Value and reality-based weapon training scoring method and system

Abstract

The invention provides a scoring method and system for weapon equipment training based on virtuality and reality, and belongs to the technical field of weapon equipment training, and the method comprises the steps: obtaining multi-source data in a target training task executed by a student, the multi-source data comprises student operation behavior data, weapon equipment state data, virtual environment data and student physiological monitoring data; based on the multi-source data, calculating to obtain a basic capability score value; analyzing historical training data of the trainees on the same or similar target training tasks to generate ability development factors; acquiring historical norm data matched with the attributes of the trainees and the attributes of the target training tasks, and calculating group performance reference information based on the historical norm data; based on the basic ability score value and the group performance reference information, calculating to obtain a standardized relative performance score; and generating a comprehensive capability evaluation report based on the basic capability score value, the capability development factor and the standardized relative performance score. According to the invention, the scientificity and effectiveness of training evaluation can be improved.

Description

Technical Field

[0001] This application relates to the field of weapon and equipment training technology, and in particular to a scoring method and system for weapon and equipment training based on virtual and real-world conditions. Background Technology

[0002] In today's military training and related security fields, the operation of weapons and equipment is becoming increasingly complex, and their performance is constantly improving. Traditional live-fire training models face many challenges, such as: live-fire training requires the consumption of a large amount of weapons, equipment, ammunition, and related materials, resulting in high costs; there are certain safety risks during training, which can lead to personnel casualties and equipment damage; live-fire training is difficult to simulate various complex, extreme, and dangerous combat scenarios, and the scope of scenario coverage is limited. With the development of technologies such as virtual reality and augmented reality, training systems that integrate virtual and real-world elements are gradually becoming a core means of weapons and equipment skills training. However, existing weapons and equipment training assessment methods have significant shortcomings. On the one hand, most assessments rely on subjective scoring, which is greatly influenced by the experience and cognitive differences of the assessors, lacking objectivity and accuracy. On the other hand, some assessments rely solely on single operational data, failing to comprehensively reflect the trainees' true skill levels. Furthermore, due to differences in experience levels, age, and other attributes among trainees, as well as significant variations in the complexity of training tasks, the current lack of quantitative assessment standards that can dynamically adapt to different situations results in a serious deficiency in the scientific rigor and guidance of scoring. In addition, the existing assessment system fails to effectively analyze the development trajectory of individual trainees' abilities and their relative level within the group, greatly restricting the targeted development and optimization of training programs.

[0003] Therefore, there is a need for a scoring method and system for weapons and equipment training based on virtual and reality, in order to significantly improve the effectiveness of virtual and reality integrated training systems and provide scientific, accurate and comprehensive evaluation support for weapons and equipment training. Summary of the Invention

[0004] To address the aforementioned technical issues, this application provides a scoring method and system for weapons and equipment training based on virtual and real-world scenarios. Through multi-source data fusion analysis, it comprehensively, objectively, and accurately assesses trainees' performance in weapons and equipment training, resolving the problems of bias, subjectivity, lack of dynamic adaptation and individual development analysis in existing training scoring methods, and improving the scientificity and effectiveness of training evaluation.

[0005] A first aspect of this application provides a scoring method for weapon and equipment training based on virtual and real-world scenarios, comprising: Acquire multi-source data from trainees performing target training tasks, including: trainee operational behavior data, weapon and equipment status data, virtual environment data, and trainee physiological monitoring data; Based on the multi-source data, a basic ability score is calculated; Analyze the trainees' historical training data on the same or similar target training tasks to generate ability development factors; Obtain historical norm data that matches the attributes of the trainees and the attributes of the target training task, and calculate the group performance benchmark information based on the historical norm data; Based on the basic ability score and the group performance benchmark information, a standardized relative performance score is calculated. Based on the basic ability score, the ability development factor, and the standardized relative performance score, a comprehensive ability assessment report is generated.

[0006] Preferably, based on the multi-source data, a basic ability score is calculated, including: Based on the multi-source data and the trainees' levels, an initial ability score is calculated. The characteristics of the target emergency event are extracted from the virtual environment data; Based on the characteristics of the target emergency and the preset interference model, the target environmental interference factor is determined; Based on the target environment interference factor, the initial capability score is corrected to obtain the basic capability score.

[0007] Preferably, determining the target environmental interference factor based on the characteristics of the target emergency and a preset interference model includes: The characteristics of the target emergency event are analyzed to obtain the event type, intensity level, duration, and spatiotemporal correlation with the student's operation; The type of the emergency event is matched to a preset interference intensity benchmark value in a preset interference model; Based on the event type and intensity level, query the preset interference influence coefficient matrix to obtain the basic interference coefficient; Based on the duration and the spatiotemporal correlation, a correction factor is calculated based on preset rules. The target environment interference factor is obtained by weighting the preset interference intensity benchmark value, the basic interference coefficient, and the correction factor.

[0008] Preferably, the step of analyzing trainees' historical training data on the same or similar target training tasks to generate ability development factors includes: Based on the trainees’ historical training data, calculate the trainees’ historical average ability level and historical performance stability index on the same or similar target training tasks. Based on the historical average ability level and historical performance stability indicators, an ability development factor is generated.

[0009] Preferred scoring methods for weapons and equipment training based on virtual and real-world scenarios also include: Historical virtual environment data is extracted from the historical training data to obtain the characteristics of sudden events during the training process; Based on the characteristics of the sudden event and the preset environmental model, historical environmental interference factors are determined. Based on the historical environmental interference factors, the historical performance stability index is corrected to obtain the corrected historical performance stability index.

[0010] Preferably, the step of calculating the group performance benchmark information based on the historical norm data includes: Based on the trainees' experience level and age, and the task complexity of the target training task, a dataset matching the reference group is selected from the historical norm data. Statistical analysis was performed on the historical basic ability scores to calculate the group baseline statistics; The calculated population baseline statistics are weighted and adjusted based on the task complexity of the target training task attributes. The weighted and adjusted group baseline statistics are used as the group performance baseline information.

[0011] Preferably, the step of weighting and adjusting the calculated population baseline statistics based on the task complexity of the target training task attributes includes: Based on the task complexity level of the target training task, the corresponding set of weight coefficients is found from the mapping table; the set of weight coefficients includes independent weight coefficients of benchmark statistics for different types of groups. The adjusted population baseline statistic is obtained by weighting the corresponding population baseline statistic using the found weighting coefficients.

[0012] Preferably, the scoring method for weapon and equipment training based on virtual and real environments further includes: when the degree of change in the training scenario in the virtual environment data is greater than a first change threshold, and the basic capability score is less than a first scoring threshold, Based on the changing characteristics of the virtual environment data, calculate the scene adaptability parameters; Based on the analysis of strategy deviation and task completion effect of trainee operational behavior data, the strategy innovation effectiveness parameter is calculated. Based on the data on trainees' response speed and handling results to emergencies in the virtual environment, emergency response effectiveness parameters are calculated. The aforementioned scenario adaptability parameters, strategy innovation effectiveness parameters, and emergency response effectiveness parameters are integrated into an environmental capability correction factor. The basic capability score is corrected based on the environmental capability correction factor to generate an environmental capability score. The environmental capability score and specific capability analysis are incorporated into the comprehensive capability assessment report to supplement the basic capability assessment, optimize the analysis of personal development trends, and provide a basis for capability improvement in complex environments. The specific capability analysis includes dimensions of scenario adaptation, strategy innovation, and emergency response.

