Data analysis-based personalized training program generation system and method

Abstract

The application discloses a personalized training scheme generation system and method based on data analysis, and relates to the technical field of training management.The personalized training scheme generation system based on data analysis comprises a training portrait initial evaluation module, a portrait reconstruction judgment module, a training path timeliness judgment module and a reconstructed path effectiveness evaluation module.The application obtains an initial portrait update priority and judges whether the employee training portrait triggers portrait update.If yes, the portrait construction data is updated, otherwise, the update criticality is evaluated, then whether the personalized training path is reconstructed is judged.If no, the personalized training path generation interval is optimized, otherwise, whether the initial portrait update priority is adjusted is judged, the generation timeliness of the personalized training scheme is improved, and the problem that the generation timeliness of the personalized training scheme and the training progress correlation are insufficient in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of intelligent training management technology, and in particular to a system and method for generating personalized training programs based on data analysis. Background Technology

[0002] With the rapid development of data analytics and the widespread application of artificial intelligence, personalized training programs are gradually becoming an important means of improving employee skills and efficiency. Data analytics-based personalized training program generation systems utilize data mining, machine learning, and other technologies to tailor training content and optimize learning paths based on learners' characteristics and learning progress. This approach enables precise and real-time allocation of learning resources, helping learners maximize their learning outcomes while also saving companies training costs and improving overall talent quality.

[0003] Existing personalized training program generation technologies primarily rely on learner information and past learning records to build recommendation systems. Common methods include content-based recommendation, collaborative filtering, and hybrid recommendation algorithms. However, these methods largely focus on static data analysis, neglecting the dynamic changes and individual differences during the learning process. Although some systems have incorporated machine learning and data mining techniques, they still face challenges in data accuracy, real-time performance, and personalization depth, making it difficult to fully meet the needs of individual differences and generate efficient learning paths.

[0004] For example, patent application CN118761874A discloses a method for generating personalized training programs based on big data analysis, which includes: learning behavior analysis, personalized content generation, dynamic feedback adjustment, and adaptive path optimization. The results of learning behavior analysis serve as the data basis for personalized content generation, and the dynamic feedback adjustment signals serve as the data support for adaptive path optimization. Adaptive path optimization is based on learning data and dynamic feedback information, and uses reinforcement learning algorithms to adaptively adjust the learning path and optimize the learning order and content arrangement.

[0005] For example, the invention patent announcement CN118396804B, concerning a precise teaching management method and system based on adaptive learning analysis, includes: for each student, determining learning trajectory data and acquiring learning resource browsing records, combining them to obtain multi-source heterogeneous learning data, determining knowledge nodes and cognitive state nodes, and constructing a personalized knowledge graph; determining the optimal learning path, performing joint optimization by combining multi-task learning, applying a multi-view attention network, determining the influencing factors of the planning path and recommending learning resources, generating an initial learning behavior sequence, updating the personalized knowledge graph in real time until reaching the preset maximum number of iterations, and obtaining a learning behavior sequence; performing deep self-encoding based on the learning behavior sequence, constructing a student learning profile, performing multi-dimensional diagnostic analysis of student learning effects, generating a personalized diagnostic report, constructing an adaptive evaluation model, generating corresponding diagnostic evaluation questions, and generating a personalized teaching plan.

[0006] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems:

[0007] In existing technologies, since employee training profiles are a core part of personalized training paths, the updates of relevant data related to the construction of employee training profiles are not refined enough, resulting in reduced timeliness of the constructed employee training profiles. Consequently, the timeliness of personalized training paths is also reduced, leading to insufficient correlation between the timeliness of personalized training program generation and training progress. Summary of the Invention

[0008] This application provides a personalized training program generation system and method based on data analysis, which solves the problem that the timeliness of personalized training program generation is not sufficiently correlated with the training progress in the prior art, and improves the timeliness of personalized training program generation.

[0009] This application provides a personalized training program generation system based on data analysis, including: an initial training profile assessment module, a profile reconstruction judgment module, a training path timeliness judgment module, and a reconstruction path effectiveness assessment module. The initial training profile assessment module retrieves the initial profile update priority from a preset database for various profile construction data, and assesses the training progress changes of employee training profiles based on changes in the various profile construction data. The employee training profile is used to measure the progress changes of employees during actual training. The profile reconstruction judgment module determines whether to trigger a profile update based on the assessment results. If so, it updates the corresponding category of profile construction data; otherwise, it performs an update threshold assessment on various types of profile construction data. The training path timeliness judgment module determines whether to reconstruct the employee training profile based on the assessment results, constructs a personalized training path based on the obtained employee training profile, and quantifies the update timeliness of the employee training profile. The reconstruction path effectiveness assessment module determines whether to reconstruct the personalized training path based on the quantification results. If not, it optimizes the personalized training path generation interval; otherwise, it performs a reconstruction effectiveness assessment of the reconstructed personalized training path to determine whether to adjust the initial profile update priority.

[0010] This application provides a method for generating personalized training programs based on data analysis, with the following specific steps: First, obtain the initial profile update priority of various profile construction data from a preset database. Then, assess the training progress of employee training profiles based on changes in the various profile construction data. Employee training profiles are used to measure the progress changes of employees during actual training. Based on the assessment results, determine whether to trigger a profile update. If so, update the corresponding category of profile construction data; otherwise, assess the update threshold for various profile construction data. Based on the assessment results, determine whether to reconstruct the employee training profile. Construct a personalized training path based on the obtained employee training profile and quantify the update timeliness of the employee training profile. Based on the quantification results, determine whether to reconstruct the personalized training path. If not, optimize the personalized training path generation interval; otherwise, assess the reconstruction effectiveness of the reconstructed personalized training path to determine whether to adjust the initial profile update priority.

[0011] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0012] 1. By combining the initial profile update priority with changes in various profile construction data, the training progress of employee training profiles is assessed. Based on this, it is determined whether to trigger a profile update. If so, an update is performed; otherwise, an update threshold assessment is conducted. Then, based on the assessment results, it is determined whether to reconstruct the employee training profile and build a personalized training path. The update timeliness of the employee training profile is quantified, and based on this, it is determined whether to rebuild the personalized training path. If not, the generation interval of the personalized training path is optimized; otherwise, it is determined whether to adjust the update priority of the initial profile. This improves the timeliness of employee training profiles, thereby improving the timeliness of personalized training plan generation. It effectively solves the problem of insufficient correlation between the timeliness of personalized training plan generation and training progress in existing technologies.

