Portable console intelligent training system and method

Abstract

The application provides a portable console intelligent training system and method, relates to the technical field of human-computer interaction and intelligent training, and the method comprises the following steps: original trajectory data acquisition, operation feature extraction, capacity score vector construction, user capacity vector generation, capacity trend analysis and personalized training path construction. The posture angular velocity, displacement acceleration and key data of a user in a training process are collected through a portable console, multi-dimensional operation features are extracted, alignment and evaluation are performed in combination with a scoring rule and a dynamic time warping method, a capacity score and a user capacity vector are generated, the capacity development trend is further analyzed, the capacity short board is identified, and a personalized path is generated by matching a training task. The technical problems that the training system does not have portability, the training process data acquisition dimension is insufficient, the capacity evaluation is rough, and there is a lack of trend analysis and personalized training path recommendation in the prior art are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of human-computer interaction and intelligent training, and particularly relates to a portable console intelligent training system and method. BACKGROUND

[0002] With the development of human-computer interaction technology and intelligent training systems, more and more fields begin to introduce virtual training and operation ability evaluation technology to improve training efficiency and personnel operation ability. In complex device control, skill training, remote control and other scenarios, the operation stability, response speed, control accuracy and other indicators of the operator become important indicators for evaluating the operation level. Traditional training systems mostly rely on fixed equipment, manual scoring or rough statistical data, and have problems such as poor portability, single evaluation dimension, difficulty in continuously tracking user ability changes, and difficulty in meeting the needs of precise and personalized training.

[0003] In the prior art, some systems have tried to introduce trajectory analysis, sensor data acquisition and scoring mechanisms for operation ability evaluation, but generally lack trend modeling and ability short board identification mechanisms for user historical data, making it difficult to develop differentiated training strategies for users. In addition, the fixed training platform limits the flexibility of the use scenario, which is not conducive to the development of multi-site, multi-frequency daily training.

[0004] Therefore, there is an urgent need for an intelligent training system with a portable structure, which can collect multi-dimensional operation data and realize dynamic ability evaluation and personalized training recommendation, to improve the precision, adaptability and practicality of training. SUMMARY

[0005] The purpose of the present application is to provide a portable console intelligent training system and method to solve the technical problems in the prior art that the training system does not have portability, the training process data collection dimension is insufficient, the ability evaluation is rough, and there is a lack of trend analysis and personalized training path recommendation.

[0006] In view of the above problems, the present application provides a portable console intelligent training system and method.

[0007] In a first aspect, the present application provides a portable console intelligent training system for performing a portable console intelligent training method, comprising: an original trajectory data acquisition module, the original trajectory data acquisition module is used for collecting original trajectory data of a user during the execution of a training task on a portable console, the portable console has posture sensing and key input capabilities, and the original trajectory data includes attitude angular velocity, displacement acceleration, key time sequence and operation instruction number; an operation feature parameter set extraction module, the operation feature parameter set extraction module is used for preprocessing the original trajectory data, cutting based on the key time sequence, obtaining a plurality of trajectory segments corresponding to user operation behaviors, extracting an operation feature parameter set for each trajectory segment, and the operation feature parameter set includes attitude fluctuation, operation stability, response time delay and trajectory continuity; a capability score vector construction module, the capability score vector construction module is used for matching the operation feature parameter set with a scoring rule, determining a reference standard trajectory sequence, performing time sequence alignment by using a dynamic time warping (DTW) method, calculating a score index, and constructing a capability score vector in combination with the operation feature parameter set; a user capability vector generation module, the user capability vector generation module is used for normalizing each score dimension and embedding a time label by using the capability score vector, generating a user capability vector, and the user capability vector is a comprehensive operation level of the user in the operation stability, response speed, control precision and execution accuracy dimensions; a capability development trend graph generation module, the capability development trend graph generation module is used for calling the user capability vectors at a plurality of time points in a user historical training record database, constructing a capability evolution time sequence, and generating a capability development trend graph based on the change slope and fluctuation trend of each capability dimension; and a personalized training path construction module, the personalized training path construction module is used for identifying the capability short board dimension of the user by using the capability dimension with a downward or slowly increasing trend in the capability development trend graph, and generating a personalized training task path for the capability short board dimension by screening a training task corresponding to the capability short board dimension from a training task database.

[0008] In a second aspect, the application provides a portable console intelligent training method, which is implemented by a portable console intelligent training system and includes the following steps: collecting original trajectory data of a user during the execution of a training task on a portable console, the portable console having posture sensing and key input capabilities, and the original trajectory data including posture angular velocity, displacement acceleration, key time sequence, and operation instruction number; preprocessing the original trajectory data, segmenting based on the key time sequence, obtaining a plurality of trajectory segments corresponding to user operation behaviors, extracting an operation feature parameter set for each trajectory segment, and the operation feature parameter set including posture fluctuation, operation stability, response time delay, and trajectory continuity; matching the operation feature parameter set with a scoring rule, determining a reference standard trajectory sequence, performing time sequence alignment using a dynamic time warping (DTW) method, calculating a scoring index, and constructing a capability score vector in combination with the operation feature parameter set; normalizing each scoring dimension and embedding a time label through the capability score vector to generate a user capability vector, the user capability vector being a comprehensive operation level of the user in the operation stability, response speed, control accuracy, and execution accuracy dimensions; calling the user capability vectors at a plurality of time points in a user historical training record database, constructing a capability evolution time sequence, and generating a capability development trend map based on the change slope and fluctuation trend of each capability dimension; identifying the capability short board dimension of the user through the capability dimension with a downward or slow growth trend in the capability development trend map, and selecting a training task corresponding to the capability short board dimension from a training task database to generate an individualized training task path for the capability short board dimension.

[0009] The technical solutions provided in the application have at least the following technical effects or advantages:

[0010] The portable console is used to collect multi-source operation data, extract key features, quantify capability scores, identify capability short boards through trend analysis, and generate individualized training paths based on task adaptation degrees, thereby achieving portable, efficient, and accurate capability evaluation and individualized training recommendation, and improving the intelligent level and practicality of the training system.