[0013] A second aspect of this application provides a scoring system for weapon and equipment training based on virtual and real-world scenarios, comprising: The data acquisition module is used to acquire multi-source data from trainees performing target training tasks. The multi-source data includes: trainee operation behavior data, weapon and equipment status data, virtual environment data, and trainee physiological monitoring data. The data calculation module is used to calculate the basic ability score based on the multi-source data; The data analysis module is used to analyze the trainees' historical training data on the same or similar target training tasks and generate ability development factors. The group information module is used to acquire historical norm data that matches the attributes of the trainees and the attributes of the target training task, and to calculate the group performance benchmark information based on the historical norm data. The comprehensive scoring module is used to calculate a standardized relative performance score based on the basic ability score and the group performance benchmark information. The assessment report module is used to generate a comprehensive ability assessment report based on the basic ability score, the ability development factor, and the standardized relative performance score.

[0014] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described scoring method for weapon and equipment training based on virtual and real-world conditions.

[0015] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned scoring system for weapon and equipment training based on virtual and real-world conditions.

[0016] The beneficial effects of the scoring method and system for weapons and equipment training based on virtual and real-world scenarios provided in this application are as follows: Firstly, by comprehensively collecting and analyzing multi-source data, this application can comprehensively and three-dimensionally assess trainees' abilities, significantly improving the comprehensiveness and accuracy of the assessment compared to traditional single-data-source assessment methods. Secondly, by dynamically adjusting the weight of basic ability scores for different task types and matching group norm data according to trainees and task attributes, the scoring system can flexibly adapt to various complex and changing training scenarios and individual differences, greatly improving the scientific nature and effectiveness of the scoring. Based on the above technical features, the application introduces capability development factors, deeply mining trainees' historical training data to clearly present the development trajectory and trends of trainees' abilities, providing strong support for the formulation of personalized training programs and helping trainees to improve their abilities in a targeted manner and achieve continuous capability development. Finally, based on the generated standardized relative performance score, the application represents the trainee's relative position within the group, providing trainees with a clear self-positioning and competitive reference, while also providing training managers with an objective and reliable basis for talent assessment, team building, and other decisions, promoting the rational allocation and efficient utilization of training resources. The comprehensive capability assessment report provided in this application offers multi-dimensional information that can provide trainees and training managers with comprehensive and in-depth training feedback. This helps to identify problems in training in a timely manner, optimize training strategies and methods, thereby significantly improving the overall effectiveness of weapons and equipment training and cultivating personnel with greater combat capabilities and comprehensive qualities. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a scoring method for weapon and equipment training based on virtual and real-world conditions, provided as an embodiment of this application; Figure 2 A structural block diagram of a scoring system for weapon and equipment training based on virtual and real-world scenarios provided in an embodiment of this application; Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0019] To make the purpose, technical solution, and advantages of this application clearer, the following will be described in conjunction with the appendix. Figure 1-3 The following is an explanation using specific examples.

[0020] Please refer to Figure 1 , Figure 1 A flowchart illustrating a scoring method for weapon and equipment training based on virtual and real-world scenarios, provided as an embodiment of this application, is shown below. The method includes: S101: Acquire multi-source data from trainees performing target training tasks. The multi-source data includes: trainee operational behavior data, weapon and equipment status data, virtual environment data, and trainee physiological monitoring data. In this embodiment, trainee operational behavior data includes the button sequence when operating weapons and equipment, the force applied to the handle, the continuity of operational actions, and the decision-making time during operation, such as the speed of making response decisions when facing emergencies. Weapon and equipment status data includes equipment operating parameters, such as engine speed, ammunition remaining, aiming accuracy error, and the wear and tear of various equipment components and fault warning information. Virtual environment data includes weather conditions, terrain features, the number, location, and movement trajectory of enemy targets in the virtual scene. Trainee physiological monitoring data is collected through specialized equipment, including heart rate, blood pressure, respiratory rate, and electroencephalogram (EEG) responses, which can characterize the trainee's psychological state, such as tension and concentration, during training.

[0021] S102: Based on multi-source data, a basic ability score is calculated; the basic ability score is used to evaluate the degree of matching between the trainee's operational behavior and the training objective in the target training task. The weight of the basic ability score is set based on the correctness of operation, task efficiency and operation safety, and the weight allocation is adjusted according to the task type. In this embodiment, the basic ability score is used to evaluate the degree of matching between the trainee's operational behavior and the training objectives.

[0022] Operational correctness is assessed by comparing trainees' actions with standard operating procedures and calculating the percentage of correct steps. For example, in the activation process of weapons and equipment, points are awarded for each correct step, while points are deducted for errors. Task efficiency is evaluated based on completion time and resource consumption; shorter completion time and less resource consumption result in higher scores. Operational safety is assessed by checking for any violations and potential risks to equipment and personnel. No safety hazards result in full marks, minor risks result in appropriate point deductions, and serious safety hazards result in significant point deductions. The weights of the basic capability score in this embodiment need to be set based on operational correctness, task efficiency, and operational safety. For example, for high-precision operational tasks, the weight of operational correctness is set at 50%, operational safety at 30%, and task efficiency at 20%; for emergency combat training, the weights of task efficiency, operational correctness, and operational safety are set at 40%. Furthermore, the weight allocation will be adjusted according to different task types to adapt to the needs of different training objectives.

[0023] S103: Analyze the trainees' historical training data on the same or similar target training tasks to generate ability development factors; ability development factors are used to characterize the historical trend of trainees' abilities. In this embodiment, in-depth analysis of trainees' historical training data on the same or similar target training tasks is conducted to generate a capability development factor that clearly characterizes the historical trend of trainees' abilities. The analysis dimensions include multiple aspects: in terms of operational correctness, whether the error rate of operational steps in historical training has gradually decreased; in terms of task efficiency, whether the time to complete the task has gradually shortened and whether resource consumption has continuously decreased; and in terms of operational safety, whether the number of violations and the risk level show a downward trend. This embodiment also analyzes whether trainees' coping abilities when facing the same or similar emergencies have improved, such as whether decision-making time has shortened and whether coping measures are more effective. This embodiment generates specific capability development factor values ​​through long-term data tracking and fitting analysis of the above dimensions. For example, if the capability development factor value is greater than 1, it indicates that the trainee's ability is on the rise; the larger the value, the more significant the progress. If the value is less than 1, it indicates that the ability is declining or stagnating.

[0024] S104: Obtain historical norm data that matches the attributes of trainees and the attributes of the target training task, and calculate the group performance benchmark information based on the historical norm data; In this embodiment, precise filtering is required when acquiring historical norm data that matches student attributes and target training task attributes. Student experience levels can be categorized as novice, beginner, intermediate, advanced, and expert, with varying performance across different experience levels. Age is considered to account for the reaction speed, physical strength, and other characteristics of students at different age levels. Target training task attributes are categorized by task complexity based on the number of objectives, frequency of environmental changes, and the complexity of operational steps. Based on the filtered historical norm data, baseline performance information for the group is calculated, including the group's average basic ability score, average level of operational correctness, average task efficiency, and average performance in operational safety.