[0013] 2. By obtaining the profile construction data change parameters and the profile construction change allocation from the preset database, and then performing weighted calculations on the profile construction data change parameters and the profile construction change allocation, the impact of employee training progress changes is obtained. This more accurately quantifies the degree of influence of employee training indicators on employee training profiles, thereby improving the timeliness of employee training profiles.

[0014] 3. By acquiring training path progress data and obtaining training path progress allocation rate and reference path progress time data from a preset database, the average training indicator completion time is compared with the reference training indicator completion time to obtain the training indicator completion time value. The training participation time is then compared with the reference training participation time to obtain the training participation value. Based on the above data, a training path effectiveness evaluation index is obtained, thereby more accurately quantifying the effectiveness of personalized training path optimization and reconstruction, and thus improving the timeliness of personalized training paths. Attached Figure Description

[0015] Figure 1 A schematic diagram of the structure of a personalized training program generation system based on data analysis provided in this application embodiment;

[0016] Figure 2 A schematic diagram illustrating the process of updating critical assessments of various types of profile construction data, provided for embodiments of this application;

[0017] Figure 3 A flowchart illustrating the process of determining whether to adjust the priority of the initial image update, provided in an embodiment of this application;

[0018] Figure 4 A flowchart illustrating the method for generating personalized training programs based on data analysis, as provided in the embodiments of this application;

[0019] Figure 5An interface diagram of the personalized training program generation system based on data analysis provided in the embodiments of this application;

[0020] Figure 6 An interface diagram of the initial assessment module for the training profile of the data analysis-based personalized training program generation system provided in this application embodiment;

[0021] Figure 7 An interface diagram of the profile reconstruction and judgment module of the personalized training program generation system based on data analysis provided in the embodiments of this application;

[0022] Figure 8 An interface diagram of the training path timeliness determination module of the personalized training program generation system based on data analysis provided in this application embodiment;

[0023] Figure 9 This is an interface diagram of the reconstruction path effectiveness evaluation module of the personalized training scheme generation system based on data analysis provided in the embodiments of this application. Detailed Implementation

[0024] This application provides a personalized training program generation system and method based on data analysis, solving the problem of insufficient correlation between the timeliness of personalized training program generation and training progress in existing technologies. It obtains the initial profile update priority of various profile building data, classifies employee profile building data, and then obtains the historical average update frequency corresponding to each type of profile building data. Next, based on the historical average update frequency, it maps the initial profile update priority of the corresponding category of profile building data into a preset database. Then, it monitors the changes in various types of profile building data in real time to obtain the corresponding impact of changes in employee training progress. Finally, it compares the impact of changes in employee training progress with the progress change threshold obtained from the preset database. If the impact of changes in employee training progress is significant... If the impact is not less than the progress change threshold, the profile construction data of the corresponding category will be updated. Otherwise, the changes in the profile construction data of the corresponding category will continue to be monitored. Based on the evaluation results, it will be determined whether to trigger a profile update. If so, the profile construction data will be updated. Otherwise, the update threshold assessment will be performed on the profile construction data of each category. Finally, based on the evaluation results, it will be determined whether to rebuild the employee training profile. Then, a personalized training path will be built based on the obtained employee training profile, and the update timeliness of the employee training profile will be quantified. Based on this result, it will be determined whether to rebuild the personalized training path. If not, the generation interval of the personalized training path will be optimized. Otherwise, it will be determined whether to adjust the update priority of the initial profile, thereby improving the timeliness of the generation of personalized training plans.

[0025] The technical solution in this application aims to address the problem of insufficient correlation between the timeliness of personalized training program generation and training progress. The overall approach is as follows:

[0026] By acquiring the initial profile update priority of various profile building data and evaluating the changes in training progress of employee training profiles to determine whether a profile update is triggered, if so, the profile building data is updated; otherwise, an update threshold assessment is conducted, and then it is determined whether to rebuild to construct a personalized training path. The update timeliness is quantified to determine whether to rebuild the personalized training path; if not, the personalized training path generation interval is optimized; otherwise, it is determined whether to adjust the initial profile update priority, thereby improving the timeliness of personalized training plan generation.

[0027] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0028] like Figure 1 The diagram shown is a structural schematic of the personalized training program generation system based on data analysis provided in this application embodiment. The personalized training program generation system based on data analysis provided in this application embodiment includes: an initial assessment module for training profiles, a profile reconstruction determination module, a training path timeliness determination module, and a reconstruction path effectiveness assessment module.

[0029] The initial assessment module for training profiles is used to obtain the initial profile update priority from the preset database for various profile construction data. It assesses the training progress changes of employee training profiles based on the changes in various profile construction data. Employee training profiles are used to measure the progress changes of employees in the actual training process. The initial profile update priority is used to initially quantify the degree of update needs for various profile construction data.

[0030] The portrait reconstruction judgment module is used to determine whether to trigger a portrait update based on the obtained evaluation results. If so, the portrait construction data of the corresponding category will be updated. Otherwise, the update threshold assessment of the portrait construction data of each category will be performed. The update threshold assessment is used to determine whether all portrait construction data meet the requirements for critical update.

[0031] The training path timeliness determination module is used to determine whether to reconstruct the employee training profile based on the obtained evaluation results. It constructs personalized training paths based on the obtained employee training profiles and quantifies the timeliness of updating the employee training profiles. The personalized training path represents the planned route for the employee to conduct training, and the update timeliness quantification is used to quantify the degree to which the current employee training profile meets the timeliness requirements of the personalized training path.

[0032] The Reconstruction Path Effectiveness Assessment module is used to determine whether to reconstruct personalized training paths based on quantitative results. If not, the generation interval of personalized training paths is optimized; otherwise, the reconstruction effectiveness assessment is performed on the reconstructed personalized training paths to determine whether the update priority of the initial profile is adjusted. The reconstructed personalized training path refers to the personalized training path reconstructed based on the initial personalized training path. The reconstruction effectiveness assessment is used to evaluate the degree to which the reconstructed personalized training path improves the progress of employee training.

