Training management method and device, electronic equipment and storage medium

Abstract

The invention discloses a training management method and device, electronic equipment and a storage medium, belongs to the technical field of training, and is used for solving the problem that related training management technologies and intervention measures are insufficient in flexibility and real-time performance. The method comprises the following steps: acquiring behavior data of a learner; based on the behavior data, through a pre-trained learning performance prediction model, learning performance information of the learner in a future learning task is predicted; and determining a target learning path of the learner based on the learning performance information, so as to determine a training strategy for the learner based on the target learning path.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of training technology, and particularly relates to a training management method and device, electronic equipment and a storage medium. BACKGROUND

[0002] Training technology refers to a technical system for designing, implementing and optimizing vocational training, skill training and other processes by means of modern information technology, data analysis, artificial intelligence and other means. It includes online training platforms, learning management systems (LMS), intelligent training systems, virtual reality (VR) and augmented reality (AR) technologies, aiming to improve learning effectiveness through digitization and personalization.

[0003] The personalized intervention module of the related training management technology may rely too much on static rules or preset intervention strategies, and lacks real-time monitoring and dynamic adjustment functions, resulting in that the intervention measures cannot accurately match the actual needs of the learners. For learners with special learning disabilities or slower progress, the intervention measures may not be flexible or timely enough.

[0004] That is, the related training management technology has the problems of insufficient flexibility and real-time performance of intervention measures. SUMMARY

[0005] The embodiments of the application provide a training management method and device, electronic equipment and a storage medium, which can solve the problem of insufficient flexibility and real-time performance of intervention measures of the related training management technology.

[0006] In a first aspect, the embodiments of the application provide a training management method, which comprises: acquiring behavior data of a learner; based on the behavior data, predicting learning performance information of the learner in a future learning task by using a pre-trained learning performance prediction model; based on the learning performance information, determining a target learning path of the learner, so as to determine a training strategy for the learner based on the target learning path.

[0007] In a second aspect, the embodiments of the application provide a training management device, which comprises: an acquisition module configured to acquire behavior data of a learner; a prediction module configured to predict learning performance information of the learner in a future learning task by using a pre-trained learning performance prediction model based on the behavior data; and a first determination module configured to determine a target learning path of the learner based on the learning performance information, so as to determine a training strategy for the learner based on the target learning path.

[0008] In a third aspect, an electronic device is provided, and the electronic device includes a processor and a memory arranged to store computer-executable instructions configured to be executed by the processor, the computer-executable instructions including instructions for performing the training management method according to the first aspect.

[0009] In a fourth aspect, a storage medium is provided, and the storage medium is configured to store computer-executable instructions, and the computer-executable instructions cause a computer to perform the training management method according to the first aspect.

[0010] In a fifth aspect, a chip is provided, and the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to run a program or instructions to implement the training management method according to the first aspect.

[0011] In a sixth aspect, a computer program product is provided, and the computer program product includes a computer program, and the computer program is configured to be executed by a processor to implement the training management method according to the first aspect.

[0012] In the embodiments of the present application, the behavior data of the learner is obtained, the learning performance information of the learner in a future learning task is predicted based on the behavior data by using a pre-trained learning performance prediction model, the target learning path of the learner is determined based on the learning performance information, and the training strategy for the learner is determined based on the target learning path. Compared with the related personalized intervention module of the training management technology, which may excessively rely on static rules or pre-set intervention strategies, the learning performance information of the learner in the future learning task is predicted by using the pre-trained learning performance prediction model, the target learning path of the learner is determined based on the learning performance information, and the training strategy for the learner is determined based on the target learning path, so that the learning difficulties of the learner are identified in advance, the current learning path of the learner is dynamically adjusted according to the different learning performance information of the learner in the future learning task, the target learning path of the learner is determined, and then the actual needs of the learner are matched accurately, and the cumulative problems of the learner are avoided, so that the flexibility and real-time performance are higher, and the problems of the related training management technology, such as insufficient flexibility and real-time performance of the intervention measures, are solved. BRIEF DESCRIPTION OF DRAWINGS

