Intelligent shooting examination training system and method

Abstract

The present application relates to the technical field of intelligent training, in particular to a kind of intelligent shooting examination training system and method, including the following contents: posture recognition module, trajectory monitoring module, hit analysis module, rhythm comparison module, label output module.In the present application, based on the motion image of the process of training personnel holding gun to firing, the synchronous angle trajectory of shoulder and elbow is identified in real time, compared with the combination of standard action, the matching difference of each period is accurately screened and quantified, the change of laser trajectory coordinate point and direction during aiming is analyzed, the action control stability is dynamically evaluated, the hit point sequence is used, the structured score is formed by combining path extensibility and hit area density, the start and end time of action unit and rhythm arrangement of training process are compared one by one, the phenomenon of advance and delay is identified, the performance score is flexibly adjusted according to the weight of multi-dimensional index, and the accurate matching between training performance evaluation and actual ability requirement is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent training, in particular to an intelligent shooting examination and training system and method. BACKGROUND

[0002] The technical field of intelligent training includes training support systems constructed based on artificial intelligence, sensor fusion, virtual simulation and other means, aiming to realize precise capture of the training process, real-time feedback of data processing and quantitative presentation of training evaluation. The core content lies in data expression of the operation behavior, physical state and task execution process of the trainee through multi-source information perception means, and evaluation and optimization of the training effect by means of analysis algorithm. It covers the collaborative operation of sensor layout, behavior capture device, evaluation terminal and control system, supports the process management, dynamic supervision and task examination of training projects, forms a closed-loop system from training implementation to feedback guidance, and improves the scientific nature and efficiency of training.

[0003] Among them, an intelligent shooting examination and training system aims to apply various data acquisition and processing means to accurately track and evaluate the whole process of shooting training. The system records and analyzes the standardization of shooting actions, the stability of aiming trajectories, the accuracy of bullet hit positions, and the reaction time nodes. Specifically, image acquisition devices are used to obtain shooting posture changes, laser positioning devices are used to capture gun movement trajectories, intelligent target equipment is used to detect hit positions, and timer devices are used to record the reaction time from target appearance to firing completion. Training data is collected by a data acquisition terminal and is processed by a processing unit for feature extraction, numerical classification and rule comparison to form training records and output examination basis for subsequent training performance evaluation and comparison.

[0004] Traditional shooting examination and training technology processes action data, aiming trajectory, hit performance, reaction time and other links independently in the operation process, resulting in insufficient data correlation and lack of linkage analysis of the whole process of action and results. When facing complex training scenarios, it is difficult to accurately track key action features and rhythm deviation, leading to missing hidden deviation, and performance scores cannot fully reflect the actual needs of task types. In actual application, it will cause the single evaluation of training performance, lack of pertinence, weak adaptability to different ability structures, and affect the improvement of combat personnel's ability and the pertinence of training. SUMMARY

[0005] In order to solve the technical problems existing in the prior art, the embodiments of the present application provide an intelligent shooting examination and training system and method. The technical solution is as follows:

[0006] On the one hand, an intelligent shooting examination and training system is provided, which comprises:

[0007] The posture recognition module analyzes real-time action images, recognizes the synchronous angle change trajectory of the shoulder and the elbow according to the action images of the trainer in the process from holding a gun to firing, compares the corresponding angle combination in the standard action, filters the deviated paragraphs and extracts the action deviation amplitude, and generates the shoulder-elbow posture information;

[0008] The trajectory monitoring module calls the shoulder-elbow posture information, obtains the continuous coordinate points of the laser pointer on the target surface during aiming, screens the fluctuation trajectory segment by calculating the spatial distance and the change angle of the direction between adjacent coordinate points, evaluates the stability of the aiming action, and generates the fluctuation frequency information;

[0009] The hit analysis module calls the fluctuation frequency information, sorts the hit points on the target surface according to the firing time, connects adjacent hit points and analyzes the direction change trend, identifies the deviation path, calculates the hit score in combination with the extension continuity of the path and the hit area coverage range, and generates the fall point analysis result;

[0010] The rhythm comparison module calls the fall point analysis result, analyzes the corresponding starting time of each action unit in the training task, compares with the preset rhythm arrangement, identifies the advance and delay trend of the action unit, evaluates the fluctuation degree of the execution rhythm, and generates the rhythm evaluation information.

[0011] As a further scheme of the present application, the shoulder-elbow posture information includes a matching trajectory, a deviation segment and a joint angle sequence, the fluctuation frequency information includes a trajectory segment sequence, a direction jump frequency and a stability mark, and the fall point analysis result specifically refers to a hit concentration range, a deviation direction trend and a path extension structure, and the rhythm evaluation information specifically refers to a time distribution structure, a rhythm deviation paragraph and an operation sequence difference.

[0012] As a further scheme of the present application, the posture recognition module includes:

[0013] The action image processing sub-module analyzes real-time action images, extracts the contour coordinate point information corresponding to the shoulder and the elbow in the action image sequence of the trainer, constructs the action time sequence of the shoulder and the elbow, positions and corresponds the key nodes in the continuous images, and generates a shoulder-elbow dynamic trajectory sequence;

[0014] The joint angle extraction sub-module calls the shoulder-elbow dynamic trajectory sequence, calculates the direction angle value of the connecting line of the two points according to the corresponding coordinate positions of the shoulder and the elbow in each image, obtains a synchronous angle sequence composed of a plurality of angle points according to the time axis sequence, and generates a joint angle change path;

[0015] The synchronization deviation judgment sub-module calls the joint angle change path, compares the change direction difference between the angle combination of the two joints in the actual action and the set combination in the standard action, screens the synchronization deviation period, identifies the amplitude of the action deviation, and generates the shoulder-elbow posture information.

[0016] As a further scheme of the present application, the trajectory monitoring module comprises:

[0017] The coordinate data acquisition submodule calls the shoulder-elbow posture information, acquires the laser point coordinate data of the laser pointer projected onto the target surface by the training personnel during the aiming period, records the coordinate points corresponding to each time node, and arranges the coordinate sequence in time sequence to establish a continuous point space movement path and generate laser movement trajectory data;

[0018] The trajectory fluctuation identification submodule calls the laser movement trajectory data, filters the fluctuation trajectory segments by calculating the spatial distance and the change angle of the adjacent points in the trajectory, and records the corresponding starting time to generate a trajectory fluctuation segment set;

[0019] The action stability evaluation submodule calls the trajectory fluctuation segment set, identifies the interval of each fluctuation trajectory segment in the time sequence, evaluates the stability of the aiming action of the training personnel according to the length and frequency of the fluctuation trajectory segments in multiple time periods, and generates fluctuation frequency information.