[0011] The above description is only a summary of the technical solutions of the application. In order to more clearly understand the technical means of the application, the application can be implemented in accordance with the content of the specification, and in order to make the above and other purposes, features and advantages of the application more obvious and easy to understand, the following specific embodiments of the application are described. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the application, nor is it intended to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of the provided drawings.

[0013] Figure 1 A structural schematic diagram of a portable console intelligent training system according to the application;

[0014] Figure 2 A flowchart of a portable console intelligent training method according to the application.

[0015] Legend: original trajectory data acquisition module 1, operation characteristic parameter set extraction module 2, ability score vector construction module 3, user ability vector generation module 4, ability development trend map generation module 5, and individualized training path construction module 6. DETAILED DESCRIPTION

[0016] The application provides a portable console intelligent training system and method, which solves the technical problems of the prior art that the training system does not have portability, the training process data acquisition dimension is insufficient, the ability evaluation is rough, and there is a lack of trend analysis and individualized training path recommendation. The technical effects of portable, efficient, and accurate ability evaluation and individualized training recommendation are achieved, and the intelligent level and practicality of the training system are improved.

[0017] The technical solutions in the application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. It should be understood that the application is not limited by the exemplary embodiments described herein. Based on the embodiments of the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application. In addition, it should be noted that, for convenience of description, only parts related to the application are shown in the drawings, not all.

[0018] Embodiment one, please refer to the accompanying Figure 1 The application provides a portable console intelligent training system, which specifically comprises:

[0019] The original trajectory data acquisition module 1 is used to acquire original trajectory data of a user during the execution of a training task on a portable console. The portable console has posture sensing and key input capabilities. The original trajectory data includes posture angular velocity, displacement acceleration, key time sequence, and operation instruction number.

[0020] Specifically, multi-dimensional original trajectory data of a user during the execution of a training task on a portable console is collected. The portable console is integrated with a posture sensing module (gyroscope, accelerometer) and a key input unit, and can obtain real-time posture angular velocity data (i.e., angular velocity of rotation around each axis), displacement acceleration data (i.e., acceleration information in each direction), a key time sequence (i.e., a time stamp of each key event), and an operation instruction number (i.e., an identifier of a task or action instruction currently executed) during operation. The original trajectory data is stored in the form of a time sequence, in which the posture angular velocity and the displacement acceleration are uniformly recorded as a three-axis vector sequence at a sampling frequency, the key time sequence records the key code and the triggering time in an event-driven manner, and the operation instruction number is bound to the trajectory segment identifier.

[0021] An operation characteristic parameter set extraction module 2 is configured to preprocess the original trajectory data, segment the original trajectory data based on the key time sequence, obtain a plurality of trajectory segments corresponding to user operation behaviors, and extract an operation characteristic parameter set for each trajectory segment. The operation characteristic parameter set includes posture fluctuation, operation stability, response time delay, and trajectory continuity.

[0022] Further, the preprocessing of the original trajectory data, the segmentation of the original trajectory data based on the key time sequence, the obtaining of a plurality of trajectory segments corresponding to user operation behaviors, and the extraction of an operation characteristic parameter set for each trajectory segment include the following steps.

[0023] The preprocessing of the original trajectory data includes performing weighted median filtering denoising processing on the posture angular velocity and displacement acceleration data, performing sampling time alignment using linear interpolation, performing amplitude normalization on the trajectory space components based on the z-score standard deviation normalization method, and generating normalized trajectory data.

[0024] The normalized trajectory data is segmented based on the key pressing time points in the key time sequence and the operation instruction number change time points, and a plurality of trajectory segments corresponding to user operations are extracted.

[0025] For each trajectory segment, the time sequence correspondence between trajectory changes and instruction responses is determined according to the key time sequence in the corresponding time period, and an operation characteristic parameter set is extracted.

[0026] Further, the determination of the time sequence correspondence between trajectory changes and instruction responses for each trajectory segment according to the key time sequence in the corresponding time period and the extraction of an operation characteristic parameter set include the following steps.

[0027] Based on the sequence of components of the attitude angular velocity in the X, Y, Z axial direction in the trajectory segment, the mean value, the standard deviation and the coefficient of variation in each dimension are calculated, the mean value is used to reflect the average attitude direction, and the standard deviation and the coefficient of variation are used to characterize the fluctuation degree of the attitude control, so as to obtain the attitude fluctuation feature;

[0028] Based on the components of displacement acceleration in the X, Y, Z axial direction in the trajectory segment, the amplitude interval is calculated, combined with the standard deviation of each axial direction and the acceleration change rate of the adjacent time point, the acceleration fluctuation degree in the operation process is evaluated, and the operation stability feature is obtained;

[0029] Based on the attitude angular velocity components in the trajectory segment, the sliding window method is used to analyze the angular velocity change rate of adjacent time points, when the change rate exceeds the preset mutation threshold, the corresponding time point is determined as the attitude change mutation time point, the attitude change mutation time point is matched with the key trigger time point in the key time sequence, and the time difference between the two is calculated, and the response time delay feature is obtained;

[0030] Based on the spatial offset distance between the trajectory continuous points in the trajectory segment, the trajectory turning angle change rate and the path smoothness index are calculated by comparing the consistency of the direction and amplitude change of the trajectory points in the adjacent time period, and the trajectory continuity feature is obtained.