[0013] Figure 1 FIG. 1 is a flow diagram of a training management method provided by the embodiments of the present application; Figure 2 FIG. 2 is a diagram showing the relationship between feature indicators in the behavior data of a learner at different stages provided by the embodiments of the present application; Figure 3A flowchart illustrating another training management method provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of a training management device provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0015] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0016] The training management method, apparatus, electronic device, and storage medium provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0017] Figure 1 This illustration shows a training management method provided by an embodiment of the present invention. The method can be executed by an electronic device, which may include a server and / or a terminal device, wherein the terminal device may be, for example, a vehicle-mounted terminal or a mobile terminal. The method includes the following steps: S102: Obtain learner behavioral data.

[0018] Behavioral data refers to learners' interactions with learning resources or tasks on the training management platform during the learning process. The training management platform, such as a learning management system or online education platform, is not specifically limited in this regard. Learning tasks, such as Open Educational Resources (OER) and online courses, are also not specifically limited in this regard. Interactive behaviors, such as attempting to answer questions, submitting assignments, or performing other learning tasks, are also not specifically limited in this regard.

[0019] Given that many related training management solutions rely on manual intervention or traditional data collection methods, this may lead to omissions or inaccuracies in the data collection process, thus affecting the quality of subsequent predictions and interventions. In practical applications, whenever a learner engages in an interaction, the learner's raw behavioral data can be automatically recorded. This collected raw behavioral data can then be synchronized in real-time, or pre-processed and synchronized to a backend server or database in real-time, ensuring data integrity and security. This provides a solid data foundation for predicting subsequent learning performance and personalized interventions. Specifically, the electronic device in this embodiment can collect the learner's raw behavioral data in real-time via an Application Programming Interface (API) or WebSocket protocol. The raw behavioral data can then be pre-processed to ensure its suitability for subsequent analysis, or it can be left unprocessed to ensure data integrity. The pre-processed behavioral data or raw behavioral data is then organized and stored according to learner identification codes (Identity Document, ID), task IDs, timestamps, and other information for subsequent analysis and processing. Distributed database synchronization technology enables real-time synchronization of behavioral data or raw behavioral data across multiple training management systems or platforms, ensuring timely updates and sharing of this data. This includes preprocessing such as data cleaning, format conversion, and standardization; data cleaning including, but not limited to, missing value handling and outlier detection; missing value handling such as filling or deleting missing values; and outlier detection such as using statistical methods or pre-trained isolated forest models to identify and handle outliers. This preprocessing can be configured according to actual needs and is not specifically limited. Behavioral data or raw behavioral data can be stored in a structured format in a database, ensuring efficient querying and access. Relational databases or NoSQL databases can be used to store learner behavioral data or raw behavioral data, ensuring data reliability and scalability. Relational databases include MySQL; NoSQL databases include MongoDB.

[0020] S104: Based on behavioral data, a pre-trained learning performance prediction model is used to predict learners' learning performance information in future learning tasks.

[0021] Learning performance information includes, but is not limited to, one or more of the following: the learner's future completion rate, grades, pass rate for learning tasks, and the number of failed attempts for learning resources or learning tasks.

[0022] In practical applications, if the backend server or database stores raw behavioral data (i.e., unprocessed behavioral data), the raw behavioral data is first preprocessed. Then, based on the learner's current behavioral data, a pre-trained learning performance prediction model is used to predict the learner's learning performance in future learning tasks.

[0023] S106: Based on learning performance information, determine the learner's target learning path, and based on the target learning path, determine the training strategy for the learner.

[0024] In practical applications, learners can be trained according to training strategies.