[0020] As a further scheme of the present application, the specific formula for evaluating the stability of the aiming action of the training personnel is:

[0021] ;

[0022] Calculate the stability score of the aiming action;

[0023] wherein, represents the stability score of the aiming action, is a score adjustment coefficient, represents the normalized value of the duration of the th fluctuation trajectory segment, represents the normalized value of the spatial trajectory fluctuation distance of the th fluctuation trajectory segment, represents a fluctuation frequency correction factor, represents the total number of fluctuation trajectory segments, represents the number index of the trajectory fluctuation segment in the time sequence.

[0024] As a further scheme of the present application, the hit analysis module comprises:

[0025] The hit point data sorting submodule calls the fluctuation frequency information, acquires the hit point coordinate information formed by the actual firing on the target surface and the corresponding firing time sequence, sorts and connects the hit points according to the time sequence to form a hit path structure, and generates a hit connection path sequence;

[0026] The offset trend extraction submodule calls the hit connection path sequence, extracts the angle of the connection direction of each path segment, and identifies the offset trend path of the connection direction between hit points by comparing the trajectory of the direction change of multiple shot hit points on the target surface, and generates the offset path identification result.

[0027] The orientation aggregation evaluation submodule calls the offset path identification results, analyzes the extension continuity of the offset path, and evaluates the stability and consistency of the hit point aggregation direction in combination with the spatial coverage of the hit point on the target surface. Combined with the path offset direction, it generates the impact point analysis results.

[0028] The specific formula for the spatial coverage of the hit point on the target surface is as follows:

[0029] ;

[0030] Calculate the clustering consistency index;

[0031] in, Representing the The coordinates of each hit point in the horizontal direction of the target surface. Representing the The coordinates of each hit point in the longitudinal direction of the target surface. This represents the average of the horizontal coordinates of all hit points. Represents the average of the vertical coordinates of all hit points. This is a fixed setting for the reference radius of the firing hit area. For the first Normalized value of the hit point density in the sector region containing each hit point This is the normalized value that maximizes the density value across all sector regions during the training process. This represents the total number of hits within the current mission phase. As a consensus indicator, This represents the j-th hit point currently being calculated.

[0032] As a further aspect of the present invention, the rhythm comparison module includes:

[0033] The task time period identification submodule calls the landing point analysis results, collects the start time and end time records of each action unit in the training task, calculates the duration of each action unit, and generates an action time structure sequence.

[0034] The rhythm trend comparison submodule calls the action time structure sequence, compares the start time of each action unit with the preset rhythm arrangement, identifies the advance and delay trends of the action units, and generates rhythm offset trend data.

[0035] The fluctuation degree calculation sub-module calls the rhythm deviation trend data, analyzes the number of action segments with continuous rhythm deviation and the duration range of each segment, calculates the proportion of rhythm deviation segments in the training process, evaluates the fluctuation degree of the rhythm performed by the personnel in the training task, and generates rhythm evaluation information.

[0036] As a further scheme of the present application, the system further comprises:

[0037] The label output module calls the rhythm evaluation information, adjusts the weight distribution of each evaluation index according to the ability priority set by the training task, analyzes the corresponding relationship between each index and the label level interval corresponding to the task type, and calculates the performance score of the training personnel to generate a training performance evaluation level.

[0038] The training performance evaluation level is specifically a label interval matching result, an ability score composition, and a level classification number.

[0039] As a further scheme of the present application, the label output module comprises:

[0040] The index weight configuration sub-module calls the rhythm evaluation information, extracts the corresponding ability priority parameters according to the training task type, and adjusts the weight of each evaluation index, including the action deviation amplitude, the stability of the aiming action, the hit score, and the fluctuation degree of the execution rhythm, to generate an ability weight distribution coefficient.

[0041] The level attribution matching sub-module calls the ability weight distribution coefficient, classifies and judges the label level interval corresponding to each evaluation result, identifies the attribution position of each index value in the level interval, and generates a level interval matching relationship group.

[0042] The result label generation sub-module calls the level interval matching relationship group, combines the weight of each evaluation index, calculates the performance score of the training personnel, identifies the performance level of each training personnel, and generates a training performance evaluation level.

[0043] On the other hand, an intelligent shooting examination and training method is provided, which is applied to an intelligent shooting examination and training system, and the method comprises:

[0044] S1: analyze real-time action images, extract continuous image sequences in the process of holding a gun to firing by the training personnel, perform inter-frame node extraction and angle path construction on the shoulder and elbow actions, perform difference comparison on the actual angle ratio change according to the standard action track, screen deviation paragraphs and extract action deviation amplitudes, and generate shoulder and elbow posture information.

[0045] S2: Based on the shoulder and elbow gesture information, record the coordinates of the laser pointer on the target surface during aiming, construct a coordinate time sequence path, measure the distance and direction variation amplitude between adjacent coordinates, screen the fluctuation trajectory segment, and evaluate the stability of the aiming action to generate fluctuation frequency information;

[0046] S3: Based on the fluctuation frequency information, sort the multiple hit points formed by firing according to time to establish a hit point path structure, identify the offset path and analyze the extension continuity of the path, calculate the hit score combined with the coverage range of the hit area, and generate the drop point analysis result;

[0047] S4: Based on the drop point analysis result, collect the start and end time of each action unit in the training task, identify the advance and delay trend of the action unit combined with the standard rhythm arrangement set in the training plan, evaluate the fluctuation degree of the execution rhythm, and generate the rhythm evaluation information;

[0048] S5: Based on the rhythm evaluation information, adjust the weight of each evaluation index according to the ability priority setting configured for each type of training task, identify the corresponding grade label of each index, calculate the performance score of the training personnel, and establish the training performance evaluation grade.

[0049] The technical scheme provided by the embodiment of the application has at least the following beneficial effects:

[0050] Based on the action image of the training personnel holding a gun to the firing process, the synchronization angle trajectory of the shoulder and elbow is identified in real time, combined with the comparison of the standard action combination, the ratio difference of each period is accurately screened and quantified, the action control stability is dynamically evaluated by analyzing the laser trajectory coordinate points and direction changes during aiming, the hit point sequence is used, combined with the path extension and hit area density to form a structured score, the start and end time of the action unit in the training process is compared with the rhythm arrangement one by one, the advance and delay phenomenon is identified, and the performance score is flexibly adjusted according to the weight of multiple indexes, which realizes the accurate matching between the training performance evaluation and the actual ability requirement. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical scheme in the embodiment of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can be obtained by those skilled in the art without creating labor on the premise of the drawings.