[0031] Specifically, the operation feature parameter set extraction module is used for pre-processing and operation feature extraction of the original trajectory data collected by the portable console. The original trajectory data includes: a three-axis attitude angular velocity sequence , a three-axis displacement acceleration sequence , and a key time sequence and an operation instruction number sequence. First, the weighted median filtering is performed on the attitude angular velocity and acceleration data respectively to remove high-frequency noise; then the linear interpolation method is used to time-align the sampling points of different channels; then the z-score standardization method is applied to the data of each sensor channel for amplitude normalization processing, and the processing formula is: Wherein, represents any time value in the original data sequence, represents the mean value of the channel in the whole time sequence, and the calculation formula is: , represents the standard deviation, and the calculation formula is: =1 to Normalization transforms trajectory data from different users or under different sampling conditions into a uniform distribution with a mean of 0 and a standard deviation of 1. Next, based on the time points of key press events and changes in operation command numbers recorded in the key press time series, the normalized trajectory data is divided into multiple trajectory segments, each representing a single independent user action. Within each trajectory segment, the following operational feature parameters are extracted: Attitude fluctuation characteristics: normalized sequence of attitude angular velocity. , , Calculate the mean respectively Standard deviation and coefficient of variation The coefficient of variation is defined as: Used to quantify the stability during attitude control. The larger the value, the more drastic the fluctuations and the more unstable the attitude. Operational stability characteristics: for acceleration sequences , , Calculate the normalized root mean square on each axis. Defined as: ( =1 to )in This represents the number of sampling points within the trajectory segment. If A preset stability threshold (e.g., 1.5) is used to determine if an axis exhibits significant fluctuations and is therefore unstable. This threshold can be set using a statistical sample of a standard user group. Additionally, the range of maximum amplitude on each axis is calculated. As a supplementary criterion. Response delay characteristics: sliding window analysis of the rate of change of angular velocity. , If the threshold for a mutation is exceeded (e.g., 2.0), it is recorded as a change in attitude. Compare this time point with the most recent key press trigger time point. To perform the matching, the response latency is defined as follows: This metric is used to evaluate the timeliness of instruction execution. Trajectory coherence feature: based on the spatial distance between adjacent sampling points within a trajectory segment. ,in, , , They represent the trajectory at time [time]. The three-axis coordinate components, express The spatial displacement between a given moment and the previous moment. The total path length is obtained by accumulating the changes over the entire trajectory segment. Furthermore, the rate of change of direction of the trajectory at consecutive moments is calculated, i.e., the rate of change of the turning angle. and the variance of the angle between the trajectory points is counted as the path smoothness index (such as the angle variance between the trajectory points) to measure whether the curvature change of the trajectory is smooth and consistent. The path length, the turning angle change rate and the angle variance are combined to form the trajectory continuity feature. The feature is used to represent the smoothness and stability of the user's action in the operation process. The higher the continuity, the more natural and mature the operation process is. Otherwise, there may be unstable or hesitant behavior.

[0032] The ability score vector construction module 3 is used to match the operation feature parameter set with the scoring rules, determine the reference standard trajectory sequence, perform time alignment using the dynamic time warping (DTW) method, calculate the scoring indicators, and construct the ability score vector in combination with the operation feature parameter set.

[0033] Further, it comprises:

[0034] The operation feature parameter set extracted by the user in the current training task is matched with the scoring rules in the training scoring standard database. Whether the operation feature index and the scoring rule item setting threshold fall within the scoring level interval is determined to determine the reference standard trajectory sequence. The scoring rules include trajectory offset tolerance threshold, posture control deviation threshold, time rhythm tolerance, and operation stability threshold.

[0035] The dynamic time warping (DTW) method is used to perform time alignment on the user trajectory segment and the reference standard trajectory sequence to obtain an aligned path.

[0036] Based on the aligned path, the scoring indicators are calculated, including trajectory space deviation score, time rhythm matching score, and posture matching score, and the matching degree is corrected according to the scoring rules.

[0037] The operation feature parameter set and the scoring rules are compared, and the posture fluctuation score, the operation stability score, the response time delay score, and the trajectory continuity score are determined according to the relationship between the feature values in each dimension and the set threshold.

[0038] The trajectory space deviation score, the time rhythm matching score, the posture matching score, the posture fluctuation score, the operation stability score, the response time delay score, and the trajectory continuity score are combined by weighting according to the preset weight parameters to generate an ability score vector.

[0039] Further, the calculation of the scoring indicators based on the aligned path includes:

[0040] Based on each pair of matching trajectory points in the aligned path , the position of the i-th sampling point in the user trajectory segment is obtained ​ corresponding to the i-th alignment point in the reference standard trajectory sequence and calculate a trajectory space deviation score , which is calculated as:

[0041] ;

[0042] wherein N is the total number of trajectory point pairs in the alignment path, is the i-th matched trajectory point pair, is the spatial distance of the i-th point pair, is the trajectory deviation tolerance threshold set in the scoring rule; k extract the time stamp difference of each matched point pair from the alignment path, and calculate a time rhythm matching score , which is calculated as:

[0043]

[0044] ;

[0045] wherein N is the total number of trajectory point pairs in the alignment path, and T are the time stamps of the i-th matched point of the user trajectory segment and the reference standard trajectory sequence respectively, is the time rhythm tolerance; based on the alignment path, extract the difference of the attitude angle parameters corresponding to each trajectory point pair, which includes the difference between the user trajectory segment and the reference standard trajectory sequence in pitch angle , yaw angle and roll angle

[0046] ; calculate an attitude matching score , which is calculated as:

[0047]

[0048] ;

[0049] wherein N is the total number of trajectory point pairs in the alignment path, are the pitch, yaw and roll angles of the i-th user trajectory segment respectively, are the pitch, yaw and roll angles of the i-th reference standard trajectory sequence respectively, is the preset maximum attitude deviation tolerance value; ​​​​​​​​​​

[0050] the trajectory space deviation score , the time rhythm matching score , the posture matching score together constitute the dimension elements of the capability score vector.