[0033] In this embodiment, when the data related to the construction of employee training profiles in the data analysis-based personalized training program generation system is not updated in a refined manner, it may lead to a decrease in the timeliness of the constructed employee training profiles, which in turn reduces the timeliness of the personalized training path. Consequently, the timeliness of the personalized training program generation is not sufficiently correlated with the training progress. By conducting closed-loop analysis of the feedback between the employee training profiles and the personalized training paths, it is helpful to improve the timeliness of the employee training profiles, thereby improving the timeliness of the personalized training paths, and ultimately improving the timeliness of the personalized training program generation.

[0034] It should be added that before designing the data analysis-based personalized training program generation system, a preset database was established by pre-set personnel to store various types of set data. The preset database includes, but is not limited to, initial profile update priority, progress change threshold, profile construction change allocation amount, preset threshold, path timeliness impact limit, path timeliness allocation value, reference profile update duration, path generation interval impact multiple, path-profile conformity judgment value, training path progress allocation rate, and reference path progress time data. Among these, various values ​​are directly set by pre-set professionals. For example, the path-profile conformity judgment value is obtained by pre-set staff by substituting the training path progress data corresponding to the reconstruction of personalized training paths in the historical database into the specific constraint expression of the training path effectiveness evaluation index to obtain the corresponding dataset, averaging the dataset to obtain the path-profile conformity judgment value, and pre-storing it in the preset database.

[0035] As a further step, the specific steps for assessing changes in training progress based on employee training profiles are as follows:

[0036] Step 1: Classify the employee profile data and obtain the historical average update frequency for each type of profile data. Based on the historical average update frequency, map the initial profile update priority of the corresponding category of profile data into a preset database.

[0037] It should be added that a priority mapping set is constructed to map the historical average update frequency of the portrait construction data for each category to the initial portrait update priority. The category corresponding to the portrait construction data is input into the priority mapping set and the corresponding initial portrait update priority is output. The priority mapping set represents the set of mapping relationships between the historical average update frequency of the portrait construction data for each category and the initial portrait update priority.

[0038] Step 2: Monitor changes in various profile construction data in real time to obtain the corresponding impact of changes in employee training progress.

[0039] Step 3: Determine the impact of changes in employee training progress against the progress change threshold obtained from the preset database: If the impact of changes in employee training progress is not less than the progress change threshold, then update the profile data for the corresponding category; otherwise, continue to monitor the changes in the profile data for the corresponding category.

[0040] In this embodiment, by monitoring the changes in various profile construction data in real time, the system can promptly capture changes in the progress of employee training. This dynamic monitoring can effectively prevent the lag in employee training progress and help to adjust the training plan in a timely manner. The method updates the profile according to the changes in the employee's training progress, making the profile update of each employee more personalized.

[0041] As a further solution, the specific methods for obtaining the impact of changes in employee training progress are as follows:

[0042] First, obtain the parameters for changes in the profile building data. These parameters include the initial profile update priority and the number of changes in training metrics.

[0043] It should be added that the initial profile update priority is obtained from the preset database, and the number of changes in training indicators is obtained by counting the number of changes in the indicators that employees need to be trained through system logs.

[0044] Next, the profile building change allocation is obtained from the preset database. The profile building change allocation includes the initial priority allocation and the training indicator allocation.

[0045] Specifically, the profile construction change allocation is obtained from a preset database. The profile construction change allocation represents the degree of influence of profile construction data change parameters on the change in employee training progress. Each profile construction data change parameter has a unique mapping relationship with the profile construction change allocation, and the value ranges from 0 to 1. For example, a mapping set of profile construction data change parameters and preset profile construction change allocation is constructed. The real-time initial profile update priority and the number of training indicator changes are input into the mapping set to obtain the corresponding initial priority allocation and training indicator allocation, which respectively represent the degree of influence of the initial profile update priority and the number of training indicator changes on the change in employee training progress, and the sum of the two is 1.

[0046] Finally, after weighting the parameters of the profile construction data change and the allocation of profile construction changes, the impact of employee training progress change is obtained by coupling. The impact of employee training progress change is used to quantify the degree of influence of employee training indicators on employee training profiles.

[0047] The specific constraint expression for the impact of changes in employee training progress is as follows:

[0048]

[0049] In the formula, IPU represents the initial profile update priority of the profile construction data for the corresponding category, CTI represents the number of training metric changes of the profile construction data for the corresponding category, and μ represents the initial priority allocation. This represents the amount of training indicators allocated, while ETP represents the impact of changes in employee training progress on the corresponding category of profile building data.

[0050] In this embodiment, the algorithm combines the parameters of changes in profile construction data with the allocation of profile construction changes to obtain the impact of changes in employee training progress. In this formula, a higher initial profile update priority indicates a greater need to update the corresponding category of profile construction data, resulting in a higher degree of influence on the update of employee training profiles and thus a greater impact on employee training progress. Simultaneously, a larger number of changes in training indicators indicates a greater change in the progress of the corresponding category of profile construction data, further increasing the impact on employee training progress. Analyzing the impact of changes in employee training progress helps to more accurately quantify the degree of influence of changes in employee training indicators on employee training profiles, improving the timeliness of personalized training program generation.

[0051] Furthermore, the parameters for changes in profile building data are not independent. The initial profile update priority and the number of changes in training indicators are interrelated. For example, if the initial profile update priority of a certain type of profile building data is higher, it means that the update requirement for that type of profile building data may be higher, the update frequency in historical data may be higher, and the changes in that type of profile building data may be more, and the number of changes in the corresponding training indicators of that type of profile building data may be more.