[0052] Fig. 1 The system flowchart of the application;

[0053] Fig. 2 The system framework schematic diagram of the application;

[0054] Fig. 3 The method steps of the present application are schematically shown in the figure. DETAILED DESCRIPTION

[0055] The technical solutions in the present application will be described below with reference to the drawings.

[0056] In the embodiments of the present application, the words such as "example", "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "example" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0057] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized. "Of", "corresponding" and "corresponding" can be used interchangeably at times, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized.

[0058] In the embodiments of the present application, sometimes the subscript such as W1 can be written in the form of non-subscript such as W1, and the meanings expressed are consistent when the distinction is not emphasized.

[0059] In order to make the technical problems, technical solutions and advantages to be solved by the present application more clear, the following will be described in detail with reference to the drawings and specific embodiments.

[0060] The embodiments of the present application provide an intelligent shooting examination and training system, please refer to Figs. 1-2 The present application provides a technical solution, an intelligent shooting examination and training system comprises:

[0061] The posture recognition module analyzes real-time action images, identifies the synchronous angle change trajectory of the shoulder and the elbow according to the action images of the training personnel in the process from holding a gun to firing, compares the corresponding angle combination in the standard action, filters the deviated paragraphs and extracts the action deviation amplitude, and generates shoulder-elbow posture information;

[0062] The trajectory monitoring module calls the shoulder-elbow posture information, obtains the continuous coordinate points of the laser pointer on the target surface during aiming, filters the fluctuation trajectory segment by calculating the spatial distance and the change angle of the direction between adjacent coordinate points, evaluates the stability of the aiming action, and generates fluctuation frequency information;

[0063] The hit analysis module calls the fluctuation frequency information, sorts the target surface hit points according to the firing time, connects adjacent hit points and analyzes the direction change trend, identifies the deviation path, combines the extension continuity of the path and the hit area coverage range, calculates the hit score, and generates the fall point analysis result;

[0064] The rhythm comparison module calls the fall point analysis result, analyzes the starting time corresponding to each action unit in the training task, compares it with the preset rhythm arrangement, identifies the advance and delay trend of the action unit, evaluates the fluctuation degree of the execution rhythm, and generates rhythm evaluation information;

[0065] The label output module calls the rhythm evaluation information, adjusts the weight distribution of each evaluation index according to the ability priority set by the training task, analyzes the attribution corresponding relationship of each index and the label level interval corresponding to the task type, and calculates the performance score of the training personnel, and generates the training performance evaluation level.

[0066] The shoulder and elbow posture information includes matching trajectory, deviation section, joint angle sequence, the fluctuation frequency information includes trajectory segment sequence, direction jump frequency, stability mark, the fall point analysis result is specifically the hit concentration range, deviation direction trend, path extension structure, the rhythm evaluation information is specifically the time distribution structure, rhythm deviation paragraph, operation sequence difference, and the training performance evaluation level is specifically the label interval matching result, ability score composition, and grade classification number.

[0067] The posture recognition module comprises:

[0068] The action image processing submodule analyzes the real-time action image, extracts the contour coordinate point information corresponding to the shoulder and elbow in the action image sequence of the training personnel, constructs the action time sequence of the shoulder and elbow, positions and corresponds the key nodes in the continuous image, and generates the shoulder and elbow dynamic trajectory sequence;

[0069] In the real-time action image analysis process, first, a high-speed camera device is used to collect the whole process image of the training personnel from holding a gun to firing at 60 frames per second. Taking a 3-second complete shooting action as an example, 180 frames of continuous images are generated, and the key feature points of the shoulder and elbow of the training personnel are identified one by one in each frame of image. The two-dimensional coordinate positions of the shoulder vertex and the elbow joint are extracted respectively, and the shoulder coordinates are marked as point , and the elbow coordinates are marked as point . For example, in the 50th frame of image, the shoulder coordinates =(210, 325) pixels, and the elbow coordinates =(240, 410) pixels. Then in the 51st frame of image, the shoulder coordinates are updated to =(211, 327) pixels, and the elbow coordinates are updated to = (242, 412) pixels. In this way, the shoulder and elbow coordinate points of each frame of image are determined in sequence, and a shoulder coordinate sequence is constructed and an elbow coordinate sequence . Subsequently, by associating the spatial coordinates of the key nodes in each frame of image and positioning the time sequence, the spatial trajectory data of the shoulder and elbow changing with the action is finally obtained, and a shoulder-elbow dynamic trajectory sequence is generated.

[0070] The joint angle extraction submodule calls the shoulder-elbow dynamic trajectory sequence, calculates the direction angle value of the two-point connection according to the corresponding coordinate positions of the shoulder and elbow in each frame of image, obtains a synchronous angle sequence composed of multiple angle points according to the time axis sequence, and generates a joint angle change path;

[0071] For the shoulder-elbow dynamic trajectory sequence, the shoulder coordinate and the elbow coordinate in each frame of image are called, and the direction angle is calculated using the coordinate connection, that is, the azimuth angle calculation method of the rectangular coordinate system, and the calculation formula is: , wherein is the shoulder-elbow connection direction angle value, , is the horizontal and vertical coordinates of the same frame of shoulder-elbow coordinate pair. Taking the 50th frame of image as an example, the coordinates and are substituted into the above formula to obtain: , and similarly, the 51st frame obtains a direction angle of . By repeating the above calculation steps for all 180 frames of image, a continuous angle value sequence is obtained, and the joint angle change path is generated according to the time sequence.

[0072] The synchronous offset judgment submodule calls the joint angle change path, compares the change direction difference between the two joint angle combinations in the actual action and the set combination in the standard action, filters the synchronous deviation period, and identifies the amplitude of the action deviation, to generate the shoulder-elbow posture information;

[0073] Based on the joint angle change path, the shoulder-elbow angle combination reference value of the standard shooting action is called. The reference value is usually determined by standard action experiment statistics, and is based on the standard shooting posture measured data. After 100 times of repeated action test, it is determined that the best direction angle combination range of shoulder and elbow is (see Table 1).