[0051] Specifically, the capability score vector construction module is used to match the operation characteristic parameter set extracted by the user in the portable console training task with the preset score rule, and realize the time sequence alignment of the user trajectory and the standard trajectory based on the dynamic time warping (DTW) method, and quantify the operation capability performance. First, the operation characteristic parameter set obtained by the user in the current training task is input into the system, the system accesses the training score standard database, and matches the reference standard trajectory sequence of the task type, action type and difficulty level according to the tolerance interval of each dimension index set in the score rule. The score rule is a set of judgment standards for mapping low-dimensional operation characteristic values to structured score results, which is preloaded in the system training score standard database. The setting of the score rule is based on a large number of expert operation sample data analysis and experience domain knowledge modeling, covering different task types, action categories and training difficulty levels. The score rule includes: trajectory deviation tolerance threshold ; used to evaluate the deviation degree between the user trajectory and the standard trajectory in the spatial position. The value is set based on the average deviation range of the standard trajectory sample. A higher score is given within the range of trajectory deviation less than the threshold, and a proportional deduction is made when it exceeds, reflecting the operation accuracy. Posture control deviation threshold ; used to evaluate the change trend and fluctuation range of the attitude angular velocity (Pitch, Roll, Yaw), and determine whether the user control is stable. The threshold is determined according to the attitude angular velocity characteristics (such as mean, standard deviation, coefficient of variation) and expert data modeling results, which is used to map the posture fluctuation score. Time rhythm tolerance , for evaluating the synchronization degree between user operation events (e.g. posture mutation, trajectory turning) and system expected action time points. Its tolerance range is set based on task rhythm requirements, reflecting the rhythm sense and reaction speed of user operation, which is converted into response time delay score. Operation stability threshold, for evaluating the smoothness of acceleration change in user operation, reflecting its operation continuity and force control level. The threshold is set based on the amplitude interval, rate of change and standard deviation statistical characteristics of each axial acceleration component in the standard operation sample, used to limit the fluctuation degree within a reasonable range. When the acceleration change in user operation falls within the threshold range, it means that its action output is relatively stable, and the score is higher; if there are frequent sharp fluctuations or sudden acceleration changes (i.e. beyond the threshold range), it is considered as unstable operation, and a lower score is given according to the set deduction rule. The threshold reflects the operation fluency and control accuracy, and is the key basis for calculating the operation stability score. Secondly, the DTW algorithm is used to time-align the user trajectory segment and the matching reference standard trajectory sequence to obtain the optimal alignment path W, where each pair of alignment points is composed of user trajectory point and reference trajectory point . Based on the alignment path, multiple score indicators are calculated: ① trajectory space deviation score , formula is ; where N is the total number of trajectory point pairs in the alignment path, is the th matching trajectory point pair, is the spatial distance of the th point, is the trajectory offset tolerance threshold set in the scoring rule, with a value range of [0, 1], the closer to 1 represents the closer to the reference trajectory; ② time rhythm matching score , calculated according to the timestamp difference of the alignment points: ; where and are the timestamps of the user trajectory segment and the reference standard trajectory at the th matching point, is the time rhythm tolerance; ③ posture matching score , the difference in pitch angle, yaw angle and roll angle of each pair of alignment points is extracted, and the calculation formula is: ; where is the total number of trajectory point pairs in the alignment path, are the pitch, yaw and roll angles of the th user trajectory segment, are the pitch, yaw and roll angles of the th reference standard trajectory sequence, The preset maximum attitude deviation tolerance value is then obtained. Then, the system performs scoring processing on each feature in the operation feature parameter set according to a scoring rule, and completes mapping from the feature value to the ability score. The scoring rule includes a numerical threshold preset for different operation dimensions for mapping the feature parameter to a quantitative score value. For the component sequence of the attitude angular velocity in the X, Y and Z axial directions, the mean value, standard deviation and coefficient of variation of the attitude fluctuation feature are calculated, and the feature value is matched with the attitude control deviation threshold set in the scoring rule to determine the scoring interval in which it falls, so as to obtain the attitude fluctuation score. Specifically, when the attitude fluctuation range exceeds the set attitude control deviation threshold, the score is correspondingly reduced. When the attitude fluctuation is small and remains within the normal fluctuation range, a higher score is given. For the component sequence of the displacement acceleration in each axial direction, the amplitude interval, acceleration change rate and standard deviation are calculated respectively to construct the operation stability feature. The amplitude interval reflects the amplitude range of the acceleration change, the change rate reflects the degree of change of the acceleration in a short time, and the standard deviation is used to represent the fluctuation of the acceleration. The calculation results are compared with the operation stability scoring standard to obtain the operation stability score. If the acceleration fluctuation is large and exceeds the operation stability threshold in the preset scoring rule, the operation stability score is low. Conversely, if the acceleration is stable and the fluctuation range is small, the operation stability score is high. The angular velocity change rate is analyzed through a sliding window, the attitude change mutation time points whose changes exceed the preset mutation threshold are extracted, and the time difference between the instruction trigger time points in the key time sequence is calculated to obtain the response time delay feature. The time difference is compared with the time rhythm tolerance threshold in the scoring rule, and the response time delay score is mapped according to the scoring threshold in which it falls. If the time difference is small, the response time delay score is high. In terms of trajectory continuity, the trajectory direction change rate, path smoothness and spatial offset consistency index are calculated to construct the trajectory continuity feature, and the trajectory offset tolerance threshold set in the scoring rule is combined to complete the trajectory continuity scoring. If the trajectory is smooth and the consistency is high, the score is high. If the trajectory changes dramatically or has a large deviation, the score is low. Finally, the above scoring results and the space, time and attitude matching scores calculated in the DTW alignment process are combined by weighting according to the preset weight parameters to form the ability score vector of the user in the training task, which is used as the basic data for subsequent ability evaluation and path recommendation.

[0052] The user ability vector generation module 4 is configured to generate a user ability vector by normalizing each scoring dimension and embedding a time label in the ability score vector, the user ability vector being a comprehensive operation level of the user in the operation stability, response speed, control precision and execution accuracy dimensions.

[0053] Further, the generating a user ability vector by normalizing each scoring dimension and embedding a time label in the ability score vector comprises:

[0054] performing linear normalization processing on each dimension of the capability score vector to obtain a normalized capability score vector;

[0055] corresponding the normalized capability score vector with each operation time based on the operation timestamp information contained in the original trajectory data and the key time sequence to generate a user capability vector containing a time label.