[0052] like Figure 2 The diagram illustrates the process for evaluating the update threshold of various types of profile construction data according to an embodiment of this application. The specific logic is as follows: First, obtain the progress change difference of various types of profile construction data that have not been updated, and compare each progress change difference with a preset threshold. Then, if the progress change difference of a corresponding category of profile construction data is lower than the preset threshold, record the progress update value of the corresponding category of profile construction data as the first progress update value; otherwise, record the progress update value of the corresponding category of profile construction data as the second progress update value. Finally, calculate the cumulative progress update value of all categories of profile construction data. If the cumulative progress update value is higher than the preset cumulative value, update the employee training profile; otherwise, no additional processing is performed. This process helps to more accurately quantify the timeliness of the employee training profile obtained based on the determination of the impact of changes in employee training progress, thereby enabling timely updates and optimizations, and ultimately improving the timeliness of generating personalized training programs.

[0053] As a further solution, the specific process for updating the critical assessment of various profile construction data is as follows:

[0054] H1 retrieves the progress change difference of various profile construction data that have not been updated, and compares each progress change difference with a preset threshold value obtained from a preset database. The progress change difference represents the difference between the impact of changes in employee training progress and the progress change threshold value.

[0055] Specifically, the preset threshold values ​​are pre-set by preset staff and stored in a preset database.

[0056] H2, if the progress change difference of the corresponding category of portrait construction data is lower than the preset threshold, then the progress update value of the corresponding category of portrait construction data is recorded as the first progress update value; otherwise, the progress update value of the corresponding category of portrait construction data is recorded as the second progress update value.

[0057] The progress update value represents the value used to mark the comparison result between the progress change difference of various profile construction data and the preset threshold value, and is used to quantify the degree of progress change under different comparison conditions. The first progress update value is higher than the second progress update value. For example, the first progress update value is 1 and the second progress update value is 0.

[0058] H3 calculates the cumulative progress update value of the profile building data for all categories. If the cumulative progress update value is higher than the preset cumulative value, the employee training profile will be updated; otherwise, no additional processing will be performed.

[0059] In this embodiment, by acquiring the progress change differences of various profile construction data and comparing them with preset threshold differences, the system can more accurately determine which employee profiles need to be updated in a timely manner, improving the timeliness of employee training profiles. By statistically analyzing the progress update values ​​of all categories of profile construction data, calculating the cumulative progress update value, and comparing it with a preset cumulative value, it helps to further control whether to perform an overall update of employee training profiles. This mechanism ensures that an overall training profile update is only performed when the progress update of all employee profiles reaches a certain threshold, avoiding overly frequent overall updates, ensuring the timeliness of employee training profiles, and improving the timeliness of personalized training program generation.

[0060] As a further solution, the specific process for updating and quantifying the timeliness of employee training profiles is as follows:

[0061] When generating a personalized training path, the update status of various profile construction data is obtained to obtain the personalized path timeliness impact value of the personalized training path, and the current personalized path timeliness impact value is compared with the path timeliness impact limit obtained from the preset database.

[0062] Specifically, the path timeliness impact limit is obtained from a pre-set database. In one specific embodiment, pre-set staff substitute qualified path timeliness assessment data from the historical database into the specific constraint expression for the personalized path timeliness impact value to obtain the corresponding dataset, and then perform a mean calculation on the dataset to obtain the path timeliness impact limit.

[0063] On the one hand, if the impact value of personalized path timeliness is not greater than the path timeliness impact limit, the generation interval of personalized training path will be optimized.

[0064] On the other hand, if the impact value of the timeliness of the personalized path is greater than the timeliness impact limit, then an effectiveness assessment of the reconstruction of the personalized training path should be conducted.

[0065] In this embodiment, by acquiring real-time updates of various profile construction data, the system can dynamically adjust the timeliness of personalized training paths based on the latest employee profile information. This ensures that personalized training paths always match the actual status and needs of employee training profiles, avoids fixed-time training models, and improves the timeliness of personalized training paths for employees.

[0066] As a further solution, the specific process for obtaining the impact value of personalized route timeliness is as follows:

[0067] The first step is to obtain path timeliness assessment data, which includes the cumulative value of progress updates, the impact of changes in employee training progress, the critical value of progress changes, and the profile update time.

[0068] Specifically, the profile update time is obtained through system log records.

[0069] The second step is to obtain the path timeliness allocation value and the reference profile update duration from the preset database. The path timeliness allocation value includes the progress update allocation value, the progress judgment allocation value, and the profile update allocation value.

[0070] Specifically, the path timeliness allocation value is obtained from a preset database. This value represents the degree of influence of the path timeliness assessment data on the personalized path timeliness impact value. Each path timeliness assessment data point has a unique mapping relationship with its allocation value, and the value ranges from 0 to 1. For example, a mapping set between path timeliness assessment data and preset path timeliness allocation values ​​is constructed. The real-time cumulative progress update value, the impact of changes in employee training progress, and the profile update duration are input into the mapping set to obtain the corresponding progress update allocation value, progress judgment allocation value, and profile update allocation value. These represent the degree of influence of the cumulative progress update value, the impact of changes in employee training progress, and the profile update duration on the personalized path timeliness impact value, respectively, and the sum of the three is 1.

[0071] Specifically, the reference portrait update interval is preset by the designated staff and stored in a preset database, representing the maximum acceptable interval for portrait updates.

[0072] The third step is to calculate the deviation between the impact of changes in employee training progress and the critical value of progress change to obtain the progress judgment deviation.

[0073] It should be explained that the deviation calculation means taking the difference between the impact of changes in employee training progress and the critical value of progress change, and then performing a ratio calculation with the critical value of progress change.

[0074] The specific method for obtaining the progress determination deviation is as follows:

[0075]

[0076] Where n represents the category number of each type of profile construction data, n = 1, 2, ..., N, and N represents the total number of profile construction data categories. DP n DP0 represents the impact of changes in employee training progress on the data constructed for the nth type of profile, DPJ represents the progress change threshold, and DPJ represents the progress judgment deviation. When the impact of changes in employee training progress is greater than the corresponding progress change threshold, the corresponding progress judgment deviation is greater, indicating a higher degree of change in employee training progress. At the same time, a larger progress judgment deviation also indicates a higher timeliness of various types of employee training profiles, and it is independent of the cumulative progress update value. The two represent quantitative values ​​for evaluating the timeliness of employee training profiles under different circumstances. However, when both are larger, they both indicate a higher timeliness of employee training profiles.