[0074] Table 1 Standard Shoulder-Elbow Angle Combination Reference Table

[0075]

[0076] The average value of the shoulder-elbow combined angle experimental data in Table 1 is 66.5°, and the standard deviation is about 0.8°, and then the reasonable interval of the combined direction angle of the standard shooting posture is set to 65° to 68°. The actual motion angle of each frame is compared and judged with the interval: for example, the actual measurement of the shoulder-elbow direction angle of the 50th frame image is 70.56°, which is obviously beyond the above reasonable interval, and is marked as a deviation frame; if the actual measurement of the direction angle of the 52nd frame is 66.7°, which falls within the above reasonable interval, it is marked as a normal frame. The above-mentioned frame-by-frame comparison and judgment are performed on all 180 frames, and the continuous frame segments deviating from the normal interval are marked and continuously counted. Assuming that the 50th to 55th frames and the 120th to 130th frames are marked as deviation paragraphs, the total number of frames is 17, and the proportion of deviation paragraphs to the total number of frames is 17 / 180≈0.094, i.e. the proportion of deviation paragraphs is about 9.4%. Further, the difference between each actual angle of the marked frame segment and the boundary value of the standard interval is calculated, for example, the difference of the 50th frame is 70.56°-68°=2.56°, and the difference of the 120th frame is 2.03° after similar processing, and the difference data of each deviation frame is obtained in turn. After analyzing all the difference data, the maximum deviation amplitude is selected as 2.56° as the maximum deviation value, and the average deviation amplitude is calculated as (2.56°+2.03°+…) / 17, and the result is assumed to be 2.1°. Finally, the shoulder-elbow posture information is obtained by comprehensive calculation.

[0077] The trajectory monitoring module comprises:

[0078] The coordinate data acquisition submodule calls the shoulder-elbow posture information, acquires the laser point coordinate data projected by the laser pointer to the target surface in a continuous time period during the aiming period of the training personnel, records the coordinate points corresponding to each time node, and arranges the coordinate sequence in time sequence to establish a continuous point space movement path and generate laser movement trajectory data.

[0079] During the coordinate data acquisition process, the laser pointer continuously projects to the front fixed target surface position during the execution of the shooting aiming action of the training personnel, and the two-dimensional coordinates of the laser point are collected in real time by using the coordinate capture device. The laser coordinates on the target surface are acquired by the acquisition equipment at a frequency of 50 times per second, and 100 coordinate points are acquired in 2 seconds of continuous capture, for example, the coordinate position of the first acquisition point is , the second acquisition point is , and so on, and the position coordinate of the 100th acquisition point is assumed to be , and all the acquisition coordinate points form a coordinate sequence . Each coordinate point is paired according to the acquisition sequence and the corresponding acquisition time node, for example, the first coordinate corresponds to the time , the second coordinate corresponds to the time , and so on until the 100th coordinate corresponds to the time . Then, the coordinate points are connected in sequence according to the acquisition sequence, for example, the first point With the second point , the second point is connected with the third point, and the 99th point is connected with the 100th point, to form a continuous point space moving path, and laser moving track data is obtained.

[0080] The trajectory fluctuation identification submodule calls the laser moving track data, calculates the spatial distance and the change angle of the direction of adjacent points in the trajectory, filters the fluctuation trajectory segment, and records the corresponding starting time to generate a trajectory fluctuation segment set;

[0081] In the trajectory fluctuation identification process, the continuous point coordinate sequence of the above laser moving track data is called, and the spatial distance and the change angle of the direction of each pair of adjacent coordinate points are calculated. Taking the first point and the second point as an example, the spatial distance between the two points is The calculation using the Euclidean distance formula is: The change angle of the direction is The calculation is the angle between the coordinate line of the two points relative to the horizontal axis, that is: Similar calculations are performed for the second point and the third point, the third point and the fourth point, and all continuous point pairs. If the distance between the two adjacent point pairs exceeds the set distance reference value of 2.0 mm, or the change angle of the direction exceeds the set angle reference value of 30°, it is marked as a trajectory fluctuation point segment. For example, the 20th to 24th point pairs satisfy the above distance or angle exceeding the reference, and are marked as a fluctuation trajectory segment, and the starting time node is recorded as the time corresponding to the 20th point The end time is the time corresponding to the 24th point Similar marking methods are assumed to obtain two fluctuation trajectory segments of the 45th to 50th point pairs and the 80th to 85th point pairs, and the trajectory fluctuation segment set is recorded after being summarized. The example data is shown in Table 2.

[0082] Table 2: Example data table of laser trajectory fluctuation segment

[0083]

[0084] Table 2 gives the time information of the fluctuation trajectory segment collected in the example. After the trajectory fluctuation identification submodule calls the data, the trajectory fluctuation segment set is formed.

[0085] The action stability evaluation submodule calls the trajectory fluctuation segment set, identifies the interval of each fluctuation trajectory segment in the time sequence, and evaluates the stability of the training personnel's aiming action according to the length and frequency of the fluctuation trajectory segment in multiple time periods to generate fluctuation frequency information.

[0086] The specific formula for evaluating the stability of the training personnel's aiming action is:

[0087] ​

[0088] calculating the aiming action stability score;

[0089] wherein, represents the aiming action stability score, is the score adjustment coefficient, represents the normalized value of the duration of the first fluctuation trajectory segment, represents the normalized value of the spatial fluctuation distance of the first fluctuation trajectory segment, represents the fluctuation frequency correction factor, represents the total number of fluctuation trajectory segments, represents the index number of the trajectory fluctuation segment in the time sequence.