[0056] Specifically, the user capability vector generation module is configured to construct a user capability vector from a capability score vector to reflect the comprehensive capability performance of a user in dimensions such as operation stability, response speed, control accuracy, and execution accuracy and the change trend thereof over time. The capability score vector is composed of multiple sub-scores, which respectively reflect the evaluation results in aspects such as posture fluctuation, operation stability, response time delay, trajectory continuity, trajectory spatial deviation, time rhythm matching, and posture matching. In order to realize comparative and trend analysis across time periods and across users, the system performs linear normalization processing on each dimension of the capability score vector, and the normalization formula is: wherein is the current score value, and are the historical minimum value and the maximum value of the score dimension, respectively, which can be obtained according to the statistics of similar tasks. The normalized score value ensures comparability of different dimensions and traceability of the same dimension. Subsequently, the system embeds the normalized score vector with a time label, and the time label can be derived from the operation start timestamp in the original trajectory data and the key time sequence to realize the construction of the user capability vector Each user capability vector represents the operation capability state of a user when performing a training task.

[0057] The capability development trend map generation module 5 is configured to call the user capability vectors at multiple time points in the user historical training record database, construct a capability evolution time sequence, and generate a capability development trend map based on the change slope and fluctuation trend of each capability dimension.

[0058] Further, the calling of the user capability vectors at multiple time points in the user historical training record database, the construction of the capability evolution time sequence, and the generation of the capability development trend map based on the change slope and fluctuation trend of each capability dimension include:

[0059] extracting the user capability vectors corresponding to multiple training time points in the user historical training record database;

[0060] arranging the user capability vectors in chronological order to construct a capability evolution time sequence;

[0061] Based on the preset sliding window length and step, the score of each dimension in the ability evolution time sequence is calculated by sliding window difference, and the score change slope between continuous time points is obtained;

[0062] In each sliding window, the standard deviation of the score of each dimension is calculated as a volatility indicator;

[0063] Based on the score sequence of each ability dimension, the score change slope and the corresponding volatility indicator are combined, and a weighted linear regression method is used for trend fitting, and the weighted coefficient is the reciprocal of the volatility indicator in the sliding window;

[0064] The trend fitting results of each dimension are combined to generate a user ability development trend graph, and the user ability development trend graph is a curve set of the score of each dimension changing with time.

[0065] Specifically, the ability development trend graph generation module is used to extract user ability vectors at multiple time points from the user historical training record database to construct an ability score time sequence of user operation ability evolution over time, and generate an ability development trend graph by a trend analysis method to visually reflect the growth trajectory of the user in the dimensions of operation stability, response speed, control accuracy and execution accuracy. The system first extracts multiple training time points from the user historical training record database , where the th vector is represented as , which represents the normalized score value of the user at time in the th ability score dimension (such as operation stability). These ability vectors are arranged in ascending order of time to construct an ability evolution time sequence. For each ability score dimension , its score sequence changing over time is extracted , and sliding window processing is performed on the sequence, with a window length of and a sliding step of (for example, , ). In each sliding window, the score change slope and the volatility indicator of the current window are calculated. The calculation method of the score change slope is: for the window whose starting point is the th time point, the score change slope is defined as: , wherein represents the score growth rate of the th score dimension in the current window, which measures the improvement speed of the user in that ability dimension. At the same time, the score volatility indicator in the window, i.e. the score standard deviation, is calculated: , wherein The mean of scores within the window. Volatility indicator For measuring the stability of the score dimension in the current window. In order to comprehensively reflect the trend and stability of the ability score, the system adopts a weighted linear regression method to fit the trend of each dimension score sequence The fitting function is as follows: ; wherein the regression weight is set as the inverse of the volatility of the current window To enhance the contribution of the stable interval of the score to the fitted trend. Finally, the system combines the score fitting curves of all dimensions to generate a user ability development trend graph, which is a set of time-ability two-dimensional coordinate curves, used to dynamically visualize the development trajectory of the user in multiple ability dimensions. This method takes into account the score change rate and volatility factor, improving the accuracy and analysis interpretation of trend modeling, which helps to find slow or unstable operation dimensions of user progress, and supports subsequent training plan optimization and personalized ability intervention.

[0066] The personalized training path construction module 6 is used to identify the user's ability short board dimension through the ability dimension with a downward or slow growth trend in the ability development trend graph, and filter the training tasks corresponding to the ability short board dimension from the training task database to generate a personalized training task path for the ability short board dimension.

[0067] Further, the ability short board dimension of the user is identified through the ability dimension with a downward or slow growth trend in the ability development trend graph, and the training tasks corresponding to the ability short board dimension are filtered from the training task database to generate a personalized training task path for the ability short board dimension, which includes:

[0068] Extract the score change slope of each ability dimension in the ability development trend graph, and mark the positive slope less than the preset threshold or the negative value of the score dimension as the ability short board dimension;

[0069] Filter the training tasks matching the ability short board dimension from the training task database to form a candidate task set;

[0070] Calculate the adaptation score of each task in the candidate task set, the adaptation score is based on the coincidence ratio of the training target label and the user ability short board dimension label, the coverage degree of the operation feature parameter set in the training task and the ability short board feature parameter, and the matching between the training rhythm and the user historical training rhythm;

[0071] Sort the candidate task set according to the adaptation score, and select several tasks to form the personalized training task path.

[0072] Further, the calculation of the adaptation degree score comprises:

[0073] For each training task in the candidate task set, the task label set thereof is extracted and compared with the user ability short board dimension set D, the ratio of the intersection item number to the total item number of the user ability short board dimension set is calculated to obtain the label overlap ratio ;

[0074] The intersection proportion between the operation feature parameter set involved in the training operation in the candidate task set and the operation feature parameter set corresponding to the ability short board dimension is counted to obtain the parameter coverage ratio , as a feature coverage index;

[0075] The Euclidean distance of the training duration of the candidate task set and the average of the training duration in the user historical training record is calculated, and the reciprocal thereof is taken as the rhythm matching score ;

[0076] According to the preset weight , , , the label overlap ratio , the parameter coverage ratio and the rhythm matching score are weighted and summed to generate the final adaptation degree score .