[0077] The fourth step involves weighting and coupling the progress judgment deviation with the cumulative progress update value, the profile update duration, and the corresponding path timeliness allocation value to obtain the personalized path timeliness impact value. The personalized path timeliness impact value is used to quantify the degree of influence of the current employee training profile on the personalized training path to be generated.

[0078] The specific constraint expression for the impact value of personalized route timeliness is as follows:

[0079]

[0080] In the formula, PUV represents the cumulative progress update value, IUD represents the image update duration, and IUD0 represents the reference image update duration. This indicates the progress update allocation value. This indicates the allocation value for the progress determination. The PPT represents the value allocated for updating the profile and the impact of the timeliness of the personalized path.

[0081] In this embodiment, the algorithm combines the progress judgment deviation, the cumulative progress update value, the profile update duration, and the corresponding path timeliness allocation value to analyze and obtain the personalized path timeliness impact value. Specifically, a larger cumulative progress update value indicates higher timeliness of the corresponding employee training profile, resulting in a lower impact on the timeliness of the personalized training path and a lower personalized path timeliness impact value. Similarly, a larger progress judgment deviation indicates higher timeliness of the profile construction data for the corresponding category, leading to a lower personalized path timeliness impact value. Furthermore, a longer profile update duration than the reference profile update duration indicates a longer past update duration for the employee training profile, resulting in a greater impact on the timeliness of the personalized training path and a higher personalized path timeliness impact value. Analyzing the personalized path timeliness impact value helps to more accurately quantify the influence of the current employee training profile on the upcoming personalized training path, thereby optimizing the personalized training path generation interval and improving the timeliness of the personalized training path.

[0082] As a further solution, the specific process for optimizing the personalized training path generation interval is as follows:

[0083] R1 is the difference between the personalized route timeliness impact value and the route timeliness impact limit.

[0084] R2, by mapping the timeliness impact difference in the preset database, obtains the path generation interval impact multiple of the next personalized training path.

[0085] Specifically, a timeliness mapping set is constructed in the preset database between the timeliness impact difference and the path generation interval impact multiple. The real-time timeliness impact difference is input into the timeliness mapping set and the corresponding path generation interval impact multiple is output. The timeliness mapping set represents the set of mapping relationships between the timeliness impact difference and the path generation interval impact multiple.

[0086] R3 calculates the corresponding optimized path reconstruction interval by compensating the path generation interval impact factor with the interval duration of the previous one-time training path generation.

[0087] The compensation operation represents the product of the impact factor of the path generation interval and the interval duration of the previous one-time training path generation.

[0088] R4, after optimizing the path reconstruction interval, performs personalized training path construction again.

[0089] In this embodiment, by mapping the difference between the difference and the timeliness impact difference, the system can dynamically identify the progress changes of employees during the training process and adjust the generation interval of personalized training paths in a timely manner. At the same time, the system will dynamically shorten the generation interval of personalized training paths, thereby ensuring the timeliness of employee training profiles and improving the timeliness of personalized training program generation.

[0090] like Figure 3 The diagram illustrates the process for determining whether to adjust the initial profile update priority according to an embodiment of this application. The specific logic is as follows: The effectiveness of reconstructing personalized training paths is evaluated to obtain a corresponding training path effectiveness evaluation index. This index is then compared with the path-profile conformity judgment value. If the training path effectiveness evaluation index is less than the path-profile conformity judgment value, the employee training profile update impact rate is mapped based on the training path effectiveness evaluation index. The employee training profile update impact rate is then compensated with the initial profile update priority of various profile construction data to obtain the frequency compensation amount for each type of profile construction data. This frequency compensation amount is then compensated with the initial update frequency of each type of profile construction data to obtain the optimized update frequency. The various types of profile construction data are updated based on this optimized update frequency. If the training path effectiveness evaluation index is not less than the path-profile conformity judgment value, the initial profile update priority is not adjusted. Through this process, it is possible to accurately determine whether the initial profile update priority of the employee training profile needs to be adjusted, improving the timeliness of the employee training profile and the timeliness of generating personalized training plans.

[0091] As a further solution, the specific steps to determine whether to adjust the priority of the initial profile update are as follows: Evaluate the effectiveness of the reconstructed personalized training path, obtain the corresponding training path effectiveness evaluation index, and compare the training path effectiveness evaluation index with the path-profile conformity judgment value obtained from the preset database:

[0092] In the first scenario, if the training path effectiveness evaluation index is less than the path-profile conformity judgment value, the employee training profile update impact rate is obtained by mapping the training path effectiveness evaluation index. The employee training profile update impact rate is then compensated with the initial profile update priority of various profile construction data to obtain the frequency compensation amount of various profile construction data. The frequency compensation amount is then compensated with the initial update frequency of various profile construction data to obtain the optimized update frequency. Various profile construction data are updated based on the optimized update frequency.

[0093] It should be added that a path mapping set between the training path effectiveness evaluation index and the employee training profile update impact rate is constructed in the preset database. The real-time training path effectiveness evaluation index is input into the path mapping set and the employee training profile update impact rate is output. The path mapping set represents the set of mapping relationships between the training path effectiveness evaluation index and the employee training profile update impact rate.

[0094] Secondly, the compensation operation represents the product operation of the impact rate of employee training profile updates and the initial profile update priority of various profile construction data.

[0095] In the second scenario, if the training path effectiveness evaluation index is not less than the path-profile conformity judgment value, then the initial profile update priority will not be adjusted.

[0096] In this embodiment, by evaluating the effectiveness of personalized training paths, the system can dynamically adjust the priority of employee profile updates. When the effectiveness of a training path is low, the system can increase the priority of employee training profile updates by optimizing the update frequency, ensuring that the employee training profile remains consistently relevant to their training progress. Based on the training path effectiveness evaluation index and the path-profile consistency judgment value, the system can accurately determine whether the initial profile update priority needs to be adjusted. This adjustment mechanism ensures that employee training profile updates are not delayed, improving the timeliness of employee training profiles and the timeliness of personalized training plan generation.