[0025] To distinguish it from the future learning tasks described below, the aforementioned future learning tasks will be referred to as the first future learning task. Specifically, if, based on learning performance information, it is determined that there exists a second future learning task for the learner that meets the first preset condition within the aforementioned first future learning task; then, the learner's target learning path can be determined based on the second future learning task and the current learning path; and / or, if, based on learning performance information, it is determined that there exists a third future learning task for the learner that meets the second preset condition within the aforementioned first future learning task; then, the learner's target learning path can be determined based on the third future learning task and the current learning path; wherein, the first preset condition may include one or more of the following: the learner's completion rate for the first future learning task is less than or equal to a first preset completion rate threshold; ... The learning task score is lower than a first preset score threshold; the learner's pass rate for the first future learning task is less than or equal to a first preset pass rate threshold; and the number of failed attempts for the learning resource or the first future learning task is greater than a first preset failure attempt threshold. The second preset condition may include one or more of the following: the learner's completion rate for the first future learning task is greater than a second preset completion rate threshold; the learner's score for the first future learning task is greater than or equal to a second preset score threshold; the learner's pass rate for the first future learning task is greater than a second preset pass rate threshold; and the number of failed attempts for the learning resource or the first future learning task is less than or equal to a second preset failure attempt threshold. Therefore, if a learner encounters difficulty in a certain module, it recommends relearning the relevant content or provides review materials. If a learner performs well on certain learning tasks, some basic content can be skipped, and more challenging learning materials can be recommended. This allows for early identification of learners' learning difficulties, determination of target learning paths, and enhancement of learners' learning motivation and interest.

[0026] Furthermore, based on the learner's performance in future learning tasks and their progress on the current learning path, a target learning path can be determined. This further increases the accuracy of the determined target learning path.

[0027] The training management method provided in this invention acquires learner behavioral data; based on the behavioral data, it uses a pre-trained learning performance prediction model to predict learner performance information in future learning tasks; based on the learning performance information, it determines the learner's target learning path, and then determines a training strategy for the learner based on the target learning path. Compared to the personalized intervention modules of related training management technologies, which may rely too much on static rules or preset intervention strategies, this application uses a pre-trained learning performance prediction model to predict learner performance information in future learning tasks, and determines the learner's target learning path based on the learning performance information, thereby determining a training strategy for the learner. This allows for the early identification of learners' learning difficulties, and dynamically adjusts the learner's current learning path according to different learning performance information in future learning tasks, determining the learner's target learning path. This ensures accurate matching of learners' actual needs while avoiding cumulative problems, offering greater flexibility and real-time performance. It solves the problem of insufficient flexibility and real-time performance in intervention measures of related training management technologies.

[0028] In one implementation, after predicting the learner's learning performance information in future learning tasks (i.e., S104) using a pre-trained learning performance prediction model, the following step A1 can also be performed: Step A1: Based on learning performance information, determine the target future learning task with corresponding target preset learning difficulty information, and then determine the training strategy for the learner based on the target future learning task.

[0029] In practical applications, learners can be trained according to this training strategy.

[0030] This includes the ability to preset learning difficulty information for the target future learning task; the preset learning difficulty information may include multiple difficulty levels, as well as corresponding knowledge points and / or learning resources.

[0031] Specifically, based on the learner's learning performance information for future learning tasks, if it is determined, based on the learning performance information, that there exists a fourth future learning task for the learner that meets the third preset condition among the aforementioned first future learning tasks; then, based on the preset learning difficulty information of the fourth future learning task, a target future learning task with a corresponding difficulty level lower than the preset learning difficulty information of the fourth future learning task (i.e., the target preset learning difficulty information) can be determined; and / or, if it is determined, based on the learning performance information, that there exists a fifth future learning task for the learner that meets the fourth preset condition among the aforementioned first future learning tasks; then, based on the preset learning difficulty information of the fifth future learning task, a target future learning task with a corresponding difficulty level higher than the preset learning difficulty information of the fifth future learning task (i.e., the target preset learning difficulty information) can be determined; wherein, the third preset condition may include The fourth preset condition may include one or more of the following: the learner's completion rate for the first future learning task is less than or equal to a third preset completion rate threshold; the learner's score for the first future learning task is less than a third preset score threshold; the learner's pass rate for the first future learning task is less than or equal to a third preset pass rate threshold; and the number of failed attempts for learning resources or the first future learning task is greater than a third preset failure attempt threshold. The fourth preset condition may include one or more of the following: the learner's completion rate for the first future learning task is greater than a fourth preset completion threshold; the learner's score for the first future learning task is greater than or equal to a fourth preset score threshold; the learner's pass rate for the first future learning task is greater than a fourth preset pass rate threshold; and the number of failed attempts for learning resources or the first future learning task is less than or equal to a fourth preset failure attempt threshold. Therefore, for learners predicted to perform poorly, the system automatically reduces the task difficulty or recommends more supplementary materials to help them gradually overcome learning obstacles; for learners predicted to perform well, the system can increase the task difficulty, adding challenges to promote further learning and progress.