[0077] Specifically, in the user ability development trend graph, the ability dimensions with a downward or slow growth trend are identified as the user's ability short board, and accordingly suitable tasks are selected from the training task database to construct a targeted personalized training path. First, the module extracts the change slope of each ability dimension score in the user ability development trend graph, which is obtained by difference calculation on the time series user ability vector through the sliding window method. Specifically, the sliding window length w and step s are set, and the mean difference in the adjacent window is calculated for each dimension score , and then divided by the time interval to obtain the score slope: ; wherein is the mean value of the score of the th ability dimension in the window starting time . If < (wherein is the preset progress threshold of the dimension, such as 0.01 by experience), the ability dimension is marked as the user ability short board dimension set D, denoted as . Then, tasks matching the ability short board dimension D are selected from the training task database to form a candidate task set . Each training task with a set of task labels and a set of involved operation characteristic parameters For each candidate task, a fitness score is calculated , which takes into account the overlap ratio of training target labels and user ability short board dimension labels, the coverage degree of the set of operation characteristic parameters in the training task and the ability short board characteristic parameters, and the matching between the training rhythm and the user historical training rhythm. The fitness score is composed of three parts: label overlap ratio : defined as , which measures the matching degree of task target and short board dimension; parameter coverage ratio : defined as , where is the set of all operation characteristic parameters associated with the dimension in D , which measures the coverage degree of task operation content and short board parameters; rhythm matching score : calculated by comparing the Euclidean distance between the task training duration and the user historical training average duration , the formula is , which measures whether the training rhythm matches the user's habit. The final fitness score is obtained by weighted combination of the above three parts by a preset weight 。

[0078] In summary, the portable console intelligent training system provided by the present application has the following technical effects:

[0079] An original trajectory data acquisition module 1 is configured to acquire original trajectory data of a user during the execution of a training task on a portable console, the portable console being capable of posture sensing and key input. The original trajectory data includes posture angular velocity, displacement acceleration, key time sequence, and operation instruction number.

[0080] An operation characteristic parameter set extraction module 2 is configured to preprocess the original trajectory data, split based on the key time sequence, obtain a plurality of trajectory segments corresponding to user operation behaviors, and extract an operation characteristic parameter set for each trajectory segment. The operation characteristic parameter set includes posture fluctuation, operation stability, response time delay, and trajectory continuity.

[0081] ​The capability score vector construction module 3 is configured to match the operation characteristic parameter set with the scoring rules, determine the reference standard trajectory sequence, perform time sequence alignment by using a dynamic time warping (DTW) method, calculate the scoring indexes, and construct the capability score vector in combination with the operation characteristic parameter set.

[0082] The user capability vector generation module 4 is configured to normalize each scoring dimension and embed a time label by using the capability score vector, and generate a user capability vector, which is a comprehensive operation level of the user in the operation stability, response speed, control precision and execution accuracy dimensions.

[0083] The capability development trend graph generation module 5 is configured to call the user capability vectors at multiple time points in the user historical training record database, construct a capability evolution time sequence, and generate a capability development trend graph based on the change slope and fluctuation trend of each capability dimension.

[0084] The individualized training path construction module 6 is configured to identify the capability short board dimension of the user by using the capability development trend graph, and filter a training task corresponding to the capability short board dimension from a training task database to generate an individualized training task path for the capability short board dimension.

[0085] In the second embodiment, based on the same inventive concept as the portable console intelligent training system in the foregoing embodiments, the present application further provides a portable console intelligent training method, please refer to the accompanying drawings Figure 2 , which comprises the following steps.

[0086] The original trajectory data of a user during the execution of a training task on a portable console is collected, the portable console has posture sensing and key input capabilities, and the original trajectory data includes posture angular velocity, displacement acceleration, key time sequence, and operation instruction number; the original trajectory data is preprocessed, segmented based on the key time sequence, a plurality of trajectory segments corresponding to user operation behaviors are obtained, operation feature parameter sets are extracted for each trajectory segment, and the operation feature parameter sets include posture fluctuation, operation stability, response time delay, and trajectory continuity; the operation feature parameter sets are matched with scoring rules to determine a reference standard trajectory sequence, dynamic time warping (DTW) is used for time sequence alignment, a scoring index is calculated, and a capability scoring vector is constructed in combination with the operation feature parameter sets; through the capability scoring vector, each scoring dimension is normalized and embedded with a time label to generate a user capability vector, the user capability vector is the comprehensive operation level of the user in the operation stability, response speed, control accuracy, and execution accuracy dimensions; a plurality of time point user capability vectors in a user historical training record database are called to construct a capability evolution time sequence, and a capability development trend map is generated based on the change slope and fluctuation trend of each capability dimension; through the capability development trend map, a capability short board dimension of the user is identified, and a training task corresponding to the capability short board dimension is selected from a training task database to generate a personalized training task path for the capability short board dimension.

[0087] Each embodiment in the specification is described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The portable console intelligent training system in the first embodiment and the specific example are also applicable to the portable console intelligent training method of the present embodiment. Based on the foregoing detailed description of the portable console intelligent training system, those skilled in the art can clearly understand the portable console intelligent training method of the present embodiment. Therefore, for the sake of brevity of the specification, the portable console intelligent training method of the present embodiment will not be described in detail.