[0090] Formula:

[0091] ;

[0092] Formula details and formula calculation derivation process:

[0093] The formula is used to calculate the action stability score of the training personnel in the aiming stage. The score result is used to reflect the action continuous stability level in the training process. The higher the value, the more stable the aiming is;

[0094] Parameter meaning and setting value:

[0095] is the normalized value of the duration of the first fluctuation trajectory segment. The original duration is obtained by the change time period of the continuous laser pointing coordinates in the time sequence. The value is normalized by dividing the total training duration If the durations of the first, second and third fluctuation trajectory segments are 0.6 seconds, 0.9 seconds and 1.2 seconds respectively, and the total training duration is 10 seconds, then: , , ;

[0096] is the normalized value of the spatial fluctuation distance of the first fluctuation trajectory segment. The value is the approximate arc length of the curve formed by the continuous change of the coordinates of the laser point. It is obtained by dividing the total distance of each segment trajectory by the standard reference distance If the fluctuation distances of the first, second and third segments are 4.5 cm, 5.1 cm and 5.7 cm respectively, and the standard reference distance is 10 cm, then: , , ;

[0097] is a frequency correction factor, representing the normalized difference between the number of trajectory fluctuations per unit time and the set threshold value. The reasonable interval for fluctuation frequency is set to 0 to 6 times per 10 seconds. If the actual collection frequency is 8 times, the correction factor is: ;

[0098] is a score adjustment coefficient, which is determined according to the fitting analysis between the evaluation accuracy and the fluctuation characteristics of a plurality of samples. It is usually set to 15;

[0099] is the number of trajectory fluctuation segments, which is 3 in the current sample;

[0100] Substitute the parameters into the formula for calculation:

[0101] ;

[0102] The result 94.34 indicates that the aiming action has a high stability score in this training sample, and the value is close to full score, indicating that the trajectory fluctuation is small, the duration is short, and the frequency does not exceed the set reference range, and the action stability is strong. This value is used as a key indicator in the subsequent comprehensive evaluation results to participate in the final training level output calculation.

[0103] The hit analysis module includes:

[0104] The hit point data sorting submodule calls the fluctuation frequency information, collects the hit point coordinate information formed by the actual firing on the target surface and obtains the corresponding firing time sequence, sorts and connects the hit points according to the time sequence, forms a hit path structure, and generates a hit connection path sequence;

[0105] During the hit point data sorting process, the fluctuation frequency information corresponding to the shooting stage generated by the previous module is called, and the intelligent target device records the spatial coordinates of the impact point on the target surface formed by each firing in real time. Specifically, two-dimensional coordinate positioning is performed in millimeters (mm). Assuming that the training personnel perform a shooting training, a total of 5 firings are performed, and the intelligent target obtains 5 hit point coordinates and corresponding firing time nodes, as shown in Table 3.

[0106] Table 3 Hit point coordinate and firing time record table

[0107]

[0108] Based on the data in Table 3, the call firing time sorts the 5 hit points in the order: the first firing point (85, 102), the second (88, 100), the third (91, 97), the fourth (95, 94), and the fifth (100, 90), and the hit points are connected in this order in sequence, specifically using a straight line connection method, that is, the first point is connected to the second point, the second point is connected to the third point, and so on, to finally form a continuous hit connection path sequence.

[0109] The offset trend extraction submodule calls the hit connection path sequence, extracts the angle of the connection direction of each path, and compares the direction change trajectories of the hit points on the target surface to identify the offset trend path of the connection direction between the hit points, and generates an offset path identification result;

[0110] During the offset trend extraction process, the hit connection path sequence is called to extract the angle of the direction of adjacent connection paths, and the azimuth angle of the connection line is calculated through the path coordinate difference. Taking the path from the first point (85, 102) to the second point (88, 100) as an example, the direction angle calculation formula of the connection path is , and the specific data is , and the direction angles of subsequent paths are calculated similarly, such as the direction angle of the connection path from the second point to the third point , the direction angle from the third point to the fourth point , and the path angle from the fourth point to the fifth point , to obtain the complete direction angle sequence: . By comparing the direction change angle of the standard hit trajectory (for example, taking the horizontal right 0° as the reference, and allowing a floating range of ±10° within the standard offset range), it is determined whether each angle in the angle sequence exceeds the standard offset range. For example, the first path -33.69° exceeds the standard ±10° range (-10°~10°), which is marked as an offset direction path, and the same is marked for each path, and finally the offset trend path of the hit point connection direction is identified, and the offset path identification result is generated.

[0111] The direction aggregation evaluation submodule calls the offset path identification result, analyzes the extension continuity of the offset path, combines the spatial coverage range of the hit points on the target surface, evaluates the stability and consistency degree of the hit point aggregation direction, and generates a drop point analysis result in combination with the path offset direction;

[0112] The specific formula for combining the spatial coverage range of the hit points on the target surface is:

[0113] ;

[0114] Calculate the aggregation consistency index;

[0115] wherein, represents the The coordinates of each hit point in the horizontal direction of the target surface. Representing the The coordinates of each hit point in the longitudinal direction of the target surface. This represents the average of the horizontal coordinates of all hit points. Represents the average of the vertical coordinates of all hit points. This is a fixed setting for the reference radius of the firing hit area. For the first Normalized value of the hit point density in the sector region containing each hit point This is the normalized value that maximizes the density value across all sector regions during the training process. This represents the total number of hits within the current mission phase. As a consensus indicator, This represents the j-th hit point currently being calculated.

[0116] formula:

[0117] ;

[0118] Detailed explanation of the formula and its calculation derivation:

[0119] The formula calculates the hit point convergence consistency index to quantify the degree of convergence and stability of hit points in shooting training, and to evaluate the stability of the trainee's aiming action.

[0120] Parameter meanings and settings:

[0121] and : are respectively the The horizontal and vertical coordinates of each hit point on the target surface are given in meters. Five hit points are defined, with the horizontal coordinate being... , , , , The vertical axis is , , , , ;

[0122] and : These are the average values ​​of the horizontal and vertical coordinates of all hit points, respectively, and the average value of the horizontal coordinate.

[0123] The average value of the ordinate ;

[0124] : is the reference radius of the hit area, unit: meter, used to standardize the offset of the hit point, assuming that the

[0125] : are the density normalized value and the density value of the most dense area of the region where the

[0126] : is the total number of hit points in the training stage, assuming that

[0127] Substitute the parameters into the formula for calculation:

[0128]

[0129]

[0130]

[0131]

[0132]

[0133]

[0134]

[0135]

[0136] The results show that the consistency of the hit point aggregation is low, indicating that the hit points are distributed more dispersedly on the target surface, and the shooting stability is poor.

[0137] The rhythm comparison module includes:

[0138] The task period identification submodule calls the hit point analysis result, collects the start time and end time records of each action unit in the training task, calculates the duration length of each action unit, and generates an action time structure sequence;

[0139] ​​​​​​​​​​​​​​​​​​In the task period identification process, the landing point analysis result is called to correspond to the training task stage, and the starting and ending time of each action unit in the shooting training process is collected in real time through the task data recording device. Taking a complete shooting training task as an example, it is assumed that the task flow includes preparation action, aiming action, firing action and recovery action four action units, and the data recording device collects the starting and ending time points of each unit respectively, and records them in seconds as and , as shown in Table 4.