[0025] S105: Based on the basic ability score and the group performance benchmark information, the standardized relative performance score is calculated; the attributes of the trainees include experience level and age, and the attributes of the target training task include the task complexity of the target training task. In this embodiment, the calculation of the standardized relative performance score (SRS) is a crucial step in comparing a trainee's individual performance with that of the group. Specifically, based on the difference between the basic ability score and the group performance benchmark, the basic ability score is converted into a standardized score using a formula (standard deviation method). For example, if a trainee's basic ability score is higher than the group average, and the excess is 1.5 times the group standard deviation, assuming a maximum score of 100, then their SRS would be 85. Further adjustments are made based on factors such as the trainee's experience level, age, and task complexity. For instance, for younger trainees with lower experience levels, if their performance on complex tasks is close to the group average, their SRS would be appropriately increased to reflect their potential.

[0026] S106: Generate a comprehensive ability assessment report based on the basic ability score, ability development factor, and standardized relative performance score; the comprehensive ability assessment report includes: basic ability assessment, personal development trend analysis, group relative positioning, and comprehensive ability conclusion.

[0027] In this embodiment, the comprehensive capability assessment report is a complete summary of the trainee's training performance. The basic capability assessment section details the trainee's specific scores and performance in three areas: operational correctness, task efficiency, and operational safety. It points out the trainee's strengths and weaknesses during operation. For example, regarding operational correctness, the correct completion rate of the weapon and equipment activation procedure is 90%, but there were multiple deviations in the aiming operation. The individual development trend analysis uses charts and other forms to display the trainee's historical changes in ability, and analyzes the reasons for progress or regression based on capability development factors. For example, compared with the previous three training sessions, the trainee has significantly improved task efficiency, mainly due to the reduction in decision-making time, and the capability development factor is 1.2, showing a good upward trend. The group relative positioning clarifies the trainee's position within a group of similar attributes. For example, in training with the same task complexity, the trainee's standardized relative performance score is in the top 30% of the group, better than most trainees of the same experience level. The comprehensive ability conclusion integrates the above analyses and provides an overall assessment of the trainee's abilities, including their strengths in the current training task, areas for improvement, and future training suggestions. For example, the trainee has strong comprehensive abilities and outstanding performance in operational safety, but there is still room for improvement in task efficiency. It is recommended to strengthen training in rapid decision-making in complex environments. This application, through the aforementioned comprehensive and detailed scoring methods, can provide a scientific evaluation basis for weapons and equipment training, helping trainees to improve their capabilities in a targeted manner and enhance the overall training quality.

[0028] As can be seen from the above, this application, through the comprehensive collection and analysis of multi-source data, can comprehensively and three-dimensionally assess trainees' abilities, significantly improving the comprehensiveness and accuracy of the assessment compared to traditional assessment methods based on a single data source. Secondly, by dynamically adjusting the weight of basic ability scores for different task types and matching group norm data according to trainees and task attributes, the scoring system can flexibly adapt to various complex and changing training scenarios and individual differences, greatly enhancing the scientific validity and effectiveness of the scoring. Based on the above technical features, the introduction of ability development factors deeply mines trainees' historical training data, clearly presenting the development trajectory and trends of trainees' abilities, providing strong support for the formulation of personalized training programs, and helping trainees to improve their abilities in a targeted manner and achieve continuous development. Finally, based on the generated standardized relative performance scores, the relative position of trainees within the group is represented, providing trainees with a clear self-positioning and competitive reference, while also providing training managers with an objective and reliable basis for talent assessment, team building, and other decisions, promoting the rational allocation and efficient utilization of training resources. The comprehensive capability assessment report provided in this application offers multi-dimensional information that can provide trainees and training managers with comprehensive and in-depth training feedback. This helps to identify problems in training in a timely manner, optimize training strategies and methods, thereby significantly improving the overall effectiveness of weapons and equipment training and cultivating personnel with greater combat capabilities and comprehensive qualities.

[0029] In one embodiment of this application, a basic ability score is calculated based on multi-source data, including: Based on multi-source data and the trainees' levels, an initial ability score is calculated. The characteristics of the target emergency event are extracted from the virtual environment data; Determine the target environment interference factors based on the characteristics of the target emergency and the pre-set interference model; Based on the target environment interference factor, the initial capability score is corrected to obtain the basic capability score.

[0030] In this embodiment, the process of calculating the basic capability score based on multi-source data is a dynamic evaluation process that combines individual trainee characteristics with environmental interference factors. Specifically, the initial capability score is calculated based on multi-source data and the trainee's level differences to ensure the relevance and accuracy of the assessment. When calculating the initial capability score, key indicators related to operational correctness, task efficiency, and operational safety are extracted from the multi-source data. For example, regarding operational correctness, the standard for novice trainees focuses on the completion rate of basic operational steps, while advanced trainees are assessed on the precision of complex tactical maneuvers. Regarding task efficiency, the assessment focus for junior trainees is the percentage of basic tasks completed within a specified time, while expert trainees need to consider both task completion speed and resource optimization (e.g., achieving the operational objective with minimal ammunition consumption in multi-target strike missions). Operational safety indicators are adjusted according to the level; novice trainees primarily focus on the existence of fatal operational errors, while advanced trainees need to be assessed on their risk prediction ability under high-pressure environments. This embodiment calculates the initial capability score by comparing the trainee's actual operational data with the standard indicators for the corresponding level and using a weighted summation method.

[0031] This embodiment targets unforeseen events including sudden malfunctions in the virtual scenario, enemy attacks, environmental changes, and temporary adjustments to task parameters. During feature extraction, this embodiment will label events from multiple dimensions. The event type needs to be clearly identified as a technical malfunction, tactical attack, environmental interference, or task change. The intensity level is categorized as minor, moderate, or severe based on the event's impact on the task. The triggering timing needs to record the task progress at the time of the event and its correlation with the trainee's current actions. Furthermore, features such as the event's duration and scope of impact will be extracted. The interference model preset in this embodiment is a quantitative analysis model built based on historical training data. Its core function is to transform the characteristics of the target sudden event into environmental interference factors that can be directly used for score correction. The model is built based on the student performance data under the sudden event and can use machine learning algorithms to explore the correlation between event characteristics and ability score deviations, such as random forests and neural networks. For example, for a moderate-intensity enemy surprise attack, the interference model analyzes the impact of the event on trainees' operations at different mission stages: if triggered at the beginning of the mission, it will disrupt trainees' mission planning and reduce operational efficiency by 20%, corresponding to an interference factor of 0.8; if triggered at the end of the mission, trainees have established a stable tactical rhythm, and the efficiency reduction is reduced to 5%, with an interference factor of 0.95. For severe technical malfunction events, regardless of the timing of the trigger, they will significantly affect operational correctness, with an interference factor of 0.6. However, for advanced trainees, due to their extensive experience in troubleshooting, the interference factor can be adjusted to 0.75. In actual calculations, the extracted features of the target sudden events are input into a preset interference model, and the corresponding interference coefficients are output. If multiple sudden events occur simultaneously in a training task, a weighted summation is used to calculate the comprehensive interference factor, with the weights allocated according to the intensity of the events' impact. For example, if a moderate environmental mutation (e.g., interference factor 0.85, weight 60%) and a minor tactical raid (e.g., interference factor 0.92, weight 40%) occur simultaneously, the comprehensive interference factor is 0.85 × 60% + 0.92 × 40% = 0.878. In this embodiment, the basic ability score is the result of correcting the initial ability score by the target environmental interference factor. The calculation formula is: the basic ability score is the product of the initial ability score and the target environmental interference factor. This correction process in this embodiment is used to eliminate the influence of environmental differences on ability assessment, more accurately reflecting the trainee's actual operational level. For example, a junior cadet's initial ability score in mountain warfare training is 75 points. If he encounters a severe environmental change (interference factor 0.7) during the training, his basic ability score will be 52.5 points. This score objectively reflects the cadet's adaptability in extreme environments. If another cadet of the same level has an initial score of 70 points in the same mission without any unexpected events, his basic ability score will also be 70 points. Comparing the two, it can be found that although the former has a higher initial score, his actual performance is slightly inferior to the latter due to the influence of environmental interference. This embodiment uses a dynamic correction mechanism to ensure that the basic ability score reflects both the trainee's basic abilities in standardized scenarios and their adaptability in complex and unexpected environments, providing a more accurate basis for subsequent comprehensive assessment.