[0032] In one implementation, after predicting the learner's learning performance information in future learning tasks (i.e., S104) using a pre-trained learning performance prediction model, the following step B1 can also be performed: Step B1: Based on learning performance information and behavioral data, determine the learning resources to recommend to learners.

[0033] In practical applications, behavioral data can also include learners' task completion rates. Based on learning performance information and behavioral data, learners' learning preferences, learning progress, and / or target learning resources can be determined. Then, based on these preferences, progress, and / or target resources, recommended learning resources can be determined. Specifically, future learning tasks or corresponding learning resources that meet the fifth pre-set condition in the learning performance information and behavioral data can be identified—the target learning resources. The type of learning resources that meet the sixth pre-set condition in the learning performance information and behavioral data can also be identified—that is, the learners' learning preferences. This includes information on the type of learning resources, such as video explanations, text / charts, audio explanations, practice questions, and related textbooks. The fifth preset condition may include one or more of the following: the learner's completion rate for the future learning task is less than or equal to the fifth preset completion rate threshold; the learner's score for the future learning task is less than the fifth preset score threshold; the learner's pass rate for the future learning task is less than or equal to the fifth preset pass rate threshold; and the number of failed attempts for the future learning task is greater than the fifth preset failure attempt threshold. The sixth preset condition may include one or more of the following: the learner's completion rate for the future learning task is greater than the sixth preset completion threshold; the learner's score for the future learning task is greater than or equal to the sixth preset score threshold; the learner's pass rate for the future learning task is greater than the sixth preset pass rate threshold; and the number of failed attempts for the future learning task is less than or equal to the sixth preset failure attempt threshold. Therefore, the system dynamically adjusts based on the learner's learning progress, preferences, and difficulties to ensure that the most suitable learning resources are recommended to the learner, providing optimal learning support.

[0034] In one implementation, the learning performance prediction model is trained based on a random forest regression model.

[0035] In practical applications, historical behavior data can be retrieved from the aforementioned backend server or database. If the backend server or database stores raw historical behavior data (i.e., unprocessed historical behavior data), then the raw historical behavior data is first preprocessed to obtain the historical behavior data. Afterward, the random forest regression model can be trained based on the historical behavior data.

[0036] Considering that some feature indicators in historical behavioral data may have a higher correlation with learning performance information, while others may be redundant or unimportant, the selection of feature indicators is crucial. Specifically, based on a random forest regression model, the correlation coefficient between each feature indicator in the historical behavioral data and learning performance information can be calculated, along with recursive feature elimination (RFE), to determine the target feature indicator. The historical behavioral data corresponding to the target feature indicator is then used as the sample set. Based on this sample set, the random forest regression model is trained to obtain the aforementioned learning performance prediction model. Specifically, the Pearson correlation coefficient between each feature indicator in the historical behavioral data and learning performance information can be calculated to determine the first feature indicator whose Pearson correlation coefficient is greater than a preset correlation threshold. Based on this first feature indicator, the random forest regression model is trained through recursive feature elimination, gradually eliminating unimportant feature indicators and selecting the feature indicator most helpful for prediction, i.e., determining the target feature indicator.