[0097] As a further solution, the specific process for obtaining the training path effectiveness evaluation index is as follows:

[0098] A1. Obtain training path progress data, which includes average training indicator completion time, training progress percentage, training participation time, and training indicator completion rate.

[0099] Specifically, the average training indicator completion time is obtained by averaging the completion times of each training indicator recorded in the system logs. The training progress percentage is obtained by comparing the current training indicator completion amount with the total amount of tasks. The training participation time is obtained by counting the time employees spend in training through the system logs. The number of training indicators that have completed all tasks is counted and compared with the total training indicator data to obtain the training indicator completion rate.

[0100] A2. Obtain training path progress allocation rate and reference path progress time data from the preset database. The training path progress allocation rate includes indicator completion time allocation rate, training progress allocation rate, training duration allocation rate and indicator completion allocation rate. The reference path progress time data includes reference training indicator completion time and reference training participation time.

[0101] Specifically, the training path progress allocation rate is obtained from a pre-set database. This rate represents the degree of influence of training path progress data on the training path effectiveness evaluation index. Each training path progress data point has a unique mapping relationship with its training path progress allocation rate, and the value ranges from 0 to 1. For example, a mapping set between training path progress data and the pre-set training path progress allocation rate is constructed. Inputting real-time average training indicator completion time, training progress percentage, training participation time, and training indicator completion rate into the mapping set yields the corresponding indicator completion time allocation rate, training progress allocation rate, training duration allocation rate, and indicator completion allocation rate. These represent the degree of influence of average training indicator completion time, training progress percentage, training participation time, and training indicator completion rate on the training path effectiveness evaluation index, and the sum of these four is 1.

[0102] Specifically, the reference path progress time data is pre-set by designated staff and stored in a pre-defined database.

[0103] A3. The training indicator completion time value is obtained by comparing the average training indicator completion time with the reference training indicator completion time, and the training participation value is obtained by comparing the training participation duration with the reference training participation duration.

[0104] It should be added that the training indicator completion time value is Training participation value

[0105] A4, based on the training indicator completion time value, training participation value, training progress percentage, training indicator completion rate and corresponding training path progress allocation rate, after weighted calculation, the training path effectiveness evaluation index is obtained. The training path effectiveness evaluation index is used to quantify the effectiveness of personalized training path optimization and reconstruction.

[0106] The specific constraint expression for the training path effectiveness evaluation index is as follows:

[0107]

[0108] In the formula, ACT represents the average training indicator completion time, TPP represents the training progress percentage, TID represents the training participation time, CTI represents the training indicator completion rate, ACT0 represents the reference training indicator completion time, and TID0 represents the reference training participation time. This indicates the time allocation rate for indicator completion. Indicates the training progress allocation rate. Indicates the training time allocation rate. This indicates the completion rate of the target allocation, and TPE represents the training path effectiveness evaluation index.

[0109] In this embodiment, the algorithm combines training path progress data, training path progress allocation rate, and reference path progress time data to analyze and obtain a training path effectiveness evaluation index. In this index, as the completion time value of training indicators, training participation value, training progress percentage, and training indicator completion rate increase, it indicates that the training progress of employees learning based on the current personalized training path is faster, and the corresponding training quality is higher. Therefore, the corresponding training path effectiveness evaluation index is also larger. By analyzing the training path effectiveness evaluation index, not only is the effectiveness of the optimized and reconstructed personalized training path more accurately quantified, but it also helps to improve the timeliness of personalized training program generation and the sufficiency of the correlation between training progress and the personalized training program, thereby ensuring the personalization of the personalized training program and the accuracy of the training program for each employee.

[0110] It should be added that the training path effectiveness evaluation index can be used to evaluate the effectiveness of the reconstructed personalized training path in a timely manner, thereby providing timely feedback on the training effect of the personalized path and optimizing the priority of updating the initial profile in a timely manner. This makes the generation of personalized training programs form a closed loop, which not only improves the correlation between personalized training paths and employee training profiles, but also improves the timeliness of personalized training programs.

[0111] like Figure 4 The diagram shows a flowchart of a data analysis-based personalized training program generation method provided in this application embodiment. The specific logic is as follows: First, the initial profile update priority of various profile construction data is obtained from a preset database. The training progress of employee training profiles is evaluated based on changes in the various profile construction data. Next, based on the evaluation results, it is determined whether a profile update is triggered. If so, the corresponding category of profile construction data is updated; otherwise, a critical update assessment is performed on various types of profile construction data. Then, based on the evaluation results, it is determined whether to reconstruct the employee training profile. A personalized training path is constructed based on the obtained employee training profile, and the update timeliness of the employee training profile is quantified. Finally, based on the quantification results, it is determined whether to reconstruct the personalized training path. If not, the personalized training path generation interval is optimized; otherwise, the reconstruction effectiveness of the reconstructed personalized training path is evaluated to determine whether the initial profile update priority should be adjusted. Through the above process, not only is the timeliness of employee training profiles improved, but the generation timeliness of personalized training programs is also improved.

[0112] This application also provides a method for generating personalized training programs based on data analysis, the specific steps of which are as follows;

[0113] The initial profile update priority is obtained from the preset database to obtain various profile construction data. The training progress change of the employee training profile is evaluated based on the changes in various profile construction data. The employee training profile is used to measure the progress change of employees in the actual training process.

[0114] Based on the obtained evaluation results, determine whether to trigger a profile update. If so, update the profile construction data for the corresponding category; otherwise, conduct a critical assessment for updating the profile construction data for all categories.

[0115] Based on the evaluation results, determine whether to reconstruct the employee training profile, build a personalized training path based on the obtained employee training profile, and quantify the timeliness of updating the employee training profile.

[0116] Based on the quantitative results, determine whether to reconstruct the personalized training path. If not, optimize the generation interval of the personalized training path. Otherwise, conduct an effectiveness assessment of the reconstructed personalized training path to determine whether to adjust the update priority of the initial profile.

