greater than the preset standard decibel is recorded as the third abnormal data, and the number of the third abnormal data is counted to obtain the third abnormal value;

[0156] Half of the number of real-time decibels is recorded as the third safety value. When the third abnormal value is greater than the third safety value, it indicates that the number of real-time decibels greater than or less than the preset standard decibel is relatively large, and the sound intensity difference is recorded as optimized data.

[0157] An abnormal point location refers to an explosion point location or a smoke point location that causes low stability and reliability of the personalized exercise environment. At this time, the abnormal point location can be used as the corresponding point location for subsequent optimization and adjustment of the environment simulation system;

[0158] Specifically, when the optimized data is the detonation point trigger delay value, the abnormal points are concentratedly distributed on the detonation points. At this time, all detonation points with a trigger duration longer than the preset standard duration are recorded as abnormal points. When the optimized data is the eruption rate difference, the abnormal points are concentratedly distributed on the smoke points. At this time, all smoke points with a real-time rate less than the preset standard rate are recorded as abnormal points. When the optimized data is the sound intensity difference, the abnormal points are concentratedly distributed on the detonation points. At this time, all detonation points with a real-time decibel greater than or less than the preset standard decibel are recorded as abnormal points.

[0159] It should be noted that after identifying the abnormal points, corresponding optimization and adjustment operations need to be performed on the abnormal points to improve the stability and reliability of the environmental simulation system for the personalized exercise environment simulation of the user side. Exemplarily, when the optimized data is the detonation point trigger delay value, relevant devices such as the human infrared sensor and the detonation point controller on the abnormal points need to be repaired or replaced. When the optimized data is the eruption rate difference, relevant devices such as the smoke ejector on the abnormal points need to be repaired or replaced. When the optimized data is the sound intensity difference, the amount of explosives and the installation position of the explosives on the abnormal points need to be repaired or replaced.

[0160] In this embodiment, by receiving the comprehensive input data of the user side and extracting the request features from the comprehensive input data, it is possible to simplify the representation of the complex and lengthy comprehensive input data, and at the same time eliminate a large amount of useless data, narrowing the scope of use of the simulation data. By identifying the feature attributes of the request features and based on the feature discrimination criteria, the request features are divided into environmental features and personality features. Taking the environmental features as the simulation standard, a basic exercise environment is simulated, and taking the personality features as the optimization standard, the basic exercise environment is optimized into a personalized exercise environment, so that the environmental features and personality features can respectively represent the conventional and personalized needs of the training exercise, and the constructed personalized exercise environment is used to meet the personalized special training exercise needs of the user side, thereby improving the matching degree between the personalized exercise environment and the user side's needs. In the effective simulation state, the comprehensive simulation data of the personalized exercise environment is collected, and the environmental simulation index is calculated. The environmental simulation index is compared with the environmental simulation safety value to determine whether to perform the environmental anomaly tracking operation. The optimized data is identified from the comprehensive simulation data, and the abnormal points are identified from the personalized exercise environment. Through the collection and calculation of the comprehensive simulation data, the stability and reliability of the personalized exercise environment can be accurately calculated, achieving the effect of environmental simulation analysis and evaluation of the environmental simulation system, and tracking and positioning the abnormal points according to the evaluation results, thereby providing a basis for subsequent optimization and adjustment to improve the stability and reliability of the environmental simulation.

[0161] Embodiment 2: Please refer to Figure 2As shown, for the parts not described in detail in this embodiment, refer to the description in Embodiment 1. A method for simulating an environment for training exercises is provided, which is applied to an environment simulator and implemented based on an environment simulation system for training exercises, including:

[0162] S1: Receive the comprehensive input data from the user terminal and extract the request features from the comprehensive input data;

[0163] S2: Identify the feature attributes of the request features. The feature attributes include basic attributes and optimization attributes, and based on the feature discrimination criteria, divide the request features into environmental features and personality features;

[0164] S3: Use the environmental features as the simulation standard to simulate the basic exercise environment, and use the personality features as the optimization standard to optimize the basic exercise environment into a personalized exercise environment;

[0165] S4: Under the effective simulation state, collect the comprehensive simulation data of the personalized exercise environment. The comprehensive simulation data includes the detonation point trigger delay value, the eruption rate difference, and the sound intensity difference, and calculate the environment simulation index;

[0166] S5: Compare the environment simulation index with the environment simulation safety value and determine whether to perform the environment anomaly tracking operation;

[0167] S6: If the environment anomaly tracking operation is performed, identify the optimization data from the comprehensive simulation data and identify the abnormal points from the personalized exercise environment.