[0032] In one embodiment of this application, determining the target environmental interference factor based on the characteristics of the target sudden event and a preset interference model includes: The characteristics of the target emergency event are analyzed to obtain the event type, intensity level, duration, and spatiotemporal correlation with the trainee's operation; Match the type of emergency event to the preset interference intensity benchmark value in the preset interference model; Based on the event type and intensity level, query the preset interference impact coefficient matrix to obtain the basic interference coefficient; Based on the duration and spatiotemporal correlation, a correction factor is calculated based on preset rules. The target environment interference factor is obtained by weighting the preset interference intensity benchmark value, the basic interference coefficient, and the correction factor.

[0033] In this embodiment, the preset interference model sets corresponding preset interference intensity benchmark values ​​for different event types. These benchmark values ​​are derived from a large amount of historical data and reflect the average interference level of that type of event on training. For example, the benchmark values ​​for technical failure events are generally low, with a benchmark value of 0.85 for sensor failure and 0.6 for power system failure; the benchmark values ​​for tactical confrontation events are generally low, with a benchmark value of 0.7 for enemy ambush and 0.55 for enemy reinforcement raid; for environmental interference, the benchmark value for heavy rain is 0.8 and for sandstorm is 0.65; for mission change, the benchmark value for target priority adjustment is 0.88 and for mission area expansion is 0.75. By accurately matching the parsed sudden event types with the types in the preset interference model, the corresponding preset interference intensity benchmark values ​​can be obtained. In this embodiment, the preset interference impact coefficient matrix is ​​a two-dimensional matrix constructed based on event type and intensity level. The values ​​in the matrix represent the degree of interference impact under different combinations; the smaller the value, the greater the interference impact. Based on the parsed event type and intensity level, a precise lookup in the matrix yields the corresponding basic interference coefficient. In this embodiment, the calculation of the correction factor requires quantification based on duration, spatiotemporal correlation, and preset rules. Among these preset rules, duration is negatively correlated with the correction factor; that is, the longer the duration, the smaller the correction factor. The final value of the correction factor is obtained by multiplying the duration correction coefficient and the spatiotemporal correlation correction coefficient. The target environment interference factor is calculated using a weighted summation method, where the weights of the preset interference intensity benchmark value, the basic interference coefficient, and the correction factor are set based on expert experience.

[0034] This embodiment uses the weighted calculation described above to enable the target environment interference factor to more accurately reflect the actual degree of interference of sudden events on training, providing a reliable basis for the correction of basic ability scores, and making the final score result more in line with the trainees' real ability level in complex environments.

[0035] In one embodiment of this application, the scoring method for weapon and equipment training based on virtual and real-world scenarios further includes: after calculating the basic capability score, correcting the basic capability score, including: Calculate the historical average ability level based on the trainees' historical training data; Calculate the difference between the basic ability score and the historical average ability level; The basic ability score is corrected based on the difference indicators to generate the corrected basic ability score.

[0036] In this embodiment, after calculating the basic ability score, it is corrected based on the student's historical training data. This eliminates the influence of accidental factors in a single training session and more objectively reflects the student's true ability level. The calculation of historical average ability levels requires a foundation of trainees' historical training data on the same or similar target training tasks, with time decay applied to the historical training data. Recent training data better reflects the trainees' current ability status and is therefore given higher weight, while older data is given lower weight. In addition, for new trainees (with insufficient historical data), the initial average ability level of a group with similar attributes (same experience level, age) can be used as a substitute value to ensure the completeness of the correction process.

[0037] In this embodiment, the difference index is used to quantify the degree of deviation between the current basic ability score and the historical average ability level. The calculation formula is: Difference index = (current basic ability score - historical average ability level) / historical average ability level × 100%. For example, if the current basic ability score is 85 points and the historical average ability level is 79.4 points, then the difference index = (85-79.4) / 79.4×100%≈7.05%, indicating that the current performance is better than the historical average. If the current score is 70 points, then the difference index = (70-79.4) / 79.4×100%≈-11.84%, indicating that the current performance is lower than the historical average. The absolute value of the difference index reflects the degree of deviation; a positive number indicates progress, and a negative number indicates regression, providing a clear direction and magnitude for subsequent adjustments. This embodiment corrects the current basic ability score based on the difference index. The correction principle is as follows: when the absolute value of the difference index exceeds the preset fluctuation threshold, a moderate pullback is performed to reduce the impact of random factors in a single training session; if it is within the threshold range, the original score remains unchanged. The revised basic ability score in this embodiment will serve as the core data for subsequent calculation of standardized relative performance scores and generation of comprehensive ability assessment reports. Its advantages include reducing the randomness of a single training session, making the score more closely reflect the learner's long-term ability trends, for example, avoiding overestimation of a learner's ability due to a single exceptional performance; secondly, providing a more stable benchmark for individual development trend analysis, clearly presenting the learner's true ability fluctuations by comparing score changes before and after revision; and in group relative positioning, the revised score can more accurately reflect the learner's actual position within the group, avoiding positioning bias caused by accidental factors. Simultaneously, the comprehensive ability assessment report must indicate the revision process and reasons to ensure the transparency and interpretability of the assessment.

[0038] This embodiment, through a correction process, enables the basic ability score to retain information on individual training performance while incorporating historical ability trends, thus providing a more reliable quantitative basis for comprehensive ability assessment.

[0039] In one embodiment of this application, the basic ability score is corrected based on the difference index to generate a corrected basic ability score, including: When the difference index is greater than or equal to the first difference threshold, the basic ability score is adjusted upward, and the adjustment range increases with the difference index. When the difference index is less than or equal to the second difference threshold, the basic ability score is adjusted downward, and the adjustment range decreases as the difference index decreases. When the difference index is greater than the second difference threshold but less than the first difference threshold, the basic ability score remains unchanged; where the first difference threshold is greater than the second difference threshold.