[0140] Table 4 Shooting training action unit time data table

[0141]

[0142] According to the data in Table 4, the duration of each action unit is calculated one by one, for example, the preparation action duration is calculated as , the aiming action duration is calculated as , the firing action duration is calculated as , and the recovery action duration is calculated as . The duration of each action unit is recorded in the order of actual execution to generate an action time structure sequence.

[0143] The rhythm trend comparison submodule calls the action time structure sequence, compares the starting period of each action unit with the preset rhythm arrangement, identifies the advance and delay trend of the action unit, and generates rhythm offset trend data;

[0144] The above action time structure sequence is called, and comparison is made according to the time reference of the standard shooting training action rhythm arrangement. The standard rhythm arrangement is obtained through a large number of experiments, and it is assumed that the data of the standard action unit rhythm arrangement is shown in Table 5.

[0145] Table 5 Standard action rhythm arrangement data table

[0146]

[0147] The starting time of the actual action unit is compared with the standard starting time one by one, for example, the actual starting time of the preparation action is 0.00s, the standard is 0.00s, the time difference is 0.00s, no advance or delay; the actual starting time of the aiming action is 1.00s, the standard is 1.20s, the difference is -0.20s, which indicates that the action is advanced; the actual starting time of the firing action is 3.00s, the standard is 3.20s, the difference is -0.20s, which is 0.20s in advance; the actual starting time of the recovery action is 3.50s, the standard is 3.70s, the difference is -0.20s, which is also an advance trend. In this way, the advance or delay trend of each action unit relative to the standard rhythm arrangement is identified one by one, and the rhythm deviation trend data is recorded in sequence.

[0148] The fluctuation degree calculation submodule calls the rhythm deviation trend data, analyzes the number of action segments with continuous rhythm deviation and the duration range of each segment, calculates the proportion of rhythm deviation segments in the training process, evaluates the fluctuation degree of the rhythm performed by the personnel in the training task, and generates rhythm evaluation information;

[0149] The rhythm deviation trend data is called to statistically analyze the identified continuous rhythm deviation paragraphs. First, the deviation trend type of each action unit is recorded, for example, the data in Table 4. Action units 2, 3 and 4 all have continuous advance deviation trend, and action unit 1 has no deviation trend. The number of continuous deviation action units is 3. Then, the total duration of continuous deviation paragraphs is calculated, for example, the sum of the durations of action units 2, 3 and 4 is , the total duration of the training task is 4.50s, and the proportion of deviation paragraphs is calculated as , that is, the proportion of rhythm deviation segments is 77.8%. Further, compared with the standard allowed rhythm deviation proportion threshold of 30%, the actual calculated deviation segment proportion of 77.8% is obviously higher than the standard threshold. Based on the percentage system, set the rhythm fluctuation evaluation coefficient, deduct 10 points for every 10% exceeding the standard allowed deviation proportion, and calculate the specific deduction as points, therefore the rhythm stability score is points. This score indicates that there is a large fluctuation in the rhythm performed by the personnel in the training task, and the final evaluation result is used as the rhythm evaluation information.

[0150] The label output module comprises:

[0151] The index weight configuration submodule calls the rhythm evaluation information, extracts the corresponding ability priority parameters according to the type of the training task, and adjusts the weight of each evaluation index, including the action deviation amplitude, the stability of the aiming action, the hit score, and the fluctuation degree of the execution rhythm, to generate the ability weight distribution coefficient;

[0152] The rhythm evaluation information is called, and the ability priority is configured according to the actual training task type. The task type is specifically divided into three types of precision priority task, stability priority task and rhythm control priority task. Taking the precision priority task as an example, the priority of different ability indexes is determined. For the four evaluation indexes of action offset amplitude, aiming action stability, hit score and execution rhythm fluctuation degree, the priority parameters are obtained according to the actual scene statistics, wherein the hit score is determined as the first priority, the action offset amplitude is the second priority, the aiming stability is the third priority, and the execution rhythm fluctuation is the fourth priority. The specific weight proportion parameters are set for different priorities, for example, the hit score is configured with the highest priority weight of 0.4, the action offset amplitude is configured with the secondary weight of 0.3, the aiming stability is 0.2, and the execution rhythm fluctuation is 0.1. The training task type is judged, when the training personnel execute the precision priority task, the above parameters are directly called to adjust the weight of each evaluation index, and the comprehensive weight distribution coefficient of the index is calculated by using the weight adjustment formula: in the actual evaluation, the hit score is 0.4, the action offset amplitude is 0.3, the aiming stability is 0.2, and the rhythm fluctuation is 0.1 as the ability weight distribution coefficient.

[0153] The level attribution matching sub-module calls the ability weight distribution coefficient, classifies and judges the label level interval corresponding to each evaluation result, identifies the attribution position of each index value in the level interval, and generates a level interval matching relationship group;

[0154] The above ability weight distribution coefficient is called to classify and judge the values of each specific evaluation index one by one. Taking hit score, action offset amplitude, aiming stability, and execution rhythm fluctuation as specific indexes, the respective grade interval specific division standard is obtained based on the shooting task comprehensive performance evaluation experiment. For example, according to the experiment, if the hit score is 85 or above, it is determined to be "excellent", 75 to 85 is "good", 60 to 75 is "medium", and 60 or below is "poor". If the actual score is 92, it is directly classified as "excellent". If the action offset amplitude is taken as the angle error as the judgment standard, the offset amplitude in the 0 to 1.5 degree interval is defined as "excellent", 1.5 to 3 degrees is "good", 3 to 5 degrees is "medium", and 5 degrees or above is "poor". If the actual offset amplitude is 2.1 degrees, it is determined to be "good". The aiming stability is judged by the fluctuation score, and the score of 85 or above is "excellent", 70 to 85 is "good", 55 to 70 is "medium", and 55 or below is "poor". If the actual score is 69.5, the level is determined to be "medium". The execution rhythm fluctuation degree is judged by the offset segment proportion, and 0 to 20% is "excellent", 20 to 40% is "good", 40 to 60% is "medium", and 60% or above is "poor". If the actual fluctuation proportion is 77.8%, the level is determined to be "poor". Through the above grade classification operation, the corresponding grade label position of each index is obtained, that is, the hit score is "excellent", the action offset amplitude is "good", the aiming stability is "medium", and the execution rhythm fluctuation is "poor", which is integrated into a grade interval matching relationship group.