[0168] Embodiment 3: Please refer to Figure 3 As shown, this embodiment publicly provides an electronic device, including a processor and a memory;

[0169] Wherein, a computer program that can be called by the processor is stored in the memory;

[0170] The processor executes the implemented method for simulating an environment for training exercises by calling the computer program stored in the memory.

[0171] Since the electronic device introduced in this embodiment is the electronic device used to implement the method for simulating an environment for training exercises in Embodiment 2 of the present application, based on the method for simulating an environment for training exercises introduced in the embodiments of the present application, those skilled in the art can understand the specific implementation manners and various variations of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiments of the present application will not be described in detail here. As long as those skilled in the art implement the electronic device used in the method for simulating an environment for training exercises in the embodiments of the present application, it falls within the scope of protection of the present application.

[0172] Embodiment 4: Please refer toFigure 4 As shown, this embodiment discloses a computer-readable storage medium with a rewritable computer program stored thereon;

[0173] When the computer program is run, it implements the described environmental simulation method for training exercises.

[0174] As mentioned above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. An environmental simulation system for training exercises, applied to an environmental simulator, characterized in that, It includes: A feature extraction module, which is used to receive the comprehensive input data from the user side and extract the request features from the comprehensive input data; A feature division module, which is used to identify the feature attributes of the request features. The feature attributes include basic attributes and optimization attributes, and based on the feature discrimination criteria, divide the request features into environmental features and personality features; Feature discrimination criteria are as follows: the literal phrases of the environmental features should contain the standard phrases, and the numerical phrases should be less than or equal to the standard value; The division methods of environmental features and personality features include: Compare the literal phrases of A request features one by one with the standard phrases pre-stored in the database; Mark the request features whose literal phrases contain any standard phrase as the to-be-verified features, and mark the numerical phrases in the to-be-verified features as the feature values to obtain B feature values; Mark the literal parts of the standard values pre-stored in the database one by one, and mark the standard values whose literal parts are the same as the literal phrases in the to-be-verified features as the comparison values to obtain B comparison values; Mark the to-be-verified features whose feature values are less than or equal to the comparison values as environmental features to obtain C environmental features, and mark the remaining request features and to-be-verified features as personality features to obtain D personality features; An environment simulation module, which is used to simulate the basic exercise environment with the environmental features as the simulation standard, and optimize the basic exercise environment into a personalized exercise environment with the personality features as the optimization standard; A data calculation module, which is used to collect the comprehensive simulation data of the personalized exercise environment in the effective simulation state. The comprehensive simulation data includes the blast point trigger delay value, the eruption rate difference, and the sound intensity difference, and calculate the environment simulation index; The method for obtaining the blast point trigger delay value includes: Mark E explosion points in the personalized exercise environment one by one, and record the moment when the human body infrared sensor configured at the explosion point first receives the human body infrared signal as the starting moment to obtain E starting moments; Query the moments when E explosion points execute explosion operations one by one through the data concentrator to obtain E explosion moments, and record the duration between the E starting moments and the E explosion moments as the trigger duration to obtain E trigger durations; After subtracting the E trigger durations from the preset standard duration respectively, obtain E sub-delay values. After removing the maximum and minimum values of the sub-delay values, accumulate and average the remaining E - 2 sub-delay values to obtain the blast point trigger delay value; The method for obtaining the eruption rate difference includes: Mark F smoke points in the personalized exercise environment one by one, and mark the smoke ejectors configured at the smoke points as the target ejectors to obtain F target ejectors; In the marked order, query the initial rates of the F target ejectors ejecting smoke one by one through the data concentrator to obtain F real-time rates; After subtracting the preset standard rate from the F real-time rates in turn, obtain F sub-rate differences, and accumulate and average the F sub-rate differences to obtain the eruption rate difference; The method for obtaining the sound intensity difference includes: Query the maximum sound decibels of E explosion points at E explosion moments one by one through the data concentrator to obtain E real-time decibels; Subtract the absolute values of the E real-time decibel values from the preset standard decibel values to obtain E sub-intensity differences, and then accumulate and average the E sub-intensity differences to obtain the sound intensity difference; A comparison and determination module is used to compare the environmental simulation index with the environmental simulation safety value and determine whether to perform an environmental anomaly tracking operation; The point recognition module is used to identify optimized data from comprehensive simulation data and identify abnormal points from personalized exercise environments.