[0040] In this embodiment, when correcting the basic ability score based on the difference index, a first difference threshold and a second difference threshold are set to clarify the correction rules for different intervals, making the correction process more targeted and logical. The first and second difference thresholds are set based on the stability requirements of the training task and historical data on student ability fluctuations, with the first difference threshold being greater than the second difference threshold. Furthermore, the settings of the first and second thresholds can be adjusted according to the task type; for example, for tasks requiring high precision, the first difference threshold can be lowered by adjusting the first step length, and the second difference threshold can be increased by adjusting the first step length. In this embodiment, when the difference index is greater than or equal to the first difference threshold, it indicates that the student's current performance is significantly better than the historical average level. The basic ability score needs to be revised upward, and the revision range increases with the increase of the difference index to reflect the student's breakthrough performance. The correction formula is: Corrected basic ability score = Current basic ability score × (1 + (Difference index - First difference threshold) × Upward correction coefficient). The upward correction coefficient is set according to the task type. For example, if the first difference threshold for a routine task is 15%, the upward correction coefficient is 0.5. In this embodiment, when the difference index is less than or equal to the second difference threshold, it indicates that the student's current performance is significantly lower than the historical average level, and the basic ability score needs to be corrected downward. The correction range increases as the difference index decreases to reflect the student's decline in ability. The correction formula is: Corrected basic ability score = Current basic ability score × (1 + (Difference index - Second difference threshold) × Downward correction coefficient); where the downward correction coefficient is a negative number. In this embodiment, when the difference index is greater than the second difference threshold but less than the first difference threshold, it indicates that the student's current performance is within the normal fluctuation range of the historical average level, and no correction is required; the basic ability score remains unchanged. The basic ability score obtained through the above-described correction method in this embodiment can accurately identify students' breakthrough progress and significant regression. By making upward and downward corrections, it more realistically reflects the significant changes in students' abilities. The correction range is positively correlated with the difference index, avoiding over-correction or under-correction, making the score more reasonable. Keeping the score unchanged within the normal fluctuation range reduces unnecessary corrections and ensures the stability of the score. In one embodiment of this application, analyzing historical training data of trainees on the same or similar target training tasks to generate ability development factors includes: Based on the trainees’ historical training data, calculate the trainees’ historical average ability level and historical performance stability index on the same or similar target training tasks. Based on historical average ability levels and historical performance stability indicators, an ability development factor is generated; the ability development factor is used to characterize the progress or decline trend of trainees' abilities.

[0041] In this embodiment, the historical average ability level is a benchmark value reflecting the trainee's long-term performance on the same or similar tasks. The calculation requires combining basic ability scores from multiple training sessions and considering the weight of training time. Recent training data better reflects the trainee's current ability status and is therefore given higher weight, while older data has lower weight. Furthermore, subdivided average levels can be calculated based on ability dimensions, such as historical average operation accuracy and historical average task completion efficiency. The historical performance stability index in this embodiment measures the degree of fluctuation in a student's ability; the smaller the fluctuation, the more stable the student's ability. Commonly used stability indicators include standard deviation, coefficient of variation, and range. Standard deviation is calculated by measuring the deviation of multiple basic ability scores from the historical average ability level; the smaller the standard deviation, the more stable the student's performance. The coefficient of variation is the ratio of the standard deviation to the historical average ability level, used to eliminate the influence of absolute scores and facilitate comparisons of stability among different students or different task types. The smaller the coefficient of variation, the higher the stability. The range is the difference between the highest and lowest scores in multiple assessments; the smaller the range, the better the stability. The ability development factor in this embodiment is used to characterize the historical average ability level and historical performance stability index. It is calculated by weighting and its value directly reflects the progress or decline trend of the trainee's ability.

[0042] When calculating the capability development factor, the weighting of the historical average capability level change trend and the weighting of the historical performance stability index are derived from experience and will not be elaborated here.

[0043] The ability development factor in this embodiment can not only clearly characterize the historical trend of trainees' abilities, but also provide a longitudinal comparison basis for comprehensive ability assessment, helping coaches to develop targeted follow-up training plans and promote the continuous improvement of trainees' abilities.

[0044] In one embodiment of this application, the scoring method for weapon training based on virtual and real-world methods further includes: Historical virtual environment data is extracted from historical training data to obtain the characteristics of sudden events during the training process; the characteristics of sudden events include: sudden event type encoding, sudden event spatiotemporal distribution parameters, and sudden event intensity level; Historical environmental disturbance factors are determined based on the characteristics of emergencies and a pre-set environmental model. Based on historical environmental interference factors, the historical performance stability index is modified to obtain the modified historical performance stability index. The weighting coefficient of the historical environmental interference factor is determined according to the task type.

[0045] In this embodiment, the emergency event type encoding adopts a digital encoding system, dividing common emergencies into multiple major categories and subcategories. Encoding allows for rapid identification of event types, facilitating subsequent matching with the environment model. The spatiotemporal distribution parameters of the emergency events include the time node and spatial location of the event. The time node is recorded as the number of minutes since the start of the training task, and the percentage of the task phase is indicated. The spatial location is quantified using the coordinate system of the virtual scene, simultaneously calculating the straight-line distance and relative orientation to the trainee's current operating position. These spatiotemporal distribution parameters reflect the immediate impact and timing of the event on the trainee's operations. The intensity level of emergencies is based on the original five-level classification (weak, minor, moderate, severe, and extreme), and is assigned a corresponding quantitative value. The higher the quantitative value, the greater the interference of the event on training.

[0046] In this embodiment, the preset environment model is a quantitative model trained on a large amount of historical data. It can calculate the corresponding historical environment interference factor based on the characteristics of sudden events. The smaller the value, the stronger the interference of the historical environment on the trainees' performance. The core of the model is to establish a mapping relationship between the characteristics of sudden events and the degree of interference. The specific calculation steps are as follows: matching the basic interference coefficient according to the type of sudden event; different types of events have different basic interference capabilities; secondly, adjusting the basic interference coefficient based on the intensity level of the sudden event; finally, introducing the spatiotemporal distribution parameters of the sudden event for correction to obtain the historical environment interference factor.

[0047] The initial calculation of the historical performance stability index did not consider differences in environmental interference, which could lead to misjudgments of trainees' capability stability. Therefore, it is necessary to correct it based on historical environmental interference factors, including: determining the weighting coefficients of historical environmental interference factors, where the weighting coefficients are set according to the environmental sensitivity of the mission type. For missions with strong environmental dependence (such as reconnaissance in complex terrain and combat in adverse weather), the weighting coefficients of historical environmental interference factors are set higher; for missions with less environmental impact (such as indoor weapon disassembly and basic aiming training), the weighting coefficients are set lower. This embodiment modifies the historical performance stability index. The modified standard deviation is calculated by multiplying the base ability score for each training session by the corresponding correction coefficient and then recalculating the standard deviation. The modified coefficient of variation is calculated based on the modified standard deviation and the modified historical average ability level, eliminating numerical bias caused by environmental interference. The modified range is calculated by subtracting the modified lowest score from the modified highest score, resulting in a fluctuation range that more closely reflects the actual ability.

[0048] This embodiment uses historical environmental interference factors to correct historical performance stability indicators, which can eliminate the accidental influence of extreme environments on trainees' performance. The corrected indicators more accurately reflect the stability of trainees' own abilities, providing more reliable input for the calculation of subsequent ability development factors, and ultimately improving the objectivity and guidance of the comprehensive ability assessment report.