[0117] In this embodiment, data analysis in personalized training programs is specifically manifested in the collection, mining, and analysis of employee data to design highly relevant personalized training paths for each employee, and to continuously track and evaluate training effectiveness. The data analysis-based personalized training program generation method combines precise profile updates, personalized path optimization, timeliness quantification, and reconstruction effectiveness assessment, ensuring that training content is closely aligned with employees' actual training progress and avoiding outdated or ineffective training content. Furthermore, this method not only improves the timeliness of employee training profiles but also enhances the timeliness of personalized training program generation.

[0118] It's worth noting that in data-driven personalized training programs, building employee training profiles is crucial. This process helps to personalize training plans for each employee, primarily through the following steps: First, data is collected, including but not limited to personal information, work performance data, training history, and behavioral data. Next, features are extracted and standardized from the collected data. Then, data is analyzed through data modeling, using techniques such as cluster analysis, regression analysis, association rule analysis, and deep learning and artificial intelligence. Finally, profiles are constructed based on the data modeling, typically including dimensions such as basic information, skills, development needs, and behavioral characteristics. Furthermore, based on the analysis results of the employee training profiles, personalized training programs are built and recommended to the corresponding employees' clients. Simultaneously, the timeliness of the employee training profiles is evaluated based on the progress feedback of the training programs. Therefore, the construction of employee training profiles and personalized training paths are mutually influential; analyzing the timeliness of employee training profiles helps improve the timeliness of personalized training paths.

[0119] It should be added that, such as Figure 5 The diagram shows the interface of the personalized training program generation system based on data analysis provided in this embodiment. The left side of the interface is the system navigation bar, which includes options such as "Home," "Training Data Analysis," "Training Plan Management," "Execution and Feedback," "Report Center," and "System Settings." The upper center displays the group's achievements, updating group news in real time. The lower center features "Recommended for You," recommending training tasks of varying difficulty levels to users. This facilitates quick access to training and improves training progress.

[0120] like Figure 6 The diagram shows the interface of the initial assessment module of the personalized training program generation system based on data analysis provided in this application embodiment. The left side of the interface is the navigation bar of the initial assessment module. The left area is the status display area for "Initial Profile Update Priority," presenting various data types and their corresponding initial profile update priorities in a list format. The right area is the analysis results area, displayed in the form of a curve graph, showing the progress trend of each training indicator, making it easier for users to view the progress of each training indicator more intuitively.

[0121] like Figure 7 The diagram shows the interface of the profile reconstruction judgment module of the personalized training program generation system based on data analysis provided in this application embodiment. The left side of the interface is the navigation bar of the profile reconstruction judgment module, and the middle left side is a bar chart of the speed change difference of various profile construction data. The middle right side is the corresponding progress update value section, where "first progress update value" corresponds to "data pre-update score", "second progress update value" corresponds to "data waiting to be updated score", and "cumulative progress update value" corresponds to "profile update score", which makes it easier for users to understand the current update status of employee training profiles more intuitively.

[0122] like Figure 8 The image shown is an interface diagram of the training path timeliness determination module of the personalized training program generation system based on data analysis provided in this application embodiment. The left side of the interface is the navigation bar of the training path timeliness determination module. The middle left side is a curve graph showing the change of the personalized path timeliness impact value, while the middle right side updates the progress of personalized training path reconstruction in real time, which helps to more intuitively understand the progress of personalized training path updates.

[0123] like Figure 9The image shown is an interface diagram of the reconstruction path effectiveness evaluation module of the personalized training program generation system based on data analysis provided in this application embodiment. The left side of the interface is the navigation bar of the reconstruction path effectiveness evaluation module. The middle left side displays relevant data on the optimization of the initial profile update priority, and the middle right side is a curve graph of the training path effectiveness evaluation index, which helps users understand whether the current personalized training path is more timely.

[0124] In summary, this application embodiment assesses the training progress of employee training profiles by combining the initial profile update priority with changes in various profile construction data. Based on this assessment, it determines whether a profile update should be triggered. If so, an update is performed; otherwise, an update threshold assessment is conducted. Then, based on the assessment results, it determines whether to reconstruct the employee training profile and build a personalized training path. The update timeliness of the employee training profile is quantified, and based on this, it determines whether to reconstruct the personalized training path. If not, the personalized training path generation interval is optimized; otherwise, it determines whether to adjust the initial profile update priority. This improves the timeliness of employee training profiles, thereby improving the timeliness of personalized training plan generation and effectively solving the problem of insufficient correlation between the timeliness of personalized training plan generation and training progress in existing technologies.

[0125] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

Claims

1. A personalized training program generation system based on data analysis, characterized in that: This includes modules for initial assessment of training profiles, determination of profile reconstruction, determination of the timeliness of training paths, and assessment of the effectiveness of reconstructed paths. The initial assessment module for training profiles is used to obtain the initial profile update priority of various profile construction data from a preset database, and to assess the training progress changes of employee training profiles in combination with the changes in various profile construction data. The employee training profiles are used to measure the progress changes of employees in the actual training process. The portrait reconstruction determination module is used to determine whether to trigger portrait update based on the obtained evaluation results. If so, the portrait construction data of the corresponding category is updated; otherwise, the critical evaluation of the update of the portrait construction data of each category is performed. The training path timeliness determination module is used to determine whether to reconstruct the employee training profile based on the obtained evaluation results, construct a personalized training path based on the obtained employee training profile, and quantify the timeliness of updating the employee training profile. The reconstruction path effectiveness evaluation module is used to determine whether to reconstruct the personalized training path based on the quantitative results. If not, the generation interval of the personalized training path is optimized; otherwise, the reconstruction effectiveness evaluation of the reconstructed personalized training path is performed to determine whether to adjust the update priority of the initial profile. The specific process for updating and quantifying the timeliness of employee training profiles is as follows: When generating personalized training paths, the update status of various profile construction data is obtained to acquire the personalized path timeliness impact value. The current personalized path timeliness impact value is then compared with the path timeliness impact limit obtained from the preset database. If the impact value of personalized path timeliness is not greater than the path timeliness impact limit, then the personalized training path generation interval will be optimized. If the impact value of the timeliness of the personalized path exceeds the timeliness impact limit, then an effectiveness assessment of the reconstructed personalized training path should be conducted. The specific process for obtaining the personalized path timeliness impact value is as follows: Obtain path timeliness assessment data, which includes cumulative progress update value, impact of changes in employee training progress, progress change threshold, and profile update duration; The path timeliness allocation value and reference profile update duration are obtained from the preset database. The path timeliness allocation value includes the progress update allocation value, the progress judgment allocation value, and the profile update allocation value. The deviation of the progress judgment is obtained by calculating the deviation between the impact of changes in employee training progress and the critical value of progress change. The personalized path timeliness impact value is obtained by weighting and coupling the progress judgment deviation with the cumulative progress update value, the profile update duration and the corresponding path timeliness allocation value. The personalized path timeliness impact value is used to quantify the degree of influence of the current employee training profile on the personalized training path to be generated.