2. The environmental simulation system for training exercises according to claim 1, characterized in that Methods for extracting request features include: Identify the data semantics of the comprehensive input data one by one through natural language processing technology, and split the data semantics into text phrases and numeric phrases according to the different semantic types; Record the data semantics that do not contain both text phrases and numeric phrases as useless semantics, and remove the comprehensive input data corresponding to the useless semantics; Combining the text phrases and numeric phrases in the remaining comprehensive input data in sequence to generate comprehensive features; The status values of the comprehensive features are queried one by one, and the comprehensive features with status values of 001, 010 or 100 are recorded as request features, thereby obtaining A request features.

3. An environment simulation system for training exercises according to claim 2, characterized in that The simulation methods for the basic exercise environment include: The environmental semantics of C environmental features are identified one by one through natural language processing technology, and the environmental features with the environmental semantics of explosion point, smoke, sound and light are recorded as the first exercise element, the second exercise element, the third exercise element and the fourth exercise element respectively; On the environmental simulator, the simulation positions corresponding to the explosion point, smoke, sound, and light are marked respectively, and recorded as the first simulation position, the second simulation position, the third simulation position, and the fourth simulation position; The simulation values of the first simulation bit, the second simulation bit, the third simulation bit and the fourth simulation bit are adjusted to be consistent with the characteristic values of the first exercise element, the second exercise element, the third exercise element and the fourth exercise element respectively to obtain a basic exercise environment.

4. An environment simulation system for training exercises according to claim 3, characterized in that, Methods for optimizing the personalized practice environment include: Mark D independent optimization positions in the basic exercise environment, and number the D optimization positions in ascending order according to the order of marking; Create two cells in the D optimized positions respectively, and record them as the first cell and the second cell; In ascending order of numbering, the first cells of the D optimized positions are annotated with the same text as the text phrases in the D personality traits, and the second cells of the D optimized positions are annotated with the same numbers as the numeric phrases in the D personality traits, to obtain the optimized D optimized positions; An interactive channel is established between two adjacent optimized positions to obtain D-1 interactive channels, and simulation cycles with the same duration are set on the D-1 interactive channels to generate a personalized exercise environment.

5. An environment simulation system for training exercises according to claim 4, characterized in that, The expression of the explosion point trigger delay value is: Wherein, ZD ys is the detonation point trigger delay value, CF sce is the e-th sub-delay value, BZ sc is the preset standard duration.

6. The environmental simulation system for training exercises according to claim 5, wherein The expression for the difference in eruption rate is: Wherein, PF sl is the difference in eruption rate, BZ sl is the preset standard rate, and SS slf is the f-th real-time rate.

7. An environment simulation system for training exercises according to claim 6, characterized in that, The expression of the sound intensity difference is: Wherein, SY qd is the sound intensity difference, SS qde is the e-th real-time decibel, and BZ qd is the preset standard decibel.

8. An environment simulation system for training exercises according to claim 7, characterized in that, The expression of environmental simulation index is: where, MN zs is the environmental simulation index, and ρ1, ρ2, and ρ3 are all proportionality coefficients greater than 0; The determination method for whether to perform the environmental anomaly tracking operation includes: Compare the environmental simulation index MN zs with the environmental simulation safety value MN aq ; When MN zs is greater than or equal to MN aq it is determined to perform an abnormal trace operation on the execution environment; When MN zs is less than MN aq it is determined that the environmental anomaly tracing operation is not executed.

9. An environment simulation system for training exercises according to claim 8, characterized in that Identification methods for optimizing data include: In the personalized exercise environment, the trigger duration that is longer than the preset standard duration is recorded as the first abnormal data, and the number of the first abnormal data is counted to obtain the first abnormal value; Record half of the number of trigger durations as the first safety value. When the first outlier is greater than the first safety value, record the detonation point trigger delay value as the optimized data; Record the real-time rate that is less than the preset standard rate as the second abnormal data, count the number of the second abnormal data, and obtain the second outlier; Record half of the number of real-time rates as the second safety value. When the second outlier is greater than the second safety value, record the difference in eruption rates as the optimized data; Record the real-time decibel that is less than or greater than the preset standard decibel as the third abnormal data, count the number of the third abnormal data, and obtain the third outlier; Record half of the number of real-time decibels as the third safety value. When the third outlier is greater than the third safety value, record the difference in sound intensity as the optimized data.

Images