[0037] Random forest is an ensemble learning method that improves prediction accuracy by constructing multiple decision trees and combining their predictions. Each decision tree is trained independently, and the final prediction is obtained by averaging the results.

[0038] Specifically, training the random forest regression model based on the above sample set can include the following steps: dividing the sample set into a training set and a test set, using 70% as the training set and 30% as the test set; using the bootstrap method, randomly extracting data and feature indicators from the training set for each decision tree as a training subset, and training the decision tree based on the training subset; wherein, the division of nodes in the decision tree is determined according to the maximum information gain or minimum Gini index of the feature indicators; the hyperparameters of the random forest regression model include the number of decision trees T, the maximum depth of each decision tree, the minimum number of sample splits for each decision tree, etc., and optimizing these hyperparameters through grid search and cross-validation methods can find the optimal configuration of the random forest regression model. Then, the trained random forest regression model is evaluated using indicators such as mean squared error (MSE) or root mean square error (RMSE) to verify its prediction accuracy on the test set, as shown in the following formulas (1) and (2): (1) (2) Where N is the number of learners, and i is the i-th learner; The first prediction made by the trained random forest regression model. Learning performance information of each learner; It is the first one on the test set Learning performance information for each learner.

[0039] Once the trained random forest regression model passes the evaluation, it will be used as the pre-trained learning performance prediction model.

[0040] Accordingly, for each learner, their behavioral data is input into a pre-trained learning performance prediction model. The model outputs prediction results through multiple decision trees trained within it, and the average of these predictions is determined as the learner's learning performance information for future learning tasks. For example, the behavioral data of each learner i is represented as a vector. ,in It is the first Each learner One characteristic indicator; for each learner The learner's behavioral data is input into a pre-trained learning performance prediction model. The pre-trained learning performance prediction model predicts the learner's learning performance information in future learning tasks using the following formula (3): (3) in, It is the first prediction made by the pre-trained random forest regression model. Learning performance information of individual learners It is the number of decision trees. It is the first decision trees for the first Behavioral data of individual learners The prediction results.

[0041] In one implementation, the aforementioned behavioral data includes one or more of the following: the number of times the learner failed to complete the learning task, the number of times the learner made mistakes in the learning task, and the learning time the learner spent on the learning task.

[0042] The number of times a learner fails to complete a learning task reflects the difficulty they encounter in that task; the number of errors a learner makes in a learning task reflects a lack of understanding or operational skills; and the amount of time a learner spends on a learning task may indicate that the task is too difficult for them or that they do not understand it clearly.

[0043] In S102 above, the behavioral data can be stored according to the structure shown in the table below:

[0044] In this table, Learner_ID represents the learner's ID, and FailureAttempts (FA), WrongActions (WA), and TimeTaken (TT) represent the number of times the learner failed to complete the learning task, the number of times the learner made errors in the learning task, and the learning time spent on the learning task, respectively. It should be noted that the above example is only for the purpose of understanding how behavioral data is stored and does not constitute a specific limitation on behavioral data or its storage method.

[0045] For the number of times learners make mistakes in the learning task and the learning time for the learning task in the behavioral data, i.e., numerical feature indicators, in order to avoid the difference in scale of different feature indicators in the behavioral data, the above S102 or S104 preprocesses the original behavioral data, which may include standardization, such as Z-score standardization, as shown in the following formula (4): (4) Where x is the original value of the numerical feature indicator, μ is the mean of the numerical feature indicator, and σ is the standard deviation of the numerical feature indicator. Through standardization, the numerical feature indicator will be transformed into a distribution with a mean of 0 and a standard deviation of 1.

[0046] In addition, behavioral data can also include task completion rate, which reflects the learner's degree of completion of the learning task and is used to determine the learner's learning progress.