2. The personalized training program generation system based on data analysis as described in claim 1, characterized in that: The specific steps for assessing changes in training progress based on employee training profiles are as follows: The employee profile data is classified and the historical average update frequency of each type of profile data is obtained. Based on the historical average update frequency, the initial profile update priority of the corresponding category of profile data is mapped in the preset database. Real-time monitoring of changes in various profile building data to obtain the corresponding impact of changes in employee training progress; The impact of changes in employee training progress is compared with the critical value for progress changes obtained from a pre-set database: If the impact of changes in employee training progress is not less than the progress change threshold, the profile data for the corresponding category will be updated; otherwise, the changes in the profile data for the corresponding category will continue to be monitored.

3. The personalized training program generation system based on data analysis as described in claim 2, characterized in that: The specific methods for obtaining the impact of changes in employee training progress are as follows: Obtain profile construction data change parameters, including the initial profile update priority and the number of training indicator changes; The profile construction change allocation amount is obtained from the preset database. The profile construction change allocation amount includes the initial priority allocation amount and the training indicator allocation amount. After weighting the parameters of the profile construction data change and the profile construction change allocation, the impact of the employee training progress change is obtained by coupling. The impact of the employee training progress change is used to quantify the degree of influence of employee training indicators on employee training profiles.

4. The personalized training program generation system based on data analysis as described in claim 1, characterized in that: The specific process for updating the critical assessment of various profile construction data is as follows: Obtain the progress change difference of various profile construction data that have not been updated, and compare each progress change difference with a preset threshold value obtained from a preset database. The progress change difference represents the difference between the impact of employee training progress change and the progress change threshold value. If the progress change difference of the corresponding category of portrait construction data is lower than the preset threshold, then the progress update value of the corresponding category of portrait construction data is recorded as the first progress update value; otherwise, the progress update value of the corresponding category of portrait construction data is recorded as the second progress update value. The progress update value of the profile construction data for all categories is calculated to obtain the cumulative progress update value. If the cumulative progress update value is higher than the preset cumulative value, the employee training profile is updated; otherwise, no additional processing is performed.

5. The personalized training program generation system based on data analysis as described in claim 1, characterized in that: The specific process for optimizing the personalized training path generation interval is as follows: The difference between the timeliness impact value of the personalized route and the timeliness impact limit is calculated to obtain the timeliness impact difference; The impact factor of the path generation interval for the next personalized training path is obtained by mapping the timeliness impact difference to a preset database. The corresponding optimized path reconstruction interval is obtained by compensating the path generation interval impact factor with the interval duration of the previous one-time training path generation. After optimizing the path reconstruction interval, a personalized training path is constructed again.

6. The personalized training program generation system based on data analysis as described in claim 1, characterized in that: The specific steps for determining whether to adjust the initial image update priority are as follows: The effectiveness of reconstructing personalized training paths is evaluated to obtain the corresponding training path effectiveness evaluation index. This index is then compared with the path-profile conformity score obtained from a pre-set database. If the training path effectiveness evaluation index is less than the path-profile conformity judgment value, the employee training profile update impact rate is obtained by mapping the training path effectiveness evaluation index. The employee training profile update impact rate is then compensated with the initial profile update priority of various profile construction data to obtain the frequency compensation amount of various profile construction data. The frequency compensation amount is then compensated with the initial update frequency of various profile construction data to obtain the optimized update frequency. Various profile construction data are updated based on the optimized update frequency. If the training path effectiveness evaluation index is not less than the path-profile conformity judgment value, the initial profile update priority will not be adjusted.

7. The personalized training program generation system based on data analysis as described in claim 6, characterized in that: The specific process for obtaining the training path effectiveness evaluation index is as follows: Acquire training path progress data, which includes average training indicator completion time, training progress percentage, training participation duration, and training indicator completion rate. The training path progress allocation rate and reference path progress time data are obtained from a preset database. The training path progress allocation rate includes the indicator completion time allocation rate, training progress allocation rate, training duration allocation rate, and indicator completion allocation rate. The reference path progress time data includes the reference training indicator completion time and the reference training participation time. The training indicator completion time value is obtained by comparing the average training indicator completion time with the reference training indicator completion time, and the training participation value is obtained by comparing the training participation duration with the reference training participation duration. The training path effectiveness evaluation index is obtained by weighting and coupling the training indicator completion time value, training participation value, training progress percentage, training indicator completion rate and corresponding training path progress allocation rate. The training path effectiveness evaluation index is used to quantify the effectiveness of personalized training path optimization and reconstruction.

8. A method for generating personalized training programs based on data analysis, characterized in that: The method is executed by the data analysis-based personalized training program generation system as described in claim 7, and the specific steps are as follows; The initial profile update priority is obtained from the preset database for various profile construction data. The training progress change of the employee training profile is evaluated based on the changes in various profile construction data. The employee training profile is used to measure the progress change of employees in the actual training process. Based on the obtained evaluation results, determine whether to trigger a profile update. If so, update the profile construction data for the corresponding category; otherwise, conduct a critical assessment for updating the profile construction data for each category. Based on the obtained evaluation results, determine whether to reconstruct the employee training profile, construct a personalized training path based on the obtained employee training profile, and quantify the timeliness of updating the employee training profile. Based on the quantitative results, determine whether to reconstruct the personalized training path. If not, optimize the generation interval of the personalized training path. Otherwise, conduct an effectiveness assessment of the reconstructed personalized training path to determine whether to adjust the update priority of the initial profile.

Images