[0088] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0089] Obviously, many modifications and variations of the present application are possible in light of the above teachings. It is, therefore, to be understood that within the scope of the application and its equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A portable control console intelligent training system, characterized in that, The system includes: The original trajectory data acquisition module is used to acquire the original trajectory data of the user performing training tasks on the portable control panel. The portable control panel has attitude perception and key input capabilities. The original trajectory data includes attitude angular velocity, displacement acceleration, key time sequence and operation command number. The operation feature parameter set extraction module is used to preprocess the original trajectory data, segment it based on the key time series, obtain multiple trajectory segments corresponding to user operation behaviors, and extract an operation feature parameter set for each trajectory segment. The operation feature parameter set includes attitude fluctuation, operation stability, response delay and trajectory coherence. A capability scoring vector construction module is used to match the set of operational feature parameters with scoring rules, determine a reference standard trajectory sequence, perform time alignment using the Dynamic Time Warping (DTW) method, calculate scoring indicators, and construct a capability scoring vector by combining the set of operational feature parameters. Constructing the capability scoring vector includes: matching the set of operational feature parameters extracted by the user in the current training task with scoring rules in the training scoring standard database; determining a reference standard trajectory sequence by comparing whether the operational feature indicators and the thresholds set by the scoring rule items fall within the scoring level range; and determining the reference standard trajectory sequence. The scoring rules include a trajectory offset tolerance threshold, an attitude control deviation threshold, a time rhythm tolerance, and an operational stability threshold. The Dynamic Time Warping (DTW) method is used to perform temporal alignment between the user trajectory segment and the reference standard trajectory sequence to obtain the alignment path. Based on the alignment path, a scoring index is calculated, including trajectory space deviation score, time rhythm matching score, and posture matching score, and the matching degree is corrected according to the scoring rules. By comparing the set of operational feature parameters with the scoring rules, and based on the relationship between the feature values ​​of each dimension and the set thresholds, the attitude fluctuation score, operational stability score, response delay score and trajectory consistency score are determined. The trajectory space deviation score, time rhythm matching score, attitude matching score, attitude fluctuation score, operation stability score, response delay score and trajectory coherence score are weighted and combined according to preset weight parameters to generate a capability score vector. The user capability vector generation module is used to normalize each scoring dimension and embed time tags through the capability scoring vector to generate a user capability vector. The user capability vector is the user's comprehensive operational level in the dimensions of operational stability, response speed, control precision and execution accuracy. The capability development trend map generation module is used to call the user capability vectors at multiple time points in the user's historical training record database, construct a capability evolution time series, and generate a capability development trend map based on the change slope and fluctuation trend of each capability dimension. A personalized training path construction module is used to identify the user's capability deficiency dimension by identifying capability dimensions that show a downward or slow growth trend in the capability development trend map, and to select training tasks corresponding to the capability deficiency dimension from the training task database to generate a personalized training task path oriented towards the capability deficiency dimension.

2. The portable control console intelligent training system as described in claim 1, characterized in that, The original trajectory data is preprocessed and segmented based on the key press time series to obtain multiple trajectory segments corresponding to user operation behaviors. An operation feature parameter set is extracted from each trajectory segment, including: The original trajectory data is preprocessed, including performing weighted median filtering to denoise the attitude angular velocity and displacement acceleration data, using linear interpolation to align the sampling time, and normalizing the amplitude of the trajectory spatial components based on the z-score standard deviation normalization method to generate normalized trajectory data. Based on the key press time and operation command number change time in the key time series, the normalized trajectory data is segmented into time series to extract multiple trajectory segments corresponding to user operations. For each trajectory segment, the temporal correspondence between trajectory changes and command responses is determined based on the key press time sequence within the corresponding time period, and the set of operation feature parameters is extracted.

3. The portable control console intelligent training system as described in claim 2, characterized in that, For each trajectory segment, based on the key press time sequence within the corresponding time period, the temporal correspondence between trajectory changes and command responses is determined, and an operation feature parameter set is extracted, including: Based on the component sequences of attitude angular velocity in the X, Y, and Z axes of the trajectory segment, the mean, standard deviation, and coefficient of variation of each dimension are calculated. The mean is used to reflect the average attitude direction, and the standard deviation and coefficient of variation are used to characterize the degree of attitude control fluctuation, thereby obtaining attitude fluctuation characteristics. Based on the components of displacement acceleration in the X, Y, and Z axes of the trajectory segment, the amplitude range is calculated. Combining the standard deviation of each axis with the rate of change of acceleration at adjacent time points, the degree of acceleration fluctuation during the operation is evaluated, and the operational stability characteristics are obtained. Based on the attitude angular velocity components in the trajectory segment, the sliding window method is used to analyze the rate of change of angular velocity at adjacent moments. When the rate of change exceeds a preset abrupt change threshold, the corresponding moment is determined as the attitude change abrupt change time point. The attitude change abrupt change time point is matched with the key trigger time point in the key time sequence, and the time difference between the two is calculated to obtain the response delay characteristics. Based on the cumulative spatial offset distance between continuous points in the trajectory segment, the consistency of the changes in direction and amplitude of trajectory points in adjacent time periods is compared, and the trajectory turning angle change rate and path smoothness index are calculated to obtain the trajectory continuity characteristics.

4. The portable control console intelligent training system as described in claim 1, characterized in that, Based on the alignment path, a scoring index is calculated, including trajectory space deviation score, temporal rhythm matching score, and posture matching score. The matching degree is then corrected according to the scoring rules, including: Based on each pair of matching trajectory points in the alignment path Obtain the first segment of the user trajectory from each segment. Location of each sampling point The corresponding first in the reference standard trajectory sequence Alignment points And calculate the trajectory space deviation score. The formula is: ； in The total number of trajectory point pairs in the alignment path. For the first For matching trajectory point pairs, For the first k Spatial distance between points The trajectory deviation tolerance threshold set in the scoring rules; Extract the timestamp difference of each pair of matching points from the alignment path, and calculate the time rhythm matching score. The calculation formula is as follows: ； in, The total number of trajectory point pairs in the alignment path. and The user trajectory segment and the reference standard trajectory sequence are respectively in the 1st... The timestamp of each matching point This refers to the time rhythm tolerance; Based on the alignment path, the attitude angle parameter difference corresponding to each pair of trajectory points is extracted. The attitude angle parameter difference includes the pitch angle difference between the user trajectory segment and the reference standard trajectory sequence. Yaw angle and roll angle Differences in; Calculate posture matching score The calculation formula is as follows: ； in, The total number of trajectory point pairs in the alignment path. The first Pitch, yaw, and roll angles of individual user trajectory segments For the first Pitch, yaw, and roll angles of a reference standard trajectory sequence This is the preset maximum attitude deviation tolerance value; The trajectory space deviation score Time and rhythm matching score Posture matching score These together constitute the dimensional elements of the aforementioned ability score vector.