[0047] For example, the relationship between learners' failure attempts (FA) and learning time (TT) was analyzed to explore the potential regularities in learners' behavioral characteristics, providing data support for personalized intervention and learning path adjustment. Specifically, the learners' behavioral data included the following key characteristic indicators: PreviousLB-FA: number of failure attempts in the previous stage (i.e., the number of times the learner failed to complete the learning task); PreviousLB-TT: learning time in the previous stage; CurrentLB-FA: number of failure attempts in the current stage; CurrentLB-TT: learning time in the current stage. Scatter plots were created to compare the distribution of behavioral characteristics between the two stages, such as... Figure 2As shown, this study analyzes the relationship between the number of failed attempts and learning time to observe whether a positive correlation exists. Here, ○ represents learner behavior data from previous stages (Previous LB-FA and Previous LB-TT). × represents learner behavior data from the current stage (Current LB-FA and Current LB-TT). From... Figure 2 It can be intuitively observed that there is a positive correlation between the number of failed attempts (FA) and the learning time (TT), that is, the more failed attempts, the longer the learning time. The data in the current stage is more concentrated in distribution than the data in the previous stage, indicating that personalized intervention and real-time feedback may have improved learners' learning behavior.

[0048] In one implementation, after acquiring the learner's behavioral data (i.e., S102), the following step C1 may also be performed: Step C1: Based on the behavioral data, determine whether there is any abnormal behavioral data.

[0049] Abnormal behavior data, such as learners failing to complete learning tasks too many times or taking too long to complete them, are not specifically limited.

[0050] In addition, a real-time feedback mechanism can be set up. Specifically, when learners make mistakes in learning tasks, corresponding error analysis and correction suggestions can be provided immediately to help learners correct their mistakes in a timely manner. Furthermore, if a learner's learning progress lags behind the expected learning progress, timely reminders can be provided and additional learning resources can be recommended, or the learning tasks can be adjusted.

[0051] Based on behavioral data, the learning performance information of learners in future learning tasks is predicted through a pre-trained learning performance prediction model (i.e., S104). The following step C2 can be performed: If so, in step C2, based on the behavioral data, the learner's learning performance information in future learning tasks is predicted using a pre-trained learning performance prediction model.

[0052] If so, an alert will be triggered, and step S104 above can be executed. Simultaneously, the alert mechanism can be used to remind learners or teachers in advance.

[0053] Figure 3 This is a flowchart illustrating another training management method provided in an embodiment of this application. Figure 3 As shown, the method includes: Step 302: Obtain learner behavior data.

[0054] Behavioral data includes one or more of the following: the number of times learners fail to complete learning tasks, the number of times learners make mistakes in learning tasks, and the time learners spend on learning tasks.

[0055] Step 304: Based on the behavioral data, determine whether there is any abnormal behavioral data.

[0056] Step 306: If so, then based on the behavioral data, the learner's learning performance information in future learning tasks is predicted using a pre-trained learning performance prediction model.

[0057] The learning performance prediction model was trained based on a random forest regression model.

[0058] Step 308: Based on learning performance information, determine the learner's target learning path and, based on learning performance information, determine the target future learning task with corresponding target preset learning difficulty information, so as to determine the training strategy for the learner based on the target learning path and the target future learning task.

[0059] The specific processes of steps 302 to 308 have been described in detail in the above embodiments and will not be repeated here.

[0060] This embodiment acquires learner behavioral data; based on this data, a pre-trained learning performance prediction model predicts learner performance in future learning tasks; based on this performance, a target learning path is determined, and a training strategy is then developed accordingly. Compared to related training management technologies where personalized intervention modules may rely too heavily on static rules or pre-set intervention strategies, this application uses a pre-trained learning performance prediction model to predict learner performance in future tasks. Based on this performance, a target learning path is determined, and a training strategy is then developed to identify learners' learning difficulties in advance. Furthermore, the current learning path is dynamically adjusted based on learners' performance in future tasks to determine their target learning path. This approach ensures accurate matching of learners' actual needs while preventing cumulative problems, offering greater flexibility and real-time performance. It addresses the shortcomings of related training management technologies in terms of flexibility and real-time intervention measures.