[0049] In one embodiment of this application, population performance benchmark information is calculated based on historical norm data, including: Based on the trainees' experience level and age, as well as the complexity of the target training task, a dataset matching the reference group is selected from the historical norm data; the matching reference group is a historical trainee group whose attributes are similar to those of the trainees and the target training task. Statistical analysis was performed on the historical basic ability scores to calculate the group baseline statistics; The calculated population baseline statistics are weighted and adjusted according to the task complexity of the target training task attributes. The higher the task complexity, the higher the reference weight is given to the baseline statistics reflecting high standard performance, or the baseline statistics reflecting average performance are adjusted downward to reflect the expected deviation of population performance under high complexity tasks. The weighted and adjusted group baseline statistics are used as the group performance baseline information.

[0050] In this embodiment, the dataset for selecting the matching reference group needs to be analyzed from historical norm data using both student attributes and target training task attributes as dual dimensions. A multi-dimensional similarity algorithm is used for selection. If a historical student group perfectly matches the current student's experience level and age range, and the difference in complexity of the target training task is less than or equal to one level, then it is determined to be a matching reference group. Simultaneously, to ensure statistical validity, the sample size of the reference group must meet a minimum threshold. If the sample size is insufficient, the age range or experience level range is appropriately broadened. This embodiment performs statistical analysis on the historical basic ability scores in the selected matching reference group dataset to generate multi-dimensional group benchmark statistics that comprehensively reflect the performance distribution characteristics of the group. Specifically, these include: central tendency indicators, dispersion indicators, high-end performance indicators, and low-end performance indicators. The central tendency indicators include the group mean score and the median (the middle value after sorting by score). Dispersion indicators include the standard deviation and interquartile range. High-end performance indicators include the 90th percentile and the percentage of excellent performance. Low-end performance indicators include the 10th percentile and the percentage of unsatisfactory performance.

[0051] In this embodiment, task complexity is adjusted by applying differentiated weights to the baseline statistics of the group based on its level, to reflect the expected differences in performance under different levels of complexity. Specifically, for high-complexity tasks, the adjustment rule is to assign higher weights to baseline statistics reflecting high-standard performance. Baseline statistics reflecting average performance are adjusted downwards by 5%-15% to match the expected decline in overall group performance under high complexity; the standard deviation in the dispersion index is appropriately amplified to reflect the increased differences in group performance in high-complexity tasks. For medium- and low-complexity tasks, the adjustment rule is as follows: baseline statistics reflecting average performance are given dominant weights to ensure accurate characterization of the overall level; the weights of high-standard performance indicators are slightly reduced, while low-end performance indicators maintain their normal weights; the adjustment range for complex tasks is smaller than that for extremely complex tasks, and simple tasks can basically maintain their original statistics.

[0052] In this embodiment, the weighted and adjusted group baseline statistics will serve as the final group performance baseline information, presented in structured data format, including: Core benchmarks: Adjusted mean score, median, 90th percentile, 10th percentile; Fluctuation range: adjusted standard deviation, interquartile range; Proportional indicators: adjusted percentage of excellent products and percentage of unqualified products; Adjustment Notes: The adjustment range and weight allocation basis for the annotation task complexity are explained to facilitate the subsequent calculation and interpretation of the standardized relative performance score. The group performance benchmark information in this embodiment can reflect the objective performance of the historical group and adapt to the complexity characteristics of the current task, providing an accurate reference system for the subsequent calculation of the standardized relative performance score of trainees and ensuring the scientific nature of the group's relative positioning.

[0053] In one embodiment of this application, the calculated population baseline statistics are weighted and adjusted according to the task complexity of the target training task attributes, including: Based on the task complexity level of the target training task, the corresponding set of weight coefficients is found from the mapping table; the set of weight coefficients includes independent weight coefficients of the benchmark statistics of different types of groups. The found weighting coefficients are used to weight the corresponding group baseline statistics to obtain the adjusted group baseline statistics. Specifically, the higher the task complexity level, the larger the weighting coefficient for group baseline statistics reflecting high-standard performance, or the smaller the weighting coefficient for group baseline statistics reflecting average performance, or the greater the downward correction.

[0054] In this embodiment, the mapping table is the core tool for weighted adjustment. Its construction is based on statistical analysis of a large amount of historical training data and expert experience, using task complexity levels as indexes to associate corresponding sets of weight coefficients. Each task complexity level corresponds to an independent set of weight coefficients, including independent weight coefficients for all types of group benchmark statistics. The mapping table can be stored in a two-dimensional structure. In this embodiment, the adjusted core benchmark values ​​reflect the comprehensive impact of each statistic through weighted aggregation. This embodiment, through weighted adjustment based on the mapping table, enables the group benchmark statistics to accurately adapt to performance evaluation needs under different task complexities, ensuring the objectivity of statistical data while highlighting the reference value of high-standard performance in high-complexity tasks through weight allocation.

[0055] In one embodiment of this application, the generation rule of the weight coefficient set in the mapping table is differentiated according to the type of the group benchmark statistic.

[0056] In one embodiment of this application, the calculated population baseline statistic includes a specific quantile; Group performance benchmark information, including: Multiple performance level intervals defined based on specific quantiles; The calculation of standardized relative performance scores and the group relative positioning in the comprehensive ability assessment report are determined based on the performance level range in which the trainee's basic ability score falls.

[0057] In this embodiment, the generation rules for the weight coefficient set in the mapping table are differentiated according to the type of the group benchmark statistics, so as to accurately match the correlation characteristics of the evaluation value and task complexity of different statistics. The specific rules are as follows: The rules for generating statistics reflecting high-standard performance are centered on incentivizing breakthroughs, with weighting coefficients exhibiting an exponential growth relationship positively correlated with task complexity. For each level of complexity increase, the increase in the weighting coefficient gradually widens, and the percentage increase is referenced to the contributions of high-performing trainees in complex tasks based on historical data. Simultaneously, the system avoids a single statistic dominating benchmark information, ensuring a balanced evaluation.

[0058] The statistical measures reflecting average performance follow the baseline sinking principle, with the weighting coefficients exhibiting a linear negative correlation with task complexity. For each level increase in complexity, the weighting coefficient decreases, with the magnitude of the decrease referencing the decay rate of the group's average performance with increasing complexity. The generation rule for the statistics reflecting the degree of dispersion adopts a fluctuation-sensitive strategy, with the weight coefficient increasing in a slow positive correlation with the complexity, and the increase rate based on the rate of change of the dispersion of group performance in historical data; to ensure that its position as an auxiliary reference does not exceed the weight of the core performance statistics. The statistical rules for reflecting low-end performance aim to ensure a minimum standard, with weighting coefficients remaining relatively stable and only slightly adjusted according to complexity. This is because the baseline value for low-end performance is primarily used to determine whether the ability meets the minimum standard and has a low correlation with task complexity. In this embodiment, specific quantiles in the group baseline statistics are used to define multiple performance level intervals, providing an intuitive basis for interval division in the calculation of standardized relative performance scores and the relative positioning of the group. The calculation of standardized relative performance scores no longer depends on the difference of specific scores, but rather assigns corresponding scores based on the performance level interval in which the student's basic ability score falls.

[0059] In this embodiment, the generation of weight coefficients in the mapping table is more logical, and the application of performance level intervals makes the relative assessment of the group more intuitive and accurate, further enhancing the reference value of the comprehensive ability assessment report.