[0155] The result label generation submodule calls the grade interval matching relationship group, combines the weight of each evaluation index, calculates the performance score of the training personnel, identifies the performance level of each training personnel, and generates the training performance evaluation level.

[0156] The grade interval matching relationship group is called, and the ability weight of each evaluation index is taken as the parameter to calculate the overall performance score of the training personnel. The calculation process adopts the grade corresponding basic score, which is 95 points for excellent, 85 points for good, 70 points for medium, and 55 points for poor. The total score is calculated by bringing in the aforementioned grade matching result and the ability weight distribution coefficient: the hit score "excellent" basic score 95 points multiplied by the corresponding weight 0.4 to calculate 38 points, the action offset amplitude "good" basic score 85 points multiplied by the weight 0.3 to calculate 25.5 points, the aiming stability "medium" basic score 70 points multiplied by the weight 0.2 to calculate 14 points, and the execution rhythm fluctuation "poor" basic score 55 points multiplied by the weight 0.1 to calculate 5.5 points. The cumulative score is 38+25.5+14+5.5=83 points. The score is further matched with the performance level standard, and the overall score of 85 points or above is defined as the overall performance "excellent", 75 to 85 points is "good", 60 to 75 points is "general", and 60 points or below is "poor". The score obtained by this calculation is 83 points, and the overall performance level is determined to be "good", which is taken as the training performance evaluation level.

[0157] Referring to Fig. 3 In another aspect, a smart shooting examination and training method is provided, which is applied to a smart shooting examination and training system, and the method comprises the following steps:

[0158] S1: analyze real-time action images, extract a continuous image sequence in a process from holding a gun to firing, perform frame node extraction and angle path construction on shoulder and elbow actions, compare differences in actual angle proportion changes based on a standard action trajectory, screen deviation paragraphs and extract action deviation amplitudes, and generate shoulder and elbow posture information;

[0159] S2: based on the shoulder and elbow posture information, record point coordinates of a laser pointer on a target surface during aiming, construct a coordinate time sequence path, measure distances and direction variation amplitudes between adjacent coordinates, screen fluctuation trajectory segments, evaluate stability of aiming actions, and generate fluctuation frequency information;

[0160] S3: based on the fluctuation frequency information, sort a plurality of hit points formed by firing according to time to establish a hit point path structure, identify deviation paths and analyze extension continuity of the paths, calculate a hit score in combination with a coverage range of a hit area, and generate a fall point analysis result;

[0161] S4: based on the fall point analysis result, collect start and end times of each action unit in a training task, identify early and late trends of the action units in combination with a standard rhythm arrangement set in a training plan, evaluate a fluctuation degree of an execution rhythm, and generate rhythm evaluation information;

[0162] S5: based on the rhythm evaluation information, adjust weights of each evaluation index according to an ability priority setting configured for each training task type, identify a corresponding grade label of each index, calculate a performance score of a training personnel, and establish a training performance evaluation grade.

[0163] The above-described embodiments can be implemented in whole or in part by software, hardware (such as a circuit), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0164] It should be understood that the term "and / or" herein merely describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents that the associated objects before and after it are in an "or" relationship, but it can also represent an "and / or" relationship, which can be understood according to the context before and after it.

[0165] In the present application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or the like means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0166] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0167] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed 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 implementation should not be considered beyond the scope of the present application.

[0168] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the devices, apparatuses and units described above can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0169] In several embodiments provided by the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0170] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0171] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0172] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the present application that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of software products. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0173] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent shooting assessment and training system, characterized in that, The system includes: The posture recognition module analyzes real-time motion images. Based on the motion images of trainees from holding the gun to firing, it identifies the synchronous angle change trajectory of the shoulder and elbow, compares it with the corresponding angle combination in the standard motion, filters out deviation segments and extracts the motion offset amplitude, and generates shoulder and elbow posture information. The trajectory monitoring module calls the shoulder and elbow posture information to obtain the continuous coordinate points of the laser pointer on the target surface during aiming. By calculating the spatial distance and orientation change angle between adjacent coordinate points, it filters the fluctuating trajectory segments, evaluates the stability of the aiming action, and generates fluctuation frequency information. The hit analysis module calls the fluctuation frequency information, sorts the target hit points by firing time, connects adjacent hit points and analyzes the trend of directional change, identifies the offset path, and calculates the hit score by combining the extension continuity of the path and the coverage of the hit area, generating the landing point analysis result. The rhythm comparison module calls the landing point analysis results to analyze the start time corresponding to each action unit in the training task. By comparing it with the preset rhythm arrangement, it identifies the trend of action units being advanced or delayed, evaluates the degree of fluctuation in the execution rhythm, and generates rhythm evaluation information.

2. The intelligent shooting assessment and training system according to claim 1, characterized in that, The shoulder and elbow posture information includes the matching trajectory, offset segment, and joint angle sequence; the fluctuation frequency information includes the trajectory segment sequence, direction jump frequency, and stability marker; the landing point analysis results specifically include the hit concentration range, offset direction trend, and path extension structure; and the rhythm evaluation information specifically refers to the time distribution structure, rhythm offset segment, and operation sequence difference.

3. The intelligent shooting assessment and training system according to claim 1, characterized in that, The posture recognition module includes: The motion image processing submodule analyzes real-time motion images, extracts the contour coordinate point information corresponding to the shoulder and elbow in the sequence of motion images of trainees, constructs the motion time sequence of the shoulder and elbow, locates and corresponds key nodes in continuous images, and generates a dynamic trajectory sequence of the shoulder and elbow. The joint angle extraction submodule calls the shoulder and elbow dynamic trajectory sequence, calculates the angle value of the line connecting the two points according to the corresponding coordinate positions of the shoulder and elbow in each frame image, obtains a synchronous angle sequence composed of multiple angle points according to the time axis order, and generates the joint angle change path. The synchronization offset judgment submodule calls the joint angle change path, compares the change direction difference between the combination of two joint angles in the actual movement and the set combination in the standard movement, filters the synchronization deviation period, identifies the magnitude of the movement offset, and generates shoulder and elbow posture information.