[0061] Corresponding to the training management method provided in the above embodiments, based on the same technical concept, the present invention also provides a training management device. Figure 4 This is a schematic diagram of a training management device according to an embodiment of the present invention, which is used to perform... Figures 1 to 3 The training management methods described, such as Figure 4 As shown, the training management device includes: an acquisition module 410, a prediction module 420, and a first determination module 430.

[0062] Module 410 is used to acquire learner behavioral data; The prediction module 420 is used to predict learners' learning performance information in future learning tasks based on behavioral data and through a pre-trained learning performance prediction model. The first determining module 430 is used to determine the learner's target learning path based on learning performance information, and to determine the training strategy for the learner based on the target learning path.

[0063] In one implementation, the training management device further includes a second determining module. The second determining module is specifically used for: Based on learning performance information, target future learning tasks with corresponding preset learning difficulty information are determined, and training strategies for learners are determined based on these target future learning tasks.

[0064] In one implementation, the training management device further includes a third determining module. The third determining module is specifically used for: Based on learning performance information and behavioral data, we determine the learning resources to recommend to learners.

[0065] In one implementation, the learning performance prediction model is obtained by training a random forest regression model.

[0066] In one implementation, the aforementioned behavioral data includes one or more of the following: the number of times the learner failed to complete the learning task, the number of times the learner made mistakes in the learning task, and the learning time the learner spent on the learning task.

[0067] In one implementation, the training management device further includes a fourth determining module. The fourth determining module is specifically used for: Based on behavioral data, determine whether there is any abnormal behavioral data; Prediction module 420 is specifically used for: If so, then based on behavioral data, a pre-trained learning performance prediction model can be used to predict the learner's learning performance information in future learning tasks.

[0068] This embodiment acquires learner behavioral data; based on this data, a pre-trained learning performance prediction model predicts learner performance in future learning tasks; based on this performance, a target learning path is determined, and a training strategy is then developed accordingly. Compared to related training management technologies where personalized intervention modules may rely too heavily on static rules or pre-set intervention strategies, this application uses a pre-trained learning performance prediction model to predict learner performance in future tasks. Based on this performance, a target learning path is determined, and a training strategy is then developed to identify learners' learning difficulties in advance. Furthermore, the current learning path is dynamically adjusted based on learners' performance in future tasks to determine their target learning path. This approach ensures accurate matching of learners' actual needs while preventing cumulative problems, offering greater flexibility and real-time performance. It addresses the shortcomings of related training management technologies in terms of flexibility and real-time intervention measures.

[0069] Those skilled in the art will understand that the above-described training management device can be used to implement the training management method described above, and the detailed description therein should be similar to the description in the method section above. To avoid repetition, it will not be repeated here.

[0070] Based on the same technical concept, embodiments of this application also provide an electronic device for executing the above-described training management method. Figure 5 This is a schematic diagram of the structure of an electronic device to implement various embodiments of this application. The electronic device can vary significantly due to differences in configuration or performance, and may include a processor 510, a communications interface 520, a memory 530, and a communication bus 540. The processor 510, communications interface 520, and memory 530 communicate with each other via the communication bus 540. The processor 510 can call a computer program stored in the memory 530 and executable on the processor 510 to perform the following steps: Acquire learners' behavioral data; Based on behavioral data, a pre-trained learning performance prediction model is used to predict learners' learning performance information in future learning tasks. Based on learning performance information, the learner's target learning path is determined, and based on the target learning path, a training strategy is determined for the learner.