[0060] In one embodiment of this application, the downward correction of a group baseline statistic reflecting average performance includes: Based on historical norm data, establish a statistical regression model or empirical correction function between task complexity and the average basic ability score of the group. Input the task complexity of the target training task into the statistical regression model or empirical correction function to predict the expected correction value of the average basic ability score of the group under that complexity. The predicted corrected value is used to replace or adjust the group mean as the corrected group baseline statistic; whereby the statistical regression model or empirical correction function is used to show that the task complexity is negatively correlated with the predicted group mean basic ability score.

[0061] In this embodiment, constructing a correlation model between task complexity and the average basic ability score of the group based on historical norm data is the core step in downward correction. The historical norm data includes the average basic ability score of the group corresponding to different task complexities, and the sample size includes training data from different task scenarios to ensure the reliability of the model. This embodiment employs a univariate linear regression or nonlinear regression model, with the task complexity index as the independent variable and the group's average basic ability score as the dependent variable. The data is fitted using the least squares method to obtain the regression equation. The model must pass significance and goodness-of-fit tests to ensure that the negative correlation between task complexity and the group's average score is statistically significant. This embodiment employs a piecewise empirical correction function when the historical data distribution exhibits phased characteristics. Based on expert experience and data clustering results, the task complexity is divided into multiple intervals, each corresponding to a fixed correction coefficient or linear correction formula. The parameters of the empirical correction function need to be adjusted in conjunction with the average score decay rate of each interval in the historical data to ensure that the deviation between the correction result and the actual performance is less than a preset value. The alternatives in this embodiment include: Direct substitution: For the group's average basic ability score, the original average is directly replaced with the corrected value as the core benchmark reflecting average performance. Weighted adjustment: For other statistics reflecting average performance, such as the median, a weighted adjustment is made based on the deviation between the corrected value and the original median. Interval correction: The corrected average is used as the center value to adjust the interval range reflecting average performance, more accurately covering the actual performance range of the group under this complexity. The revised population baseline statistics in this embodiment will be marked with the basis for the revision, which will facilitate the interpretation of parameters when calculating the standardized relative performance score.

[0062] In this embodiment, the statistical regression model or empirical correction function is periodically iteratively optimized based on newly added training data, refitting parameters to adapt to performance fluctuations caused by factors such as updated training content and changes in the trainee group. For example, when a new weapon training module is introduced, the correlation between task complexity and group performance will change, requiring adjustments to the regression equation coefficients or the interval parameters of the correction function using new data to ensure the model's timeliness and accuracy. This embodiment achieves downward correction by establishing a quantitative model, enabling the group baseline statistics to dynamically adapt to task complexity, further improving the scientific nature and relevance of the group performance baseline information, and providing reliable basic data for subsequent standardized relative performance score calculation and comprehensive capability assessment.

[0063] In one embodiment of this application, The scoring method for weapon and equipment training based on virtual and real environments also includes: when the degree of change in the training scenario in the virtual environment data exceeds a first change threshold, and the basic capability score is less than a first scoring threshold, Calculate scene adaptability parameters based on the changing characteristics of virtual environment data; Based on the analysis of strategy deviation and task completion effect of trainee operational behavior data, the strategy innovation effectiveness parameter is calculated. Based on the data on trainees' response speed and handling results to emergencies in the virtual environment, emergency response effectiveness parameters are calculated. The parameters of scenario adaptability, strategy innovation effectiveness, and emergency response effectiveness are integrated into an environmental capability correction factor. The basic capability score is corrected based on the environmental capability correction factor to generate an environmental capability score. The environmental capability score and specific capability analysis are incorporated into the comprehensive capability assessment report to supplement the basic capability assessment, optimize the analysis of personal development trends, and provide a basis for capability improvement in complex environments. The specific capability analysis includes the dimensions of scenario adaptation, strategy innovation, and emergency response.

[0064] In this embodiment, when the degree of change in the training scenario in the virtual environment data exceeds a first change threshold, and the basic ability score is less than a first score threshold, the environmental ability assessment process is initiated. The degree of change in the training scenario can be quantified by the proportion of change in scenario elements. The first score threshold is set according to the task type and is usually the passing line for basic ability. If the trainee's basic ability score is lower than this value, it indicates that their general performance under scenario changes is poor, and their specific abilities such as environmental adaptation need to be further evaluated. This embodiment calculates scene adaptability parameters based on the changing characteristics of virtual environment data; wherein, the rate of change is measured by the duration of scene element changes, the range of change is calculated by the proportion of the training area affected, and the type of change is distinguished between gradual change and sudden change. This embodiment calculates this parameter by analyzing the strategy deviation and task completion effect of trainee operational behavior data. The strategy deviation refers to the degree of difference between the trainee's actual operational strategy and the conventional optimal strategy, which can be obtained through a behavior sequence comparison algorithm. The task completion effect is measured by the proportion of task objectives achieved after deviating from the conventional strategy. This embodiment calculates data based on the trainee's response speed and handling results in the virtual environment. Response speed is the time from the occurrence of the emergency to the trainee taking the first effective action; handling results data includes the event impact control rate and the secondary loss occurrence rate. In this embodiment, the comprehensive ability assessment report not only reflects the trainees' basic abilities in conventional environments, but also reveals their specialized competencies in complex and dynamic environments, providing a more comprehensive basis for the formulation of personalized training programs. It is especially suitable for selecting and cultivating high-quality talents who can adapt to the ever-changing environments in actual combat.

[0065] In one embodiment of this application, The calculation of scene adaptability parameters includes: Extract scene complexity indicators (including at least one of terrain abrupt change coefficient, meteorological interference level, and electromagnetic suppression intensity) from virtual environment data. Based on the path planning efficiency, target relocation time, and operational error rate under environmental interference in the student's operational behavior data, a raw score for scenario adaptability is generated. The scene complexity index is used as an adjustment weight to perform weighted calibration on the original scene adaptability score, thus obtaining the scene adaptability parameter.

[0066] The scenario adaptability parameters in this embodiment not only reflect the trainees' actual operational performance after scenario changes, but also achieve horizontal comparability of adaptability in different environments by adjusting the scenario complexity index, providing more accurate basic data for the subsequent integration of environmental capability correction factors.

[0067] In one embodiment of this application, The generation of strategic innovation effectiveness parameters satisfies: If the student's operational behavior data deviates from the standard operating procedure, then the data from the virtual environment will be used to verify whether this deviation produces the following positive effects: The reduction in task time exceeds the preset efficiency threshold; The reduction in resource consumption exceeds the preset conservation threshold; The stealth / survivability index has improved beyond the preset safety threshold; The strategy innovation effectiveness parameter is calculated based on the effect level only if at least one positive effect is met; otherwise, the innovation is marked as invalid.

[0068] The strategy innovation effectiveness parameters in this embodiment encourage trainees to make effective attempts to break with convention, while avoiding ineffective operations that innovate for the sake of innovation through strict threshold verification, ensuring that the parameters can truly reflect the trainees' innovative value and practical application ability in tactical strategies.

[0069] Corresponding to the scoring method for weapon and equipment training based on virtual and real-world scenarios in the above embodiments, Figure 2 This is a structural block diagram of a scoring system for weapon and equipment training based on virtual and real-world scenarios, provided as an embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The scoring system 20 for weapons and equipment training based on virtual and reality includes: a data acquisition module 21, a data calculation module 22, a data analysis module 23, a group information module 24, a comprehensive scoring module 25, and an evaluation report module 26.