4. The intelligent shooting assessment and training system according to claim 3, characterized in that, The trajectory monitoring module includes: The coordinate data acquisition submodule calls the shoulder and elbow posture information to acquire the coordinate data of the laser points projected onto the target surface by the trainee using the laser pointer during the aiming period. It records the coordinate points corresponding to each time node, arranges them in chronological order to form a coordinate sequence, establishes a continuous point spatial movement path, and generates laser movement trajectory data. The trajectory fluctuation recognition submodule calls the laser movement trajectory data, calculates the spatial distance and orientation change angle of adjacent points in the trajectory, filters the fluctuating trajectory segments, records the corresponding start time, and generates a set of trajectory fluctuation segments. The motion stability assessment submodule calls the set of trajectory fluctuation segments, identifies the interval of each fluctuation trajectory segment in the time series, and assesses the stability of the trainee's aiming motion based on the duration and frequency of the fluctuation trajectory segments in multiple time periods, generating fluctuation frequency information.

5. The intelligent shooting assessment and training system according to claim 4, characterized in that, The specific formula for assessing the stability of a trainee's aiming motion is as follows: ； Calculate the stability score of the aiming action; in, This indicates the stability score of the aiming action. This is the rating adjustment factor. Indicates the first Normalized value of the duration of each fluctuation trajectory segment Indicates the first The normalized value of the spatial trajectory fluctuation distance of each fluctuation trajectory segment. Represents the fluctuation frequency correction factor. This indicates the total number of fluctuation trajectory segments. This indicates the index of the trajectory fluctuation segment in the time series.

6. The intelligent shooting assessment and training system according to claim 4, characterized in that, The hit analysis module includes: The impact point data sorting submodule calls the fluctuation frequency information, collects the coordinate information of the actual hit points formed by firing on the target surface and obtains the corresponding firing time sequence, sorts and connects the hit points according to the time sequence to form a hit path structure and generates a hit connection path sequence. The offset trend extraction submodule calls the hit connection path sequence, extracts the angle of the connection direction of each path segment, and identifies the offset trend path of the connection direction between hit points by comparing the trajectory of the direction change of multiple shot hit points on the target surface, and generates the offset path identification result. The orientation aggregation evaluation submodule calls the offset path identification results, analyzes the extension continuity of the offset path, and evaluates the stability and consistency of the hit point aggregation direction in combination with the spatial coverage of the hit point on the target surface. Combined with the path offset direction, it generates the impact point analysis results. The specific formula for the spatial coverage of the hit point on the target surface is as follows: ； Calculate the clustering consistency index; in, Representing the The coordinates of each hit point in the horizontal direction of the target surface. Representing the The coordinates of each hit point in the longitudinal direction of the target surface. This represents the average of the horizontal coordinates of all hit points. This represents the average of the vertical coordinates of all hit points. This is a fixed setting for the reference radius of the firing hit area. For the first Normalized value of the hit point density in the sector region containing each hit point This is the normalized value that maximizes the density value across all sector regions during the training process. This represents the total number of hits during the current mission phase. As a consensus indicator, This represents the j-th hit point currently being calculated.

7. The intelligent shooting assessment and training system according to claim 6, characterized in that, The rhythm comparison module includes: The task time period identification submodule calls the landing point analysis results, collects the start time and end time records of each action unit in the training task, calculates the duration of each action unit, and generates an action time structure sequence. The rhythm trend comparison submodule calls the action time structure sequence, compares the start time of each action unit with the preset rhythm arrangement, identifies the advance and delay trends of the action units, and generates rhythm offset trend data. The fluctuation degree calculation submodule calls the rhythm offset trend data, analyzes the number of action segments with consecutive rhythm offsets and the duration range of each segment, calculates the proportion of rhythm offset segments during training, evaluates the fluctuation degree of the rhythm performed by the personnel in the training task, and generates rhythm evaluation information.

8. The intelligent shooting assessment and training system according to claim 1, characterized in that, The system also includes: The label output module calls the rhythm assessment information, adjusts the weight distribution of each assessment indicator according to the ability priority set in the training task, analyzes the attribution relationship between each indicator and the label level interval corresponding to the task type, calculates the performance score of the trainees, and generates the training performance assessment level. The training performance evaluation level specifically includes the label interval matching result, ability score composition, and level classification number.

9. The intelligent shooting assessment and training system according to claim 8, characterized in that, The tag output module includes: The indicator weight configuration submodule calls the rhythm evaluation information, extracts the corresponding capability priority parameters according to the training task type, and adjusts the weight of each evaluation indicator, including the magnitude of action deviation, the stability of aiming action, the hit score, and the degree of fluctuation of execution rhythm, to generate capability weight distribution coefficients. The level attribution matching submodule calls the capability weight distribution coefficient to classify and judge the label level interval corresponding to each evaluation result, identify the attribution position of each indicator value within the level interval, and generate a level interval matching relationship group. The result label generation submodule calls the level interval matching relationship group, combines the weight of each evaluation indicator, calculates the performance score of the trainees, identifies the performance level of each trainee, and generates the training performance evaluation level.

10. A method for intelligent shooting assessment and training, characterized in that, The method is used to implement the intelligent shooting assessment and training system according to any one of claims 1-9, the method comprising: S1: Analyze real-time motion images, extract continuous image sequences from the trainee holding the gun to firing, extract inter-frame nodes and construct angle paths for shoulder and elbow movements, compare the actual angle ratio changes based on standard motion trajectories, filter out deviation segments and extract the motion offset amplitude, and generate shoulder and elbow posture information. S2: Based on the shoulder and elbow posture information, record the position coordinates of the laser pointer on the target surface during aiming, construct a coordinate time series path, calculate the distance and direction change amplitude between adjacent coordinates, filter the fluctuation trajectory segment, evaluate the stability of the aiming action, and generate fluctuation frequency information. S3: Based on the fluctuation frequency information, the multiple hit points formed by firing are sorted in chronological order to establish the hit point path structure, the offset path is identified and the extension continuity of the path is analyzed, and the hit score is calculated in combination with the coverage of the hit area to generate the landing point analysis result. S4: Based on the landing point analysis results, collect the start and end times of each action unit in the training task, combine them with the standard rhythm arrangement set in the training plan, identify the advance and delay trends of action units, evaluate the degree of fluctuation in the execution rhythm, and generate rhythm evaluation information. S5: Based on the rhythm assessment information, adjust the weight of each assessment indicator according to the ability priority settings configured for each training task type, identify the level label corresponding to each indicator, calculate the performance score of the trainees, and establish a training performance assessment level.

Images