[0071] This embodiment acquires learner behavioral data; based on this data, a pre-trained learning performance prediction model predicts learner performance in future learning tasks; based on this performance, a target learning path is determined, and a training strategy is then developed accordingly. Compared to related training management technologies where personalized intervention modules may rely too heavily on static rules or pre-set intervention strategies, this application uses a pre-trained learning performance prediction model to predict learner performance in future tasks. Based on this performance, a target learning path is determined, and a training strategy is then developed to identify learners' learning difficulties in advance. Furthermore, the current learning path is dynamically adjusted based on learners' performance in future tasks to determine their target learning path. This approach ensures accurate matching of learners' actual needs while preventing cumulative problems, offering greater flexibility and real-time performance. It addresses the shortcomings of related training management technologies in terms of flexibility and real-time intervention measures.

[0072] The specific implementation steps can be found in the various steps of the above training management method embodiment, and can achieve the same technical effect. To avoid repetition, they will not be repeated here.

[0073] It should be noted that the electronic devices in the embodiments of this application include: servers, terminals, or other devices besides terminals.

[0074] The above electronic device structure does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or arrange them differently. For example, an input unit may include a Graphics Processing Unit (GPU) and a microphone, and a display unit may use a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar display panels. User input units include at least one of a touch panel and other input devices. A touch panel is also called a touchscreen. Other input devices may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be elaborated further here.

[0075] Memory can be used to store software programs and various data. Memory can primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory can include volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0076] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0077] This application also provides a storage medium storing computer-executable instructions. When these computer-executable instructions are executed by a processor, they implement the various processes of the above-described training management method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0078] The processor is the processor in the electronic device described in the above embodiments. The storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0079] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described training management method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0080] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0081] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the various processes of the above-described training management method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0082] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include multitasking and parallel processing according to the functions involved, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0083] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of the various embodiments of this application.

[0084] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A training management method characterized by, The method comprises: obtaining behavior data of a learner; based on the behavior data, predicting learning performance information of the learner in a future learning task by a pre-trained learning performance prediction model; based on the learning performance information, determining a target learning path of the learner, to determine a training strategy for the learner based on the target learning path.

2. The method of claim 1, wherein, After the predicting learning performance information of the learner in a future learning task by a pre-trained learning performance prediction model, the method further comprises: based on the learning performance information, determining a target future learning task corresponding to target preset learning difficulty information, to determine a training strategy for the learner based on the target future learning task.

3. The method of claim 1, wherein, After the predicting learning performance information of the learner in a future learning task by a pre-trained learning performance prediction model, the method further comprises: determining learning resources recommended to the learner according to the learning performance information and the behavior data.

4. The method of claim 1, wherein, The learning performance prediction model is trained based on a random forest regression model.

5. The method of claim 1, wherein, The behavior data comprises one or more of the following: the number of times the learner fails to complete a learning task, the number of times the learner makes errors in a learning task, and the learning time of the learner for a learning task.

6. The method of claim 1, wherein, After the obtaining behavior data of a learner, the method further comprises: based on the behavior data, determining whether there is abnormal behavior data; The predicting learning performance information of the learner in a future learning task by a pre-trained learning performance prediction model based on the behavior data comprises: if yes, predicting the learning performance information of the learner in the future learning task by the pre-trained learning performance prediction model based on the behavior data.

7. A training management apparatus characterized by comprising: The apparatus comprises: an obtaining module configured to obtain behavior data of a learner; a predicting module configured to predict learning performance information of the learner in a future learning task by a pre-trained learning performance prediction model based on the behavior data; a first determining module configured to determine a target learning path of the learner based on the learning performance information, to determine a training strategy for the learner based on the target learning path.

8. The method of claim 7, wherein, The apparatus comprises: a second determining module configured to determine a target future learning task based on the learning performance information and task difficulty information of a current learning task of the learner, to determine a training strategy for the learner based on the target future learning task.

9. An electronic device, comprising: comprise: a processor; and a memory arranged to store computer-executable instructions configured to be executed by the processor, the computer-executable instructions comprising instructions for performing the training management method according to any one of claims 1-6.

10. A storage medium, characterized by The storage medium is configured to store computer-executable instructions, which cause a computer to perform the training management method according to any one of claims 1-6.

Images