[0070] Among them, the data acquisition module 21 is used to acquire multi-source data in the training tasks performed by trainees. The multi-source data includes: trainee operation behavior data, weapon and equipment status data, virtual environment data and trainee physiological monitoring data. Data calculation module 22 is used to calculate basic ability score values ​​based on multi-source data; Data analysis module 23 is used to analyze the trainees' historical training data on the same or similar target training tasks and generate ability development factors. The group information module 24 is used to acquire historical norm data that matches the attributes of trainees and the attributes of the target training task, and to calculate the group performance benchmark information based on the historical norm data. The comprehensive scoring module 25 is used to calculate the standardized relative performance score based on the basic ability score and the group performance benchmark information; The assessment report module 26 is used to generate a comprehensive ability assessment report based on the basic ability score, ability development factor and standardized relative performance score.

[0071] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned device embodiments, for example... Figure 2 The functions of the data acquisition module 21, data calculation module 22, data analysis module 23, group information module 24, comprehensive scoring module 25, and evaluation report module 26 are shown.

[0072] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0073] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0074] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store device type information.

[0075] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation methods described in any embodiment of the scoring method for training of weapons and equipment based on virtual and real-world conditions provided in the embodiments of this application, or they can execute the implementation methods of the electronic devices described in the embodiments of this application, which will not be repeated here.

[0076] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0077] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0078] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0079] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0080] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0081] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0082] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0083] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A scoring method for weapon and equipment training based on virtual and real-world scenarios, characterized in that, include: Acquire multi-source data from trainees performing target training tasks, including: trainee operational behavior data, weapon and equipment status data, virtual environment data, and trainee physiological monitoring data; Based on the multi-source data, a basic ability score is calculated; Analyze the trainees' historical training data on the same or similar target training tasks to generate ability development factors; Obtain historical norm data that matches the attributes of the trainees and the attributes of the target training task, and calculate the group performance benchmark information based on the historical norm data; Based on the basic ability score and the group performance benchmark information, a standardized relative performance score is calculated. Based on the basic ability score, the ability development factor, and the standardized relative performance score, a comprehensive ability assessment report is generated.

2. The scoring method for weapon and equipment training based on virtual and real-world scenarios according to claim 1, characterized in that, Based on the aforementioned multi-source data, a basic ability score is calculated, including: Based on the multi-source data and the trainees' levels, an initial ability score is calculated. The characteristics of the target emergency event are extracted from the virtual environment data; Based on the characteristics of the target emergency and the preset interference model, the target environmental interference factor is determined; Based on the target environment interference factor, the initial capability score is corrected to obtain the basic capability score.

3. The scoring method for weapon and equipment training based on virtual and real-world scenarios according to claim 2, characterized in that, The determination of the target environmental interference factor based on the characteristics of the target emergency and the preset interference model includes: The characteristics of the target emergency event are analyzed to obtain the event type, intensity level, duration, and spatiotemporal correlation with the student's operation; The type of the emergency event is matched to a preset interference intensity benchmark value in a preset interference model; Based on the event type and intensity level, query the preset interference influence coefficient matrix to obtain the basic interference coefficient; Based on the duration and the spatiotemporal correlation, a correction factor is calculated based on preset rules. The target environment interference factor is obtained by weighting the preset interference intensity benchmark value, the basic interference coefficient, and the correction factor.

4. The scoring method for weapon and equipment training based on virtual and real-world scenarios according to claim 1, characterized in that, The analysis of trainees' historical training data on the same or similar target training tasks to generate ability development factors includes: Based on the trainees’ historical training data, calculate the trainees’ historical average ability level and historical performance stability index on the same or similar target training tasks. Based on the historical average ability level and historical performance stability indicators, an ability development factor is generated.

5. The scoring method for weapon and equipment training based on virtual and real-world scenarios according to claim 4, characterized in that, Also includes: Historical virtual environment data is extracted from the historical training data to obtain the characteristics of sudden events during the training process; Based on the characteristics of the sudden event and the preset environmental model, historical environmental interference factors are determined. Based on the historical environmental interference factors, the historical performance stability index is corrected to obtain the corrected historical performance stability index.

6. The scoring method for weapon and equipment training based on virtual and real-world scenarios according to claim 1, characterized in that, The calculation of the group performance benchmark information based on the historical norm data includes: Based on the trainees' experience level and age, and the task complexity of the target training task, a dataset matching the reference group is selected from the historical norm data. Statistical analysis was performed on the historical basic ability scores to calculate the group baseline statistics; The calculated population baseline statistics are weighted and adjusted based on the task complexity of the target training task attributes. The weighted and adjusted group baseline statistics are used as the group performance baseline information.

7. The scoring method for weapon and equipment training based on virtual and real-world scenarios according to claim 6, characterized in that, The step of weighting and adjusting the calculated population baseline statistics based on the task complexity of the target training task attributes includes: Based on the task complexity level of the target training task, the corresponding set of weight coefficients is found from the mapping table; the set of weight coefficients includes independent weight coefficients of benchmark statistics for different types of groups. The adjusted population baseline statistic is obtained by weighting the corresponding population baseline statistic using the found weighting coefficients.

8. The scoring method for weapon and equipment training based on virtual and real-world scenarios according to claim 1, characterized in that, Also includes: When the degree of change in the training scene in the virtual environment data exceeds a first change threshold, and the basic ability score is less than a first score threshold, Based on the changing characteristics of the virtual environment data, calculate the scene adaptability parameters; Based on the analysis of strategy deviation and task completion effect of trainee operational behavior data, the strategy innovation effectiveness parameter is calculated. Based on the data on trainees' response speed and handling results to emergencies in the virtual environment, emergency response effectiveness parameters are calculated. The aforementioned scenario adaptability parameters, strategy innovation effectiveness parameters, and emergency response effectiveness parameters are integrated into an environmental capability correction factor. The basic capability score is corrected based on the environmental capability correction factor to generate an environmental capability score. The environmental capability score and specific capability analysis are incorporated into the comprehensive capability assessment report to supplement the basic capability assessment, optimize the analysis of personal development trends, and provide a basis for capability improvement in complex environments. The specific capability analysis includes dimensions of scenario adaptation, strategy innovation, and emergency response.

9. A scoring system for weapon and equipment training based on virtual and real-world methods, characterized in that, include: The data acquisition module is used to acquire multi-source data from trainees performing target training tasks. The multi-source data includes: trainee operation behavior data, weapon and equipment status data, virtual environment data, and trainee physiological monitoring data. The data calculation module is used to calculate the basic ability score based on the multi-source data; The data analysis module is used to analyze the trainees' historical training data on the same or similar target training tasks and generate ability development factors. The group information module is used to acquire historical norm data that matches the attributes of the trainees and the attributes of the target training task, and to calculate the group performance benchmark information based on the historical norm data. The comprehensive scoring module is used to calculate a standardized relative performance score based on the basic ability score and the group performance benchmark information. The assessment report module is used to generate a comprehensive ability assessment report based on the basic ability score, the ability development factor, and the standardized relative performance score.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 8.

Images