5. The portable control console intelligent training system as described in claim 1, characterized in that, The process of generating a user capability vector by normalizing each scoring dimension and embedding time tags using the capability scoring vector includes: Perform linear normalization on each dimension of the ability score vector to obtain a normalized ability score vector; Based on the original trajectory data and the operation timestamp information contained in the key press time sequence, the normalized ability score vector is mapped to each operation time to generate a user ability vector containing time tags.

6. The portable control console intelligent training system as described in claim 1, characterized in that, The process involves retrieving user capability vectors from multiple time points in the user's historical training record database, constructing a capability evolution time series, and generating a capability development trend map based on the slope and fluctuation trend of each capability dimension. This includes: Extract user capability vectors corresponding to multiple training time points from the user's historical training record database; Arrange the user capability vectors in chronological order to construct a capability evolution time series; Based on the preset sliding window length and step size, the sliding window difference calculation is performed on the scores of each dimension in the capability evolution time series to obtain the slope of score change between consecutive time points. Within each sliding window, the standard deviation of the scores for each dimension is calculated as a volatility indicator; Based on the scoring sequence of each capability dimension, and combining the slope of the score change with the corresponding volatility index, a weighted linear regression method is used to fit the trend. The weighting coefficient of the weighted linear regression method is the reciprocal of the volatility index within the sliding window. The fitting results of trends in each dimension are combined to generate a user capability development trend map, which is a set of curves showing how scores in each dimension change over time.

7. The portable control console intelligent training system as described in claim 1, characterized in that, The process of identifying user skill gap dimensions by analyzing skill dimensions exhibiting a declining or slow growth trend in the skill development trend graph, and then selecting training tasks corresponding to these skill gap dimensions from the training task database to generate personalized training task paths tailored to those skill gap dimensions, includes: Extract the slope of the score change of each ability dimension in the ability development trend map, and mark the score dimensions with a positive slope less than the preset threshold or a negative value as ability weakness dimensions. Training tasks that match the aforementioned capability deficiency dimension are selected from the training task database to form a candidate task set; For each task in the candidate task set, a fit score is calculated. The fit score is based on the overlap ratio between the training target label and the user's capability deficiency dimension label, the coverage of the set of operational feature parameters in the training task with the capability deficiency feature parameters, and the matching between the training rhythm and the user's historical training rhythm. The candidate task set is sorted according to the fit score, and several tasks are selected to form the personalized training task path.

8. The portable control console intelligent training system as described in claim 7, characterized in that, The calculation of the fit score includes: For each training task in the candidate task set, extract its task label set and compare it with the user capability weakness dimension set D. Calculate the ratio of the number of intersection items to the total number of items in the user capability weakness dimension set to obtain the label overlap ratio. ; The parameter coverage ratio is obtained by statistically analyzing the intersection ratio between the set of operational feature parameters involved in the training operations in the candidate task set and the set of operational feature parameters corresponding to the capability shortcoming dimension. , as a feature coverage metric; The Euclidean distance between the training duration of the candidate task set and the mean of the training duration in the user's historical training records is calculated, and the reciprocal of the distance is taken as the rhythm matching score. ; According to preset weights , , Regarding the label overlap ratio Parameter coverage ratio and rhythm matching score Perform a weighted summation to generate the final fit score. .

9. A portable control panel intelligent training method, characterized in that, Performed by a portable console intelligent training system according to any one of claims 1 to 8, comprising: The system collects raw trajectory data of the user during the execution of training tasks on a portable control console. The portable control console has attitude sensing and key input capabilities. The raw trajectory data includes attitude angular velocity, displacement acceleration, key time sequence, and operation command number. The original trajectory data is preprocessed and segmented based on the key time series to obtain multiple trajectory segments corresponding to user operation behaviors. An operation feature parameter set is extracted for each trajectory segment, which includes attitude fluctuation, operation stability, response delay and trajectory coherence. The operation feature parameter set is matched with the scoring rules to determine the reference standard trajectory sequence. The Dynamic Time Warping (DTW) method is used for time alignment, and the scoring index is calculated. A capability scoring vector is constructed by combining the operation feature parameter set. The construction of the capability scoring vector includes: matching the operation feature parameter set extracted by the user in the current training task with the scoring rules in the training scoring standard database; determining the reference standard trajectory sequence by comparing whether the operation feature index and the threshold set by the scoring rule items fall within the scoring level range; the scoring rules include trajectory offset tolerance threshold, attitude control deviation threshold, time rhythm tolerance, and operation stability threshold. The Dynamic Time Warping (DTW) method is used to perform temporal alignment between the user trajectory segment and the reference standard trajectory sequence to obtain the alignment path. Based on the alignment path, a scoring index is calculated, including trajectory space deviation score, time rhythm matching score, and posture matching score, and the matching degree is corrected according to the scoring rules. By comparing the set of operational feature parameters with the scoring rules, and based on the relationship between the feature values ​​of each dimension and the set thresholds, the attitude fluctuation score, operational stability score, response delay score and trajectory consistency score are determined. The trajectory space deviation score, time rhythm matching score, attitude matching score, attitude fluctuation score, operation stability score, response delay score and trajectory coherence score are weighted and combined according to preset weight parameters to generate a capability score vector. The user capability vector is generated by normalizing each rating dimension and embedding time tags through the capability rating vector. The user capability vector is the user’s comprehensive operational level in the dimensions of operational stability, response speed, control precision and execution accuracy. The user capability vectors from multiple time points in the user's historical training record database are called to construct a capability evolution time series. Based on the slope and fluctuation trend of each capability dimension, a capability development trend map is generated. By identifying the user's capability shortcomings through capability dimensions that show a downward or slow growth trend in the capability development trend map, and by selecting training tasks corresponding to the capability shortcomings from the training task database, a personalized training task path is generated for the capability shortcomings.

Images